From c6f5d36ff25122e383b4aea52b1d40e7a8f9d9a5 Mon Sep 17 00:00:00 2001 From: Junping Du Date: Mon, 18 Dec 2017 22:30:32 -0800 Subject: [PATCH] Add 2.8.3 release jdiff files. (cherry picked from commit c89f99aade575ab1f6a9836df719cda272293d90) --- .../jdiff/Apache_Hadoop_Common_2.8.3.xml | 38433 ++++++++++++++++ .../jdiff/Apache_Hadoop_HDFS_2.8.3.xml | 312 + .../Apache_Hadoop_MapReduce_Common_2.8.3.xml | 113 + .../Apache_Hadoop_MapReduce_Core_2.8.3.xml | 27495 +++++++++++ ...pache_Hadoop_MapReduce_JobClient_2.8.3.xml | 16 + .../jdiff/Apache_Hadoop_YARN_Client_2.8.3.xml | 2316 + .../jdiff/Apache_Hadoop_YARN_Common_2.8.3.xml | 2665 ++ ...Apache_Hadoop_YARN_Server_Common_2.8.3.xml | 829 + 8 files changed, 72179 insertions(+) create mode 100644 hadoop-common-project/hadoop-common/dev-support/jdiff/Apache_Hadoop_Common_2.8.3.xml create mode 100644 hadoop-hdfs-project/hadoop-hdfs/dev-support/jdiff/Apache_Hadoop_HDFS_2.8.3.xml create mode 100644 hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_Common_2.8.3.xml create mode 100644 hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_Core_2.8.3.xml create mode 100644 hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_JobClient_2.8.3.xml create mode 100644 hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Client_2.8.3.xml create mode 100644 hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Common_2.8.3.xml create mode 100644 hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Server_Common_2.8.3.xml diff --git a/hadoop-common-project/hadoop-common/dev-support/jdiff/Apache_Hadoop_Common_2.8.3.xml b/hadoop-common-project/hadoop-common/dev-support/jdiff/Apache_Hadoop_Common_2.8.3.xml new file mode 100644 index 00000000000..bd7e69c0265 --- /dev/null +++ b/hadoop-common-project/hadoop-common/dev-support/jdiff/Apache_Hadoop_Common_2.8.3.xml @@ -0,0 +1,38433 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + UnsupportedOperationException + + If a key is deprecated in favor of multiple keys, they are all treated as + aliases of each other, and setting any one of them resets all the others + to the new value. + + If you have multiple deprecation entries to add, it is more efficient to + use #addDeprecations(DeprecationDelta[] deltas) instead. + + @param key + @param newKeys + @param customMessage + @deprecated use {@link #addDeprecation(String key, String newKey, + String customMessage)} instead]]> + + + + + + + + UnsupportedOperationException + + If you have multiple deprecation entries to add, it is more efficient to + use #addDeprecations(DeprecationDelta[] deltas) instead. + + @param key + @param newKey + @param customMessage]]> + + + + + + + UnsupportedOperationException + + If a key is deprecated in favor of multiple keys, they are all treated as + aliases of each other, and setting any one of them resets all the others + to the new value. + + If you have multiple deprecation entries to add, it is more efficient to + use #addDeprecations(DeprecationDelta[] deltas) instead. + + @param key Key that is to be deprecated + @param newKeys list of keys that take up the values of deprecated key + @deprecated use {@link #addDeprecation(String key, String newKey)} instead]]> + + + + + + + UnsupportedOperationException + + If you have multiple deprecation entries to add, it is more efficient to + use #addDeprecations(DeprecationDelta[] deltas) instead. + + @param key Key that is to be deprecated + @param newKey key that takes up the value of deprecated key]]> + + + + + + key is deprecated. + + @param key the parameter which is to be checked for deprecation + @return true if the key is deprecated and + false otherwise.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + final. + + @param name resource to be added, the classpath is examined for a file + with that name.]]> + + + + + + + + + + final. + + @param url url of the resource to be added, the local filesystem is + examined directly to find the resource, without referring to + the classpath.]]> + + + + + + + + + + final. + + @param file file-path of resource to be added, the local filesystem is + examined directly to find the resource, without referring to + the classpath.]]> + + + + + + + + + + final. + + WARNING: The contents of the InputStream will be cached, by this method. + So use this sparingly because it does increase the memory consumption. + + @param in InputStream to deserialize the object from. In will be read from + when a get or set is called next. After it is read the stream will be + closed.]]> + + + + + + + + + + + final. + + @param in InputStream to deserialize the object from. + @param name the name of the resource because InputStream.toString is not + very descriptive some times.]]> + + + + + + + + + + + final. + + @param conf Configuration object from which to load properties]]> + + + + + + + + + + + name property, null if + no such property exists. If the key is deprecated, it returns the value of + the first key which replaces the deprecated key and is not null. + + Values are processed for variable expansion + before being returned. + + @param name the property name, will be trimmed before get value. + @return the value of the name or its replacing property, + or null if no such property exists.]]> + + + + + + + + + + + + + + + name property, but only for + names which have no valid value, usually non-existent or commented + out in XML. + + @param name the property name + @return true if the property name exists without value]]> + + + + + + name property as a trimmed String, + null if no such property exists. + If the key is deprecated, it returns the value of + the first key which replaces the deprecated key and is not null + + Values are processed for variable expansion + before being returned. + + @param name the property name. + @return the value of the name or its replacing property, + or null if no such property exists.]]> + + + + + + + name property as a trimmed String, + defaultValue if no such property exists. + See @{Configuration#getTrimmed} for more details. + + @param name the property name. + @param defaultValue the property default value. + @return the value of the name or defaultValue + if it is not set.]]> + + + + + + name property, without doing + variable expansion.If the key is + deprecated, it returns the value of the first key which replaces + the deprecated key and is not null. + + @param name the property name. + @return the value of the name property or + its replacing property and null if no such property exists.]]> + + + + + + + value of the name property. If + name is deprecated or there is a deprecated name associated to it, + it sets the value to both names. Name will be trimmed before put into + configuration. + + @param name property name. + @param value property value.]]> + + + + + + + + value of the name property. If + name is deprecated, it also sets the value to + the keys that replace the deprecated key. Name will be trimmed before put + into configuration. + + @param name property name. + @param value property value. + @param source the place that this configuration value came from + (For debugging). + @throws IllegalArgumentException when the value or name is null.]]> + + + + + + + + + + + + + + + + + + + + name. If the key is deprecated, + it returns the value of the first key which replaces the deprecated key + and is not null. + If no such property exists, + then defaultValue is returned. + + @param name property name, will be trimmed before get value. + @param defaultValue default value. + @return property value, or defaultValue if the property + doesn't exist.]]> + + + + + + + name property as an int. + + If no such property exists, the provided default value is returned, + or if the specified value is not a valid int, + then an error is thrown. + + @param name property name. + @param defaultValue default value. + @throws NumberFormatException when the value is invalid + @return property value as an int, + or defaultValue.]]> + + + + + + name property as a set of comma-delimited + int values. + + If no such property exists, an empty array is returned. + + @param name property name + @return property value interpreted as an array of comma-delimited + int values]]> + + + + + + + name property to an int. + + @param name property name. + @param value int value of the property.]]> + + + + + + + name property as a long. + If no such property exists, the provided default value is returned, + or if the specified value is not a valid long, + then an error is thrown. + + @param name property name. + @param defaultValue default value. + @throws NumberFormatException when the value is invalid + @return property value as a long, + or defaultValue.]]> + + + + + + + name property as a long or + human readable format. If no such property exists, the provided default + value is returned, or if the specified value is not a valid + long or human readable format, then an error is thrown. You + can use the following suffix (case insensitive): k(kilo), m(mega), g(giga), + t(tera), p(peta), e(exa) + + @param name property name. + @param defaultValue default value. + @throws NumberFormatException when the value is invalid + @return property value as a long, + or defaultValue.]]> + + + + + + + name property to a long. + + @param name property name. + @param value long value of the property.]]> + + + + + + + name property as a float. + If no such property exists, the provided default value is returned, + or if the specified value is not a valid float, + then an error is thrown. + + @param name property name. + @param defaultValue default value. + @throws NumberFormatException when the value is invalid + @return property value as a float, + or defaultValue.]]> + + + + + + + name property to a float. + + @param name property name. + @param value property value.]]> + + + + + + + name property as a double. + If no such property exists, the provided default value is returned, + or if the specified value is not a valid double, + then an error is thrown. + + @param name property name. + @param defaultValue default value. + @throws NumberFormatException when the value is invalid + @return property value as a double, + or defaultValue.]]> + + + + + + + name property to a double. + + @param name property name. + @param value property value.]]> + + + + + + + name property as a boolean. + If no such property is specified, or if the specified value is not a valid + boolean, then defaultValue is returned. + + @param name property name. + @param defaultValue default value. + @return property value as a boolean, + or defaultValue.]]> + + + + + + + name property to a boolean. + + @param name property name. + @param value boolean value of the property.]]> + + + + + + + + + + + + + + name property to the given type. This + is equivalent to set(<name>, value.toString()). + @param name property name + @param value new value]]> + + + + + + + + + + + + + + + name to the given time duration. This + is equivalent to set(<name>, value + <time suffix>). + @param name Property name + @param value Time duration + @param unit Unit of time]]> + + + + + + + + + + + + + + + + + + + name property as a Pattern. + If no such property is specified, or if the specified value is not a valid + Pattern, then DefaultValue is returned. + Note that the returned value is NOT trimmed by this method. + + @param name property name + @param defaultValue default value + @return property value as a compiled Pattern, or defaultValue]]> + + + + + + + Pattern. + If the pattern is passed as null, sets the empty pattern which results in + further calls to getPattern(...) returning the default value. + + @param name property name + @param pattern new value]]> + + + + + + + + + + + + + + + + + + + name property as + a collection of Strings. + If no such property is specified then empty collection is returned. +

+ This is an optimized version of {@link #getStrings(String)} + + @param name property name. + @return property value as a collection of Strings.]]> + + + + + + name property as + an array of Strings. + If no such property is specified then null is returned. + + @param name property name. + @return property value as an array of Strings, + or null.]]> + + + + + + + name property as + an array of Strings. + If no such property is specified then default value is returned. + + @param name property name. + @param defaultValue The default value + @return property value as an array of Strings, + or default value.]]> + + + + + + name property as + a collection of Strings, trimmed of the leading and trailing whitespace. + If no such property is specified then empty Collection is returned. + + @param name property name. + @return property value as a collection of Strings, or empty Collection]]> + + + + + + name property as + an array of Strings, trimmed of the leading and trailing whitespace. + If no such property is specified then an empty array is returned. + + @param name property name. + @return property value as an array of trimmed Strings, + or empty array.]]> + + + + + + + name property as + an array of Strings, trimmed of the leading and trailing whitespace. + If no such property is specified then default value is returned. + + @param name property name. + @param defaultValue The default value + @return property value as an array of trimmed Strings, + or default value.]]> + + + + + + + name property as + as comma delimited values. + + @param name property name. + @param values The values]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + hostProperty as a + InetSocketAddress. If hostProperty is + null, addressProperty will be used. This + is useful for cases where we want to differentiate between host + bind address and address clients should use to establish connection. + + @param hostProperty bind host property name. + @param addressProperty address property name. + @param defaultAddressValue the default value + @param defaultPort the default port + @return InetSocketAddress]]> + + + + + + + + name property as a + InetSocketAddress. + @param name property name. + @param defaultAddress the default value + @param defaultPort the default port + @return InetSocketAddress]]> + + + + + + + name property as + a host:port.]]> + + + + + + + + + name property as a host:port. The wildcard + address is replaced with the local host's address. If the host and address + properties are configured the host component of the address will be combined + with the port component of the addr to generate the address. This is to allow + optional control over which host name is used in multi-home bind-host + cases where a host can have multiple names + @param hostProperty the bind-host configuration name + @param addressProperty the service address configuration name + @param defaultAddressValue the service default address configuration value + @param addr InetSocketAddress of the service listener + @return InetSocketAddress for clients to connect]]> + + + + + + + name property as a host:port. The wildcard + address is replaced with the local host's address. + @param name property name. + @param addr InetSocketAddress of a listener to store in the given property + @return InetSocketAddress for clients to connect]]> + + + + + + + + + + + + + + + + + + + + name property + as an array of Class. + The value of the property specifies a list of comma separated class names. + If no such property is specified, then defaultValue is + returned. + + @param name the property name. + @param defaultValue default value. + @return property value as a Class[], + or defaultValue.]]> + + + + + + + name property as a Class. + If no such property is specified, then defaultValue is + returned. + + @param name the class name. + @param defaultValue default value. + @return property value as a Class, + or defaultValue.]]> + + + + + + + + name property as a Class + implementing the interface specified by xface. + + If no such property is specified, then defaultValue is + returned. + + An exception is thrown if the returned class does not implement the named + interface. + + @param name the class name. + @param defaultValue default value. + @param xface the interface implemented by the named class. + @return property value as a Class, + or defaultValue.]]> + + + + + + + name property as a List + of objects implementing the interface specified by xface. + + An exception is thrown if any of the classes does not exist, or if it does + not implement the named interface. + + @param name the property name. + @param xface the interface implemented by the classes named by + name. + @return a List of objects implementing xface.]]> + + + + + + + + name property to the name of a + theClass implementing the given interface xface. + + An exception is thrown if theClass does not implement the + interface xface. + + @param name property name. + @param theClass property value. + @param xface the interface implemented by the named class.]]> + + + + + + + + dirsProp with + the given path. If dirsProp contains multiple directories, + then one is chosen based on path's hash code. If the selected + directory does not exist, an attempt is made to create it. + + @param dirsProp directory in which to locate the file. + @param path file-path. + @return local file under the directory with the given path.]]> + + + + + + + + dirsProp with + the given path. If dirsProp contains multiple directories, + then one is chosen based on path's hash code. If the selected + directory does not exist, an attempt is made to create it. + + @param dirsProp directory in which to locate the file. + @param path file-path. + @return local file under the directory with the given path.]]> + + + + + + + + + + + + name. + + @param name configuration resource name. + @return an input stream attached to the resource.]]> + + + + + + name. + + @param name configuration resource name. + @return a reader attached to the resource.]]> + + + + + + + + + + + + + + + + + + + + + + String + key-value pairs in the configuration. + + @return an iterator over the entries.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + When property name is not empty and the property exists in the + configuration, this method writes the property and its attributes + to the {@link Writer}. + +

+ +

  • + When property name is null or empty, this method writes all the + configuration properties and their attributes to the {@link Writer}. +
    • +

    + +

  • + When property name is not empty but the property doesn't exist in + the configuration, this method throws an {@link IllegalArgumentException}. +
    • +

    + @param out the writer to write to.]]> + + + + + + + + + + When propertyName is not empty, and the property exists + in the configuration, the format of the output would be, + 

    +  {
+    "property": {
+      "key" : "key1",
+      "value" : "value1",
+      "isFinal" : "key1.isFinal",
+      "resource" : "key1.resource"
+    }
+  }
+
    + + +
  • + When propertyName is null or empty, it behaves same as + {@link #dumpConfiguration(Configuration, Writer)}, the + output would be, + 
    +  { "properties" :
+      [ { key : "key1",
+          value : "value1",
+          isFinal : "key1.isFinal",
+          resource : "key1.resource" },
+        { key : "key2",
+          value : "value2",
+          isFinal : "ke2.isFinal",
+          resource : "key2.resource" }
+       ]
+   }
+
    +
    • + +
  • + When propertyName is not empty, and the property is not + found in the configuration, this method will throw an + {@link IllegalArgumentException}. +
    • +

    + @param config the configuration + @param propertyName property name + @param out the Writer to write to + @throws IOException + @throws IllegalArgumentException when property name is not + empty and the property is not found in configuration]]> + + + + + + + + + { "properties" : + [ { key : "key1", + value : "value1", + isFinal : "key1.isFinal", + resource : "key1.resource" }, + { key : "key2", + value : "value2", + isFinal : "ke2.isFinal", + resource : "key2.resource" } + ] + } + + + It does not output the properties of the configuration object which + is loaded from an input stream. +

    + + @param config the configuration + @param out the Writer to write to + @throws IOException]]> + + + + + + + + + + + + + + + + + + + true to set quiet-mode on, false + to turn it off.]]> + + + + + + + + + + + + + + + + + + + + + with matching keys]]> + + + + + + + + + + + + Resources + +

    Configurations are specified by resources. A resource contains a set of + name/value pairs as XML data. Each resource is named by either a + String or by a {@link Path}. If named by a String, + then the classpath is examined for a file with that name. If named by a + Path, then the local filesystem is examined directly, without + referring to the classpath. + +

    Unless explicitly turned off, Hadoop by default specifies two + resources, loaded in-order from the classpath:

      +
    1. + + core-default.xml: Read-only defaults for hadoop.
      2. +
    2. core-site.xml: Site-specific configuration for a given hadoop + installation.
      3. +
    + Applications may add additional resources, which are loaded + subsequent to these resources in the order they are added. + +

    Final Parameters

    + +

    Configuration parameters may be declared final. + Once a resource declares a value final, no subsequently-loaded + resource can alter that value. + For example, one might define a final parameter with: + 

    +  <property>
+    <name>dfs.hosts.include</name>
+    <value>/etc/hadoop/conf/hosts.include</value>
+    <final>true</final>
+  </property>
    + + Administrators typically define parameters as final in + core-site.xml for values that user applications may not alter. + +

    Variable Expansion

    + +

    Value strings are first processed for variable expansion. The + available properties are:

      +
    1. Other properties defined in this Configuration; and, if a name is + undefined here,
      2. +
    2. Properties in {@link System#getProperties()}.
      3. +
    + +

    For example, if a configuration resource contains the following property + definitions: + 

    +  <property>
+    <name>basedir</name>
+    <value>/user/${user.name}</value>
+  </property>
+  
+  <property>
+    <name>tempdir</name>
+    <value>${basedir}/tmp</value>
+  </property>
    + + When conf.get("tempdir") is called, then ${basedir} + will be resolved to another property in this Configuration, while + ${user.name} would then ordinarily be resolved to the value + of the System property with that name. +

    When conf.get("otherdir") is called, then ${env.BASE_DIR} + will be resolved to the value of the ${BASE_DIR} environment variable. + It supports ${env.NAME:-default} and ${env.NAME-default} notations. + The former is resolved to "default" if ${NAME} environment variable is undefined + or its value is empty. + The latter behaves the same way only if ${NAME} is undefined. +

    By default, warnings will be given to any deprecated configuration + parameters and these are suppressible by configuring + log4j.logger.org.apache.hadoop.conf.Configuration.deprecation in + log4j.properties file.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This implementation generates the key material and calls the + {@link #createKey(String, byte[], Options)} method. + + @param name the base name of the key + @param options the options for the new key. + @return the version name of the first version of the key. + @throws IOException + @throws NoSuchAlgorithmException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This implementation generates the key material and calls the + {@link #rollNewVersion(String, byte[])} method. + + @param name the basename of the key + @return the name of the new version of the key + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + KeyProvider implementations must be thread safe.]]> + + + + + + + + + + + + + + + + + + + + + + NULL if + a provider for the specified URI scheme could not be found. + @throws IOException thrown if the provider failed to initialize.]]> + + + + + + + + + + + + + + + + + + + + + uri has syntax error]]> + + + + + + + + + + + + + + + + uri is + not found]]> + + + + + + + + + + + + + + + + + + + + + + + uri + determines a configuration property name, + fs.AbstractFileSystem.scheme.impl whose value names the + AbstractFileSystem class. + + The entire URI and conf is passed to the AbstractFileSystem factory method. + + @param uri for the file system to be created. + @param conf which is passed to the file system impl. + + @return file system for the given URI. + + @throws UnsupportedFileSystemException if the file system for + uri is not supported.]]> + + + + + + + + + + + + default port;]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + describing modifications + @throws IOException if an ACL could not be modified]]> + + + + + + + + describing entries to remove + @throws IOException if an ACL could not be modified]]> + + + + + + + + + + + + + + + + + + + + + + describing modifications, must include entries + for user, group, and others for compatibility with permission bits. + @throws IOException if an ACL could not be modified]]> + + + + + + + which returns each AclStatus + @throws IOException if an ACL could not be read]]> + + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to modify + @param name xattr name. + @param value xattr value. + @throws IOException]]> + + + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to modify + @param name xattr name. + @param value xattr value. + @param flag xattr set flag + @throws IOException]]> + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attribute + @param name xattr name. + @return byte[] xattr value. + @throws IOException]]> + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attributes + @return Map describing the XAttrs of the file or directory + @throws IOException]]> + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attributes + @param names XAttr names. + @return Map describing the XAttrs of the file or directory + @throws IOException]]> + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attributes + @return Map describing the XAttrs of the file or directory + @throws IOException]]> + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to remove extended attribute + @param name xattr name + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + After a successful call, buf.position() will be advanced by the number + of bytes read and buf.limit() should be unchanged. +

    + In the case of an exception, the values of buf.position() and buf.limit() + are undefined, and callers should be prepared to recover from this + eventuality. +

    + Many implementations will throw {@link UnsupportedOperationException}, so + callers that are not confident in support for this method from the + underlying filesystem should be prepared to handle that exception. +

    + Implementations should treat 0-length requests as legitimate, and must not + signal an error upon their receipt. + + @param buf + the ByteBuffer to receive the results of the read operation. + @return the number of bytes read, possibly zero, or -1 if + reach end-of-stream + @throws IOException + if there is some error performing the read]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + setReplication of FileSystem + @param src file name + @param replication new replication + @throws IOException + @return true if successful; + false if file does not exist or is a directory]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + + + core-default.xml]]> + + + + + + + + + + + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + + + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + + + + + + + + core-default.xml]]> + + + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + + + + + + + core-default.xml]]> + + + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + + + + + + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + + + + + + core-default.xml]]> + + + + + + core-default.xml]]> + + + + + + + + core-default.xml]]> + + + + + + + + core-default.xml]]> + + + + + + + + core-default.xml]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + EnumSet.of(CreateFlag.CREATE, CreateFlag.APPEND) + +

    + + Use the CreateFlag as follows: +

      +
    1. CREATE - to create a file if it does not exist, + else throw FileAlreadyExists.
      2. +
    2. APPEND - to append to a file if it exists, + else throw FileNotFoundException.
      3. +
    3. OVERWRITE - to truncate a file if it exists, + else throw FileNotFoundException.
      4. +
    4. CREATE|APPEND - to create a file if it does not exist, + else append to an existing file.
      5. +
    5. CREATE|OVERWRITE - to create a file if it does not exist, + else overwrite an existing file.
      6. +
    6. SYNC_BLOCK - to force closed blocks to the disk device. + In addition {@link Syncable#hsync()} should be called after each write, + if true synchronous behavior is required.
      7. +
    7. LAZY_PERSIST - Create the block on transient storage (RAM) if + available.
      8. +
    8. APPEND_NEWBLOCK - Append data to a new block instead of end of the last + partial block.
      9. +
    + + Following combinations are not valid and will result in + {@link HadoopIllegalArgumentException}: +
      +
    1. APPEND|OVERWRITE
      2. +
    2. CREATE|APPEND|OVERWRITE
      3. +
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + absOrFqPath is not supported. + @throws IOException If the file system for absOrFqPath could + not be instantiated.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + defaultFsUri is not supported]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + NewWdir can be one of: +
      +
    • relative path: "foo/bar";
      • +
    • absolute without scheme: "/foo/bar"
      • +
    • fully qualified with scheme: "xx://auth/foo/bar"
      • +
    +
    + Illegal WDs: +
      +
    • relative with scheme: "xx:foo/bar"
      • +
    • non existent directory
      • +
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + f does not exist + @throws AccessControlException if access denied + @throws IOException If an IO Error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server + + RuntimeExceptions: + @throws InvalidPathException If path f is not valid]]> + + + + + + + + + + + + + + + + + + + + +
  • Progress - to report progress on the operation - default null +
  • Permission - umask is applied against permisssion: default is + FsPermissions:getDefault() + +
  • CreateParent - create missing parent path; default is to not + to create parents +
  • The defaults for the following are SS defaults of the file + server implementing the target path. Not all parameters make sense + for all kinds of file system - eg. localFS ignores Blocksize, + replication, checksum +
      +
    • BufferSize - buffersize used in FSDataOutputStream +
    • Blocksize - block size for file blocks +
    • ReplicationFactor - replication for blocks +
    • ChecksumParam - Checksum parameters. server default is used + if not specified. +
    + + + @return {@link FSDataOutputStream} for created file + + @throws AccessControlException If access is denied + @throws FileAlreadyExistsException If file f already exists + @throws FileNotFoundException If parent of f does not exist + and createParent is false + @throws ParentNotDirectoryException If parent of f is not a + directory. + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server + + RuntimeExceptions: + @throws InvalidPathException If path f is not valid]]> + + + + + + + + + + + + + + dir already + exists + @throws FileNotFoundException If parent of dir does not exist + and createParent is false + @throws ParentNotDirectoryException If parent of dir is not a + directory + @throws UnsupportedFileSystemException If file system for dir + is not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server + + RuntimeExceptions: + @throws InvalidPathException If path dir is not valid]]> + + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server + + RuntimeExceptions: + @throws InvalidPathException If path f is invalid]]> + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f + is not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + + +
  • Fails if path is a directory. +
  • Fails if path does not exist. +
  • Fails if path is not closed. +
  • Fails if new size is greater than current size. + + @param f The path to the file to be truncated + @param newLength The size the file is to be truncated to + + @return true if the file has been truncated to the desired + newLength and is immediately available to be reused for + write operations such as append, or + false if a background process of adjusting the length of + the last block has been started, and clients should wait for it to + complete before proceeding with further file updates. + + @throws AccessControlException If access is denied + @throws FileNotFoundException If file f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + f does not exist + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + + + + + +
  • Fails if src is a file and dst is a directory. +
  • Fails if src is a directory and dst is a file. +
  • Fails if the parent of dst does not exist or is a file. + +

    + If OVERWRITE option is not passed as an argument, rename fails if the dst + already exists. +

    + If OVERWRITE option is passed as an argument, rename overwrites the dst if + it is a file or an empty directory. Rename fails if dst is a non-empty + directory. +

    + Note that atomicity of rename is dependent on the file system + implementation. Please refer to the file system documentation for details +

    + + @param src path to be renamed + @param dst new path after rename + + @throws AccessControlException If access is denied + @throws FileAlreadyExistsException If dst already exists and + options has {@link Options.Rename#OVERWRITE} + option false. + @throws FileNotFoundException If src does not exist + @throws ParentNotDirectoryException If parent of dst is not a + directory + @throws UnsupportedFileSystemException If file system for src + and dst is not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f + is not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server + + RuntimeExceptions: + @throws HadoopIllegalArgumentException If username or + groupname is invalid.]]> + + + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + f does not exist + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred]]> + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If the given path does not refer to a symlink + or an I/O error occurred]]> + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + + + + + + Given a path referring to a symlink of form: + + <---X---> + fs://host/A/B/link + <-----Y-----> + + In this path X is the scheme and authority that identify the file system, + and Y is the path leading up to the final path component "link". If Y is + a symlink itself then let Y' be the target of Y and X' be the scheme and + authority of Y'. Symlink targets may: + + 1. Fully qualified URIs + + fs://hostX/A/B/file Resolved according to the target file system. + + 2. Partially qualified URIs (eg scheme but no host) + + fs:///A/B/file Resolved according to the target file system. Eg resolving + a symlink to hdfs:///A results in an exception because + HDFS URIs must be fully qualified, while a symlink to + file:///A will not since Hadoop's local file systems + require partially qualified URIs. + + 3. Relative paths + + path Resolves to [Y'][path]. Eg if Y resolves to hdfs://host/A and path + is "../B/file" then [Y'][path] is hdfs://host/B/file + + 4. Absolute paths + + path Resolves to [X'][path]. Eg if Y resolves hdfs://host/A/B and path + is "/file" then [X][path] is hdfs://host/file + + + @param target the target of the symbolic link + @param link the path to be created that points to target + @param createParent if true then missing parent dirs are created if + false then parent must exist + + + @throws AccessControlException If access is denied + @throws FileAlreadyExistsException If file linkcode> already exists + @throws FileNotFoundException If target does not exist + @throws ParentNotDirectoryException If parent of link is not a + directory. + @throws UnsupportedFileSystemException If file system for + target or link is not supported + @throws IOException If an I/O error occurred]]> + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + + + + + + + + f does not exist + @throws UnsupportedFileSystemException If file system for f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + f is + not supported + @throws IOException If an I/O error occurred + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + describing modifications + @throws IOException if an ACL could not be modified]]> + + + + + + + + describing entries to remove + @throws IOException if an ACL could not be modified]]> + + + + + + + + + + + + + + + + + + + + + + describing modifications, must include entries + for user, group, and others for compatibility with permission bits. + @throws IOException if an ACL could not be modified]]> + + + + + + + which returns each AclStatus + @throws IOException if an ACL could not be read]]> + + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to modify + @param name xattr name. + @param value xattr value. + @throws IOException]]> + + + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to modify + @param name xattr name. + @param value xattr value. + @param flag xattr set flag + @throws IOException]]> + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attribute + @param name xattr name. + @return byte[] xattr value. + @throws IOException]]> + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attributes + @return Map describing the XAttrs of the file or directory + @throws IOException]]> + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attributes + @param names XAttr names. + @return Map describing the XAttrs of the file or directory + @throws IOException]]> + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to remove extended attribute + @param name xattr name + @throws IOException]]> + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attributes + @return List of the XAttr names of the file or directory + @throws IOException]]> + + + + + + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + Exceptions applicable to file systems accessed over RPC: + @throws RpcClientException If an exception occurred in the RPC client + @throws RpcServerException If an exception occurred in the RPC server + @throws UnexpectedServerException If server implementation throws + undeclared exception to RPC server]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + *** Path Names *** +

    + + The Hadoop file system supports a URI name space and URI names. + It offers a forest of file systems that can be referenced using fully + qualified URIs. + Two common Hadoop file systems implementations are +

      +
    • the local file system: file:///path +
    • the hdfs file system hdfs://nnAddress:nnPort/path +
    + + While URI names are very flexible, it requires knowing the name or address + of the server. For convenience one often wants to access the default system + in one's environment without knowing its name/address. This has an + additional benefit that it allows one to change one's default fs + (e.g. admin moves application from cluster1 to cluster2). +

    + + To facilitate this, Hadoop supports a notion of a default file system. + The user can set his default file system, although this is + typically set up for you in your environment via your default config. + A default file system implies a default scheme and authority; slash-relative + names (such as /for/bar) are resolved relative to that default FS. + Similarly a user can also have working-directory-relative names (i.e. names + not starting with a slash). While the working directory is generally in the + same default FS, the wd can be in a different FS. +

    + Hence Hadoop path names can be one of: +

      +
    • fully qualified URI: scheme://authority/path +
    • slash relative names: /path relative to the default file system +
    • wd-relative names: path relative to the working dir +
    + Relative paths with scheme (scheme:foo/bar) are illegal. + +

    + ****The Role of the FileContext and configuration defaults**** +

    + The FileContext provides file namespace context for resolving file names; + it also contains the umask for permissions, In that sense it is like the + per-process file-related state in Unix system. + These two properties +

      +
    • default file system i.e your slash) +
    • umask +
    + in general, are obtained from the default configuration file + in your environment, (@see {@link Configuration}). + + No other configuration parameters are obtained from the default config as + far as the file context layer is concerned. All file system instances + (i.e. deployments of file systems) have default properties; we call these + server side (SS) defaults. Operation like create allow one to select many + properties: either pass them in as explicit parameters or use + the SS properties. +

    + The file system related SS defaults are +

      +
    • the home directory (default is "/user/userName") +
    • the initial wd (only for local fs) +
    • replication factor +
    • block size +
    • buffer size +
    • encryptDataTransfer +
    • checksum option. (checksumType and bytesPerChecksum) +
    + +

    + *** Usage Model for the FileContext class *** +

    + Example 1: use the default config read from the $HADOOP_CONFIG/core.xml. + Unspecified values come from core-defaults.xml in the release jar. +

      +
    • myFContext = FileContext.getFileContext(); // uses the default config + // which has your default FS +
    • myFContext.create(path, ...); +
    • myFContext.setWorkingDir(path) +
    • myFContext.open (path, ...); +
    + Example 2: Get a FileContext with a specific URI as the default FS +
      +
    • myFContext = FileContext.getFileContext(URI) +
    • myFContext.create(path, ...); + ... +
    + Example 3: FileContext with local file system as the default +
      +
    • myFContext = FileContext.getLocalFSFileContext() +
    • myFContext.create(path, ...); +
    • ... +
    + Example 4: Use a specific config, ignoring $HADOOP_CONFIG + Generally you should not need use a config unless you are doing +
      +
    • configX = someConfigSomeOnePassedToYou. +
    • myFContext = getFileContext(configX); // configX is not changed, + // is passed down +
    • myFContext.create(path, ...); +
    • ... +
    ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This implementation throws an UnsupportedOperationException. + + @return the protocol scheme for the FileSystem.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + fs.scheme.class whose value names the FileSystem class. + The entire URI is passed to the FileSystem instance's initialize method.]]> + + + + + + + + + + + + + + + + + + fs.scheme.class whose value names the FileSystem class. + The entire URI is passed to the FileSystem instance's initialize method. + This always returns a new FileSystem object.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
  • Fails if src is a file and dst is a directory. +
  • Fails if src is a directory and dst is a file. +
  • Fails if the parent of dst does not exist or is a file. + +

    + If OVERWRITE option is not passed as an argument, rename fails + if the dst already exists. +

    + If OVERWRITE option is passed as an argument, rename overwrites + the dst if it is a file or an empty directory. Rename fails if dst is + a non-empty directory. +

    + Note that atomicity of rename is dependent on the file system + implementation. Please refer to the file system documentation for + details. This default implementation is non atomic. +

    + This method is deprecated since it is a temporary method added to + support the transition from FileSystem to FileContext for user + applications. + + @param src path to be renamed + @param dst new path after rename + @throws IOException on failure]]> + + + + + + + + +

  • Fails if path is a directory. +
  • Fails if path does not exist. +
  • Fails if path is not closed. +
  • Fails if new size is greater than current size. + + @param f The path to the file to be truncated + @param newLength The size the file is to be truncated to + + @return true if the file has been truncated to the desired + newLength and is immediately available to be reused for + write operations such as append, or + false if a background process of adjusting the length of + the last block has been started, and clients should wait for it to + complete before proceeding with further file updates.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Does not guarantee to return the List of files/directories status in a + sorted order. + @param f given path + @return the statuses of the files/directories in the given patch + @throws FileNotFoundException when the path does not exist; + IOException see specific implementation]]> + + + + + + + + + + + + + + + + + Does not guarantee to return the List of files/directories status in a + sorted order. + + @param f + a path name + @param filter + the user-supplied path filter + @return an array of FileStatus objects for the files under the given path + after applying the filter + @throws FileNotFoundException when the path does not exist; + IOException see specific implementation]]> + + + + + + + + + Does not guarantee to return the List of files/directories status in a + sorted order. + + @param files + a list of paths + @return a list of statuses for the files under the given paths after + applying the filter default Path filter + @throws FileNotFoundException when the path does not exist; + IOException see specific implementation]]> + + + + + + + + + + Does not guarantee to return the List of files/directories status in a + sorted order. + + @param files + a list of paths + @param filter + the user-supplied path filter + @return a list of statuses for the files under the given paths after + applying the filter + @throws FileNotFoundException when the path does not exist; + IOException see specific implementation]]> + + + + + + + Return all the files that match filePattern and are not checksum + files. Results are sorted by their names. + +

    + A filename pattern is composed of regular characters and + special pattern matching characters, which are: + +

    +
    +
    +

    +

    ? +
    Matches any single character. + +

    +

    * +
    Matches zero or more characters. + +

    +

    [abc] +
    Matches a single character from character set + {a,b,c}. + +

    +

    [a-b] +
    Matches a single character from the character range + {a...b}. Note that character a must be + lexicographically less than or equal to character b. + +

    +

    [^a] +
    Matches a single character that is not from character set or range + {a}. Note that the ^ character must occur + immediately to the right of the opening bracket. + +

    +

    \c +
    Removes (escapes) any special meaning of character c. + +

    +

    {ab,cd} +
    Matches a string from the string set {ab, cd} + +

    +

    {ab,c{de,fh}} +
    Matches a string from the string set {ab, cde, cfh} + +
    +
    +
    + + @param pathPattern a regular expression specifying a pth pattern + + @return an array of paths that match the path pattern + @throws IOException]]> +     +     + + + + + + + + + + + + + + f does not exist + @throws IOException If an I/O error occurred]]> + + + + + + + + + f does not exist + @throws IOException if any I/O error occurred]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + describing modifications + @throws IOException if an ACL could not be modified]]> + + + + + + + + describing entries to remove + @throws IOException if an ACL could not be modified]]> + + + + + + + + + + + + + + + + + + + + + + describing modifications, must include entries + for user, group, and others for compatibility with permission bits. + @throws IOException if an ACL could not be modified]]> + + + + + + + + + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to modify + @param name xattr name. + @param value xattr value. + @throws IOException]]> + + + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to modify + @param name xattr name. + @param value xattr value. + @param flag xattr set flag + @throws IOException]]> + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attribute + @param name xattr name. + @return byte[] xattr value. + @throws IOException]]> + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attributes + @return Map describing the XAttrs of the file or directory + @throws IOException]]> + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attributes + @param names XAttr names. + @return Map describing the XAttrs of the file or directory + @throws IOException]]> + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to get extended attributes + @return List of the XAttr names of the file or directory + @throws IOException]]> + + + + + + + + + Refer to the HDFS extended attributes user documentation for details. + + @param path Path to remove extended attribute + @param name xattr name + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This is a default method which is intended to be overridden by + subclasses. The default implementation returns an empty storage statistics + object.

    + + @return The StorageStatistics for this FileSystem instance. + Will never be null.]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + All user code that may potentially use the Hadoop Distributed + File System should be written to use a FileSystem object. The + Hadoop DFS is a multi-machine system that appears as a single + disk. It's useful because of its fault tolerance and potentially + very large capacity. + +

    + The local implementation is {@link LocalFileSystem} and distributed + implementation is DistributedFileSystem.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + caller's environment variables to use + for expansion + @return String[] with absolute path to new jar in position 0 and + unexpanded wild card entry path in position 1 + @throws IOException if there is an I/O error while writing the jar file]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + FilterFileSystem contains + some other file system, which it uses as + its basic file system, possibly transforming + the data along the way or providing additional + functionality. The class FilterFileSystem + itself simply overrides all methods of + FileSystem with versions that + pass all requests to the contained file + system. Subclasses of FilterFileSystem + may further override some of these methods + and may also provide additional methods + and fields.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + -1 + if there is no more data because the end of the stream has been + reached]]> + + + + + + + + + + length bytes have been read. + + @param position position in the input stream to seek + @param buffer buffer into which data is read + @param offset offset into the buffer in which data is written + @param length the number of bytes to read + @throws IOException IO problems + @throws EOFException If the end of stream is reached while reading. + If an exception is thrown an undetermined number + of bytes in the buffer may have been written.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + path is invalid]]> + + + + + + + + + + + + + + + + + + + + + + + @return file]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + and the scheme is null, and the authority + is null. + + @return whether the path is absolute and the URI has no scheme nor + authority parts]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if and only if pathname + should be included]]> + + + + + + + + + + + + + + Warning: Not all filesystems satisfy the thread-safety requirement. + @param position position within file + @param buffer destination buffer + @param offset offset in the buffer + @param length number of bytes to read + @return actual number of bytes read; -1 means "none" + @throws IOException IO problems.]]> + + + + + + + + + + Warning: Not all filesystems satisfy the thread-safety requirement. + @param position position within file + @param buffer destination buffer + @param offset offset in the buffer + @param length number of bytes to read + @throws IOException IO problems. + @throws EOFException the end of the data was reached before + the read operation completed]]> + + + + + + + + Warning: Not all filesystems satisfy the thread-safety requirement. + @param position position within file + @param buffer destination buffer + @throws IOException IO problems. + @throws EOFException the end of the data was reached before + the read operation completed]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + <----15----> <----15----> <----15----> <-------18-------> + QUOTA REMAINING_QUATA SPACE_QUOTA SPACE_QUOTA_REM FILE_NAME]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + XAttr is byte[], this class is to + covert byte[] to some kind of string representation or convert back. + String representation is convenient for display and input. For example + display in screen as shell response and json response, input as http + or shell parameter.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @return ftp]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + A {@link FileSystem} backed by an FTP client provided by Apache Commons Net. +

    ]]> +     + + + + + + + + + + + + + + + + + + + (cause==null ? null : cause.toString()) (which + typically contains the class and detail message of cause). + @param cause the cause (which is saved for later retrieval by the + {@link #getCause()} method). (A null value is + permitted, and indicates that the cause is nonexistent or + unknown.)]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + But for removeAcl operation it will be false. i.e. AclSpec should + not contain permissions.
    + Example: "user:foo,group:bar" + @return Returns list of {@link AclEntry} parsed]]> +     +     + + + + + + The expected format of ACL entries in the string parameter is the same + format produced by the {@link #toStringStable()} method. + + @param aclStr + String representation of an ACL.
    + Example: "user:foo:rw-" + @param includePermission + for setAcl operations this will be true. i.e. Acl should include + permissions.
    + But for removeAcl operation it will be false. i.e. Acl should not + contain permissions.
    + Example: "user:foo,group:bar,mask::" + @return Returns an {@link AclEntry} object]]> +     +     + + + + + + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + unmodifiable ordered list of all ACL entries]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + Recommended to use this API ONLY if client communicates with the old + NameNode, needs to pass the Permission for the path to get effective + permission, else use {@link AclStatus#getEffectivePermission(AclEntry)}. + @param entry AclEntry to get the effective action + @param permArg Permission for the path. However if the client is NOT + communicating with old namenode, then this argument will not have + any preference. + @return Returns the effective permission for the entry. + @throws IllegalArgumentException If the client communicating with old + namenode and permission is not passed as an argument.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + mode is invalid]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @return viewfs]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
  • /user -> hdfs://nnContainingUserDir/user +
  • /project/foo -> hdfs://nnProject1/projects/foo +
  • /project/bar -> hdfs://nnProject2/projects/bar +
  • /tmp -> hdfs://nnTmp/privateTmpForUserXXX + + + ViewFs is specified with the following URI: viewfs:/// +

    + To use viewfs one would typically set the default file system in the + config (i.e. fs.defaultFS < = viewfs:///) along with the + mount table config variables as described below. + +

    + ** Config variables to specify the mount table entries ** +

    + + The file system is initialized from the standard Hadoop config through + config variables. + See {@link FsConstants} for URI and Scheme constants; + See {@link Constants} for config var constants; + see {@link ConfigUtil} for convenient lib. + +

    + All the mount table config entries for view fs are prefixed by + fs.viewfs.mounttable. + For example the above example can be specified with the following + config variables: +

      +
    • fs.viewfs.mounttable.default.link./user= + hdfs://nnContainingUserDir/user +
    • fs.viewfs.mounttable.default.link./project/foo= + hdfs://nnProject1/projects/foo +
    • fs.viewfs.mounttable.default.link./project/bar= + hdfs://nnProject2/projects/bar +
    • fs.viewfs.mounttable.default.link./tmp= + hdfs://nnTmp/privateTmpForUserXXX +
    + + The default mount table (when no authority is specified) is + from config variables prefixed by fs.viewFs.mounttable.default + The authority component of a URI can be used to specify a different mount + table. For example, +
      +
    • viewfs://sanjayMountable/ +
    + is initialized from fs.viewFs.mounttable.sanjayMountable.* config variables. + +

    + **** Merge Mounts **** (NOTE: merge mounts are not implemented yet.) +

    + + One can also use "MergeMounts" to merge several directories (this is + sometimes called union-mounts or junction-mounts in the literature. + For example of the home directories are stored on say two file systems + (because they do not fit on one) then one could specify a mount + entry such as following merges two dirs: +

      +
    • /user -> hdfs://nnUser1/user,hdfs://nnUser2/user +
    + Such a mergeLink can be specified with the following config var where "," + is used as the separator for each of links to be merged: +
      +
    • fs.viewfs.mounttable.default.linkMerge./user= + hdfs://nnUser1/user,hdfs://nnUser1/user +
    + A special case of the merge mount is where mount table's root is merged + with the root (slash) of another file system: +
      +
    • fs.viewfs.mounttable.default.linkMergeSlash=hdfs://nn99/ +
    + In this cases the root of the mount table is merged with the root of + hdfs://nn99/ ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Since these methods are often vendor- or device-specific, operators + may implement this interface in order to achieve fencing. +

    + Fencing is configured by the operator as an ordered list of methods to + attempt. Each method will be tried in turn, and the next in the list + will only be attempted if the previous one fails. See {@link NodeFencer} + for more information. +

    + If an implementation also implements {@link Configurable} then its + setConf method will be called upon instantiation.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + state (e.g ACTIVE/STANDBY) as well as + some additional information. + + @throws AccessControlException + if access is denied. + @throws IOException + if other errors happen + @see HAServiceStatus]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + hadoop.http.filter.initializers. + +

      +
    • StaticUserWebFilter - An authorization plugin that makes all +users a static configured user. +
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + public class IntArrayWritable extends ArrayWritable { + public IntArrayWritable() { + super(IntWritable.class); + } + } + ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + o is a ByteWritable with the same value.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + the class of the item + @param conf the configuration to store + @param item the object to be stored + @param keyName the name of the key to use + @throws IOException : forwards Exceptions from the underlying + {@link Serialization} classes.]]> + + + + + + + + + the class of the item + @param conf the configuration to use + @param keyName the name of the key to use + @param itemClass the class of the item + @return restored object + @throws IOException : forwards Exceptions from the underlying + {@link Serialization} classes.]]> + + + + + + + + + the class of the item + @param conf the configuration to use + @param items the objects to be stored + @param keyName the name of the key to use + @throws IndexOutOfBoundsException if the items array is empty + @throws IOException : forwards Exceptions from the underlying + {@link Serialization} classes.]]> + + + + + + + + + the class of the item + @param conf the configuration to use + @param keyName the name of the key to use + @param itemClass the class of the item + @return restored object + @throws IOException : forwards Exceptions from the underlying + {@link Serialization} classes.]]> + + + + + DefaultStringifier offers convenience methods to store/load objects to/from + the configuration. + + @param the class of the objects to stringify]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + o is a DoubleWritable with the same value.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + value argument is null or + its size is zero, the elementType argument must not be null. If + the argument value's size is bigger than zero, the argument + elementType is not be used. + + @param value + @param elementType]]> + + + + + value should not be null + or empty. + + @param value]]> + + + + + + + + + + + + + + value and elementType. If the value argument + is null or its size is zero, the elementType argument must not be + null. If the argument value's size is bigger than zero, the + argument elementType is not be used. + + @param value + @param elementType]]> + + + + + + + + + + + + + + + + + + + o is an EnumSetWritable with the same value, + or both are null.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + o is a FloatWritable with the same value.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + When two sequence files, which have same Key type but different Value + types, are mapped out to reduce, multiple Value types is not allowed. + In this case, this class can help you wrap instances with different types. +

    + +

    + Compared with ObjectWritable, this class is much more effective, + because ObjectWritable will append the class declaration as a String + into the output file in every Key-Value pair. +

    + +

    + Generic Writable implements {@link Configurable} interface, so that it will be + configured by the framework. The configuration is passed to the wrapped objects + implementing {@link Configurable} interface before deserialization. +

    + + how to use it:
    + 1. Write your own class, such as GenericObject, which extends GenericWritable.
    + 2. Implements the abstract method getTypes(), defines + the classes which will be wrapped in GenericObject in application. + Attention: this classes defined in getTypes() method, must + implement Writable interface. +

    + + The code looks like this: + 
    + public class GenericObject extends GenericWritable {
+ 
+   private static Class[] CLASSES = {
+               ClassType1.class, 
+               ClassType2.class,
+               ClassType3.class,
+               };
+
+   protected Class[] getTypes() {
+       return CLASSES;
+   }
+
+ }
+
    + + @since Nov 8, 2006]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + o is a IntWritable with the same value.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + closes the input and output streams + at the end. + + @param in InputStrem to read from + @param out OutputStream to write to + @param conf the Configuration object]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ignore any {@link IOException} or + null pointers. Must only be used for cleanup in exception handlers. + + @param log the log to record problems to at debug level. Can be null. + @param closeables the objects to close]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This is better than File#listDir because it does not ignore IOExceptions. + + @param dir The directory to list. + @param filter If non-null, the filter to use when listing + this directory. + @return The list of files in the directory. + + @throws IOException On I/O error]]> + + + + + + + + Borrowed from Uwe Schindler in LUCENE-5588 + @param fileToSync the file to fsync]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + o is a LongWritable with the same value.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + A map is a directory containing two files, the data file, + containing all keys and values in the map, and a smaller index + file, containing a fraction of the keys. The fraction is determined by + {@link Writer#getIndexInterval()}. + +

    The index file is read entirely into memory. Thus key implementations + should try to keep themselves small. + +

    Map files are created by adding entries in-order. To maintain a large + database, perform updates by copying the previous version of a database and + merging in a sorted change list, to create a new version of the database in + a new file. Sorting large change lists can be done with {@link + SequenceFile.Sorter}.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + o is an MD5Hash whose digest contains the + same values.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + className by first finding + it in the specified conf. If the specified conf is null, + try load it directly.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + A {@link Comparator} that operates directly on byte representations of + objects. +

    + @param + @see DeserializerComparator]]> +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + SequenceFiles are flat files consisting of binary key/value + pairs. + +

    SequenceFile provides {@link SequenceFile.Writer}, + {@link SequenceFile.Reader} and {@link Sorter} classes for writing, + reading and sorting respectively.

    + + There are three SequenceFile Writers based on the + {@link CompressionType} used to compress key/value pairs: +
      +
    1. + Writer : Uncompressed records. +
      2. +
    2. + RecordCompressWriter : Record-compressed files, only compress + values. +
      3. +
    3. + BlockCompressWriter : Block-compressed files, both keys & + values are collected in 'blocks' + separately and compressed. The size of + the 'block' is configurable. +
    + +

    The actual compression algorithm used to compress key and/or values can be + specified by using the appropriate {@link CompressionCodec}.

    + +

    The recommended way is to use the static createWriter methods + provided by the SequenceFile to chose the preferred format.

    + +

    The {@link SequenceFile.Reader} acts as the bridge and can read any of the + above SequenceFile formats.

    + +

    SequenceFile Formats

    + +

    Essentially there are 3 different formats for SequenceFiles + depending on the CompressionType specified. All of them share a + common header described below. + +

    +
      +
    • + version - 3 bytes of magic header SEQ, followed by 1 byte of actual + version number (e.g. SEQ4 or SEQ6) +
      • +
    • + keyClassName -key class +
      • +
    • + valueClassName - value class +
      • +
    • + compression - A boolean which specifies if compression is turned on for + keys/values in this file. +
      • +
    • + blockCompression - A boolean which specifies if block-compression is + turned on for keys/values in this file. +
      • +
    • + compression codec - CompressionCodec class which is used for + compression of keys and/or values (if compression is + enabled). +
      • +
    • + metadata - {@link Metadata} for this file. +
      • +
    • + sync - A sync marker to denote end of the header. +
      • +
    + +
    Uncompressed SequenceFile Format
    +
      +
    • + Header +
      • +
    • + Record +
        +
      • Record length
        • +
      • Key length
        • +
      • Key
        • +
      • Value
        • +
      +
      • +
    • + A sync-marker every few 100 bytes or so. +
      • +
    + +
    Record-Compressed SequenceFile Format
    +
      +
    • + Header +
      • +
    • + Record +
        +
      • Record length
        • +
      • Key length
        • +
      • Key
        • +
      • Compressed Value
        • +
      +
      • +
    • + A sync-marker every few 100 bytes or so. +
      • +
    + +
    Block-Compressed SequenceFile Format
    +
      +
    • + Header +
      • +
    • + Record Block +
        +
      • Uncompressed number of records in the block
        • +
      • Compressed key-lengths block-size
        • +
      • Compressed key-lengths block
        • +
      • Compressed keys block-size
        • +
      • Compressed keys block
        • +
      • Compressed value-lengths block-size
        • +
      • Compressed value-lengths block
        • +
      • Compressed values block-size
        • +
      • Compressed values block
        • +
      +
      • +
    • + A sync-marker every block. +
      • +
    + +

    The compressed blocks of key lengths and value lengths consist of the + actual lengths of individual keys/values encoded in ZeroCompressedInteger + format.

    + + @see CompressionCodec]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + o is a ShortWritable with the same value.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + the class of the objects to stringify]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + position. Note that this + method avoids using the converter or doing String instantiation + @return the Unicode scalar value at position or -1 + if the position is invalid or points to a + trailing byte]]> + + + + + + + + + + what in the backing + buffer, starting as position start. The starting + position is measured in bytes and the return value is in + terms of byte position in the buffer. The backing buffer is + not converted to a string for this operation. + @return byte position of the first occurence of the search + string in the UTF-8 buffer or -1 if not found]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Note: For performance reasons, this call does not clear the + underlying byte array that is retrievable via {@link #getBytes()}. + In order to free the byte-array memory, call {@link #set(byte[])} + with an empty byte array (For example, new byte[0]).]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + o is a Text with the same contents.]]> + + + + + + + + + + + + + + + + + + + + + + + + + replace is true, then + malformed input is replaced with the + substitution character, which is U+FFFD. Otherwise the + method throws a MalformedInputException.]]> + + + + + + + + + + + + + + + replace is true, then + malformed input is replaced with the + substitution character, which is U+FFFD. Otherwise the + method throws a MalformedInputException. + @return ByteBuffer: bytes stores at ByteBuffer.array() + and length is ByteBuffer.limit()]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + In + addition, it provides methods for string traversal without converting the + byte array to a string.

    Also includes utilities for + serializing/deserialing a string, coding/decoding a string, checking if a + byte array contains valid UTF8 code, calculating the length of an encoded + string.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This is useful when a class may evolve, so that instances written by the + old version of the class may still be processed by the new version. To + handle this situation, {@link #readFields(DataInput)} + implementations should catch {@link VersionMismatchException}.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + o is a VIntWritable with the same value.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + o is a VLongWritable with the same value.]]> + + + + + + + + + + + + + + + + + + + + + + + + out. + + @param out DataOuput to serialize this object into. + @throws IOException]]> + + + + + + + in. + +

    For efficiency, implementations should attempt to re-use storage in the + existing object where possible.

    + + @param in DataInput to deseriablize this object from. + @throws IOException]]> +     + + + Any key or value type in the Hadoop Map-Reduce + framework implements this interface.

    + +

    Implementations typically implement a static read(DataInput) + method which constructs a new instance, calls {@link #readFields(DataInput)} + and returns the instance.

    + +

    Example:

    + 

    +     public class MyWritable implements Writable {
+       // Some data     
+       private int counter;
+       private long timestamp;
+       
+       public void write(DataOutput out) throws IOException {
+         out.writeInt(counter);
+         out.writeLong(timestamp);
+       }
+       
+       public void readFields(DataInput in) throws IOException {
+         counter = in.readInt();
+         timestamp = in.readLong();
+       }
+       
+       public static MyWritable read(DataInput in) throws IOException {
+         MyWritable w = new MyWritable();
+         w.readFields(in);
+         return w;
+       }
+     }
+

    ]]> +     + + + + + + + + WritableComparables can be compared to each other, typically + via Comparators. Any type which is to be used as a + key in the Hadoop Map-Reduce framework should implement this + interface.

    + +

    Note that hashCode() is frequently used in Hadoop to partition + keys. It's important that your implementation of hashCode() returns the same + result across different instances of the JVM. Note also that the default + hashCode() implementation in Object does not + satisfy this property.

    + +

    Example:

    + 

    +     public class MyWritableComparable implements WritableComparable {
+       // Some data
+       private int counter;
+       private long timestamp;
+       
+       public void write(DataOutput out) throws IOException {
+         out.writeInt(counter);
+         out.writeLong(timestamp);
+       }
+       
+       public void readFields(DataInput in) throws IOException {
+         counter = in.readInt();
+         timestamp = in.readLong();
+       }
+       
+       public int compareTo(MyWritableComparable o) {
+         int thisValue = this.value;
+         int thatValue = o.value;
+         return (thisValue < thatValue ? -1 : (thisValue==thatValue ? 0 : 1));
+       }
+
+       public int hashCode() {
+         final int prime = 31;
+         int result = 1;
+         result = prime * result + counter;
+         result = prime * result + (int) (timestamp ^ (timestamp >>> 32));
+         return result
+       }
+     }
+

    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + The default implementation reads the data into two {@link + WritableComparable}s (using {@link + Writable#readFields(DataInput)}, then calls {@link + #compare(WritableComparable,WritableComparable)}.]]> + + + + + + + The default implementation uses the natural ordering, calling {@link + Comparable#compareTo(Object)}.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This base implemenation uses the natural ordering. To define alternate + orderings, override {@link #compare(WritableComparable,WritableComparable)}. + +

    One may optimize compare-intensive operations by overriding + {@link #compare(byte[],int,int,byte[],int,int)}. Static utility methods are + provided to assist in optimized implementations of this method.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Enum type + @param in DataInput to read from + @param enumType Class type of Enum + @return Enum represented by String read from DataInput + @throws IOException]]> + + + + + + + + + + + + + + + + len number of bytes in input streamin + @param in input stream + @param len number of bytes to skip + @throws IOException when skipped less number of bytes]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + CompressionCodec for which to get the + Compressor + @param conf the Configuration object which contains confs for creating or reinit the compressor + @return Compressor for the given + CompressionCodec from the pool or a new one]]> + + + + + + + + + CompressionCodec for which to get the + Decompressor + @return Decompressor for the given + CompressionCodec the pool or a new one]]> + + + + + + Compressor to be returned to the pool]]> + + + + + + Decompressor to be returned to the + pool]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Codec aliases are case insensitive. +

    + The code alias is the short class name (without the package name). + If the short class name ends with 'Codec', then there are two aliases for + the codec, the complete short class name and the short class name without + the 'Codec' ending. For example for the 'GzipCodec' codec class name the + alias are 'gzip' and 'gzipcodec'. + + @param codecName the canonical class name of the codec + @return the codec object]]> + + + + + + + Codec aliases are case insensitive. +

    + The code alias is the short class name (without the package name). + If the short class name ends with 'Codec', then there are two aliases for + the codec, the complete short class name and the short class name without + the 'Codec' ending. For example for the 'GzipCodec' codec class name the + alias are 'gzip' and 'gzipcodec'. + + @param codecName the canonical class name of the codec + @return the codec class]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Implementations are assumed to be buffered. This permits clients to + reposition the underlying input stream then call {@link #resetState()}, + without having to also synchronize client buffers.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true indicating that more input data is required. + + @param b Input data + @param off Start offset + @param len Length]]> + + + + + true if the input data buffer is empty and + #setInput() should be called in order to provide more input.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if the end of the compressed + data output stream has been reached.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true indicating that more input data is required. + (Both native and non-native versions of various Decompressors require + that the data passed in via b[] remain unmodified until + the caller is explicitly notified--via {@link #needsInput()}--that the + buffer may be safely modified. With this requirement, an extra + buffer-copy can be avoided.) + + @param b Input data + @param off Start offset + @param len Length]]> + + + + + true if the input data buffer is empty and + {@link #setInput(byte[], int, int)} should be called to + provide more input. + + @return true if the input data buffer is empty and + {@link #setInput(byte[], int, int)} should be called in + order to provide more input.]]> + + + + + + + + + + + + + true if a preset dictionary is needed for decompression. + @return true if a preset dictionary is needed for decompression]]> + + + + + true if the end of the decompressed + data output stream has been reached. Indicates a concatenated data stream + when finished() returns true and {@link #getRemaining()} + returns a positive value. finished() will be reset with the + {@link #reset()} method. + @return true if the end of the decompressed + data output stream has been reached.]]> + + + + + + + + + + + + + + true and getRemaining() returns a positive value. If + {@link #finished()} returns true and getRemaining() returns + a zero value, indicates that the end of data stream has been reached and + is not a concatenated data stream. + @return The number of bytes remaining in the compressed data buffer.]]> + + + + + true and {@link #getRemaining()} returns a positive value, + reset() is called before processing of the next data stream in the + concatenated data stream. {@link #finished()} will be reset and will + return false when reset() is called.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +

  • "none" - No compression. +
  • "lzo" - LZO compression. +
  • "gz" - GZIP compression. + ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
  • Block Compression. +
  • Named meta data blocks. +
  • Sorted or unsorted keys. +
  • Seek by key or by file offset. + + The memory footprint of a TFile includes the following: +
      +
    • Some constant overhead of reading or writing a compressed block. +
        +
      • Each compressed block requires one compression/decompression codec for + I/O. +
      • Temporary space to buffer the key. +
      • Temporary space to buffer the value (for TFile.Writer only). Values are + chunk encoded, so that we buffer at most one chunk of user data. By default, + the chunk buffer is 1MB. Reading chunked value does not require additional + memory. +
      +
    • TFile index, which is proportional to the total number of Data Blocks. + The total amount of memory needed to hold the index can be estimated as + (56+AvgKeySize)*NumBlocks. +
    • MetaBlock index, which is proportional to the total number of Meta + Blocks.The total amount of memory needed to hold the index for Meta Blocks + can be estimated as (40+AvgMetaBlockName)*NumMetaBlock. +
    +

    + The behavior of TFile can be customized by the following variables through + Configuration: +

      +
    • tfile.io.chunk.size: Value chunk size. Integer (in bytes). Default + to 1MB. Values of the length less than the chunk size is guaranteed to have + known value length in read time (See + {@link TFile.Reader.Scanner.Entry#isValueLengthKnown()}). +
    • tfile.fs.output.buffer.size: Buffer size used for + FSDataOutputStream. Integer (in bytes). Default to 256KB. +
    • tfile.fs.input.buffer.size: Buffer size used for + FSDataInputStream. Integer (in bytes). Default to 256KB. +
    +

    + Suggestions on performance optimization. +

      +
    • Minimum block size. We recommend a setting of minimum block size between + 256KB to 1MB for general usage. Larger block size is preferred if files are + primarily for sequential access. However, it would lead to inefficient random + access (because there are more data to decompress). Smaller blocks are good + for random access, but require more memory to hold the block index, and may + be slower to create (because we must flush the compressor stream at the + conclusion of each data block, which leads to an FS I/O flush). Further, due + to the internal caching in Compression codec, the smallest possible block + size would be around 20KB-30KB. +
    • The current implementation does not offer true multi-threading for + reading. The implementation uses FSDataInputStream seek()+read(), which is + shown to be much faster than positioned-read call in single thread mode. + However, it also means that if multiple threads attempt to access the same + TFile (using multiple scanners) simultaneously, the actual I/O is carried out + sequentially even if they access different DFS blocks. +
    • Compression codec. Use "none" if the data is not very compressable (by + compressable, I mean a compression ratio at least 2:1). Generally, use "lzo" + as the starting point for experimenting. "gz" overs slightly better + compression ratio over "lzo" but requires 4x CPU to compress and 2x CPU to + decompress, comparing to "lzo". +
    • File system buffering, if the underlying FSDataInputStream and + FSDataOutputStream is already adequately buffered; or if applications + reads/writes keys and values in large buffers, we can reduce the sizes of + input/output buffering in TFile layer by setting the configuration parameters + "tfile.fs.input.buffer.size" and "tfile.fs.output.buffer.size". +
    + + Some design rationale behind TFile can be found at Hadoop-3315.]]> + + + + + + + + + + + Utils#writeVLong(out, n). + + @param out + output stream + @param n + The integer to be encoded + @throws IOException + @see Utils#writeVLong(DataOutput, long)]]> + + + + + + + + +
  • if n in [-32, 127): encode in one byte with the actual value. + Otherwise, +
  • if n in [-20*2^8, 20*2^8): encode in two bytes: byte[0] = n/256 - 52; + byte[1]=n&0xff. Otherwise, +
  • if n IN [-16*2^16, 16*2^16): encode in three bytes: byte[0]=n/2^16 - + 88; byte[1]=(n>>8)&0xff; byte[2]=n&0xff. Otherwise, +
  • if n in [-8*2^24, 8*2^24): encode in four bytes: byte[0]=n/2^24 - 112; + byte[1] = (n>>16)&0xff; byte[2] = (n>>8)&0xff; byte[3]=n&0xff. Otherwise: +
  • if n in [-2^31, 2^31): encode in five bytes: byte[0]=-125; byte[1] = + (n>>24)&0xff; byte[2]=(n>>16)&0xff; byte[3]=(n>>8)&0xff; byte[4]=n&0xff; +
  • if n in [-2^39, 2^39): encode in six bytes: byte[0]=-124; byte[1] = + (n>>32)&0xff; byte[2]=(n>>24)&0xff; byte[3]=(n>>16)&0xff; + byte[4]=(n>>8)&0xff; byte[5]=n&0xff +
  • if n in [-2^47, 2^47): encode in seven bytes: byte[0]=-123; byte[1] = + (n>>40)&0xff; byte[2]=(n>>32)&0xff; byte[3]=(n>>24)&0xff; + byte[4]=(n>>16)&0xff; byte[5]=(n>>8)&0xff; byte[6]=n&0xff; +
  • if n in [-2^55, 2^55): encode in eight bytes: byte[0]=-122; byte[1] = + (n>>48)&0xff; byte[2] = (n>>40)&0xff; byte[3]=(n>>32)&0xff; + byte[4]=(n>>24)&0xff; byte[5]=(n>>16)&0xff; byte[6]=(n>>8)&0xff; + byte[7]=n&0xff; +
  • if n in [-2^63, 2^63): encode in nine bytes: byte[0]=-121; byte[1] = + (n>>54)&0xff; byte[2] = (n>>48)&0xff; byte[3] = (n>>40)&0xff; + byte[4]=(n>>32)&0xff; byte[5]=(n>>24)&0xff; byte[6]=(n>>16)&0xff; + byte[7]=(n>>8)&0xff; byte[8]=n&0xff; + + + @param out + output stream + @param n + the integer number + @throws IOException]]> + + + + + + + (int)Utils#readVLong(in). + + @param in + input stream + @return the decoded integer + @throws IOException + + @see Utils#readVLong(DataInput)]]> + + + + + + + +
  • if (FB >= -32), return (long)FB; +
  • if (FB in [-72, -33]), return (FB+52)<<8 + NB[0]&0xff; +
  • if (FB in [-104, -73]), return (FB+88)<<16 + (NB[0]&0xff)<<8 + + NB[1]&0xff; +
  • if (FB in [-120, -105]), return (FB+112)<<24 + (NB[0]&0xff)<<16 + + (NB[1]&0xff)<<8 + NB[2]&0xff; +
  • if (FB in [-128, -121]), return interpret NB[FB+129] as a signed + big-endian integer. + + @param in + input stream + @return the decoded long integer. + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + Type of the input key. + @param list + The list + @param key + The input key. + @param cmp + Comparator for the key. + @return The index to the desired element if it exists; or list.size() + otherwise.]]> + + + + + + + + + Type of the input key. + @param list + The list + @param key + The input key. + @param cmp + Comparator for the key. + @return The index to the desired element if it exists; or list.size() + otherwise.]]> + + + + + + + + Type of the input key. + @param list + The list + @param key + The input key. + @return The index to the desired element if it exists; or list.size() + otherwise.]]> + + + + + + + + Type of the input key. + @param list + The list + @param key + The input key. + @return The index to the desired element if it exists; or list.size() + otherwise.]]> + + + + + + + + + + + + + + + + + An experimental {@link Serialization} for Java {@link Serializable} classes. +

    + @see JavaSerializationComparator]]> +     +     + + + + + + + + + A {@link RawComparator} that uses a {@link JavaSerialization} + {@link Deserializer} to deserialize objects that are then compared via + their {@link Comparable} interfaces. +

    + @param + @see JavaSerialization]]> +     +     + + + + + + + + + + + + + +This package provides a mechanism for using different serialization frameworks +in Hadoop. The property "io.serializations" defines a list of +{@link org.apache.hadoop.io.serializer.Serialization}s that know how to create +{@link org.apache.hadoop.io.serializer.Serializer}s and +{@link org.apache.hadoop.io.serializer.Deserializer}s. +

    + +

    +To add a new serialization framework write an implementation of +{@link org.apache.hadoop.io.serializer.Serialization} and add its name to the +"io.serializations" property. +

    ]]> +     +     + + + + + + + + + + + + + + + + + + + avro.reflect.pkgs or implement + {@link AvroReflectSerializable} interface.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + +This package provides Avro serialization in Hadoop. This can be used to +serialize/deserialize Avro types in Hadoop. +

    + +

    +Use {@link org.apache.hadoop.io.serializer.avro.AvroSpecificSerialization} for +serialization of classes generated by Avro's 'specific' compiler. +

    + +

    +Use {@link org.apache.hadoop.io.serializer.avro.AvroReflectSerialization} for +other classes. +{@link org.apache.hadoop.io.serializer.avro.AvroReflectSerialization} work for +any class which is either in the package list configured via +{@link org.apache.hadoop.io.serializer.avro.AvroReflectSerialization#AVRO_REFLECT_PACKAGES} +or implement {@link org.apache.hadoop.io.serializer.avro.AvroReflectSerializable} +interface. +

    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + +The API is abstract so that it can be implemented on top of +a variety of metrics client libraries. The choice of +client library is a configuration option, and different +modules within the same application can use +different metrics implementation libraries. +

    +Sub-packages: +

    +
    org.apache.hadoop.metrics.spi
    +
    The abstract Server Provider Interface package. Those wishing to + integrate the metrics API with a particular metrics client library should + extend this package.
    + +
    org.apache.hadoop.metrics.file
    +
    An implementation package which writes the metric data to + a file, or sends it to the standard output stream.
    + +
    org.apache.hadoop.metrics.ganglia
    +
    An implementation package which sends metric data to + Ganglia.
    +
    + +

    Introduction to the Metrics API

    + +Here is a simple example of how to use this package to report a single +metric value: +
    +    private ContextFactory contextFactory = ContextFactory.getFactory();
+    
+    void reportMyMetric(float myMetric) {
+        MetricsContext myContext = contextFactory.getContext("myContext");
+        MetricsRecord myRecord = myContext.getRecord("myRecord");
+        myRecord.setMetric("myMetric", myMetric);
+        myRecord.update();
+    }
+
    + +In this example there are three names: +
    +
    myContext
    +
    The context name will typically identify either the application, or else a + module within an application or library.
    + +
    myRecord
    +
    The record name generally identifies some entity for which a set of + metrics are to be reported. For example, you could have a record named + "cacheStats" for reporting a number of statistics relating to the usage of + some cache in your application.
    + +
    myMetric
    +
    This identifies a particular metric. For example, you might have metrics + named "cache_hits" and "cache_misses". +
    +
    + +

    Tags

    + +In some cases it is useful to have multiple records with the same name. For +example, suppose that you want to report statistics about each disk on a computer. +In this case, the record name would be something like "diskStats", but you also +need to identify the disk which is done by adding a tag to the record. +The code could look something like this: +
    +    private MetricsRecord diskStats =
+            contextFactory.getContext("myContext").getRecord("diskStats");
+            
+    void reportDiskMetrics(String diskName, float diskBusy, float diskUsed) {
+        diskStats.setTag("diskName", diskName);
+        diskStats.setMetric("diskBusy", diskBusy);
+        diskStats.setMetric("diskUsed", diskUsed);
+        diskStats.update();
+    }
+
    + +

    Buffering and Callbacks

    + +Data is not sent immediately to the metrics system when +MetricsRecord.update() is called. Instead it is stored in an +internal table, and the contents of the table are sent periodically. +This can be important for two reasons: +
      +
    1. It means that a programmer is free to put calls to this API in an + inner loop, since updates can be very frequent without slowing down + the application significantly.
      2. +
    2. Some implementations can gain efficiency by combining many metrics + into a single UDP message.
      3. +
    + +The API provides a timer-based callback via the +registerUpdater() method. The benefit of this +versus using java.util.Timer is that the callbacks will be done +immediately before sending the data, making the data as current as possible. + +

    Configuration

    + +It is possible to programmatically examine and modify configuration data +before creating a context, like this: +
    +    ContextFactory factory = ContextFactory.getFactory();
+    ... examine and/or modify factory attributes ...
+    MetricsContext context = factory.getContext("myContext");
+
    +The factory attributes can be examined and modified using the following +ContextFactorymethods: +
      +
    • Object getAttribute(String attributeName)
      • +
    • String[] getAttributeNames()
      • +
    • void setAttribute(String name, Object value)
      • +
    • void removeAttribute(attributeName)
      • +
    + +

    +ContextFactory.getFactory() initializes the factory attributes by +reading the properties file hadoop-metrics.properties if it exists +on the class path. + +

    +A factory attribute named: +

    +contextName.class
+
    +should have as its value the fully qualified name of the class to be +instantiated by a call of the CodeFactory method +getContext(contextName). If this factory attribute is not +specified, the default is to instantiate +org.apache.hadoop.metrics.file.FileContext. + +

    +Other factory attributes are specific to a particular implementation of this +API and are documented elsewhere. For example, configuration attributes for +the file and Ganglia implementations can be found in the javadoc for +their respective packages.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +Implementation of the metrics package that sends metric data to +Ganglia. +Programmers should not normally need to use this package directly. Instead +they should use org.hadoop.metrics. + +

    +These are the implementation specific factory attributes +(See ContextFactory.getFactory()): + +

    +
    contextName.servers
    +
    Space and/or comma separated sequence of servers to which UDP + messages should be sent.
    + +
    contextName.period
    +
    The period in seconds on which the metric data is sent to the + server(s).
    + +
    contextName.multicast
    +
    Enable multicast for Ganglia
    + +
    contextName.multicast.ttl
    +
    TTL for multicast packets
    + +
    contextName.units.recordName.metricName
    +
    The units for the specified metric in the specified record.
    + +
    contextName.slope.recordName.metricName
    +
    The slope for the specified metric in the specified record.
    + +
    contextName.tmax.recordName.metricName
    +
    The tmax for the specified metric in the specified record.
    + +
    contextName.dmax.recordName.metricName
    +
    The dmax for the specified metric in the specified record.
    + +
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + contextName.tableName. The returned map consists of + those attributes with the contextName and tableName stripped off.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + recordName. + Throws an exception if the metrics implementation is configured with a fixed + set of record names and recordName is not in that set. + + @param recordName the name of the record + @throws MetricsException if recordName conflicts with configuration data]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This class implements the internal table of metric data, and the timer + on which data is to be sent to the metrics system. Subclasses must + override the abstract emitRecord method in order to transmit + the data.

    + + @deprecated Use org.apache.hadoop.metrics2 package instead.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + update + and remove(). + + @deprecated Use {@link org.apache.hadoop.metrics2.impl.MetricsRecordImpl} + instead.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + hostname or hostname:port. If + the specs string is null, defaults to localhost:defaultPort. + + @return a list of InetSocketAddress objects.]]> + + + + + + + + + org.apache.hadoop.metrics.file and +org.apache.hadoop.metrics.ganglia.

    + +Plugging in an implementation involves writing a concrete subclass of +AbstractMetricsContext. The subclass should get its + configuration information using the getAttribute(attributeName) + method.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Implementations of this interface consume the {@link MetricsRecord} generated + from {@link MetricsSource}. It registers with {@link MetricsSystem} which + periodically pushes the {@link MetricsRecord} to the sink using + {@link #putMetrics(MetricsRecord)} method. If the implementing class also + implements {@link Closeable}, then the MetricsSystem will close the sink when + it is stopped.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + the actual type of the source object + @param source object to register + @return the source object + @exception MetricsException]]> + + + + + + + + the actual type of the source object + @param source object to register + @param name of the source. Must be unique or null (then extracted from + the annotations of the source object.) + @param desc the description of the source (or null. See above.) + @return the source object + @exception MetricsException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + CollectD StatsD plugin). +
    + To configure this plugin, you will need to add the following + entries to your hadoop-metrics2.properties file: +
    + 

    + *.sink.statsd.class=org.apache.hadoop.metrics2.sink.StatsDSink
+ [prefix].sink.statsd.server.host=
+ [prefix].sink.statsd.server.port=
+ [prefix].sink.statsd.skip.hostname=true|false (optional)
+ [prefix].sink.statsd.service.name=NameNode (name you want for service)
+
    ]]> +     +     + +     + + + + + + + + + + + + + + + ,name=" + Where the and are the supplied parameters + + @param serviceName + @param nameName + @param theMbean - the MBean to register + @return the named used to register the MBean]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + hostname or hostname:port. If + the specs string is null, defaults to localhost:defaultPort. + + @param specs server specs (see description) + @param defaultPort the default port if not specified + @return a list of InetSocketAddress objects.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This method is used when parts of Hadoop need know whether to apply + single rack vs multi-rack policies, such as during block placement. + Such algorithms behave differently if they are on multi-switch systems. +

    + + @return true if the mapping thinks that it is on a single switch]]> +     +     + + + + + + + + + + + + + + + + + This predicate simply assumes that all mappings not derived from + this class are multi-switch. + @param mapping the mapping to query + @return true if the base class says it is single switch, or the mapping + is not derived from this class.]]> + + + + It is not mandatory to + derive {@link DNSToSwitchMapping} implementations from it, but it is strongly + recommended, as it makes it easy for the Hadoop developers to add new methods + to this base class that are automatically picked up by all implementations. +

    + + This class does not extend the Configured + base class, and should not be changed to do so, as it causes problems + for subclasses. The constructor of the Configured calls + the {@link #setConf(Configuration)} method, which will call into the + subclasses before they have been fully constructed.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + If a name cannot be resolved to a rack, the implementation + should return {@link NetworkTopology#DEFAULT_RACK}. This + is what the bundled implementations do, though it is not a formal requirement + + @param names the list of hosts to resolve (can be empty) + @return list of resolved network paths. + If names is empty, the returned list is also empty]]> + + + + + + + + + + + + + + + + + + + + + + + + Calling {@link #setConf(Configuration)} will trigger a + re-evaluation of the configuration settings and so be used to + set up the mapping script.]]> + + + + + + + + + + + + + + + + + + + + + This will get called in the superclass constructor, so a check is needed + to ensure that the raw mapping is defined before trying to relaying a null + configuration. + @param conf]]> + + + + + + + + + + It contains a static class RawScriptBasedMapping that performs + the work: reading the configuration parameters, executing any defined + script, handling errors and such like. The outer + class extends {@link CachedDNSToSwitchMapping} to cache the delegated + queries. +

    + This DNS mapper's {@link #isSingleSwitch()} predicate returns + true if and only if a script is defined.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Simple {@link DNSToSwitchMapping} implementation that reads a 2 column text + file. The columns are separated by whitespace. The first column is a DNS or + IP address and the second column specifies the rack where the address maps. +

    +

    + This class uses the configuration parameter {@code + net.topology.table.file.name} to locate the mapping file. +

    +

    + Calls to {@link #resolve(List)} will look up the address as defined in the + mapping file. If no entry corresponding to the address is found, the value + {@code /default-rack} is returned. +

    ]]> +     +     + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + =} getCount(). + @param newCapacity The new capacity in bytes.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + Index idx = startVector(...); + while (!idx.done()) { + .... // read element of a vector + idx.incr(); + } + + + @deprecated Replaced by Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + (DEPRECATED) Hadoop record I/O contains classes and a record description language + translator for simplifying serialization and deserialization of records in a + language-neutral manner. +

    + +

    + DEPRECATED: Replaced by Avro. +

    + +

    Introduction

    + + Software systems of any significant complexity require mechanisms for data +interchange with the outside world. These interchanges typically involve the +marshaling and unmarshaling of logical units of data to and from data streams +(files, network connections, memory buffers etc.). Applications usually have +some code for serializing and deserializing the data types that they manipulate +embedded in them. The work of serialization has several features that make +automatic code generation for it worthwhile. Given a particular output encoding +(binary, XML, etc.), serialization of primitive types and simple compositions +of primitives (structs, vectors etc.) is a very mechanical task. Manually +written serialization code can be susceptible to bugs especially when records +have a large number of fields or a record definition changes between software +versions. Lastly, it can be very useful for applications written in different +programming languages to be able to share and interchange data. This can be +made a lot easier by describing the data records manipulated by these +applications in a language agnostic manner and using the descriptions to derive +implementations of serialization in multiple target languages. + +This document describes Hadoop Record I/O, a mechanism that is aimed +at +
      +
    • enabling the specification of simple serializable data types (records) +
    • enabling the generation of code in multiple target languages for +marshaling and unmarshaling such types +
    • providing target language specific support that will enable application +programmers to incorporate generated code into their applications +
    + +The goals of Hadoop Record I/O are similar to those of mechanisms such as XDR, +ASN.1, PADS and ICE. While these systems all include a DDL that enables +the specification of most record types, they differ widely in what else they +focus on. The focus in Hadoop Record I/O is on data marshaling and +multi-lingual support. We take a translator-based approach to serialization. +Hadoop users have to describe their data in a simple data description +language. The Hadoop DDL translator rcc generates code that users +can invoke in order to read/write their data from/to simple stream +abstractions. Next we list explicitly some of the goals and non-goals of +Hadoop Record I/O. + + +

    Goals

    + +
      +
    • Support for commonly used primitive types. Hadoop should include as +primitives commonly used builtin types from programming languages we intend to +support. + +
    • Support for common data compositions (including recursive compositions). +Hadoop should support widely used composite types such as structs and +vectors. + +
    • Code generation in multiple target languages. Hadoop should be capable of +generating serialization code in multiple target languages and should be +easily extensible to new target languages. The initial target languages are +C++ and Java. + +
    • Support for generated target languages. Hadooop should include support +in the form of headers, libraries, packages for supported target languages +that enable easy inclusion and use of generated code in applications. + +
    • Support for multiple output encodings. Candidates include +packed binary, comma-separated text, XML etc. + +
    • Support for specifying record types in a backwards/forwards compatible +manner. This will probably be in the form of support for optional fields in +records. This version of the document does not include a description of the +planned mechanism, we intend to include it in the next iteration. + +
    + +

    Non-Goals

    + +
      +
    • Serializing existing arbitrary C++ classes. +
    • Serializing complex data structures such as trees, linked lists etc. +
    • Built-in indexing schemes, compression, or check-sums. +
    • Dynamic construction of objects from an XML schema. +
    + +The remainder of this document describes the features of Hadoop record I/O +in more detail. Section 2 describes the data types supported by the system. +Section 3 lays out the DDL syntax with some examples of simple records. +Section 4 describes the process of code generation with rcc. Section 5 +describes target language mappings and support for Hadoop types. We include a +fairly complete description of C++ mappings with intent to include Java and +others in upcoming iterations of this document. The last section talks about +supported output encodings. + + +

    Data Types and Streams

    + +This section describes the primitive and composite types supported by Hadoop. +We aim to support a set of types that can be used to simply and efficiently +express a wide range of record types in different programming languages. + +

    Primitive Types

    + +For the most part, the primitive types of Hadoop map directly to primitive +types in high level programming languages. Special cases are the +ustring (a Unicode string) and buffer types, which we believe +find wide use and which are usually implemented in library code and not +available as language built-ins. Hadoop also supplies these via library code +when a target language built-in is not present and there is no widely +adopted "standard" implementation. The complete list of primitive types is: + +
      +
    • byte: An 8-bit unsigned integer. +
    • boolean: A boolean value. +
    • int: A 32-bit signed integer. +
    • long: A 64-bit signed integer. +
    • float: A single precision floating point number as described by + IEEE-754. +
    • double: A double precision floating point number as described by + IEEE-754. +
    • ustring: A string consisting of Unicode characters. +
    • buffer: An arbitrary sequence of bytes. +
    + + +

    Composite Types

    +Hadoop supports a small set of composite types that enable the description +of simple aggregate types and containers. A composite type is serialized +by sequentially serializing it constituent elements. The supported +composite types are: + +
      + +
    • record: An aggregate type like a C-struct. This is a list of +typed fields that are together considered a single unit of data. A record +is serialized by sequentially serializing its constituent fields. In addition +to serialization a record has comparison operations (equality and less-than) +implemented for it, these are defined as memberwise comparisons. + +
    • vector: A sequence of entries of the same data type, primitive +or composite. + +
    • map: An associative container mapping instances of a key type to +instances of a value type. The key and value types may themselves be primitive +or composite types. + +
    + +

    Streams

    + +Hadoop generates code for serializing and deserializing record types to +abstract streams. For each target language Hadoop defines very simple input +and output stream interfaces. Application writers can usually develop +concrete implementations of these by putting a one method wrapper around +an existing stream implementation. + + +

    DDL Syntax and Examples

    + +We now describe the syntax of the Hadoop data description language. This is +followed by a few examples of DDL usage. + +

    Hadoop DDL Syntax

    + +
    
+recfile = *include module *record
+include = "include" path
+path = (relative-path / absolute-path)
+module = "module" module-name
+module-name = name *("." name)
+record := "class" name "{" 1*(field) "}"
+field := type name ";"
+name :=  ALPHA (ALPHA / DIGIT / "_" )*
+type := (ptype / ctype)
+ptype := ("byte" / "boolean" / "int" |
+          "long" / "float" / "double"
+          "ustring" / "buffer")
+ctype := (("vector" "<" type ">") /
+          ("map" "<" type "," type ">" ) ) / name)
+
    + +A DDL file describes one or more record types. It begins with zero or +more include declarations, a single mandatory module declaration +followed by zero or more class declarations. The semantics of each of +these declarations are described below: + +
      + +
    • include: An include declaration specifies a DDL file to be +referenced when generating code for types in the current DDL file. Record types +in the current compilation unit may refer to types in all included files. +File inclusion is recursive. An include does not trigger code +generation for the referenced file. + +
    • module: Every Hadoop DDL file must have a single module +declaration that follows the list of includes and precedes all record +declarations. A module declaration identifies a scope within which +the names of all types in the current file are visible. Module names are +mapped to C++ namespaces, Java packages etc. in generated code. + +
    • class: Records types are specified through class +declarations. A class declaration is like a Java class declaration. +It specifies a named record type and a list of fields that constitute records +of the type. Usage is illustrated in the following examples. + +
    + +

    Examples

    + +
      +
    • A simple DDL file links.jr with just one record declaration. +
      
+module links {
+    class Link {
+        ustring URL;
+        boolean isRelative;
+        ustring anchorText;
+    };
+}
+
      + +
    • A DDL file outlinks.jr which includes another +
      
+include "links.jr"
+
+module outlinks {
+    class OutLinks {
+        ustring baseURL;
+        vector outLinks;
+    };
+}
+
      +
    + +

    Code Generation

    + +The Hadoop translator is written in Java. Invocation is done by executing a +wrapper shell script named named rcc. It takes a list of +record description files as a mandatory argument and an +optional language argument (the default is Java) --language or +-l. Thus a typical invocation would look like: +
    
+$ rcc -l C++  ...
+
    + + +

    Target Language Mappings and Support

    + +For all target languages, the unit of code generation is a record type. +For each record type, Hadoop generates code for serialization and +deserialization, record comparison and access to record members. + +

    C++

    + +Support for including Hadoop generated C++ code in applications comes in the +form of a header file recordio.hh which needs to be included in source +that uses Hadoop types and a library librecordio.a which applications need +to be linked with. The header declares the Hadoop C++ namespace which defines +appropriate types for the various primitives, the basic interfaces for +records and streams and enumerates the supported serialization encodings. +Declarations of these interfaces and a description of their semantics follow: + +
    
+namespace hadoop {
+
+  enum RecFormat { kBinary, kXML, kCSV };
+
+  class InStream {
+  public:
+    virtual ssize_t read(void *buf, size_t n) = 0;
+  };
+
+  class OutStream {
+  public:
+    virtual ssize_t write(const void *buf, size_t n) = 0;
+  };
+
+  class IOError : public runtime_error {
+  public:
+    explicit IOError(const std::string& msg);
+  };
+
+  class IArchive;
+  class OArchive;
+
+  class RecordReader {
+  public:
+    RecordReader(InStream& in, RecFormat fmt);
+    virtual ~RecordReader(void);
+
+    virtual void read(Record& rec);
+  };
+
+  class RecordWriter {
+  public:
+    RecordWriter(OutStream& out, RecFormat fmt);
+    virtual ~RecordWriter(void);
+
+    virtual void write(Record& rec);
+  };
+
+
+  class Record {
+  public:
+    virtual std::string type(void) const = 0;
+    virtual std::string signature(void) const = 0;
+  protected:
+    virtual bool validate(void) const = 0;
+
+    virtual void
+    serialize(OArchive& oa, const std::string& tag) const = 0;
+
+    virtual void
+    deserialize(IArchive& ia, const std::string& tag) = 0;
+  };
+}
+
    + +
      + +
    • RecFormat: An enumeration of the serialization encodings supported +by this implementation of Hadoop. + +
    • InStream: A simple abstraction for an input stream. This has a +single public read method that reads n bytes from the stream into +the buffer buf. Has the same semantics as a blocking read system +call. Returns the number of bytes read or -1 if an error occurs. + +
    • OutStream: A simple abstraction for an output stream. This has a +single write method that writes n bytes to the stream from the +buffer buf. Has the same semantics as a blocking write system +call. Returns the number of bytes written or -1 if an error occurs. + +
    • RecordReader: A RecordReader reads records one at a time from +an underlying stream in a specified record format. The reader is instantiated +with a stream and a serialization format. It has a read method that +takes an instance of a record and deserializes the record from the stream. + +
    • RecordWriter: A RecordWriter writes records one at a +time to an underlying stream in a specified record format. The writer is +instantiated with a stream and a serialization format. It has a +write method that takes an instance of a record and serializes the +record to the stream. + +
    • Record: The base class for all generated record types. This has two +public methods type and signature that return the typename and the +type signature of the record. + +
    + +Two files are generated for each record file (note: not for each record). If a +record file is named "name.jr", the generated files are +"name.jr.cc" and "name.jr.hh" containing serialization +implementations and record type declarations respectively. + +For each record in the DDL file, the generated header file will contain a +class definition corresponding to the record type, method definitions for the +generated type will be present in the '.cc' file. The generated class will +inherit from the abstract class hadoop::Record. The DDL files +module declaration determines the namespace the record belongs to. +Each '.' delimited token in the module declaration results in the +creation of a namespace. For instance, the declaration module docs.links +results in the creation of a docs namespace and a nested +docs::links namespace. In the preceding examples, the Link class +is placed in the links namespace. The header file corresponding to +the links.jr file will contain: + +
    
+namespace links {
+  class Link : public hadoop::Record {
+    // ....
+  };
+};
+
    + +Each field within the record will cause the generation of a private member +declaration of the appropriate type in the class declaration, and one or more +acccessor methods. The generated class will implement the serialize and +deserialize methods defined in hadoop::Record+. It will also +implement the inspection methods type and signature from +hadoop::Record. A default constructor and virtual destructor will also +be generated. Serialization code will read/write records into streams that +implement the hadoop::InStream and the hadoop::OutStream interfaces. + +For each member of a record an accessor method is generated that returns +either the member or a reference to the member. For members that are returned +by value, a setter method is also generated. This is true for primitive +data members of the types byte, int, long, boolean, float and +double. For example, for a int field called MyField the folowing +code is generated. + +
    
+...
+private:
+  int32_t mMyField;
+  ...
+public:
+  int32_t getMyField(void) const {
+    return mMyField;
+  };
+
+  void setMyField(int32_t m) {
+    mMyField = m;
+  };
+  ...
+
    + +For a ustring or buffer or composite field. The generated code +only contains accessors that return a reference to the field. A const +and a non-const accessor are generated. For example: + +
    
+...
+private:
+  std::string mMyBuf;
+  ...
+public:
+
+  std::string& getMyBuf() {
+    return mMyBuf;
+  };
+
+  const std::string& getMyBuf() const {
+    return mMyBuf;
+  };
+  ...
+
    + +

    Examples

    + +Suppose the inclrec.jr file contains: +
    
+module inclrec {
+    class RI {
+        int      I32;
+        double   D;
+        ustring  S;
+    };
+}
+
    + +and the testrec.jr file contains: + +
    
+include "inclrec.jr"
+module testrec {
+    class R {
+        vector VF;
+        RI            Rec;
+        buffer        Buf;
+    };
+}
+
    + +Then the invocation of rcc such as: +
    
+$ rcc -l c++ inclrec.jr testrec.jr
+
    +will result in generation of four files: +inclrec.jr.{cc,hh} and testrec.jr.{cc,hh}. + +The inclrec.jr.hh will contain: + +
    
+#ifndef _INCLREC_JR_HH_
+#define _INCLREC_JR_HH_
+
+#include "recordio.hh"
+
+namespace inclrec {
+  
+  class RI : public hadoop::Record {
+
+  private:
+
+    int32_t      I32;
+    double       D;
+    std::string  S;
+
+  public:
+
+    RI(void);
+    virtual ~RI(void);
+
+    virtual bool operator==(const RI& peer) const;
+    virtual bool operator<(const RI& peer) const;
+
+    virtual int32_t getI32(void) const { return I32; }
+    virtual void setI32(int32_t v) { I32 = v; }
+
+    virtual double getD(void) const { return D; }
+    virtual void setD(double v) { D = v; }
+
+    virtual std::string& getS(void) const { return S; }
+    virtual const std::string& getS(void) const { return S; }
+
+    virtual std::string type(void) const;
+    virtual std::string signature(void) const;
+
+  protected:
+
+    virtual void serialize(hadoop::OArchive& a) const;
+    virtual void deserialize(hadoop::IArchive& a);
+  };
+} // end namespace inclrec
+
+#endif /* _INCLREC_JR_HH_ */
+
+
    + +The testrec.jr.hh file will contain: + + +
    
+
+#ifndef _TESTREC_JR_HH_
+#define _TESTREC_JR_HH_
+
+#include "inclrec.jr.hh"
+
+namespace testrec {
+  class R : public hadoop::Record {
+
+  private:
+
+    std::vector VF;
+    inclrec::RI        Rec;
+    std::string        Buf;
+
+  public:
+
+    R(void);
+    virtual ~R(void);
+
+    virtual bool operator==(const R& peer) const;
+    virtual bool operator<(const R& peer) const;
+
+    virtual std::vector& getVF(void) const;
+    virtual const std::vector& getVF(void) const;
+
+    virtual std::string& getBuf(void) const ;
+    virtual const std::string& getBuf(void) const;
+
+    virtual inclrec::RI& getRec(void) const;
+    virtual const inclrec::RI& getRec(void) const;
+    
+    virtual bool serialize(hadoop::OutArchive& a) const;
+    virtual bool deserialize(hadoop::InArchive& a);
+    
+    virtual std::string type(void) const;
+    virtual std::string signature(void) const;
+  };
+}; // end namespace testrec
+#endif /* _TESTREC_JR_HH_ */
+
+
    + +

    Java

    + +Code generation for Java is similar to that for C++. A Java class is generated +for each record type with private members corresponding to the fields. Getters +and setters for fields are also generated. Some differences arise in the +way comparison is expressed and in the mapping of modules to packages and +classes to files. For equality testing, an equals method is generated +for each record type. As per Java requirements a hashCode method is also +generated. For comparison a compareTo method is generated for each +record type. This has the semantics as defined by the Java Comparable +interface, that is, the method returns a negative integer, zero, or a positive +integer as the invoked object is less than, equal to, or greater than the +comparison parameter. + +A .java file is generated per record type as opposed to per DDL +file as in C++. The module declaration translates to a Java +package declaration. The module name maps to an identical Java package +name. In addition to this mapping, the DDL compiler creates the appropriate +directory hierarchy for the package and places the generated .java +files in the correct directories. + +

    Mapping Summary

    + +
    
+DDL Type        C++ Type            Java Type 
+
+boolean         bool                boolean
+byte            int8_t              byte
+int             int32_t             int
+long            int64_t             long
+float           float               float
+double          double              double
+ustring         std::string         java.lang.String
+buffer          std::string         org.apache.hadoop.record.Buffer
+class type      class type          class type
+vector    std::vector   java.util.ArrayList
+map  std::map java.util.TreeMap
+
    + +

    Data encodings

    + +This section describes the format of the data encodings supported by Hadoop. +Currently, three data encodings are supported, namely binary, CSV and XML. + +

    Binary Serialization Format

    + +The binary data encoding format is fairly dense. Serialization of composite +types is simply defined as a concatenation of serializations of the constituent +elements (lengths are included in vectors and maps). + +Composite types are serialized as follows: +
      +
    • class: Sequence of serialized members. +
    • vector: The number of elements serialized as an int. Followed by a +sequence of serialized elements. +
    • map: The number of key value pairs serialized as an int. Followed +by a sequence of serialized (key,value) pairs. +
    + +Serialization of primitives is more interesting, with a zero compression +optimization for integral types and normalization to UTF-8 for strings. +Primitive types are serialized as follows: + +
      +
    • byte: Represented by 1 byte, as is. +
    • boolean: Represented by 1-byte (0 or 1) +
    • int/long: Integers and longs are serialized zero compressed. +Represented as 1-byte if -120 <= value < 128. Otherwise, serialized as a +sequence of 2-5 bytes for ints, 2-9 bytes for longs. The first byte represents +the number of trailing bytes, N, as the negative number (-120-N). For example, +the number 1024 (0x400) is represented by the byte sequence 'x86 x04 x00'. +This doesn't help much for 4-byte integers but does a reasonably good job with +longs without bit twiddling. +
    • float/double: Serialized in IEEE 754 single and double precision +format in network byte order. This is the format used by Java. +
    • ustring: Serialized as 4-byte zero compressed length followed by +data encoded as UTF-8. Strings are normalized to UTF-8 regardless of native +language representation. +
    • buffer: Serialized as a 4-byte zero compressed length followed by the +raw bytes in the buffer. +
    + + +

    CSV Serialization Format

    + +The CSV serialization format has a lot more structure than the "standard" +Excel CSV format, but we believe the additional structure is useful because + +
      +
    • it makes parsing a lot easier without detracting too much from legibility +
    • the delimiters around composites make it obvious when one is reading a +sequence of Hadoop records +
    + +Serialization formats for the various types are detailed in the grammar that +follows. The notable feature of the formats is the use of delimiters for +indicating the certain field types. + +
      +
    • A string field begins with a single quote ('). +
    • A buffer field begins with a sharp (#). +
    • A class, vector or map begins with 's{', 'v{' or 'm{' respectively and +ends with '}'. +
    + +The CSV format can be described by the following grammar: + +
    
+record = primitive / struct / vector / map
+primitive = boolean / int / long / float / double / ustring / buffer
+
+boolean = "T" / "F"
+int = ["-"] 1*DIGIT
+long = ";" ["-"] 1*DIGIT
+float = ["-"] 1*DIGIT "." 1*DIGIT ["E" / "e" ["-"] 1*DIGIT]
+double = ";" ["-"] 1*DIGIT "." 1*DIGIT ["E" / "e" ["-"] 1*DIGIT]
+
+ustring = "'" *(UTF8 char except NULL, LF, % and , / "%00" / "%0a" / "%25" / "%2c" )
+
+buffer = "#" *(BYTE except NULL, LF, % and , / "%00" / "%0a" / "%25" / "%2c" )
+
+struct = "s{" record *("," record) "}"
+vector = "v{" [record *("," record)] "}"
+map = "m{" [*(record "," record)] "}"
+
    + +

    XML Serialization Format

    + +The XML serialization format is the same used by Apache XML-RPC +(http://ws.apache.org/xmlrpc/types.html). This is an extension of the original +XML-RPC format and adds some additional data types. All record I/O types are +not directly expressible in this format, and access to a DDL is required in +order to convert these to valid types. All types primitive or composite are +represented by <value> elements. The particular XML-RPC type is +indicated by a nested element in the <value> element. The encoding for +records is always UTF-8. Primitive types are serialized as follows: + +
      +
    • byte: XML tag <ex:i1>. Values: 1-byte unsigned +integers represented in US-ASCII +
    • boolean: XML tag <boolean>. Values: "0" or "1" +
    • int: XML tags <i4> or <int>. Values: 4-byte +signed integers represented in US-ASCII. +
    • long: XML tag <ex:i8>. Values: 8-byte signed integers +represented in US-ASCII. +
    • float: XML tag <ex:float>. Values: Single precision +floating point numbers represented in US-ASCII. +
    • double: XML tag <double>. Values: Double precision +floating point numbers represented in US-ASCII. +
    • ustring: XML tag <;string>. Values: String values +represented as UTF-8. XML does not permit all Unicode characters in literal +data. In particular, NULLs and control chars are not allowed. Additionally, +XML processors are required to replace carriage returns with line feeds and to +replace CRLF sequences with line feeds. Programming languages that we work +with do not impose these restrictions on string types. To work around these +restrictions, disallowed characters and CRs are percent escaped in strings. +The '%' character is also percent escaped. +
    • buffer: XML tag <string&>. Values: Arbitrary binary +data. Represented as hexBinary, each byte is replaced by its 2-byte +hexadecimal representation. +
    + +Composite types are serialized as follows: + +
      +
    • class: XML tag <struct>. A struct is a sequence of +<member> elements. Each <member> element has a <name> +element and a <value> element. The <name> is a string that must +match /[a-zA-Z][a-zA-Z0-9_]*/. The value of the member is represented +by a <value> element. + +
    • vector: XML tag <array<. An <array> contains a +single <data> element. The <data> element is a sequence of +<value> elements each of which represents an element of the vector. + +
    • map: XML tag <array>. Same as vector. + +
    + +For example: + +
    
+class {
+  int           MY_INT;            // value 5
+  vector MY_VEC;            // values 0.1, -0.89, 2.45e4
+  buffer        MY_BUF;            // value '\00\n\tabc%'
+}
+
    + +is serialized as + +
    
+<value>
+  <struct>
+    <member>
+      <name>MY_INT</name>
+      <value><i4>5</i4></value>
+    </member>
+    <member>
+      <name>MY_VEC</name>
+      <value>
+        <array>
+          <data>
+            <value><ex:float>0.1</ex:float></value>
+            <value><ex:float>-0.89</ex:float></value>
+            <value><ex:float>2.45e4</ex:float></value>
+          </data>
+        </array>
+      </value>
+    </member>
+    <member>
+      <name>MY_BUF</name>
+      <value><string>%00\n\tabc%25</string></value>
+    </member>
+  </struct>
+</value> 
+
    ]]> +     +     + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + Avro.]]> + + + + + + + + + Avro.]]> + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + Avro.]]> + + + + + + + + + Avro.]]> + + + + + + + + + + + + Avro.]]> + + + + + + (DEPRECATED) This package contains classes needed for code generation + from the hadoop record compiler. CppGenerator and JavaGenerator + are the main entry points from the parser. There are classes + corrsponding to every primitive type and compound type + included in Hadoop record I/O syntax. +

    + +

    + DEPRECATED: Replaced by Avro. +

    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This task takes the given record definition files and compiles them into + java or c++ + files. It is then up to the user to compile the generated files. + +

    The task requires the file or the nested fileset element to be + specified. Optional attributes are language (set the output + language, default is "java"), + destdir (name of the destination directory for generated java/c++ + code, default is ".") and failonerror (specifies error handling + behavior. default is true). +

    Usage

    + 
    + <recordcc
+       destdir="${basedir}/gensrc"
+       language="java">
+   <fileset include="**\/*.jr" />
+ </recordcc>
+
    + + @deprecated Replaced by Avro.]]> +     +     + +     + + + + + + ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + (DEPRECATED) This package contains code generated by JavaCC from the + Hadoop record syntax file rcc.jj. For details about the + record file syntax please @see org.apache.hadoop.record. +

    + +

    + DEPRECATED: Replaced by Avro. +

    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + + + Avro.]]> + + + + + + + + + + + + + + + + + + + + (cause==null ? null : cause.toString()) (which + typically contains the class and detail message of cause). + @param cause the cause (which is saved for later retrieval by the + {@link #getCause()} method). (A null value is + permitted, and indicates that the cause is nonexistent or + unknown.)]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + mapping + and mapping]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + /host@realm. + @param principalName principal name of format as described above + @return host name if the the string conforms to the above format, else null]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + "jack" + + @param userName + @return userName without login method]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + the return type of the run method + @param action the method to execute + @return the value from the run method]]> + + + + + + + + the return type of the run method + @param action the method to execute + @return the value from the run method + @throws IOException if the action throws an IOException + @throws Error if the action throws an Error + @throws RuntimeException if the action throws a RuntimeException + @throws InterruptedException if the action throws an InterruptedException + @throws UndeclaredThrowableException if the action throws something else]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + (cause==null ? null : cause.toString()) (which + typically contains the class and detail message of cause). + @param cause the cause (which is saved for later retrieval by the + {@link #getCause()} method). (A null value is + permitted, and indicates that the cause is nonexistent or + unknown.)]]> + + + + + + + + + + + + + + does not provide the stack trace for security purposes.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + A User-Agent String is considered to be a browser if it matches + any of the regex patterns from browser-useragent-regex; the default + behavior is to consider everything a browser that matches the following: + "^Mozilla.*,^Opera.*". Subclasses can optionally override + this method to use different behavior. + + @param userAgent The User-Agent String, or null if there isn't one + @return true if the User-Agent String refers to a browser, false if not]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + The type of the token identifier]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + T extends TokenIdentifier]]> + + + + + + + + + + DelegationTokenAuthenticatedURL. +

    + An instance of the default {@link DelegationTokenAuthenticator} will be + used.]]> + + + + + DelegationTokenAuthenticatedURL. + + @param authenticator the {@link DelegationTokenAuthenticator} instance to + use, if null the default one will be used.]]> + + + + + DelegationTokenAuthenticatedURL using the default + {@link DelegationTokenAuthenticator} class. + + @param connConfigurator a connection configurator.]]> + + + + + DelegationTokenAuthenticatedURL. + + @param authenticator the {@link DelegationTokenAuthenticator} instance to + use, if null the default one will be used. + @param connConfigurator a connection configurator.]]> + + + + + + + + + + + + The default class is {@link KerberosDelegationTokenAuthenticator} + + @return the delegation token authenticator class to use as default.]]> + + + + + + + This method is provided to enable WebHDFS backwards compatibility. + + @param useQueryString TRUE if the token is transmitted in the + URL query string, FALSE if the delegation token is transmitted + using the {@link DelegationTokenAuthenticator#DELEGATION_TOKEN_HEADER} HTTP + header.]]> + + + + + TRUE if the token is transmitted in the URL query + string, FALSE if the delegation token is transmitted using the + {@link DelegationTokenAuthenticator#DELEGATION_TOKEN_HEADER} HTTP header.]]> + + + + + + + + + + + + + + + + + + Authenticator. + + @param url the URL to connect to. Only HTTP/S URLs are supported. + @param token the authentication token being used for the user. + @return an authenticated {@link HttpURLConnection}. + @throws IOException if an IO error occurred. + @throws AuthenticationException if an authentication exception occurred.]]> + + + + + + + + + + Authenticator. If the doAs parameter is not NULL, + the request will be done on behalf of the specified doAs user. + + @param url the URL to connect to. Only HTTP/S URLs are supported. + @param token the authentication token being used for the user. + @param doAs user to do the the request on behalf of, if NULL the request is + as self. + @return an authenticated {@link HttpURLConnection}. + @throws IOException if an IO error occurred. + @throws AuthenticationException if an authentication exception occurred.]]> + + + + + + + + + + Authenticator + for authentication. + + @param url the URL to get the delegation token from. Only HTTP/S URLs are + supported. + @param token the authentication token being used for the user where the + Delegation token will be stored. + @param renewer the renewer user. + @return a delegation token. + @throws IOException if an IO error occurred. + @throws AuthenticationException if an authentication exception occurred.]]> + + + + + + + + + + + Authenticator + for authentication. + + @param url the URL to get the delegation token from. Only HTTP/S URLs are + supported. + @param token the authentication token being used for the user where the + Delegation token will be stored. + @param renewer the renewer user. + @param doAsUser the user to do as, which will be the token owner. + @return a delegation token. + @throws IOException if an IO error occurred. + @throws AuthenticationException if an authentication exception occurred.]]> + + + + + + + + + Authenticator for authentication. + + @param url the URL to renew the delegation token from. Only HTTP/S URLs are + supported. + @param token the authentication token with the Delegation Token to renew. + @throws IOException if an IO error occurred. + @throws AuthenticationException if an authentication exception occurred.]]> + + + + + + + + + + Authenticator for authentication. + + @param url the URL to renew the delegation token from. Only HTTP/S URLs are + supported. + @param token the authentication token with the Delegation Token to renew. + @param doAsUser the user to do as, which will be the token owner. + @throws IOException if an IO error occurred. + @throws AuthenticationException if an authentication exception occurred.]]> + + + + + + + + Authenticator. + + @param url the URL to cancel the delegation token from. Only HTTP/S URLs + are supported. + @param token the authentication token with the Delegation Token to cancel. + @throws IOException if an IO error occurred.]]> + + + + + + + + + Authenticator. + + @param url the URL to cancel the delegation token from. Only HTTP/S URLs + are supported. + @param token the authentication token with the Delegation Token to cancel. + @param doAsUser the user to do as, which will be the token owner. + @throws IOException if an IO error occurred.]]> + + + + DelegationTokenAuthenticatedURL is a + {@link AuthenticatedURL} sub-class with built-in Hadoop Delegation Token + functionality. +

    + The authentication mechanisms supported by default are Hadoop Simple + authentication (also known as pseudo authentication) and Kerberos SPNEGO + authentication. +

    + Additional authentication mechanisms can be supported via {@link + DelegationTokenAuthenticator} implementations. +

    + The default {@link DelegationTokenAuthenticator} is the {@link + KerberosDelegationTokenAuthenticator} class which supports + automatic fallback from Kerberos SPNEGO to Hadoop Simple authentication via + the {@link PseudoDelegationTokenAuthenticator} class. +

    + AuthenticatedURL instances are not thread-safe.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Authenticator + for authentication. + + @param url the URL to get the delegation token from. Only HTTP/S URLs are + supported. + @param token the authentication token being used for the user where the + Delegation token will be stored. + @param renewer the renewer user. + @throws IOException if an IO error occurred. + @throws AuthenticationException if an authentication exception occurred.]]> + + + + + + + + + + + Authenticator + for authentication. + + @param url the URL to get the delegation token from. Only HTTP/S URLs are + supported. + @param token the authentication token being used for the user where the + Delegation token will be stored. + @param renewer the renewer user. + @param doAsUser the user to do as, which will be the token owner. + @throws IOException if an IO error occurred. + @throws AuthenticationException if an authentication exception occurred.]]> + + + + + + + + + + Authenticator for authentication. + + @param url the URL to renew the delegation token from. Only HTTP/S URLs are + supported. + @param token the authentication token with the Delegation Token to renew. + @throws IOException if an IO error occurred. + @throws AuthenticationException if an authentication exception occurred.]]> + + + + + + + + + + + Authenticator for authentication. + + @param url the URL to renew the delegation token from. Only HTTP/S URLs are + supported. + @param token the authentication token with the Delegation Token to renew. + @param doAsUser the user to do as, which will be the token owner. + @throws IOException if an IO error occurred. + @throws AuthenticationException if an authentication exception occurred.]]> + + + + + + + + + Authenticator. + + @param url the URL to cancel the delegation token from. Only HTTP/S URLs + are supported. + @param token the authentication token with the Delegation Token to cancel. + @throws IOException if an IO error occurred.]]> + + + + + + + + + + Authenticator. + + @param url the URL to cancel the delegation token from. Only HTTP/S URLs + are supported. + @param token the authentication token with the Delegation Token to cancel. + @param doAsUser the user to do as, which will be the token owner. + @throws IOException if an IO error occurred.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + KerberosDelegationTokenAuthenticator provides support for + Kerberos SPNEGO authentication mechanism and support for Hadoop Delegation + Token operations. +

    + It falls back to the {@link PseudoDelegationTokenAuthenticator} if the HTTP + endpoint does not trigger a SPNEGO authentication]]> + + + + + + + + + PseudoDelegationTokenAuthenticator provides support for + Hadoop's pseudo authentication mechanism that accepts + the user name specified as a query string parameter and support for Hadoop + Delegation Token operations. +

    + This mimics the model of Hadoop Simple authentication trusting the + {@link UserGroupInformation#getCurrentUser()} value.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + live. + @return a (snapshotted) map of blocker name->description values]]> + + + + + + + + + + + + + Do nothing if the service is null or not + in a state in which it can be/needs to be stopped. +

    + The service state is checked before the operation begins. + This process is not thread safe. + @param service a service or null]]> + + + + + + + + + + + + + + + + + + + + + + + + + + +

  • Any long-lived operation here will prevent the service state + change from completing in a timely manner.
    • +
  • If another thread is somehow invoked from the listener, and + that thread invokes the methods of the service (including + subclass-specific methods), there is a risk of a deadlock.
    • + + + + @param service the service that has changed.]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Clients and/or applications can use the provided Progressable + to explicitly report progress to the Hadoop framework. This is especially + important for operations which take significant amount of time since, + in-lieu of the reported progress, the framework has to assume that an error + has occured and time-out the operation.

    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Class is to be obtained + @return the correctly typed Class of the given object.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + kill -0 command or equivalent]]> + + + + + + + + + + + + + + + + + + + ".cmd" on Windows, or ".sh" otherwise. + + @param parent File parent directory + @param basename String script file basename + @return File referencing the script in the directory]]> + + + + + + ".cmd" on Windows, or ".sh" otherwise. + + @param basename String script file basename + @return String script file name]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + IOException. + @return the path to {@link #WINUTILS_EXE} + @throws RuntimeException if the path is not resolvable]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Shell interface. + @param cmd shell command to execute. + @return the output of the executed command.]]> + + + + + + + + + Shell interface. + @param env the map of environment key=value + @param cmd shell command to execute. + @param timeout time in milliseconds after which script should be marked timeout + @return the output of the executed command. + @throws IOException on any problem.]]> + + + + + + + + Shell interface. + @param env the map of environment key=value + @param cmd shell command to execute. + @return the output of the executed command. + @throws IOException on any problem.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + CreateProcess synchronization object.]]> + + + + + os.name property.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Important: caller must check for this value being null. + The lack of such checks has led to many support issues being raised. +

    + @deprecated use one of the exception-raising getter methods, + specifically {@link #getWinUtilsPath()} or {@link #getWinUtilsFile()}]]> + + + + + + + + + + + + + + Shell can be used to run shell commands like du or + df. It also offers facilities to gate commands by + time-intervals.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Tool, is the standard for any Map-Reduce tool/application. + The tool/application should delegate the handling of + + standard command-line options to {@link ToolRunner#run(Tool, String[])} + and only handle its custom arguments.

    + +

    Here is how a typical Tool is implemented:

    + 

    +     public class MyApp extends Configured implements Tool {
+     
+       public int run(String[] args) throws Exception {
+         // Configuration processed by ToolRunner
+         Configuration conf = getConf();
+         
+         // Create a JobConf using the processed conf
+         JobConf job = new JobConf(conf, MyApp.class);
+         
+         // Process custom command-line options
+         Path in = new Path(args[1]);
+         Path out = new Path(args[2]);
+         
+         // Specify various job-specific parameters     
+         job.setJobName("my-app");
+         job.setInputPath(in);
+         job.setOutputPath(out);
+         job.setMapperClass(MyMapper.class);
+         job.setReducerClass(MyReducer.class);
+
+         // Submit the job, then poll for progress until the job is complete
+         RunningJob runningJob = JobClient.runJob(job);
+         if (runningJob.isSuccessful()) {
+           return 0;
+         } else {
+           return 1;
+         }
+       }
+       
+       public static void main(String[] args) throws Exception {
+         // Let ToolRunner handle generic command-line options 
+         int res = ToolRunner.run(new Configuration(), new MyApp(), args);
+         
+         System.exit(res);
+       }
+     }
+

    + + @see GenericOptionsParser + @see ToolRunner]]> +     + + + + + + + + + + + + + Tool by {@link Tool#run(String[])}, after + parsing with the given generic arguments. Uses the given + Configuration, or builds one if null. + + Sets the Tool's configuration with the possibly modified + version of the conf. + + @param conf Configuration for the Tool. + @param tool Tool to run. + @param args command-line arguments to the tool. + @return exit code of the {@link Tool#run(String[])} method.]]> + + + + + + + + Tool with its Configuration. + + Equivalent to run(tool.getConf(), tool, args). + + @param tool Tool to run. + @param args command-line arguments to the tool. + @return exit code of the {@link Tool#run(String[])} method.]]> + + + + + + + + + + + + + + + + + ToolRunner can be used to run classes implementing + Tool interface. It works in conjunction with + {@link GenericOptionsParser} to parse the + + generic hadoop command line arguments and modifies the + Configuration of the Tool. The + application-specific options are passed along without being modified. +

    + + @see Tool + @see GenericOptionsParser]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + this filter. + @param nbHash The number of hash function to consider. + @param hashType type of the hashing function (see + {@link org.apache.hadoop.util.hash.Hash}).]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Bloom filter, as defined by Bloom in 1970. +

    + The Bloom filter is a data structure that was introduced in 1970 and that has been adopted by + the networking research community in the past decade thanks to the bandwidth efficiencies that it + offers for the transmission of set membership information between networked hosts. A sender encodes + the information into a bit vector, the Bloom filter, that is more compact than a conventional + representation. Computation and space costs for construction are linear in the number of elements. + The receiver uses the filter to test whether various elements are members of the set. Though the + filter will occasionally return a false positive, it will never return a false negative. When creating + the filter, the sender can choose its desired point in a trade-off between the false positive rate and the size. + +

    + Originally created by + European Commission One-Lab Project 034819. + + @see Filter The general behavior of a filter + + @see Space/Time Trade-Offs in Hash Coding with Allowable Errors]]> + + + + + + + + + + + + + this filter. + @param nbHash The number of hash function to consider. + @param hashType type of the hashing function (see + {@link org.apache.hadoop.util.hash.Hash}).]]> + + + + + + + + + this counting Bloom filter. +

    + Invariant: nothing happens if the specified key does not belong to this counter Bloom filter. + @param key The key to remove.]]> + + + + + + + + + + + + key -> count map. +

    NOTE: due to the bucket size of this filter, inserting the same + key more than 15 times will cause an overflow at all filter positions + associated with this key, and it will significantly increase the error + rate for this and other keys. For this reason the filter can only be + used to store small count values 0 <= N << 15. + @param key key to be tested + @return 0 if the key is not present. Otherwise, a positive value v will + be returned such that v == count with probability equal to the + error rate of this filter, and v > count otherwise. + Additionally, if the filter experienced an underflow as a result of + {@link #delete(Key)} operation, the return value may be lower than the + count with the probability of the false negative rate of such + filter.]]> + + + + + + + + + + + + + + + + + + + + + + counting Bloom filter, as defined by Fan et al. in a ToN + 2000 paper. +

    + A counting Bloom filter is an improvement to standard a Bloom filter as it + allows dynamic additions and deletions of set membership information. This + is achieved through the use of a counting vector instead of a bit vector. +

    + Originally created by + European Commission One-Lab Project 034819. + + @see Filter The general behavior of a filter + + @see Summary cache: a scalable wide-area web cache sharing protocol]]> + + + + + + + + + + + + + + Builds an empty Dynamic Bloom filter. + @param vectorSize The number of bits in the vector. + @param nbHash The number of hash function to consider. + @param hashType type of the hashing function (see + {@link org.apache.hadoop.util.hash.Hash}). + @param nr The threshold for the maximum number of keys to record in a + dynamic Bloom filter row.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + dynamic Bloom filter, as defined in the INFOCOM 2006 paper. +

    + A dynamic Bloom filter (DBF) makes use of a s * m bit matrix but + each of the s rows is a standard Bloom filter. The creation + process of a DBF is iterative. At the start, the DBF is a 1 * m + bit matrix, i.e., it is composed of a single standard Bloom filter. + It assumes that nr elements are recorded in the + initial bit vector, where nr <= n (n is + the cardinality of the set A to record in the filter). +

    + As the size of A grows during the execution of the application, + several keys must be inserted in the DBF. When inserting a key into the DBF, + one must first get an active Bloom filter in the matrix. A Bloom filter is + active when the number of recorded keys, nr, is + strictly less than the current cardinality of A, n. + If an active Bloom filter is found, the key is inserted and + nr is incremented by one. On the other hand, if there + is no active Bloom filter, a new one is created (i.e., a new row is added to + the matrix) according to the current size of A and the element + is added in this new Bloom filter and the nr value of + this new Bloom filter is set to one. A given key is said to belong to the + DBF if the k positions are set to one in one of the matrix rows. +

    + Originally created by + European Commission One-Lab Project 034819. + + @see Filter The general behavior of a filter + @see BloomFilter A Bloom filter + + @see Theory and Network Applications of Dynamic Bloom Filters]]> + + + + + + + + + Builds a hash function that must obey to a given maximum number of returned values and a highest value. + @param maxValue The maximum highest returned value. + @param nbHash The number of resulting hashed values. + @param hashType type of the hashing function (see {@link Hash}).]]> + + + + + this hash function. A NOOP]]> + + + + + + + + + + + + + + + + + + + The idea is to randomly select a bit to reset.]]> + + + + + + The idea is to select the bit to reset that will generate the minimum + number of false negative.]]> + + + + + + The idea is to select the bit to reset that will remove the maximum number + of false positive.]]> + + + + + + The idea is to select the bit to reset that will, at the same time, remove + the maximum number of false positve while minimizing the amount of false + negative generated.]]> + + + + + Originally created by + European Commission One-Lab Project 034819.]]> + + + + + + + + + + + + + + this filter. + @param nbHash The number of hash function to consider. + @param hashType type of the hashing function (see + {@link org.apache.hadoop.util.hash.Hash}).]]> + + + + + + + + + this retouched Bloom filter. +

    + Invariant: if the false positive is null, nothing happens. + @param key The false positive key to add.]]> + + + + + + this retouched Bloom filter. + @param coll The collection of false positive.]]> + + + + + + this retouched Bloom filter. + @param keys The list of false positive.]]> + + + + + + this retouched Bloom filter. + @param keys The array of false positive.]]> + + + + + + + this retouched Bloom filter. + @param scheme The selective clearing scheme to apply.]]> + + + + + + + + + + + + retouched Bloom filter, as defined in the CoNEXT 2006 paper. +

    + It allows the removal of selected false positives at the cost of introducing + random false negatives, and with the benefit of eliminating some random false + positives at the same time. + +

    + Originally created by + European Commission One-Lab Project 034819. + + @see Filter The general behavior of a filter + @see BloomFilter A Bloom filter + @see RemoveScheme The different selective clearing algorithms + + @see Retouched Bloom Filters: Allowing Networked Applications to Trade Off Selected False Positives Against False Negatives]]> + + + + + + + + + + diff --git a/hadoop-hdfs-project/hadoop-hdfs/dev-support/jdiff/Apache_Hadoop_HDFS_2.8.3.xml b/hadoop-hdfs-project/hadoop-hdfs/dev-support/jdiff/Apache_Hadoop_HDFS_2.8.3.xml new file mode 100644 index 00000000000..331dd1e569b --- /dev/null +++ b/hadoop-hdfs-project/hadoop-hdfs/dev-support/jdiff/Apache_Hadoop_HDFS_2.8.3.xml @@ -0,0 +1,312 @@ + + + + + + + + + + + A distributed implementation of {@link +org.apache.hadoop.fs.FileSystem}. This is loosely modelled after +Google's GFS.

    + +

    The most important difference is that unlike GFS, Hadoop DFS files +have strictly one writer at any one time. Bytes are always appended +to the end of the writer's stream. There is no notion of "record appends" +or "mutations" that are then checked or reordered. Writers simply emit +a byte stream. That byte stream is guaranteed to be stored in the +order written.

    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This method must return as quickly as possible, since it's called + in a critical section of the NameNode's operation. + + @param succeeded Whether authorization succeeded. + @param userName Name of the user executing the request. + @param addr Remote address of the request. + @param cmd The requested command. + @param src Path of affected source file. + @param dst Path of affected destination file (if any). + @param stat File information for operations that change the file's + metadata (permissions, owner, times, etc).]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +     diff --git a/hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_Common_2.8.3.xml b/hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_Common_2.8.3.xml new file mode 100644 index 00000000000..b3d52bf810a --- /dev/null +++ b/hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_Common_2.8.3.xml @@ -0,0 +1,113 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_Core_2.8.3.xml b/hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_Core_2.8.3.xml new file mode 100644 index 00000000000..e96d0188e43 --- /dev/null +++ b/hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_Core_2.8.3.xml @@ -0,0 +1,27495 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + FileStatus of a given cache file on hdfs + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + DistributedCache is a facility provided by the Map-Reduce + framework to cache files (text, archives, jars etc.) needed by applications. +

    + +

    Applications specify the files, via urls (hdfs:// or http://) to be cached + via the {@link org.apache.hadoop.mapred.JobConf}. The + DistributedCache assumes that the files specified via urls are + already present on the {@link FileSystem} at the path specified by the url + and are accessible by every machine in the cluster.

    + +

    The framework will copy the necessary files on to the slave node before + any tasks for the job are executed on that node. Its efficiency stems from + the fact that the files are only copied once per job and the ability to + cache archives which are un-archived on the slaves.

    + +

    DistributedCache can be used to distribute simple, read-only + data/text files and/or more complex types such as archives, jars etc. + Archives (zip, tar and tgz/tar.gz files) are un-archived at the slave nodes. + Jars may be optionally added to the classpath of the tasks, a rudimentary + software distribution mechanism. Files have execution permissions. + In older version of Hadoop Map/Reduce users could optionally ask for symlinks + to be created in the working directory of the child task. In the current + version symlinks are always created. If the URL does not have a fragment + the name of the file or directory will be used. If multiple files or + directories map to the same link name, the last one added, will be used. All + others will not even be downloaded.

    + +

    DistributedCache tracks modification timestamps of the cache + files. Clearly the cache files should not be modified by the application + or externally while the job is executing.

    + +

    Here is an illustrative example on how to use the + DistributedCache:

    + 

    +     // Setting up the cache for the application
+     
+     1. Copy the requisite files to the FileSystem:
+     
+     $ bin/hadoop fs -copyFromLocal lookup.dat /myapp/lookup.dat  
+     $ bin/hadoop fs -copyFromLocal map.zip /myapp/map.zip  
+     $ bin/hadoop fs -copyFromLocal mylib.jar /myapp/mylib.jar
+     $ bin/hadoop fs -copyFromLocal mytar.tar /myapp/mytar.tar
+     $ bin/hadoop fs -copyFromLocal mytgz.tgz /myapp/mytgz.tgz
+     $ bin/hadoop fs -copyFromLocal mytargz.tar.gz /myapp/mytargz.tar.gz
+     
+     2. Setup the application's JobConf:
+     
+     JobConf job = new JobConf();
+     DistributedCache.addCacheFile(new URI("/myapp/lookup.dat#lookup.dat"), 
+                                   job);
+     DistributedCache.addCacheArchive(new URI("/myapp/map.zip", job);
+     DistributedCache.addFileToClassPath(new Path("/myapp/mylib.jar"), job);
+     DistributedCache.addCacheArchive(new URI("/myapp/mytar.tar", job);
+     DistributedCache.addCacheArchive(new URI("/myapp/mytgz.tgz", job);
+     DistributedCache.addCacheArchive(new URI("/myapp/mytargz.tar.gz", job);
+     
+     3. Use the cached files in the {@link org.apache.hadoop.mapred.Mapper}
+     or {@link org.apache.hadoop.mapred.Reducer}:
+     
+     public static class MapClass extends MapReduceBase  
+     implements Mapper<K, V, K, V> {
+     
+       private Path[] localArchives;
+       private Path[] localFiles;
+       
+       public void configure(JobConf job) {
+         // Get the cached archives/files
+         File f = new File("./map.zip/some/file/in/zip.txt");
+       }
+       
+       public void map(K key, V value, 
+                       OutputCollector<K, V> output, Reporter reporter) 
+       throws IOException {
+         // Use data from the cached archives/files here
+         // ...
+         // ...
+         output.collect(k, v);
+       }
+     }
+     
+
    + + It is also very common to use the DistributedCache by using + {@link org.apache.hadoop.util.GenericOptionsParser}. + + This class includes methods that should be used by users + (specifically those mentioned in the example above, as well + as {@link DistributedCache#addArchiveToClassPath(Path, Configuration)}), + as well as methods intended for use by the MapReduce framework + (e.g., {@link org.apache.hadoop.mapred.JobClient}). + + @see org.apache.hadoop.mapred.JobConf + @see org.apache.hadoop.mapred.JobClient + @see org.apache.hadoop.mapreduce.Job]]> +     +     + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + JobTracker, + as {@link JobTracker.State} + + {@link JobTracker.State} should no longer be used on M/R 2.x. The function + is kept to be compatible with M/R 1.x applications. + + @return the invalid state of the JobTracker.]]> + + + + + + + + + + + + + + ClusterStatus provides clients with information such as: +
      +
    1. + Size of the cluster. +
      2. +
    2. + Name of the trackers. +
      3. +
    3. + Task capacity of the cluster. +
      4. +
    4. + The number of currently running map and reduce tasks. +
      5. +
    5. + State of the JobTracker. +
      6. +
    6. + Details regarding black listed trackers. +
      7. +
    + +

    Clients can query for the latest ClusterStatus, via + {@link JobClient#getClusterStatus()}.

    + + @see JobClient]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Counters represent global counters, defined either by the + Map-Reduce framework or applications. Each Counter can be of + any {@link Enum} type.

    + +

    Counters are bunched into {@link Group}s, each comprising of + counters from a particular Enum class.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Group of counters, comprising of counters from a particular + counter {@link Enum} class. + +

    Grouphandles localization of the class name and the + counter names.

    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + FileInputFormat always returns + true. Implementations that may deal with non-splittable files must + override this method. + + FileInputFormat implementations can override this and return + false to ensure that individual input files are never split-up + so that {@link Mapper}s process entire files. + + @param fs the file system that the file is on + @param filename the file name to check + @return is this file splitable?]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + FileInputFormat is the base class for all file-based + InputFormats. This provides a generic implementation of + {@link #getSplits(JobConf, int)}. + + Implementations of FileInputFormat can also override the + {@link #isSplitable(FileSystem, Path)} method to prevent input files + from being split-up in certain situations. Implementations that may + deal with non-splittable files must override this method, since + the default implementation assumes splitting is always possible.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if the job output should be compressed, + false otherwise]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Tasks' Side-Effect Files + +

    Note: The following is valid only if the {@link OutputCommitter} + is {@link FileOutputCommitter}. If OutputCommitter is not + a FileOutputCommitter, the task's temporary output + directory is same as {@link #getOutputPath(JobConf)} i.e. + ${mapreduce.output.fileoutputformat.outputdir}$

    + +

    Some applications need to create/write-to side-files, which differ from + the actual job-outputs. + +

    In such cases there could be issues with 2 instances of the same TIP + (running simultaneously e.g. speculative tasks) trying to open/write-to the + same file (path) on HDFS. Hence the application-writer will have to pick + unique names per task-attempt (e.g. using the attemptid, say + attempt_200709221812_0001_m_000000_0), not just per TIP.

    + +

    To get around this the Map-Reduce framework helps the application-writer + out by maintaining a special + ${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid} + sub-directory for each task-attempt on HDFS where the output of the + task-attempt goes. On successful completion of the task-attempt the files + in the ${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid} (only) + are promoted to ${mapreduce.output.fileoutputformat.outputdir}. Of course, the + framework discards the sub-directory of unsuccessful task-attempts. This + is completely transparent to the application.

    + +

    The application-writer can take advantage of this by creating any + side-files required in ${mapreduce.task.output.dir} during execution + of his reduce-task i.e. via {@link #getWorkOutputPath(JobConf)}, and the + framework will move them out similarly - thus she doesn't have to pick + unique paths per task-attempt.

    + +

    Note: the value of ${mapreduce.task.output.dir} during + execution of a particular task-attempt is actually + ${mapreduce.output.fileoutputformat.outputdir}/_temporary/_{$taskid}, and this value is + set by the map-reduce framework. So, just create any side-files in the + path returned by {@link #getWorkOutputPath(JobConf)} from map/reduce + task to take advantage of this feature.

    + +

    The entire discussion holds true for maps of jobs with + reducer=NONE (i.e. 0 reduces) since output of the map, in that case, + goes directly to HDFS.

    + + @return the {@link Path} to the task's temporary output directory + for the map-reduce job.]]> +     +     + + + + + + + + + + + + + The generated name can be used to create custom files from within the + different tasks for the job, the names for different tasks will not collide + with each other.

    + +

    The given name is postfixed with the task type, 'm' for maps, 'r' for + reduces and the task partition number. For example, give a name 'test' + running on the first map o the job the generated name will be + 'test-m-00000'.

    + + @param conf the configuration for the job. + @param name the name to make unique. + @return a unique name accross all tasks of the job.]]> +     +     + + + + + The path can be used to create custom files from within the map and + reduce tasks. The path name will be unique for each task. The path parent + will be the job output directory.

    ls + +

    This method uses the {@link #getUniqueName} method to make the file name + unique for the task.

    + + @param conf the configuration for the job. + @param name the name for the file. + @return a unique path accross all tasks of the job.]]> +     +     + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
    or + conf.setInt(FixedLengthInputFormat.FIXED_RECORD_LENGTH, recordLength); +

    + @see FixedLengthRecordReader]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + Each {@link InputSplit} is then assigned to an individual {@link Mapper} + for processing.

    + +

    Note: The split is a logical split of the inputs and the + input files are not physically split into chunks. For e.g. a split could + be <input-file-path, start, offset> tuple. + + @param job job configuration. + @param numSplits the desired number of splits, a hint. + @return an array of {@link InputSplit}s for the job.]]> + + + + + + + + + It is the responsibility of the RecordReader to respect + record boundaries while processing the logical split to present a + record-oriented view to the individual task.

    + + @param split the {@link InputSplit} + @param job the job that this split belongs to + @return a {@link RecordReader}]]> +     +     + + InputFormat describes the input-specification for a + Map-Reduce job. + +

    The Map-Reduce framework relies on the InputFormat of the + job to:

    +

      +
    1. + Validate the input-specification of the job. +
    2. + Split-up the input file(s) into logical {@link InputSplit}s, each of + which is then assigned to an individual {@link Mapper}. +
      3. +
    3. + Provide the {@link RecordReader} implementation to be used to glean + input records from the logical InputSplit for processing by + the {@link Mapper}. +
      4. +
    + +

    The default behavior of file-based {@link InputFormat}s, typically + sub-classes of {@link FileInputFormat}, is to split the + input into logical {@link InputSplit}s based on the total size, in + bytes, of the input files. However, the {@link FileSystem} blocksize of + the input files is treated as an upper bound for input splits. A lower bound + on the split size can be set via + + mapreduce.input.fileinputformat.split.minsize.

    + +

    Clearly, logical splits based on input-size is insufficient for many + applications since record boundaries are to be respected. In such cases, the + application has to also implement a {@link RecordReader} on whom lies the + responsibilty to respect record-boundaries and present a record-oriented + view of the logical InputSplit to the individual task. + + @see InputSplit + @see RecordReader + @see JobClient + @see FileInputFormat]]> + + + + + + + + + + InputSplit. + + @return the number of bytes in the input split. + @throws IOException]]> + + + + + + InputSplit is + located as an array of Strings. + @throws IOException]]> + + + + InputSplit represents the data to be processed by an + individual {@link Mapper}. + +

    Typically, it presents a byte-oriented view on the input and is the + responsibility of {@link RecordReader} of the job to process this and present + a record-oriented view. + + @see InputFormat + @see RecordReader]]> + + + + + + + + + + SplitLocationInfos describing how the split + data is stored at each location. A null value indicates that all the + locations have the data stored on disk. + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + JobClient.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + jobid doesn't correspond to any known job. + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + JobClient is the primary interface for the user-job to interact + with the cluster. + + JobClient provides facilities to submit jobs, track their + progress, access component-tasks' reports/logs, get the Map-Reduce cluster + status information etc. + +

    The job submission process involves: +

      +
    1. + Checking the input and output specifications of the job. +
      2. +
    2. + Computing the {@link InputSplit}s for the job. +
      3. +
    3. + Setup the requisite accounting information for the {@link DistributedCache} + of the job, if necessary. +
      4. +
    4. + Copying the job's jar and configuration to the map-reduce system directory + on the distributed file-system. +
      5. +
    5. + Submitting the job to the cluster and optionally monitoring + it's status. +
      6. +
    + + Normally the user creates the application, describes various facets of the + job via {@link JobConf} and then uses the JobClient to submit + the job and monitor its progress. + +

    Here is an example on how to use JobClient:

    + 

    +     // Create a new JobConf
+     JobConf job = new JobConf(new Configuration(), MyJob.class);
+     
+     // Specify various job-specific parameters     
+     job.setJobName("myjob");
+     
+     job.setInputPath(new Path("in"));
+     job.setOutputPath(new Path("out"));
+     
+     job.setMapperClass(MyJob.MyMapper.class);
+     job.setReducerClass(MyJob.MyReducer.class);
+
+     // Submit the job, then poll for progress until the job is complete
+     JobClient.runJob(job);
+
    + + Job Control + +

    At times clients would chain map-reduce jobs to accomplish complex tasks + which cannot be done via a single map-reduce job. This is fairly easy since + the output of the job, typically, goes to distributed file-system and that + can be used as the input for the next job.

    + +

    However, this also means that the onus on ensuring jobs are complete + (success/failure) lies squarely on the clients. In such situations the + various job-control options are: +

      +
    1. + {@link #runJob(JobConf)} : submits the job and returns only after + the job has completed. +
      2. +
    2. + {@link #submitJob(JobConf)} : only submits the job, then poll the + returned handle to the {@link RunningJob} to query status and make + scheduling decisions. +
      3. +
    3. + {@link JobConf#setJobEndNotificationURI(String)} : setup a notification + on job-completion, thus avoiding polling. +
      4. +
    + + @see JobConf + @see ClusterStatus + @see Tool + @see DistributedCache]]> +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + If the parameter {@code loadDefaults} is false, the new instance + will not load resources from the default files. + + @param loadDefaults specifies whether to load from the default files]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if framework should keep the intermediate files + for failed tasks, false otherwise.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if the outputs of the maps are to be compressed, + false otherwise.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This comparator should be provided if the equivalence rules for keys + for sorting the intermediates are different from those for grouping keys + before each call to + {@link Reducer#reduce(Object, java.util.Iterator, OutputCollector, Reporter)}.

    + +

    For key-value pairs (K1,V1) and (K2,V2), the values (V1, V2) are passed + in a single call to the reduce function if K1 and K2 compare as equal.

    + +

    Since {@link #setOutputKeyComparatorClass(Class)} can be used to control + how keys are sorted, this can be used in conjunction to simulate + secondary sort on values.

    + +

    Note: This is not a guarantee of the combiner sort being + stable in any sense. (In any case, with the order of available + map-outputs to the combiner being non-deterministic, it wouldn't make + that much sense.)

    + + @param theClass the comparator class to be used for grouping keys for the + combiner. It should implement RawComparator. + @see #setOutputKeyComparatorClass(Class)]]> +     +     + + + + This comparator should be provided if the equivalence rules for keys + for sorting the intermediates are different from those for grouping keys + before each call to + {@link Reducer#reduce(Object, java.util.Iterator, OutputCollector, Reporter)}.

    + +

    For key-value pairs (K1,V1) and (K2,V2), the values (V1, V2) are passed + in a single call to the reduce function if K1 and K2 compare as equal.

    + +

    Since {@link #setOutputKeyComparatorClass(Class)} can be used to control + how keys are sorted, this can be used in conjunction to simulate + secondary sort on values.

    + +

    Note: This is not a guarantee of the reduce sort being + stable in any sense. (In any case, with the order of available + map-outputs to the reduce being non-deterministic, it wouldn't make + that much sense.)

    + + @param theClass the comparator class to be used for grouping keys. + It should implement RawComparator. + @see #setOutputKeyComparatorClass(Class) + @see #setCombinerKeyGroupingComparator(Class)]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + combiner class used to combine map-outputs + before being sent to the reducers. Typically the combiner is same as the + the {@link Reducer} for the job i.e. {@link #getReducerClass()}. + + @return the user-defined combiner class used to combine map-outputs.]]> + + + + + + combiner class used to combine map-outputs + before being sent to the reducers. + +

    The combiner is an application-specified aggregation operation, which + can help cut down the amount of data transferred between the + {@link Mapper} and the {@link Reducer}, leading to better performance.

    + +

    The framework may invoke the combiner 0, 1, or multiple times, in both + the mapper and reducer tasks. In general, the combiner is called as the + sort/merge result is written to disk. The combiner must: +

      +
    • be side-effect free
      • +
    • have the same input and output key types and the same input and + output value types
      • +
    + +

    Typically the combiner is same as the Reducer for the + job i.e. {@link #setReducerClass(Class)}.

    + + @param theClass the user-defined combiner class used to combine + map-outputs.]]> +     +     + + + true. + + @return true if speculative execution be used for this job, + false otherwise.]]> + + + + + + true if speculative execution + should be turned on, else false.]]> + + + + + true. + + @return true if speculative execution be + used for this job for map tasks, + false otherwise.]]> + + + + + + true if speculative execution + should be turned on for map tasks, + else false.]]> + + + + + true. + + @return true if speculative execution be used + for reduce tasks for this job, + false otherwise.]]> + + + + + + true if speculative execution + should be turned on for reduce tasks, + else false.]]> + + + + + 1. + + @return the number of map tasks for this job.]]> + + + + + + Note: This is only a hint to the framework. The actual + number of spawned map tasks depends on the number of {@link InputSplit}s + generated by the job's {@link InputFormat#getSplits(JobConf, int)}. + + A custom {@link InputFormat} is typically used to accurately control + the number of map tasks for the job.

    + + How many maps? + +

    The number of maps is usually driven by the total size of the inputs + i.e. total number of blocks of the input files.

    + +

    The right level of parallelism for maps seems to be around 10-100 maps + per-node, although it has been set up to 300 or so for very cpu-light map + tasks. Task setup takes awhile, so it is best if the maps take at least a + minute to execute.

    + +

    The default behavior of file-based {@link InputFormat}s is to split the + input into logical {@link InputSplit}s based on the total size, in + bytes, of input files. However, the {@link FileSystem} blocksize of the + input files is treated as an upper bound for input splits. A lower bound + on the split size can be set via + + mapreduce.input.fileinputformat.split.minsize.

    + +

    Thus, if you expect 10TB of input data and have a blocksize of 128MB, + you'll end up with 82,000 maps, unless {@link #setNumMapTasks(int)} is + used to set it even higher.

    + + @param n the number of map tasks for this job. + @see InputFormat#getSplits(JobConf, int) + @see FileInputFormat + @see FileSystem#getDefaultBlockSize() + @see FileStatus#getBlockSize()]]> +     +     + + + 1. + + @return the number of reduce tasks for this job.]]> + + + + + + How many reduces? + +

    The right number of reduces seems to be 0.95 or + 1.75 multiplied by ( + available memory for reduce tasks + (The value of this should be smaller than + numNodes * yarn.nodemanager.resource.memory-mb + since the resource of memory is shared by map tasks and other + applications) / + + mapreduce.reduce.memory.mb). +

    + +

    With 0.95 all of the reduces can launch immediately and + start transfering map outputs as the maps finish. With 1.75 + the faster nodes will finish their first round of reduces and launch a + second wave of reduces doing a much better job of load balancing.

    + +

    Increasing the number of reduces increases the framework overhead, but + increases load balancing and lowers the cost of failures.

    + +

    The scaling factors above are slightly less than whole numbers to + reserve a few reduce slots in the framework for speculative-tasks, failures + etc.

    + + Reducer NONE + +

    It is legal to set the number of reduce-tasks to zero.

    + +

    In this case the output of the map-tasks directly go to distributed + file-system, to the path set by + {@link FileOutputFormat#setOutputPath(JobConf, Path)}. Also, the + framework doesn't sort the map-outputs before writing it out to HDFS.

    + + @param n the number of reduce tasks for this job.]]> +     +     + + + mapreduce.map.maxattempts + property. If this property is not already set, the default is 4 attempts. + + @return the max number of attempts per map task.]]> + + + + + + + + + + + mapreduce.reduce.maxattempts + property. If this property is not already set, the default is 4 attempts. + + @return the max number of attempts per reduce task.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + noFailures, the + tasktracker is blacklisted for this job. + + @param noFailures maximum no. of failures of a given job per tasktracker.]]> + + + + + blacklisted for this job. + + @return the maximum no. of failures of a given job per tasktracker.]]> + + + + + failed. + + Defaults to zero, i.e. any failed map-task results in + the job being declared as {@link JobStatus#FAILED}. + + @return the maximum percentage of map tasks that can fail without + the job being aborted.]]> + + + + + + failed. + + @param percent the maximum percentage of map tasks that can fail without + the job being aborted.]]> + + + + + failed. + + Defaults to zero, i.e. any failed reduce-task results + in the job being declared as {@link JobStatus#FAILED}. + + @return the maximum percentage of reduce tasks that can fail without + the job being aborted.]]> + + + + + + failed. + + @param percent the maximum percentage of reduce tasks that can fail without + the job being aborted.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + The debug script can aid debugging of failed map tasks. The script is + given task's stdout, stderr, syslog, jobconf files as arguments.

    + +

    The debug command, run on the node where the map failed, is:

    + 

    + $script $stdout $stderr $syslog $jobconf.
+
    + +

    The script file is distributed through {@link DistributedCache} + APIs. The script needs to be symlinked.

    + +

    Here is an example on how to submit a script + 

    + job.setMapDebugScript("./myscript");
+ DistributedCache.createSymlink(job);
+ DistributedCache.addCacheFile("/debug/scripts/myscript#myscript");
+
    + + @param mDbgScript the script name]]> +     +     + + + + + + + + + The debug script can aid debugging of failed reduce tasks. The script + is given task's stdout, stderr, syslog, jobconf files as arguments.

    + +

    The debug command, run on the node where the map failed, is:

    + 

    + $script $stdout $stderr $syslog $jobconf.
+
    + +

    The script file is distributed through {@link DistributedCache} + APIs. The script file needs to be symlinked

    + +

    Here is an example on how to submit a script + 

    + job.setReduceDebugScript("./myscript");
+ DistributedCache.createSymlink(job);
+ DistributedCache.addCacheFile("/debug/scripts/myscript#myscript");
+
    + + @param rDbgScript the script name]]> +     +     + + + + + + + + null if it hasn't + been set. + @see #setJobEndNotificationURI(String)]]> + + + + + + The uri can contain 2 special parameters: $jobId and + $jobStatus. Those, if present, are replaced by the job's + identifier and completion-status respectively.

    + +

    This is typically used by application-writers to implement chaining of + Map-Reduce jobs in an asynchronous manner.

    + + @param uri the job end notification uri + @see JobStatus]]> +     +     + + + + When a job starts, a shared directory is created at location + + ${mapreduce.cluster.local.dir}/taskTracker/$user/jobcache/$jobid/work/ . + This directory is exposed to the users through + mapreduce.job.local.dir . + So, the tasks can use this space + as scratch space and share files among them.

    + This value is available as System property also. + + @return The localized job specific shared directory]]> +     +     + + + + For backward compatibility, if the job configuration sets the + key {@link #MAPRED_TASK_MAXVMEM_PROPERTY} to a value different + from {@link #DISABLED_MEMORY_LIMIT}, that value will be used + after converting it from bytes to MB. + @return memory required to run a map task of the job, in MB,]]> + + + + + + + + + For backward compatibility, if the job configuration sets the + key {@link #MAPRED_TASK_MAXVMEM_PROPERTY} to a value different + from {@link #DISABLED_MEMORY_LIMIT}, that value will be used + after converting it from bytes to MB. + @return memory required to run a reduce task of the job, in MB.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This method is deprecated. Now, different memory limits can be + set for map and reduce tasks of a job, in MB. +

    + For backward compatibility, if the job configuration sets the + key {@link #MAPRED_TASK_MAXVMEM_PROPERTY}, that value is returned. + Otherwise, this method will return the larger of the values returned by + {@link #getMemoryForMapTask()} and {@link #getMemoryForReduceTask()} + after converting them into bytes. + + @return Memory required to run a task of this job, in bytes. + @see #setMaxVirtualMemoryForTask(long) + @deprecated Use {@link #getMemoryForMapTask()} and + {@link #getMemoryForReduceTask()}]]> + + + + + + + mapred.task.maxvmem is split into + mapreduce.map.memory.mb + and mapreduce.map.memory.mb,mapred + each of the new key are set + as mapred.task.maxvmem / 1024 + as new values are in MB + + @param vmem Maximum amount of virtual memory in bytes any task of this job + can use. + @see #getMaxVirtualMemoryForTask() + @deprecated + Use {@link #setMemoryForMapTask(long mem)} and + Use {@link #setMemoryForReduceTask(long mem)}]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + k1=v1,k2=v2. Further it can + reference existing environment variables via $key on + Linux or %key% on Windows. + + Example: +

      +
    • A=foo - This will set the env variable A to foo.
      • +
    • B=$X:c This is inherit tasktracker's X env variable on Linux.
      • +
    • B=%X%;c This is inherit tasktracker's X env variable on Windows.
      • +
    + + @deprecated Use {@link #MAPRED_MAP_TASK_ENV} or + {@link #MAPRED_REDUCE_TASK_ENV}]]> +     + + + + k1=v1,k2=v2. Further it can + reference existing environment variables via $key on + Linux or %key% on Windows. + + Example: +
      +
    • A=foo - This will set the env variable A to foo.
      • +
    • B=$X:c This is inherit tasktracker's X env variable on Linux.
      • +
    • B=%X%;c This is inherit tasktracker's X env variable on Windows.
      • +
    ]]> +     +     + + + k1=v1,k2=v2. Further it can + reference existing environment variables via $key on + Linux or %key% on Windows. + + Example: +
      +
    • A=foo - This will set the env variable A to foo.
      • +
    • B=$X:c This is inherit tasktracker's X env variable on Linux.
      • +
    • B=%X%;c This is inherit tasktracker's X env variable on Windows.
      • +
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + JobConf is the primary interface for a user to describe a + map-reduce job to the Hadoop framework for execution. The framework tries to + faithfully execute the job as-is described by JobConf, however: +
      +
    1. + Some configuration parameters might have been marked as + + final by administrators and hence cannot be altered. +
      2. +
    2. + While some job parameters are straight-forward to set + (e.g. {@link #setNumReduceTasks(int)}), some parameters interact subtly + with the rest of the framework and/or job-configuration and is relatively + more complex for the user to control finely + (e.g. {@link #setNumMapTasks(int)}). +
      3. +
    + +

    JobConf typically specifies the {@link Mapper}, combiner + (if any), {@link Partitioner}, {@link Reducer}, {@link InputFormat} and + {@link OutputFormat} implementations to be used etc. + +

    Optionally JobConf is used to specify other advanced facets + of the job such as Comparators to be used, files to be put in + the {@link DistributedCache}, whether or not intermediate and/or job outputs + are to be compressed (and how), debugability via user-provided scripts + ( {@link #setMapDebugScript(String)}/{@link #setReduceDebugScript(String)}), + for doing post-processing on task logs, task's stdout, stderr, syslog. + and etc.

    + +

    Here is an example on how to configure a job via JobConf:

    + 

    +     // Create a new JobConf
+     JobConf job = new JobConf(new Configuration(), MyJob.class);
+     
+     // Specify various job-specific parameters     
+     job.setJobName("myjob");
+     
+     FileInputFormat.setInputPaths(job, new Path("in"));
+     FileOutputFormat.setOutputPath(job, new Path("out"));
+     
+     job.setMapperClass(MyJob.MyMapper.class);
+     job.setCombinerClass(MyJob.MyReducer.class);
+     job.setReducerClass(MyJob.MyReducer.class);
+     
+     job.setInputFormat(SequenceFileInputFormat.class);
+     job.setOutputFormat(SequenceFileOutputFormat.class);
+
    + + @see JobClient + @see ClusterStatus + @see Tool + @see DistributedCache]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + any job + run on the jobtracker started at 200707121733, we would use : + 
     
+ JobID.getTaskIDsPattern("200707121733", null);
+
    + which will return : + 
     "job_200707121733_[0-9]*"
    + @param jtIdentifier jobTracker identifier, or null + @param jobId job number, or null + @return a regex pattern matching JobIDs]]> +     +     + + + An example JobID is : + job_200707121733_0003 , which represents the third job + running at the jobtracker started at 200707121733. +

    + Applications should never construct or parse JobID strings, but rather + use appropriate constructors or {@link #forName(String)} method. + + @see TaskID + @see TaskAttemptID]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Output pairs need not be of the same types as input pairs. A given + input pair may map to zero or many output pairs. Output pairs are + collected with calls to + {@link OutputCollector#collect(Object,Object)}.

    + +

    Applications can use the {@link Reporter} provided to report progress + or just indicate that they are alive. In scenarios where the application + takes significant amount of time to process individual key/value + pairs, this is crucial since the framework might assume that the task has + timed-out and kill that task. The other way of avoiding this is to set + + mapreduce.task.timeout to a high-enough value (or even zero for no + time-outs).

    + + @param key the input key. + @param value the input value. + @param output collects mapped keys and values. + @param reporter facility to report progress.]]> +     + + + Maps are the individual tasks which transform input records into a + intermediate records. The transformed intermediate records need not be of + the same type as the input records. A given input pair may map to zero or + many output pairs.

    + +

    The Hadoop Map-Reduce framework spawns one map task for each + {@link InputSplit} generated by the {@link InputFormat} for the job. + Mapper implementations can access the {@link JobConf} for the + job via the {@link JobConfigurable#configure(JobConf)} and initialize + themselves. Similarly they can use the {@link Closeable#close()} method for + de-initialization.

    + +

    The framework then calls + {@link #map(Object, Object, OutputCollector, Reporter)} + for each key/value pair in the InputSplit for that task.

    + +

    All intermediate values associated with a given output key are + subsequently grouped by the framework, and passed to a {@link Reducer} to + determine the final output. Users can control the grouping by specifying + a Comparator via + {@link JobConf#setOutputKeyComparatorClass(Class)}.

    + +

    The grouped Mapper outputs are partitioned per + Reducer. Users can control which keys (and hence records) go to + which Reducer by implementing a custom {@link Partitioner}. + +

    Users can optionally specify a combiner, via + {@link JobConf#setCombinerClass(Class)}, to perform local aggregation of the + intermediate outputs, which helps to cut down the amount of data transferred + from the Mapper to the Reducer. + +

    The intermediate, grouped outputs are always stored in + {@link SequenceFile}s. Applications can specify if and how the intermediate + outputs are to be compressed and which {@link CompressionCodec}s are to be + used via the JobConf.

    + +

    If the job has + zero + reduces then the output of the Mapper is directly written + to the {@link FileSystem} without grouping by keys.

    + +

    Example:

    + 

    +     public class MyMapper<K extends WritableComparable, V extends Writable> 
+     extends MapReduceBase implements Mapper<K, V, K, V> {
+     
+       static enum MyCounters { NUM_RECORDS }
+       
+       private String mapTaskId;
+       private String inputFile;
+       private int noRecords = 0;
+       
+       public void configure(JobConf job) {
+         mapTaskId = job.get(JobContext.TASK_ATTEMPT_ID);
+         inputFile = job.get(JobContext.MAP_INPUT_FILE);
+       }
+       
+       public void map(K key, V val,
+                       OutputCollector<K, V> output, Reporter reporter)
+       throws IOException {
+         // Process the <key, value> pair (assume this takes a while)
+         // ...
+         // ...
+         
+         // Let the framework know that we are alive, and kicking!
+         // reporter.progress();
+         
+         // Process some more
+         // ...
+         // ...
+         
+         // Increment the no. of <key, value> pairs processed
+         ++noRecords;
+
+         // Increment counters
+         reporter.incrCounter(NUM_RECORDS, 1);
+        
+         // Every 100 records update application-level status
+         if ((noRecords%100) == 0) {
+           reporter.setStatus(mapTaskId + " processed " + noRecords + 
+                              " from input-file: " + inputFile); 
+         }
+         
+         // Output the result
+         output.collect(key, val);
+       }
+     }
+
    + +

    Applications may write a custom {@link MapRunnable} to exert greater + control on map processing e.g. multi-threaded Mappers etc.

    + + @see JobConf + @see InputFormat + @see Partitioner + @see Reducer + @see MapReduceBase + @see MapRunnable + @see SequenceFile]]> +     +     + + + + + + + + + + + + + + + + + + + + + Provides default no-op implementations for a few methods, most non-trivial + applications need to override some of them.

    ]]> +     +     + + + + + + + + + + + <key, value> pairs. + +

    Mapping of input records to output records is complete when this method + returns.

    + + @param input the {@link RecordReader} to read the input records. + @param output the {@link OutputCollector} to collect the outputrecords. + @param reporter {@link Reporter} to report progress, status-updates etc. + @throws IOException]]> +     +     + + Custom implementations of MapRunnable can exert greater + control on map processing e.g. multi-threaded, asynchronous mappers etc.

    + + @see Mapper]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + nearly + equal content length.
    + Subclasses implement {@link #getRecordReader(InputSplit, JobConf, Reporter)} + to construct RecordReader's for MultiFileSplit's. + @see MultiFileSplit]]> +     +     + + + + + + + + + + + + + MultiFileSplit can be used to implement {@link RecordReader}'s, with + reading one record per file. + @see FileSplit + @see MultiFileInputFormat]]> + + + + + + + + + + + + + + + <key, value> pairs output by {@link Mapper}s + and {@link Reducer}s. + +

    OutputCollector is the generalization of the facility + provided by the Map-Reduce framework to collect data output by either the + Mapper or the Reducer i.e. intermediate outputs + or the output of the job.

    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if task output recovery is supported, + false otherwise + @throws IOException + @see #recoverTask(TaskAttemptContext)]]> + + + + + + + true repeatable job commit is supported, + false otherwise + @throws IOException]]> + + + + + + + + + + + OutputCommitter. This is called from the application master + process, but it is called individually for each task. + + If an exception is thrown the task will be attempted again. + + @param taskContext Context of the task whose output is being recovered + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + OutputCommitter describes the commit of task output for a + Map-Reduce job. + +

    The Map-Reduce framework relies on the OutputCommitter of + the job to:

    +

      +
    1. + Setup the job during initialization. For example, create the temporary + output directory for the job during the initialization of the job. +
      2. +
    2. + Cleanup the job after the job completion. For example, remove the + temporary output directory after the job completion. +
      3. +
    3. + Setup the task temporary output. +
      4. +
    4. + Check whether a task needs a commit. This is to avoid the commit + procedure if a task does not need commit. +
      5. +
    5. + Commit of the task output. +
      6. +
    6. + Discard the task commit. +
      7. +
    + The methods in this class can be called from several different processes and + from several different contexts. It is important to know which process and + which context each is called from. Each method should be marked accordingly + in its documentation. It is also important to note that not all methods are + guaranteed to be called once and only once. If a method is not guaranteed to + have this property the output committer needs to handle this appropriately. + Also note it will only be in rare situations where they may be called + multiple times for the same task. + + @see FileOutputCommitter + @see JobContext + @see TaskAttemptContext]]> +     +     + + + + + + + + + + + + + + + + + + + This is to validate the output specification for the job when it is + a job is submitted. Typically checks that it does not already exist, + throwing an exception when it already exists, so that output is not + overwritten.

    + + @param ignored + @param job job configuration. + @throws IOException when output should not be attempted]]> +     +     + + OutputFormat describes the output-specification for a + Map-Reduce job. + +

    The Map-Reduce framework relies on the OutputFormat of the + job to:

    +

      +
    1. + Validate the output-specification of the job. For e.g. check that the + output directory doesn't already exist. +
    2. + Provide the {@link RecordWriter} implementation to be used to write out + the output files of the job. Output files are stored in a + {@link FileSystem}. +
      3. +
    + + @see RecordWriter + @see JobConf]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + Typically a hash function on a all or a subset of the key.

    + + @param key the key to be paritioned. + @param value the entry value. + @param numPartitions the total number of partitions. + @return the partition number for the key.]]> +     +     + + Partitioner controls the partitioning of the keys of the + intermediate map-outputs. The key (or a subset of the key) is used to derive + the partition, typically by a hash function. The total number of partitions + is the same as the number of reduce tasks for the job. Hence this controls + which of the m reduce tasks the intermediate key (and hence the + record) is sent for reduction.

    + + @see Reducer]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 0.0 to 1.0. + @throws IOException]]> + + + + RecordReader reads <key, value> pairs from an + {@link InputSplit}. + +

    RecordReader, typically, converts the byte-oriented view of + the input, provided by the InputSplit, and presents a + record-oriented view for the {@link Mapper} and {@link Reducer} tasks for + processing. It thus assumes the responsibility of processing record + boundaries and presenting the tasks with keys and values.

    + + @see InputSplit + @see InputFormat]]> +     +     + + + + + + + + + + + + + + + + RecordWriter to future operations. + + @param reporter facility to report progress. + @throws IOException]]> + + + + RecordWriter writes the output <key, value> pairs + to an output file. + +

    RecordWriter implementations write the job outputs to the + {@link FileSystem}. + + @see OutputFormat]]> + + + + + + + + + + + + + + + Reduces values for a given key. + +

    The framework calls this method for each + <key, (list of values)> pair in the grouped inputs. + Output values must be of the same type as input values. Input keys must + not be altered. The framework will reuse the key and value objects + that are passed into the reduce, therefore the application should clone + the objects they want to keep a copy of. In many cases, all values are + combined into zero or one value. +

    + +

    Output pairs are collected with calls to + {@link OutputCollector#collect(Object,Object)}.

    + +

    Applications can use the {@link Reporter} provided to report progress + or just indicate that they are alive. In scenarios where the application + takes a significant amount of time to process individual key/value + pairs, this is crucial since the framework might assume that the task has + timed-out and kill that task. The other way of avoiding this is to set + + mapreduce.task.timeout to a high-enough value (or even zero for no + time-outs).

    + + @param key the key. + @param values the list of values to reduce. + @param output to collect keys and combined values. + @param reporter facility to report progress.]]> +     + + + The number of Reducers for the job is set by the user via + {@link JobConf#setNumReduceTasks(int)}. Reducer implementations + can access the {@link JobConf} for the job via the + {@link JobConfigurable#configure(JobConf)} method and initialize themselves. + Similarly they can use the {@link Closeable#close()} method for + de-initialization.

    + +

    Reducer has 3 primary phases:

    +
      +
    1. + + Shuffle + +

      Reducer is input the grouped output of a {@link Mapper}. + In the phase the framework, for each Reducer, fetches the + relevant partition of the output of all the Mappers, via HTTP. +

      +
      2. + +
    2. + Sort + +

      The framework groups Reducer inputs by keys + (since different Mappers may have output the same key) in this + stage.

      + +

      The shuffle and sort phases occur simultaneously i.e. while outputs are + being fetched they are merged.

      + + SecondarySort + +

      If equivalence rules for keys while grouping the intermediates are + different from those for grouping keys before reduction, then one may + specify a Comparator via + {@link JobConf#setOutputValueGroupingComparator(Class)}.Since + {@link JobConf#setOutputKeyComparatorClass(Class)} can be used to + control how intermediate keys are grouped, these can be used in conjunction + to simulate secondary sort on values.

      + + + For example, say that you want to find duplicate web pages and tag them + all with the url of the "best" known example. You would set up the job + like: +
        +
      • Map Input Key: url
        • +
      • Map Input Value: document
        • +
      • Map Output Key: document checksum, url pagerank
        • +
      • Map Output Value: url
        • +
      • Partitioner: by checksum
        • +
      • OutputKeyComparator: by checksum and then decreasing pagerank
        • +
      • OutputValueGroupingComparator: by checksum
        • +
      +
      3. + +
    3. + Reduce + +

      In this phase the + {@link #reduce(Object, Iterator, OutputCollector, Reporter)} + method is called for each <key, (list of values)> pair in + the grouped inputs.

      +

      The output of the reduce task is typically written to the + {@link FileSystem} via + {@link OutputCollector#collect(Object, Object)}.

      +
      4. +
    + +

    The output of the Reducer is not re-sorted.

    + +

    Example:

    + 

    +     public class MyReducer<K extends WritableComparable, V extends Writable> 
+     extends MapReduceBase implements Reducer<K, V, K, V> {
+     
+       static enum MyCounters { NUM_RECORDS }
+        
+       private String reduceTaskId;
+       private int noKeys = 0;
+       
+       public void configure(JobConf job) {
+         reduceTaskId = job.get(JobContext.TASK_ATTEMPT_ID);
+       }
+       
+       public void reduce(K key, Iterator<V> values,
+                          OutputCollector<K, V> output, 
+                          Reporter reporter)
+       throws IOException {
+       
+         // Process
+         int noValues = 0;
+         while (values.hasNext()) {
+           V value = values.next();
+           
+           // Increment the no. of values for this key
+           ++noValues;
+           
+           // Process the <key, value> pair (assume this takes a while)
+           // ...
+           // ...
+           
+           // Let the framework know that we are alive, and kicking!
+           if ((noValues%10) == 0) {
+             reporter.progress();
+           }
+         
+           // Process some more
+           // ...
+           // ...
+           
+           // Output the <key, value> 
+           output.collect(key, value);
+         }
+         
+         // Increment the no. of <key, list of values> pairs processed
+         ++noKeys;
+         
+         // Increment counters
+         reporter.incrCounter(NUM_RECORDS, 1);
+         
+         // Every 100 keys update application-level status
+         if ((noKeys%100) == 0) {
+           reporter.setStatus(reduceTaskId + " processed " + noKeys);
+         }
+       }
+     }
+
    + + @see Mapper + @see Partitioner + @see Reporter + @see MapReduceBase]]> +     +     + + + + + + + + + + + + + + Counter of the given group/name.]]> + + + + + + + Counter of the given group/name.]]> + + + + + + + Enum. + @param amount A non-negative amount by which the counter is to + be incremented.]]> + + + + + + + + + + + + + + InputSplit that the map is reading from. + @throws UnsupportedOperationException if called outside a mapper]]> + + + + + + + + + + + + + + {@link Mapper} and {@link Reducer} can use the Reporter + provided to report progress or just indicate that they are alive. In + scenarios where the application takes significant amount of time to + process individual key/value pairs, this is crucial since the framework + might assume that the task has timed-out and kill that task. + +

    Applications can also update {@link Counters} via the provided + Reporter .

    + + @see Progressable + @see Counters]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + progress of the job's map-tasks, as a float between 0.0 + and 1.0. When all map tasks have completed, the function returns 1.0. + + @return the progress of the job's map-tasks. + @throws IOException]]> + + + + + + progress of the job's reduce-tasks, as a float between 0.0 + and 1.0. When all reduce tasks have completed, the function returns 1.0. + + @return the progress of the job's reduce-tasks. + @throws IOException]]> + + + + + + progress of the job's cleanup-tasks, as a float between 0.0 + and 1.0. When all cleanup tasks have completed, the function returns 1.0. + + @return the progress of the job's cleanup-tasks. + @throws IOException]]> + + + + + + progress of the job's setup-tasks, as a float between 0.0 + and 1.0. When all setup tasks have completed, the function returns 1.0. + + @return the progress of the job's setup-tasks. + @throws IOException]]> + + + + + + true if the job is complete, else false. + @throws IOException]]> + + + + + + true if the job succeeded, else false. + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if the job retired, else false. + @throws IOException]]> + + + + + + + + + + RunningJob is the user-interface to query for details on a + running Map-Reduce job. + +

    Clients can get hold of RunningJob via the {@link JobClient} + and then query the running-job for details such as name, configuration, + progress etc.

    + + @see JobClient]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + This allows the user to specify the key class to be different + from the actual class ({@link BytesWritable}) used for writing

    + + @param conf the {@link JobConf} to modify + @param theClass the SequenceFile output key class.]]> +     +     + + + + + This allows the user to specify the value class to be different + from the actual class ({@link BytesWritable}) used for writing

    + + @param conf the {@link JobConf} to modify + @param theClass the SequenceFile output key class.]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if auto increment + {@link SkipBadRecords#COUNTER_MAP_PROCESSED_RECORDS}. + false otherwise.]]> + + + + + + + + + + + + + true if auto increment + {@link SkipBadRecords#COUNTER_REDUCE_PROCESSED_GROUPS}. + false otherwise.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Hadoop provides an optional mode of execution in which the bad records + are detected and skipped in further attempts. + +

    This feature can be used when map/reduce tasks crashes deterministically on + certain input. This happens due to bugs in the map/reduce function. The usual + course would be to fix these bugs. But sometimes this is not possible; + perhaps the bug is in third party libraries for which the source code is + not available. Due to this, the task never reaches to completion even with + multiple attempts and complete data for that task is lost.

    + +

    With this feature, only a small portion of data is lost surrounding + the bad record, which may be acceptable for some user applications. + see {@link SkipBadRecords#setMapperMaxSkipRecords(Configuration, long)}

    + +

    The skipping mode gets kicked off after certain no of failures + see {@link SkipBadRecords#setAttemptsToStartSkipping(Configuration, int)}

    + +

    In the skipping mode, the map/reduce task maintains the record range which + is getting processed at all times. Before giving the input to the + map/reduce function, it sends this record range to the Task tracker. + If task crashes, the Task tracker knows which one was the last reported + range. On further attempts that range get skipped.

    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + all task attempt IDs + of any jobtracker, in any job, of the first + map task, we would use : + 
     
+ TaskAttemptID.getTaskAttemptIDsPattern(null, null, true, 1, null);
+
    + which will return : + 
     "attempt_[^_]*_[0-9]*_m_000001_[0-9]*"
    + @param jtIdentifier jobTracker identifier, or null + @param jobId job number, or null + @param isMap whether the tip is a map, or null + @param taskId taskId number, or null + @param attemptId the task attempt number, or null + @return a regex pattern matching TaskAttemptIDs]]> +     +     + + + + + + + + all task attempt IDs + of any jobtracker, in any job, of the first + map task, we would use : + 
     
+ TaskAttemptID.getTaskAttemptIDsPattern(null, null, TaskType.MAP, 1, null);
+
    + which will return : + 
     "attempt_[^_]*_[0-9]*_m_000001_[0-9]*"
    + @param jtIdentifier jobTracker identifier, or null + @param jobId job number, or null + @param type the {@link TaskType} + @param taskId taskId number, or null + @param attemptId the task attempt number, or null + @return a regex pattern matching TaskAttemptIDs]]> +     +     + + + An example TaskAttemptID is : + attempt_200707121733_0003_m_000005_0 , which represents the + zeroth task attempt for the fifth map task in the third job + running at the jobtracker started at 200707121733. +

    + Applications should never construct or parse TaskAttemptID strings + , but rather use appropriate constructors or {@link #forName(String)} + method. + + @see JobID + @see TaskID]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + the first map task + of any jobtracker, of any job, we would use : + 

     
+ TaskID.getTaskIDsPattern(null, null, true, 1);
+
    + which will return : + 
     "task_[^_]*_[0-9]*_m_000001*"
    + @param jtIdentifier jobTracker identifier, or null + @param jobId job number, or null + @param isMap whether the tip is a map, or null + @param taskId taskId number, or null + @return a regex pattern matching TaskIDs + @deprecated Use {@link TaskID#getTaskIDsPattern(String, Integer, TaskType, + Integer)}]]> +     + + + + + + + + the first map task + of any jobtracker, of any job, we would use : + 
     
+ TaskID.getTaskIDsPattern(null, null, true, 1);
+
    + which will return : + 
     "task_[^_]*_[0-9]*_m_000001*"
    + @param jtIdentifier jobTracker identifier, or null + @param jobId job number, or null + @param type the {@link TaskType}, or null + @param taskId taskId number, or null + @return a regex pattern matching TaskIDs]]> +     +     + + + + + + + An example TaskID is : + task_200707121733_0003_m_000005 , which represents the + fifth map task in the third job running at the jobtracker + started at 200707121733. +

    + Applications should never construct or parse TaskID strings + , but rather use appropriate constructors or {@link #forName(String)} + method. + + @see JobID + @see TaskAttemptID]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if the Job was added.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ([,]*) + func ::= tbl(,"") + class ::= @see java.lang.Class#forName(java.lang.String) + path ::= @see org.apache.hadoop.fs.Path#Path(java.lang.String) + } + Reads expression from the mapred.join.expr property and + user-supplied join types from mapred.join.define.<ident> + types. Paths supplied to tbl are given as input paths to the + InputFormat class listed. + @see #compose(java.lang.String, java.lang.Class, java.lang.String...)]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ,

    ) }]]> + + + + + + + + (tbl(,),tbl(,),...,tbl(,)) }]]> + + + + + + + + (tbl(,),tbl(,),...,tbl(,)) }]]> + + + + mapred.join.define.<ident> to a classname. In the expression + mapred.join.expr, the identifier will be assumed to be a + ComposableRecordReader. + mapred.join.keycomparator can be a classname used to compare keys + in the join. + @see #setFormat + @see JoinRecordReader + @see MultiFilterRecordReader]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ...... + }]]> + + + + + + + + + + + + + + + + + + + + + capacity children to position + id in the parent reader. + The id of a root CompositeRecordReader is -1 by convention, but relying + on this is not recommended.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + override(S1,S2,S3) will prefer values + from S3 over S2, and values from S2 over S1 for all keys + emitted from all sources.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + It has to be specified how key and values are passed from one element of + the chain to the next, by value or by reference. If a Mapper leverages the + assumed semantics that the key and values are not modified by the collector + 'by value' must be used. If the Mapper does not expect this semantics, as + an optimization to avoid serialization and deserialization 'by reference' + can be used. +

    + For the added Mapper the configuration given for it, + mapperConf, have precedence over the job's JobConf. This + precedence is in effect when the task is running. +

    + IMPORTANT: There is no need to specify the output key/value classes for the + ChainMapper, this is done by the addMapper for the last mapper in the chain +

    + + @param job job's JobConf to add the Mapper class. + @param klass the Mapper class to add. + @param inputKeyClass mapper input key class. + @param inputValueClass mapper input value class. + @param outputKeyClass mapper output key class. + @param outputValueClass mapper output value class. + @param byValue indicates if key/values should be passed by value + to the next Mapper in the chain, if any. + @param mapperConf a JobConf with the configuration for the Mapper + class. It is recommended to use a JobConf without default values using the + JobConf(boolean loadDefaults) constructor with FALSE.]]> + + + + + + + If this method is overriden super.configure(...) should be + invoked at the beginning of the overwriter method.]]> + + + + + + + + + + map(...) methods of the Mappers in the chain.]]> + + + + + + + If this method is overriden super.close() should be + invoked at the end of the overwriter method.]]> + + + + + The Mapper classes are invoked in a chained (or piped) fashion, the output of + the first becomes the input of the second, and so on until the last Mapper, + the output of the last Mapper will be written to the task's output. +

    + The key functionality of this feature is that the Mappers in the chain do not + need to be aware that they are executed in a chain. This enables having + reusable specialized Mappers that can be combined to perform composite + operations within a single task. +

    + Special care has to be taken when creating chains that the key/values output + by a Mapper are valid for the following Mapper in the chain. It is assumed + all Mappers and the Reduce in the chain use maching output and input key and + value classes as no conversion is done by the chaining code. +

    + Using the ChainMapper and the ChainReducer classes is possible to compose + Map/Reduce jobs that look like [MAP+ / REDUCE MAP*]. And + immediate benefit of this pattern is a dramatic reduction in disk IO. +

    + IMPORTANT: There is no need to specify the output key/value classes for the + ChainMapper, this is done by the addMapper for the last mapper in the chain. +

    + ChainMapper usage pattern: +

    + 

    + ...
+ conf.setJobName("chain");
+ conf.setInputFormat(TextInputFormat.class);
+ conf.setOutputFormat(TextOutputFormat.class);
+
+ JobConf mapAConf = new JobConf(false);
+ ...
+ ChainMapper.addMapper(conf, AMap.class, LongWritable.class, Text.class,
+   Text.class, Text.class, true, mapAConf);
+
+ JobConf mapBConf = new JobConf(false);
+ ...
+ ChainMapper.addMapper(conf, BMap.class, Text.class, Text.class,
+   LongWritable.class, Text.class, false, mapBConf);
+
+ JobConf reduceConf = new JobConf(false);
+ ...
+ ChainReducer.setReducer(conf, XReduce.class, LongWritable.class, Text.class,
+   Text.class, Text.class, true, reduceConf);
+
+ ChainReducer.addMapper(conf, CMap.class, Text.class, Text.class,
+   LongWritable.class, Text.class, false, null);
+
+ ChainReducer.addMapper(conf, DMap.class, LongWritable.class, Text.class,
+   LongWritable.class, LongWritable.class, true, null);
+
+ FileInputFormat.setInputPaths(conf, inDir);
+ FileOutputFormat.setOutputPath(conf, outDir);
+ ...
+
+ JobClient jc = new JobClient(conf);
+ RunningJob job = jc.submitJob(conf);
+ ...
+
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + It has to be specified how key and values are passed from one element of + the chain to the next, by value or by reference. If a Reducer leverages the + assumed semantics that the key and values are not modified by the collector + 'by value' must be used. If the Reducer does not expect this semantics, as + an optimization to avoid serialization and deserialization 'by reference' + can be used. +

    + For the added Reducer the configuration given for it, + reducerConf, have precedence over the job's JobConf. This + precedence is in effect when the task is running. +

    + IMPORTANT: There is no need to specify the output key/value classes for the + ChainReducer, this is done by the setReducer or the addMapper for the last + element in the chain. + + @param job job's JobConf to add the Reducer class. + @param klass the Reducer class to add. + @param inputKeyClass reducer input key class. + @param inputValueClass reducer input value class. + @param outputKeyClass reducer output key class. + @param outputValueClass reducer output value class. + @param byValue indicates if key/values should be passed by value + to the next Mapper in the chain, if any. + @param reducerConf a JobConf with the configuration for the Reducer + class. It is recommended to use a JobConf without default values using the + JobConf(boolean loadDefaults) constructor with FALSE.]]> + + + + + + + + + + + + + + It has to be specified how key and values are passed from one element of + the chain to the next, by value or by reference. If a Mapper leverages the + assumed semantics that the key and values are not modified by the collector + 'by value' must be used. If the Mapper does not expect this semantics, as + an optimization to avoid serialization and deserialization 'by reference' + can be used. +

    + For the added Mapper the configuration given for it, + mapperConf, have precedence over the job's JobConf. This + precedence is in effect when the task is running. +

    + IMPORTANT: There is no need to specify the output key/value classes for the + ChainMapper, this is done by the addMapper for the last mapper in the chain + . + + @param job chain job's JobConf to add the Mapper class. + @param klass the Mapper class to add. + @param inputKeyClass mapper input key class. + @param inputValueClass mapper input value class. + @param outputKeyClass mapper output key class. + @param outputValueClass mapper output value class. + @param byValue indicates if key/values should be passed by value + to the next Mapper in the chain, if any. + @param mapperConf a JobConf with the configuration for the Mapper + class. It is recommended to use a JobConf without default values using the + JobConf(boolean loadDefaults) constructor with FALSE.]]> + + + + + + + If this method is overriden super.configure(...) should be + invoked at the beginning of the overwriter method.]]> + + + + + + + + + + reduce(...) method of the Reducer with the + map(...) methods of the Mappers in the chain.]]> + + + + + + + If this method is overriden super.close() should be + invoked at the end of the overwriter method.]]> + + + + + For each record output by the Reducer, the Mapper classes are invoked in a + chained (or piped) fashion, the output of the first becomes the input of the + second, and so on until the last Mapper, the output of the last Mapper will + be written to the task's output. +

    + The key functionality of this feature is that the Mappers in the chain do not + need to be aware that they are executed after the Reducer or in a chain. + This enables having reusable specialized Mappers that can be combined to + perform composite operations within a single task. +

    + Special care has to be taken when creating chains that the key/values output + by a Mapper are valid for the following Mapper in the chain. It is assumed + all Mappers and the Reduce in the chain use maching output and input key and + value classes as no conversion is done by the chaining code. +

    + Using the ChainMapper and the ChainReducer classes is possible to compose + Map/Reduce jobs that look like [MAP+ / REDUCE MAP*]. And + immediate benefit of this pattern is a dramatic reduction in disk IO. +

    + IMPORTANT: There is no need to specify the output key/value classes for the + ChainReducer, this is done by the setReducer or the addMapper for the last + element in the chain. +

    + ChainReducer usage pattern: +

    + 

    + ...
+ conf.setJobName("chain");
+ conf.setInputFormat(TextInputFormat.class);
+ conf.setOutputFormat(TextOutputFormat.class);
+
+ JobConf mapAConf = new JobConf(false);
+ ...
+ ChainMapper.addMapper(conf, AMap.class, LongWritable.class, Text.class,
+   Text.class, Text.class, true, mapAConf);
+
+ JobConf mapBConf = new JobConf(false);
+ ...
+ ChainMapper.addMapper(conf, BMap.class, Text.class, Text.class,
+   LongWritable.class, Text.class, false, mapBConf);
+
+ JobConf reduceConf = new JobConf(false);
+ ...
+ ChainReducer.setReducer(conf, XReduce.class, LongWritable.class, Text.class,
+   Text.class, Text.class, true, reduceConf);
+
+ ChainReducer.addMapper(conf, CMap.class, Text.class, Text.class,
+   LongWritable.class, Text.class, false, null);
+
+ ChainReducer.addMapper(conf, DMap.class, LongWritable.class, Text.class,
+   LongWritable.class, LongWritable.class, true, null);
+
+ FileInputFormat.setInputPaths(conf, inDir);
+ FileOutputFormat.setOutputPath(conf, outDir);
+ ...
+
+ JobClient jc = new JobClient(conf);
+ RunningJob job = jc.submitJob(conf);
+ ...
+
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + RecordReader's for CombineFileSplit's. + @see CombineFileSplit]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + CombineFileRecordReader. + + Subclassing is needed to get a concrete record reader wrapper because of the + constructor requirement. + + @see CombineFileRecordReader + @see CombineFileInputFormat]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + CombineFileInputFormat-equivalent for + SequenceFileInputFormat. + + @see CombineFileInputFormat]]> + + + + + + + + + + + + + + + CombineFileInputFormat-equivalent for + TextInputFormat. + + @see CombineFileInputFormat]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if the name output is multi, false + if it is single. If the name output is not defined it returns + false]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + By default these counters are disabled. +

    + MultipleOutputs supports counters, by default the are disabled. + The counters group is the {@link MultipleOutputs} class name. +

    + The names of the counters are the same as the named outputs. For multi + named outputs the name of the counter is the concatenation of the named + output, and underscore '_' and the multiname. + + @param conf job conf to enableadd the named output. + @param enabled indicates if the counters will be enabled or not.]]> +     +     + + + + + By default these counters are disabled. +

    + MultipleOutputs supports counters, by default the are disabled. + The counters group is the {@link MultipleOutputs} class name. +

    + The names of the counters are the same as the named outputs. For multi + named outputs the name of the counter is the concatenation of the named + output, and underscore '_' and the multiname. + + + @param conf job conf to enableadd the named output. + @return TRUE if the counters are enabled, FALSE if they are disabled.]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + If overriden subclasses must invoke super.close() at the + end of their close() + + @throws java.io.IOException thrown if any of the MultipleOutput files + could not be closed properly.]]> + + + + OutputCollector passed to + the map() and reduce() methods of the + Mapper and Reducer implementations. +

    + Each additional output, or named output, may be configured with its own + OutputFormat, with its own key class and with its own value + class. +

    + A named output can be a single file or a multi file. The later is refered as + a multi named output. +

    + A multi named output is an unbound set of files all sharing the same + OutputFormat, key class and value class configuration. +

    + When named outputs are used within a Mapper implementation, + key/values written to a name output are not part of the reduce phase, only + key/values written to the job OutputCollector are part of the + reduce phase. +

    + MultipleOutputs supports counters, by default the are disabled. The counters + group is the {@link MultipleOutputs} class name. +

    + The names of the counters are the same as the named outputs. For multi + named outputs the name of the counter is the concatenation of the named + output, and underscore '_' and the multiname. +

    + Job configuration usage pattern is: + 

    +
+ JobConf conf = new JobConf();
+
+ conf.setInputPath(inDir);
+ FileOutputFormat.setOutputPath(conf, outDir);
+
+ conf.setMapperClass(MOMap.class);
+ conf.setReducerClass(MOReduce.class);
+ ...
+
+ // Defines additional single text based output 'text' for the job
+ MultipleOutputs.addNamedOutput(conf, "text", TextOutputFormat.class,
+ LongWritable.class, Text.class);
+
+ // Defines additional multi sequencefile based output 'sequence' for the
+ // job
+ MultipleOutputs.addMultiNamedOutput(conf, "seq",
+   SequenceFileOutputFormat.class,
+   LongWritable.class, Text.class);
+ ...
+
+ JobClient jc = new JobClient();
+ RunningJob job = jc.submitJob(conf);
+
+ ...
+
    +

    + Job configuration usage pattern is: + 

    +
+ public class MOReduce implements
+   Reducer<WritableComparable, Writable> {
+ private MultipleOutputs mos;
+
+ public void configure(JobConf conf) {
+ ...
+ mos = new MultipleOutputs(conf);
+ }
+
+ public void reduce(WritableComparable key, Iterator<Writable> values,
+ OutputCollector output, Reporter reporter)
+ throws IOException {
+ ...
+ mos.getCollector("text", reporter).collect(key, new Text("Hello"));
+ mos.getCollector("seq", "A", reporter).collect(key, new Text("Bye"));
+ mos.getCollector("seq", "B", reporter).collect(key, new Text("Chau"));
+ ...
+ }
+
+ public void close() throws IOException {
+ mos.close();
+ ...
+ }
+
+ }
+
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + It can be used instead of the default implementation, + of {@link org.apache.hadoop.mapred.MapRunner}, when the Map + operation is not CPU bound in order to improve throughput. +

    + Map implementations using this MapRunnable must be thread-safe. +

    + The Map-Reduce job has to be configured to use this MapRunnable class (using + the JobConf.setMapRunnerClass method) and + the number of threads the thread-pool can use with the + mapred.map.multithreadedrunner.threads property, its default + value is 10 threads. +

    ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + R reduces, there are R-1 + keys in the SequenceFile. + @deprecated Use + {@link #setPartitionFile(Configuration, Path)} + instead]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Cluster. + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ClusterMetrics provides clients with information such as: +

      +
    1. + Size of the cluster. +
      2. +
    2. + Number of blacklisted and decommissioned trackers. +
      3. +
    3. + Slot capacity of the cluster. +
      4. +
    4. + The number of currently occupied/reserved map and reduce slots. +
      5. +
    5. + The number of currently running map and reduce tasks. +
      6. +
    6. + The number of job submissions. +
      7. +
    + +

    Clients can query for the latest ClusterMetrics, via + {@link Cluster#getClusterStatus()}.

    + + @see Cluster]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Counters represent global counters, defined either by the + Map-Reduce framework or applications. Each Counter is named by + an {@link Enum} and has a long for the value.

    + +

    Counters are bunched into Groups, each comprising of + counters from a particular Enum class.]]> + + + + + + + + + + + + + + + + + + + + + the type of counter + @param the type of counter group + @param counters the old counters object]]> + + + + Counters holds per job/task counters, defined either by the + Map-Reduce framework or applications. Each Counter can be of + any {@link Enum} type.

    + +

    Counters are bunched into {@link CounterGroup}s, each + comprising of counters from a particular Enum class.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Each {@link InputSplit} is then assigned to an individual {@link Mapper} + for processing.

    + +

    Note: The split is a logical split of the inputs and the + input files are not physically split into chunks. For e.g. a split could + be <input-file-path, start, offset> tuple. The InputFormat + also creates the {@link RecordReader} to read the {@link InputSplit}. + + @param context job configuration. + @return an array of {@link InputSplit}s for the job.]]> + + + + + + + + + + + + + InputFormat describes the input-specification for a + Map-Reduce job. + +

    The Map-Reduce framework relies on the InputFormat of the + job to:

    +

      +
    1. + Validate the input-specification of the job. +
    2. + Split-up the input file(s) into logical {@link InputSplit}s, each of + which is then assigned to an individual {@link Mapper}. +
      3. +
    3. + Provide the {@link RecordReader} implementation to be used to glean + input records from the logical InputSplit for processing by + the {@link Mapper}. +
      4. +
    + +

    The default behavior of file-based {@link InputFormat}s, typically + sub-classes of {@link FileInputFormat}, is to split the + input into logical {@link InputSplit}s based on the total size, in + bytes, of the input files. However, the {@link FileSystem} blocksize of + the input files is treated as an upper bound for input splits. A lower bound + on the split size can be set via + + mapreduce.input.fileinputformat.split.minsize.

    + +

    Clearly, logical splits based on input-size is insufficient for many + applications since record boundaries are to respected. In such cases, the + application has to also implement a {@link RecordReader} on whom lies the + responsibility to respect record-boundaries and present a record-oriented + view of the logical InputSplit to the individual task. + + @see InputSplit + @see RecordReader + @see FileInputFormat]]> + + + + + + + + + + + + + + + + + + + + + + + + + SplitLocationInfos describing how the split + data is stored at each location. A null value indicates that all the + locations have the data stored on disk. + @throws IOException]]> + + + + InputSplit represents the data to be processed by an + individual {@link Mapper}. + +

    Typically, it presents a byte-oriented view on the input and is the + responsibility of {@link RecordReader} of the job to process this and present + a record-oriented view. + + @see InputFormat + @see RecordReader]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Job makes a copy of the Configuration so + that any necessary internal modifications do not reflect on the incoming + parameter. + + A Cluster will be created from the conf parameter only when it's needed. + + @param conf the configuration + @return the {@link Job} , with no connection to a cluster yet. + @throws IOException]]> + + + + + + + + Job makes a copy of the Configuration so + that any necessary internal modifications do not reflect on the incoming + parameter. + + @param conf the configuration + @return the {@link Job} , with no connection to a cluster yet. + @throws IOException]]> + + + + + + + + Job makes a copy of the Configuration so + that any necessary internal modifications do not reflect on the incoming + parameter. + + @param status job status + @param conf job configuration + @return the {@link Job} , with no connection to a cluster yet. + @throws IOException]]> + + + + + + + Job makes a copy of the Configuration so + that any necessary internal modifications do not reflect on the incoming + parameter. + + @param ignored + @return the {@link Job} , with no connection to a cluster yet. + @throws IOException + @deprecated Use {@link #getInstance()}]]> + + + + + + + + Job makes a copy of the Configuration so + that any necessary internal modifications do not reflect on the incoming + parameter. + + @param ignored + @param conf job configuration + @return the {@link Job} , with no connection to a cluster yet. + @throws IOException + @deprecated Use {@link #getInstance(Configuration)}]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + progress of the job's map-tasks, as a float between 0.0 + and 1.0. When all map tasks have completed, the function returns 1.0. + + @return the progress of the job's map-tasks. + @throws IOException]]> + + + + + + progress of the job's reduce-tasks, as a float between 0.0 + and 1.0. When all reduce tasks have completed, the function returns 1.0. + + @return the progress of the job's reduce-tasks. + @throws IOException]]> + + + + + + + progress of the job's cleanup-tasks, as a float between 0.0 + and 1.0. When all cleanup tasks have completed, the function returns 1.0. + + @return the progress of the job's cleanup-tasks. + @throws IOException]]> + + + + + + progress of the job's setup-tasks, as a float between 0.0 + and 1.0. When all setup tasks have completed, the function returns 1.0. + + @return the progress of the job's setup-tasks. + @throws IOException]]> + + + + + + true if the job is complete, else false. + @throws IOException]]> + + + + + + true if the job succeeded, else false. + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + InputFormat to use + @throws IllegalStateException if the job is submitted]]> + + + + + + + OutputFormat to use + @throws IllegalStateException if the job is submitted]]> + + + + + + + Mapper to use + @throws IllegalStateException if the job is submitted]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Reducer to use + @throws IllegalStateException if the job is submitted]]> + + + + + + + Partitioner to use + @throws IllegalStateException if the job is submitted]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if speculative execution + should be turned on, else false.]]> + + + + + + true if speculative execution + should be turned on for map tasks, + else false.]]> + + + + + + true if speculative execution + should be turned on for reduce tasks, + else false.]]> + + + + + + true, job-setup and job-cleanup will be + considered from {@link OutputCommitter} + else ignored.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + JobTracker is lost]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + It allows the user to configure the + job, submit it, control its execution, and query the state. The set methods + only work until the job is submitted, afterwards they will throw an + IllegalStateException.

    + +

    + Normally the user creates the application, describes various facets of the + job via {@link Job} and then submits the job and monitor its progress.

    + +

    Here is an example on how to submit a job:

    + 

    +     // Create a new Job
+     Job job = Job.getInstance();
+     job.setJarByClass(MyJob.class);
+     
+     // Specify various job-specific parameters     
+     job.setJobName("myjob");
+     
+     job.setInputPath(new Path("in"));
+     job.setOutputPath(new Path("out"));
+     
+     job.setMapperClass(MyJob.MyMapper.class);
+     job.setReducerClass(MyJob.MyReducer.class);
+
+     // Submit the job, then poll for progress until the job is complete
+     job.waitForCompletion(true);
+
    ]]> +     + + + + + + + + + + + + + + + + + + + + + + + 1. + @return the number of reduce tasks for this job.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + mapred.map.max.attempts + property. If this property is not already set, the default is 4 attempts. + + @return the max number of attempts per map task.]]> + + + + + mapred.reduce.max.attempts + property. If this property is not already set, the default is 4 attempts. + + @return the max number of attempts per reduce task.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + An example JobID is : + job_200707121733_0003 , which represents the third job + running at the jobtracker started at 200707121733. +

    + Applications should never construct or parse JobID strings, but rather + use appropriate constructors or {@link #forName(String)} method. + + @see TaskID + @see TaskAttemptID]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + the key input type to the Mapper + @param the value input type to the Mapper + @param the key output type from the Mapper + @param the value output type from the Mapper]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Maps are the individual tasks which transform input records into a + intermediate records. The transformed intermediate records need not be of + the same type as the input records. A given input pair may map to zero or + many output pairs.

    + +

    The Hadoop Map-Reduce framework spawns one map task for each + {@link InputSplit} generated by the {@link InputFormat} for the job. + Mapper implementations can access the {@link Configuration} for + the job via the {@link JobContext#getConfiguration()}. + +

    The framework first calls + {@link #setup(org.apache.hadoop.mapreduce.Mapper.Context)}, followed by + {@link #map(Object, Object, org.apache.hadoop.mapreduce.Mapper.Context)} + for each key/value pair in the InputSplit. Finally + {@link #cleanup(org.apache.hadoop.mapreduce.Mapper.Context)} is called.

    + +

    All intermediate values associated with a given output key are + subsequently grouped by the framework, and passed to a {@link Reducer} to + determine the final output. Users can control the sorting and grouping by + specifying two key {@link RawComparator} classes.

    + +

    The Mapper outputs are partitioned per + Reducer. Users can control which keys (and hence records) go to + which Reducer by implementing a custom {@link Partitioner}. + +

    Users can optionally specify a combiner, via + {@link Job#setCombinerClass(Class)}, to perform local aggregation of the + intermediate outputs, which helps to cut down the amount of data transferred + from the Mapper to the Reducer. + +

    Applications can specify if and how the intermediate + outputs are to be compressed and which {@link CompressionCodec}s are to be + used via the Configuration.

    + +

    If the job has zero + reduces then the output of the Mapper is directly written + to the {@link OutputFormat} without sorting by keys.

    + +

    Example:

    + 

    + public class TokenCounterMapper 
+     extends Mapper<Object, Text, Text, IntWritable>{
+    
+   private final static IntWritable one = new IntWritable(1);
+   private Text word = new Text();
+   
+   public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
+     StringTokenizer itr = new StringTokenizer(value.toString());
+     while (itr.hasMoreTokens()) {
+       word.set(itr.nextToken());
+       context.write(word, one);
+     }
+   }
+ }
+
    + +

    Applications may override the + {@link #run(org.apache.hadoop.mapreduce.Mapper.Context)} method to exert + greater control on map processing e.g. multi-threaded Mappers + etc.

    + + @see InputFormat + @see JobContext + @see Partitioner + @see Reducer]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + MarkableIterator is a wrapper iterator class that + implements the {@link MarkableIteratorInterface}.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if task output recovery is supported, + false otherwise + @see #recoverTask(TaskAttemptContext) + @deprecated Use {@link #isRecoverySupported(JobContext)} instead.]]> + + + + + + + true repeatable job commit is supported, + false otherwise + @throws IOException]]> + + + + + + + true if task output recovery is supported, + false otherwise + @throws IOException + @see #recoverTask(TaskAttemptContext)]]> + + + + + + + OutputCommitter. This is called from the application master + process, but it is called individually for each task. + + If an exception is thrown the task will be attempted again. + + This may be called multiple times for the same task. But from different + application attempts. + + @param taskContext Context of the task whose output is being recovered + @throws IOException]]> + + + + OutputCommitter describes the commit of task output for a + Map-Reduce job. + +

    The Map-Reduce framework relies on the OutputCommitter of + the job to:

    +

      +
    1. + Setup the job during initialization. For example, create the temporary + output directory for the job during the initialization of the job. +
      2. +
    2. + Cleanup the job after the job completion. For example, remove the + temporary output directory after the job completion. +
      3. +
    3. + Setup the task temporary output. +
      4. +
    4. + Check whether a task needs a commit. This is to avoid the commit + procedure if a task does not need commit. +
      5. +
    5. + Commit of the task output. +
      6. +
    6. + Discard the task commit. +
      7. +
    + The methods in this class can be called from several different processes and + from several different contexts. It is important to know which process and + which context each is called from. Each method should be marked accordingly + in its documentation. It is also important to note that not all methods are + guaranteed to be called once and only once. If a method is not guaranteed to + have this property the output committer needs to handle this appropriately. + Also note it will only be in rare situations where they may be called + multiple times for the same task. + + @see org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter + @see JobContext + @see TaskAttemptContext]]> +     +     + + + + + + + + + + + + + + + + + + + This is to validate the output specification for the job when it is + a job is submitted. Typically checks that it does not already exist, + throwing an exception when it already exists, so that output is not + overwritten.

    + + @param context information about the job + @throws IOException when output should not be attempted]]> +     +     + + + + + + + + + + OutputFormat describes the output-specification for a + Map-Reduce job. + +

    The Map-Reduce framework relies on the OutputFormat of the + job to:

    +

      +
    1. + Validate the output-specification of the job. For e.g. check that the + output directory doesn't already exist. +
    2. + Provide the {@link RecordWriter} implementation to be used to write out + the output files of the job. Output files are stored in a + {@link FileSystem}. +
      3. +
    + + @see RecordWriter]]> +     +     + + + + + + + + + + + Typically a hash function on a all or a subset of the key.

    + + @param key the key to be partioned. + @param value the entry value. + @param numPartitions the total number of partitions. + @return the partition number for the key.]]> +     +     + + Partitioner controls the partitioning of the keys of the + intermediate map-outputs. The key (or a subset of the key) is used to derive + the partition, typically by a hash function. The total number of partitions + is the same as the number of reduce tasks for the job. Hence this controls + which of the m reduce tasks the intermediate key (and hence the + record) is sent for reduction.

    + + Note: If you require your Partitioner class to obtain the Job's configuration + object, implement the {@link Configurable} interface. + + @see Reducer]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + "N/A" + + @return Scheduling information associated to particular Job Queue]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @param ]]> + + + + + + + + + + + + + + + + + + + + + + RecordWriter to future operations. + + @param context the context of the task + @throws IOException]]> + + + + RecordWriter writes the output <key, value> pairs + to an output file. + +

    RecordWriter implementations write the job outputs to the + {@link FileSystem}. + + @see OutputFormat]]> + + + + + + + + + + + + + + + + + + + + + + the class of the input keys + @param the class of the input values + @param the class of the output keys + @param the class of the output values]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Reducer implementations + can access the {@link Configuration} for the job via the + {@link JobContext#getConfiguration()} method.

    + +

    Reducer has 3 primary phases:

    +
      +
    1. + + Shuffle + +

      The Reducer copies the sorted output from each + {@link Mapper} using HTTP across the network.

      +
      2. + +
    2. + Sort + +

      The framework merge sorts Reducer inputs by + keys + (since different Mappers may have output the same key).

      + +

      The shuffle and sort phases occur simultaneously i.e. while outputs are + being fetched they are merged.

      + + SecondarySort + +

      To achieve a secondary sort on the values returned by the value + iterator, the application should extend the key with the secondary + key and define a grouping comparator. The keys will be sorted using the + entire key, but will be grouped using the grouping comparator to decide + which keys and values are sent in the same call to reduce.The grouping + comparator is specified via + {@link Job#setGroupingComparatorClass(Class)}. The sort order is + controlled by + {@link Job#setSortComparatorClass(Class)}.

      + + + For example, say that you want to find duplicate web pages and tag them + all with the url of the "best" known example. You would set up the job + like: +
        +
      • Map Input Key: url
        • +
      • Map Input Value: document
        • +
      • Map Output Key: document checksum, url pagerank
        • +
      • Map Output Value: url
        • +
      • Partitioner: by checksum
        • +
      • OutputKeyComparator: by checksum and then decreasing pagerank
        • +
      • OutputValueGroupingComparator: by checksum
        • +
      +
      3. + +
    3. + Reduce + +

      In this phase the + {@link #reduce(Object, Iterable, org.apache.hadoop.mapreduce.Reducer.Context)} + method is called for each <key, (collection of values)> in + the sorted inputs.

      +

      The output of the reduce task is typically written to a + {@link RecordWriter} via + {@link Context#write(Object, Object)}.

      +
      4. +
    + +

    The output of the Reducer is not re-sorted.

    + +

    Example:

    + 

    + public class IntSumReducer<Key> extends Reducer<Key,IntWritable,
+                                                 Key,IntWritable> {
+   private IntWritable result = new IntWritable();
+ 
+   public void reduce(Key key, Iterable<IntWritable> values,
+                      Context context) throws IOException, InterruptedException {
+     int sum = 0;
+     for (IntWritable val : values) {
+       sum += val.get();
+     }
+     result.set(sum);
+     context.write(key, result);
+   }
+ }
+
    + + @see Mapper + @see Partitioner]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + counterName. + @param counterName counter name + @return the Counter for the given counterName]]> + + + + + + + groupName and + counterName. + @param counterName counter name + @return the Counter for the given groupName and + counterName]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + An example TaskAttemptID is : + attempt_200707121733_0003_m_000005_0 , which represents the + zeroth task attempt for the fifth map task in the third job + running at the jobtracker started at 200707121733. +

    + Applications should never construct or parse TaskAttemptID strings + , but rather use appropriate constructors or {@link #forName(String)} + method. + + @see JobID + @see TaskID]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + An example TaskID is : + task_200707121733_0003_m_000005 , which represents the + fifth map task in the third job running at the jobtracker + started at 200707121733. +

    + Applications should never construct or parse TaskID strings + , but rather use appropriate constructors or {@link #forName(String)} + method. + + @see JobID + @see TaskAttemptID]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + OutputCommitter for the task-attempt]]> + + + + the input key type for the task + @param the input value type for the task + @param the output key type for the task + @param the output value type for the task]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + type of the other counter + @param type of the other counter group + @param counters the counters object to copy + @param groupFactory the factory for new groups]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + type of counter inside the counters + @param type of group inside the counters]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + type of the counter for the group]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + The key and values are passed from one element of the chain to the next, by + value. For the added Mapper the configuration given for it, + mapperConf, have precedence over the job's Configuration. This + precedence is in effect when the task is running. +

    +

    + IMPORTANT: There is no need to specify the output key/value classes for the + ChainMapper, this is done by the addMapper for the last mapper in the chain +

    + + @param job + The job. + @param klass + the Mapper class to add. + @param inputKeyClass + mapper input key class. + @param inputValueClass + mapper input value class. + @param outputKeyClass + mapper output key class. + @param outputValueClass + mapper output value class. + @param mapperConf + a configuration for the Mapper class. It is recommended to use a + Configuration without default values using the + Configuration(boolean loadDefaults) constructor with + FALSE.]]> +     + + + + + + + + + + + + The Mapper classes are invoked in a chained (or piped) fashion, the output of + the first becomes the input of the second, and so on until the last Mapper, + the output of the last Mapper will be written to the task's output. +

    +

    + The key functionality of this feature is that the Mappers in the chain do not + need to be aware that they are executed in a chain. This enables having + reusable specialized Mappers that can be combined to perform composite + operations within a single task. +

    +

    + Special care has to be taken when creating chains that the key/values output + by a Mapper are valid for the following Mapper in the chain. It is assumed + all Mappers and the Reduce in the chain use matching output and input key and + value classes as no conversion is done by the chaining code. +

    +

    + Using the ChainMapper and the ChainReducer classes is possible to compose + Map/Reduce jobs that look like [MAP+ / REDUCE MAP*]. And + immediate benefit of this pattern is a dramatic reduction in disk IO. +

    +

    + IMPORTANT: There is no need to specify the output key/value classes for the + ChainMapper, this is done by the addMapper for the last mapper in the chain. +

    + ChainMapper usage pattern: +

    + + 

    + ...
+ Job = new Job(conf);
+
+ Configuration mapAConf = new Configuration(false);
+ ...
+ ChainMapper.addMapper(job, AMap.class, LongWritable.class, Text.class,
+   Text.class, Text.class, true, mapAConf);
+
+ Configuration mapBConf = new Configuration(false);
+ ...
+ ChainMapper.addMapper(job, BMap.class, Text.class, Text.class,
+   LongWritable.class, Text.class, false, mapBConf);
+
+ ...
+
+ job.waitForComplettion(true);
+ ...
+
    ]]> +     +     + + + + + + + + + + + + + + + + The key and values are passed from one element of the chain to the next, by + value. For the added Reducer the configuration given for it, + reducerConf, have precedence over the job's Configuration. + This precedence is in effect when the task is running. +

    +

    + IMPORTANT: There is no need to specify the output key/value classes for the + ChainReducer, this is done by the setReducer or the addMapper for the last + element in the chain. +

    + + @param job + the job + @param klass + the Reducer class to add. + @param inputKeyClass + reducer input key class. + @param inputValueClass + reducer input value class. + @param outputKeyClass + reducer output key class. + @param outputValueClass + reducer output value class. + @param reducerConf + a configuration for the Reducer class. It is recommended to use a + Configuration without default values using the + Configuration(boolean loadDefaults) constructor with + FALSE.]]> +     +     + + + + + + + + + + + + The key and values are passed from one element of the chain to the next, by + value For the added Mapper the configuration given for it, + mapperConf, have precedence over the job's Configuration. This + precedence is in effect when the task is running. +

    +

    + IMPORTANT: There is no need to specify the output key/value classes for the + ChainMapper, this is done by the addMapper for the last mapper in the + chain. +

    + + @param job + The job. + @param klass + the Mapper class to add. + @param inputKeyClass + mapper input key class. + @param inputValueClass + mapper input value class. + @param outputKeyClass + mapper output key class. + @param outputValueClass + mapper output value class. + @param mapperConf + a configuration for the Mapper class. It is recommended to use a + Configuration without default values using the + Configuration(boolean loadDefaults) constructor with + FALSE.]]> +     +     + + + + + + + + + + + For each record output by the Reducer, the Mapper classes are invoked in a + chained (or piped) fashion. The output of the reducer becomes the input of + the first mapper and output of first becomes the input of the second, and so + on until the last Mapper, the output of the last Mapper will be written to + the task's output. +

    +

    + The key functionality of this feature is that the Mappers in the chain do not + need to be aware that they are executed after the Reducer or in a chain. This + enables having reusable specialized Mappers that can be combined to perform + composite operations within a single task. +

    +

    + Special care has to be taken when creating chains that the key/values output + by a Mapper are valid for the following Mapper in the chain. It is assumed + all Mappers and the Reduce in the chain use matching output and input key and + value classes as no conversion is done by the chaining code. +

    +

    Using the ChainMapper and the ChainReducer classes is possible to + compose Map/Reduce jobs that look like [MAP+ / REDUCE MAP*]. And + immediate benefit of this pattern is a dramatic reduction in disk IO.

    +

    + IMPORTANT: There is no need to specify the output key/value classes for the + ChainReducer, this is done by the setReducer or the addMapper for the last + element in the chain. +

    + ChainReducer usage pattern: +

    + + 

    + ...
+ Job = new Job(conf);
+ ....
+
+ Configuration reduceConf = new Configuration(false);
+ ...
+ ChainReducer.setReducer(job, XReduce.class, LongWritable.class, Text.class,
+   Text.class, Text.class, true, reduceConf);
+
+ ChainReducer.addMapper(job, CMap.class, Text.class, Text.class,
+   LongWritable.class, Text.class, false, null);
+
+ ChainReducer.addMapper(job, DMap.class, LongWritable.class, Text.class,
+   LongWritable.class, LongWritable.class, true, null);
+
+ ...
+
+ job.waitForCompletion(true);
+ ...
+
    ]]> +     +     + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + DBInputFormat emits LongWritables containing the record number as + key and DBWritables as value. + + The SQL query, and input class can be using one of the two + setInput methods.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + {@link DBOutputFormat} accepts <key,value> pairs, where + key has a type extending DBWritable. Returned {@link RecordWriter} + writes only the key to the database with a batch SQL query.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + DBWritable. DBWritable, is similar to {@link Writable} + except that the {@link #write(PreparedStatement)} method takes a + {@link PreparedStatement}, and {@link #readFields(ResultSet)} + takes a {@link ResultSet}. +

    + Implementations are responsible for writing the fields of the object + to PreparedStatement, and reading the fields of the object from the + ResultSet. + +

    Example:

    + If we have the following table in the database : + 
    + CREATE TABLE MyTable (
+   counter        INTEGER NOT NULL,
+   timestamp      BIGINT  NOT NULL,
+ );
+
    + then we can read/write the tuples from/to the table with : + 

    + public class MyWritable implements Writable, DBWritable {
+   // Some data     
+   private int counter;
+   private long timestamp;
+       
+   //Writable#write() implementation
+   public void write(DataOutput out) throws IOException {
+     out.writeInt(counter);
+     out.writeLong(timestamp);
+   }
+       
+   //Writable#readFields() implementation
+   public void readFields(DataInput in) throws IOException {
+     counter = in.readInt();
+     timestamp = in.readLong();
+   }
+       
+   public void write(PreparedStatement statement) throws SQLException {
+     statement.setInt(1, counter);
+     statement.setLong(2, timestamp);
+   }
+       
+   public void readFields(ResultSet resultSet) throws SQLException {
+     counter = resultSet.getInt(1);
+     timestamp = resultSet.getLong(2);
+   } 
+ }
+
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + RecordReader's for + CombineFileSplit's. + + @see CombineFileSplit]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + CombineFileRecordReader. + + Subclassing is needed to get a concrete record reader wrapper because of the + constructor requirement. + + @see CombineFileRecordReader + @see CombineFileInputFormat]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + th Path]]> + + + + + + th Path]]> + + + + + + + + + + + th Path]]> + + + + + + + + + + + + + + + + + + + + + + + + + + CombineFileSplit can be used to implement {@link RecordReader}'s, + with reading one record per file. + + @see FileSplit + @see CombineFileInputFormat]]> + + + + + + + + + + + + + + CombineFileInputFormat-equivalent for + SequenceFileInputFormat. + + @see CombineFileInputFormat]]> + + + + + + + + + + + + + + CombineFileInputFormat-equivalent for + TextInputFormat. + + @see CombineFileInputFormat]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + FileInputFormat always returns + true. Implementations that may deal with non-splittable files must + override this method. + + FileInputFormat implementations can override this and return + false to ensure that individual input files are never split-up + so that {@link Mapper}s process entire files. + + @param context the job context + @param filename the file name to check + @return is this file splitable?]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + FileInputFormat is the base class for all file-based + InputFormats. This provides a generic implementation of + {@link #getSplits(JobContext)}. + + Implementations of FileInputFormat can also override the + {@link #isSplitable(JobContext, Path)} method to prevent input files + from being split-up in certain situations. Implementations that may + deal with non-splittable files must override this method, since + the default implementation assumes splitting is always possible.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
    or + conf.setInt(FixedLengthInputFormat.FIXED_RECORD_LENGTH, recordLength); +

    + @see FixedLengthRecordReader]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if the Job was added.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ([,]*) + func ::= tbl(,"") + class ::= @see java.lang.Class#forName(java.lang.String) + path ::= @see org.apache.hadoop.fs.Path#Path(java.lang.String) + } + Reads expression from the mapreduce.join.expr property and + user-supplied join types from mapreduce.join.define.<ident> + types. Paths supplied to tbl are given as input paths to the + InputFormat class listed. + @see #compose(java.lang.String, java.lang.Class, java.lang.String...)]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ,

    ) }]]> + + + + + + + + (tbl(,),tbl(,),...,tbl(,)) }]]> + + + + + + + + (tbl(,),tbl(,),...,tbl(,)) }]]> + + + + + + + + mapreduce.join.define.<ident> to a classname. + In the expression mapreduce.join.expr, the identifier will be + assumed to be a ComposableRecordReader. + mapreduce.join.keycomparator can be a classname used to compare + keys in the join. + @see #setFormat + @see JoinRecordReader + @see MultiFilterRecordReader]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ...... + }]]> + + + + + + + + + + + + + + + + + + + + + capacity children to position + id in the parent reader. + The id of a root CompositeRecordReader is -1 by convention, but relying + on this is not recommended.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + override(S1,S2,S3) will prefer values + from S3 over S2, and values from S2 over S1 for all keys + emitted from all sources.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + [<child1>,<child2>,...,<childn>]]]> + + + + + + + out. + TupleWritable format: + {@code + ...... + }]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + the map's input key type + @param the map's input value type + @param the map's output key type + @param the map's output value type + @param job the job + @return the mapper class to run]]> + + + + + + + the map input key type + @param the map input value type + @param the map output key type + @param the map output value type + @param job the job to modify + @param cls the class to use as the mapper]]> + + + + + + + + + + + + + + + + + It can be used instead of the default implementation, + {@link org.apache.hadoop.mapred.MapRunner}, when the Map operation is not CPU + bound in order to improve throughput. +

    + Mapper implementations using this MapRunnable must be thread-safe. +

    + The Map-Reduce job has to be configured with the mapper to use via + {@link #setMapperClass(Job, Class)} and + the number of thread the thread-pool can use with the + {@link #getNumberOfThreads(JobContext)} method. The default + value is 10 threads. +

    ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + MapContext to be wrapped + @return a wrapped Mapper.Context for custom implementations]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if the job output should be compressed, + false otherwise]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Tasks' Side-Effect Files + +

    Some applications need to create/write-to side-files, which differ from + the actual job-outputs. + +

    In such cases there could be issues with 2 instances of the same TIP + (running simultaneously e.g. speculative tasks) trying to open/write-to the + same file (path) on HDFS. Hence the application-writer will have to pick + unique names per task-attempt (e.g. using the attemptid, say + attempt_200709221812_0001_m_000000_0), not just per TIP.

    + +

    To get around this the Map-Reduce framework helps the application-writer + out by maintaining a special + ${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid} + sub-directory for each task-attempt on HDFS where the output of the + task-attempt goes. On successful completion of the task-attempt the files + in the ${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid} (only) + are promoted to ${mapreduce.output.fileoutputformat.outputdir}. Of course, the + framework discards the sub-directory of unsuccessful task-attempts. This + is completely transparent to the application.

    + +

    The application-writer can take advantage of this by creating any + side-files required in a work directory during execution + of his task i.e. via + {@link #getWorkOutputPath(TaskInputOutputContext)}, and + the framework will move them out similarly - thus she doesn't have to pick + unique paths per task-attempt.

    + +

    The entire discussion holds true for maps of jobs with + reducer=NONE (i.e. 0 reduces) since output of the map, in that case, + goes directly to HDFS.

    + + @return the {@link Path} to the task's temporary output directory + for the map-reduce job.]]> +     +     + + + + + + + + The path can be used to create custom files from within the map and + reduce tasks. The path name will be unique for each task. The path parent + will be the job output directory.

    ls + +

    This method uses the {@link #getUniqueFile} method to make the file name + unique for the task.

    + + @param context the context for the task. + @param name the name for the file. + @param extension the extension for the file + @return a unique path accross all tasks of the job.]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Warning: when the baseOutputPath is a path that resolves + outside of the final job output directory, the directory is created + immediately and then persists through subsequent task retries, breaking + the concept of output committing.]]> + + + + + + + + + + Warning: when the baseOutputPath is a path that resolves + outside of the final job output directory, the directory is created + immediately and then persists through subsequent task retries, breaking + the concept of output committing.]]> + + + + + + + super.close() at the + end of their close()]]> + + + + + Case one: writing to additional outputs other than the job default output. + + Each additional output, or named output, may be configured with its own + OutputFormat, with its own key class and with its own value + class. +

    + +

    + Case two: to write data to different files provided by user +

    + +

    + MultipleOutputs supports counters, by default they are disabled. The + counters group is the {@link MultipleOutputs} class name. The names of the + counters are the same as the output name. These count the number records + written to each output name. +

    + + Usage pattern for job submission: + 
    +
+ Job job = new Job();
+
+ FileInputFormat.setInputPath(job, inDir);
+ FileOutputFormat.setOutputPath(job, outDir);
+
+ job.setMapperClass(MOMap.class);
+ job.setReducerClass(MOReduce.class);
+ ...
+
+ // Defines additional single text based output 'text' for the job
+ MultipleOutputs.addNamedOutput(job, "text", TextOutputFormat.class,
+ LongWritable.class, Text.class);
+
+ // Defines additional sequence-file based output 'sequence' for the job
+ MultipleOutputs.addNamedOutput(job, "seq",
+   SequenceFileOutputFormat.class,
+   LongWritable.class, Text.class);
+ ...
+
+ job.waitForCompletion(true);
+ ...
+
    +

    + Usage in Reducer: + 

    + <K, V> String generateFileName(K k, V v) {
+   return k.toString() + "_" + v.toString();
+ }
+ 
+ public class MOReduce extends
+   Reducer<WritableComparable, Writable,WritableComparable, Writable> {
+ private MultipleOutputs mos;
+ public void setup(Context context) {
+ ...
+ mos = new MultipleOutputs(context);
+ }
+
+ public void reduce(WritableComparable key, Iterator<Writable> values,
+ Context context)
+ throws IOException {
+ ...
+ mos.write("text", , key, new Text("Hello"));
+ mos.write("seq", LongWritable(1), new Text("Bye"), "seq_a");
+ mos.write("seq", LongWritable(2), key, new Text("Chau"), "seq_b");
+ mos.write(key, new Text("value"), generateFileName(key, new Text("value")));
+ ...
+ }
+
+ public void cleanup(Context) throws IOException {
+ mos.close();
+ ...
+ }
+
+ }
+
    + +

    + When used in conjuction with org.apache.hadoop.mapreduce.lib.output.LazyOutputFormat, + MultipleOutputs can mimic the behaviour of MultipleTextOutputFormat and MultipleSequenceFileOutputFormat + from the old Hadoop API - ie, output can be written from the Reducer to more than one location. +

    + +

    + Use MultipleOutputs.write(KEYOUT key, VALUEOUT value, String baseOutputPath) to write key and + value to a path specified by baseOutputPath, with no need to specify a named output. + Warning: when the baseOutputPath passed to MultipleOutputs.write + is a path that resolves outside of the final job output directory, the + directory is created immediately and then persists through subsequent + task retries, breaking the concept of output committing: +

    + + 
    + private MultipleOutputs<Text, Text> out;
+ 
+ public void setup(Context context) {
+   out = new MultipleOutputs<Text, Text>(context);
+   ...
+ }
+ 
+ public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
+ for (Text t : values) {
+   out.write(key, t, generateFileName(<parameter list...>));
+   }
+ }
+ 
+ protected void cleanup(Context context) throws IOException, InterruptedException {
+   out.close();
+ }
+
    + +

    + Use your own code in generateFileName() to create a custom path to your results. + '/' characters in baseOutputPath will be translated into directory levels in your file system. + Also, append your custom-generated path with "part" or similar, otherwise your output will be -00000, -00001 etc. + No call to context.write() is necessary. See example generateFileName() code below. +

    + + 
    + private String generateFileName(Text k) {
+   // expect Text k in format "Surname|Forename"
+   String[] kStr = k.toString().split("\\|");
+   
+   String sName = kStr[0];
+   String fName = kStr[1];
+
+   // example for k = Smith|John
+   // output written to /user/hadoop/path/to/output/Smith/John-r-00000 (etc)
+   return sName + "/" + fName;
+ }
+
    + +

    + Using MultipleOutputs in this way will still create zero-sized default output, eg part-00000. + To prevent this use LazyOutputFormat.setOutputFormatClass(job, TextOutputFormat.class); + instead of job.setOutputFormatClass(TextOutputFormat.class); in your Hadoop job configuration. +

    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This allows the user to specify the key class to be different + from the actual class ({@link BytesWritable}) used for writing

    + + @param job the {@link Job} to modify + @param theClass the SequenceFile output key class.]]> +     +     + + + + + This allows the user to specify the value class to be different + from the actual class ({@link BytesWritable}) used for writing

    + + @param job the {@link Job} to modify + @param theClass the SequenceFile output key class.]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + + bytes[left:(right+1)] in Python syntax. + + @param conf configuration object + @param left left Python-style offset + @param right right Python-style offset]]> + + + + + + + bytes[offset:] in Python syntax. + + @param conf configuration object + @param offset left Python-style offset]]> + + + + + + + bytes[:(offset+1)] in Python syntax. + + @param conf configuration object + @param offset right Python-style offset]]> + + + + + + + + + + + + + + + + + + + + + Partition {@link BinaryComparable} keys using a configurable part of + the bytes array returned by {@link BinaryComparable#getBytes()}.

    + +

    The subarray to be used for the partitioning can be defined by means + of the following properties: +

      +
    • + mapreduce.partition.binarypartitioner.left.offset: + left offset in array (0 by default) +
      • +
    • + mapreduce.partition.binarypartitioner.right.offset: + right offset in array (-1 by default) +
      • +
    + Like in Python, both negative and positive offsets are allowed, but + the meaning is slightly different. In case of an array of length 5, + for instance, the possible offsets are: + 
    
+  +---+---+---+---+---+
+  | B | B | B | B | B |
+  +---+---+---+---+---+
+    0   1   2   3   4
+   -5  -4  -3  -2  -1
+
    + The first row of numbers gives the position of the offsets 0...5 in + the array; the second row gives the corresponding negative offsets. + Contrary to Python, the specified subarray has byte i + and j as first and last element, repectively, when + i and j are the left and right offset. + +

    For Hadoop programs written in Java, it is advisable to use one of + the following static convenience methods for setting the offsets: +

      +
    • {@link #setOffsets}
      • +
    • {@link #setLeftOffset}
      • +
    • {@link #setRightOffset}
      • +
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + total.order.partitioner.natural.order is not false, a trie + of the first total.order.partitioner.max.trie.depth(2) + 1 bytes + will be built. Otherwise, keys will be located using a binary search of + the partition keyset using the {@link org.apache.hadoop.io.RawComparator} + defined for this job. The input file must be sorted with the same + comparator and contain {@link Job#getNumReduceTasks()} - 1 keys.]]> + + + + + + + + + + + + + + R reduces, there are R-1 + keys in the SequenceFile.]]> + + + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ReduceContext to be wrapped + @return a wrapped Reducer.Context for custom implementations]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +     diff --git a/hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_JobClient_2.8.3.xml b/hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_JobClient_2.8.3.xml new file mode 100644 index 00000000000..a63b3aca1ec --- /dev/null +++ b/hadoop-mapreduce-project/dev-support/jdiff/Apache_Hadoop_MapReduce_JobClient_2.8.3.xml @@ -0,0 +1,16 @@ + + + + + + + + + + + + diff --git a/hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Client_2.8.3.xml b/hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Client_2.8.3.xml new file mode 100644 index 00000000000..3f6c5eb5e39 --- /dev/null +++ b/hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Client_2.8.3.xml @@ -0,0 +1,2316 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + In secure mode, YARN verifies access to the application, queue + etc. before accepting the request. +

    + If the user does not have VIEW_APP access then the following + fields in the report will be set to stubbed values: +

      +
    • host - set to "N/A"
      • +
    • RPC port - set to -1
      • +
    • client token - set to "N/A"
      • +
    • diagnostics - set to "N/A"
      • +
    • tracking URL - set to "N/A"
      • +
    • original tracking URL - set to "N/A"
      • +
    • resource usage report - all values are -1
      • +
    + + @param appId + {@link ApplicationId} of the application that needs a report + @return application report + @throws YarnException + @throws IOException]]> +     +     + + + + + + Get a report (ApplicationReport) of all Applications in the cluster. +

    + +

    + If the user does not have VIEW_APP access for an application + then the corresponding report will be filtered as described in + {@link #getApplicationReport(ApplicationId)}. +

    + + @return a list of reports for all applications + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Get a report of the given ApplicationAttempt. +

    + +

    + In secure mode, YARN verifies access to the application, queue + etc. before accepting the request. +

    + + @param applicationAttemptId + {@link ApplicationAttemptId} of the application attempt that needs + a report + @return application attempt report + @throws YarnException + @throws ApplicationAttemptNotFoundException if application attempt + not found + @throws IOException]]> +     +     + + + + + + + Get a report of all (ApplicationAttempts) of Application in the cluster. +

    + + @param applicationId + @return a list of reports for all application attempts for specified + application + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Get a report of the given Container. +

    + +

    + In secure mode, YARN verifies access to the application, queue + etc. before accepting the request. +

    + + @param containerId + {@link ContainerId} of the container that needs a report + @return container report + @throws YarnException + @throws ContainerNotFoundException if container not found + @throws IOException]]> +     +     + + + + + + + Get a report of all (Containers) of ApplicationAttempt in the cluster. +

    + + @param applicationAttemptId + @return a list of reports of all containers for specified application + attempt + @throws YarnException + @throws IOException]]> +     +     +     + + + + + + + + + {@code + AMRMClient.createAMRMClientContainerRequest() + } + @return the newly create AMRMClient instance.]]> + + + + + + + + + + RegisterApplicationMasterResponse + @throws YarnException + @throws IOException]]> + + + + + + + + addContainerRequest are sent to the + ResourceManager. New containers assigned to the master are + retrieved. Status of completed containers and node health updates are also + retrieved. This also doubles up as a heartbeat to the ResourceManager and + must be made periodically. The call may not always return any new + allocations of containers. App should not make concurrent allocate + requests. May cause request loss. + +

    + Note : If the user has not removed container requests that have already + been satisfied, then the re-register may end up sending the entire + container requests to the RM (including matched requests). Which would mean + the RM could end up giving it a lot of new allocated containers. +

    + + @param progressIndicator Indicates progress made by the master + @return the response of the allocate request + @throws YarnException + @throws IOException]]> +     +     + + + + + + + + + + + + + + allocate + @param req Resource request]]> + + + + + + + + + + + + + allocate. + Any previous pending resource change request of the same container will be + removed. + + Application that calls this method is expected to maintain the + Containers that are returned from previous successful + allocations or resource changes. By passing in the existing container and a + target resource capability to this method, the application requests the + ResourceManager to change the existing resource allocation to the target + resource allocation. + + @param container The container returned from the last successful resource + allocation or resource change + @param capability The target resource capability of the container]]> + + + + + + + + + + + + + + + + + + + + + + + + ContainerRequests matching the given + parameters. These ContainerRequests should have been added via + addContainerRequest earlier in the lifecycle. For performance, + the AMRMClient may return its internal collection directly without creating + a copy. Users should not perform mutable operations on the return value. + Each collection in the list contains requests with identical + Resource size that fit in the given capability. In a + collection, requests will be returned in the same order as they were added. + @return Collection of request matching the parameters]]> + + + + + + + + + + + + + AMRMClient. This cache must + be shared with the {@link NMClient} used to manage containers for the + AMRMClient +

    + If a NM token cache is not set, the {@link NMTokenCache#getSingleton()} + singleton instance will be used. + + @param nmTokenCache the NM token cache to use.]]> + + + + + AMRMClient. This cache must be + shared with the {@link NMClient} used to manage containers for the + AMRMClient. +

    + If a NM token cache is not set, the {@link NMTokenCache#getSingleton()} + singleton instance will be used. + + @return the NM token cache.]]> + + + + + + + check to return true for each 1000 ms. + See also {@link #waitFor(com.google.common.base.Supplier, int)} + and {@link #waitFor(com.google.common.base.Supplier, int, int)} + @param check]]> + + + + + + + + check to return true for each + checkEveryMillis ms. + See also {@link #waitFor(com.google.common.base.Supplier, int, int)} + @param check user defined checker + @param checkEveryMillis interval to call check]]> + + + + + + + + + check to return true for each + checkEveryMillis ms. In the main loop, this method will log + the message "waiting in main loop" for each logInterval times + iteration to confirm the thread is alive. + @param check user defined checker + @param checkEveryMillis interval to call check + @param logInterval interval to log for each]]> + + + + + + + + + + + + + + + + + + + + + + + + + + Start an allocated container.

    + +

    The ApplicationMaster or other applications that use the + client must provide the details of the allocated container, including the + Id, the assigned node's Id and the token via {@link Container}. In + addition, the AM needs to provide the {@link ContainerLaunchContext} as + well.

    + + @param container the allocated container + @param containerLaunchContext the context information needed by the + NodeManager to launch the + container + @return a map between the auxiliary service names and their outputs + @throws YarnException + @throws IOException]]> +     +     + + + + + + Increase the resource of a container.

    + +

    The ApplicationMaster or other applications that use the + client must provide the details of the container, including the Id and + the target resource encapsulated in the updated container token via + {@link Container}. +

    + + @param container the container with updated token + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Stop an started container.

    + + @param containerId the Id of the started container + @param nodeId the Id of the NodeManager + + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Query the status of a container.

    + + @param containerId the Id of the started container + @param nodeId the Id of the NodeManager + + @return the status of a container + @throws YarnException + @throws IOException]]> +     +     + + + + Set whether the containers that are started by this client, and are + still running should be stopped when the client stops. By default, the + feature should be enabled.

    However, containers will be stopped only + when service is stopped. i.e. after {@link NMClient#stop()}. + + @param enabled whether the feature is enabled or not]]> +     +     + + + + NMClient. This cache must be + shared with the {@link AMRMClient} that requested the containers managed + by this NMClient +

    + If a NM token cache is not set, the {@link NMTokenCache#getSingleton()} + singleton instance will be used. + + @param nmTokenCache the NM token cache to use.]]> + + + + + NMClient. This cache must be + shared with the {@link AMRMClient} that requested the containers managed + by this NMClient +

    + If a NM token cache is not set, the {@link NMTokenCache#getSingleton()} + singleton instance will be used. + + @return the NM token cache]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + By default Yarn client libraries {@link AMRMClient} and {@link NMClient} use + {@link #getSingleton()} instance of the cache. +

      +
    • + Using the singleton instance of the cache is appropriate when running a + single ApplicationMaster in the same JVM. +
      • +
    • + When using the singleton, users don't need to do anything special, + {@link AMRMClient} and {@link NMClient} are already set up to use the + default singleton {@link NMTokenCache} +
      • +
    + If running multiple Application Masters in the same JVM, a different cache + instance should be used for each Application Master. +
      +
    • + If using the {@link AMRMClient} and the {@link NMClient}, setting up + and using an instance cache is as follows: + 
      +   NMTokenCache nmTokenCache = new NMTokenCache();
+   AMRMClient rmClient = AMRMClient.createAMRMClient();
+   NMClient nmClient = NMClient.createNMClient();
+   nmClient.setNMTokenCache(nmTokenCache);
+   ...
+
      +
      • +
    • + If using the {@link AMRMClientAsync} and the {@link NMClientAsync}, + setting up and using an instance cache is as follows: + 
      +   NMTokenCache nmTokenCache = new NMTokenCache();
+   AMRMClient rmClient = AMRMClient.createAMRMClient();
+   NMClient nmClient = NMClient.createNMClient();
+   nmClient.setNMTokenCache(nmTokenCache);
+   AMRMClientAsync rmClientAsync = new AMRMClientAsync(rmClient, 1000, [AMRM_CALLBACK]);
+   NMClientAsync nmClientAsync = new NMClientAsync("nmClient", nmClient, [NM_CALLBACK]);
+   ...
+
      +
      • +
    • + If using {@link ApplicationMasterProtocol} and + {@link ContainerManagementProtocol} directly, setting up and using an + instance cache is as follows: + 
      +   NMTokenCache nmTokenCache = new NMTokenCache();
+   ...
+   ApplicationMasterProtocol amPro = ClientRMProxy.createRMProxy(conf, ApplicationMasterProtocol.class);
+   ...
+   AllocateRequest allocateRequest = ...
+   ...
+   AllocateResponse allocateResponse = rmClient.allocate(allocateRequest);
+   for (NMToken token : allocateResponse.getNMTokens()) {
+     nmTokenCache.setToken(token.getNodeId().toString(), token.getToken());
+   }
+   ...
+   ContainerManagementProtocolProxy nmPro = ContainerManagementProtocolProxy(conf, nmTokenCache);
+   ...
+   nmPro.startContainer(container, containerContext);
+   ...
+
      +
      • +
    + It is also possible to mix the usage of a client ({@code AMRMClient} or + {@code NMClient}, or the async versions of them) with a protocol proxy + ({@code ContainerManagementProtocolProxy} or + {@code ApplicationMasterProtocol}).]]> +     +     + + + + + + + + + + + + + + The method to claim a resource with the SharedCacheManager. + The client uses a checksum to identify the resource and an + {@link ApplicationId} to identify which application will be using the + resource. +

    + +

    + The SharedCacheManager responds with whether or not the + resource exists in the cache. If the resource exists, a Path + to the resource in the shared cache is returned. If the resource does not + exist, null is returned instead. +

    + + @param applicationId ApplicationId of the application using the resource + @param resourceKey the key (i.e. checksum) that identifies the resource + @return Path to the resource, or null if it does not exist]]> +     +     + + + + + + + The method to release a resource with the SharedCacheManager. + This method is called once an application is no longer using a claimed + resource in the shared cache. The client uses a checksum to identify the + resource and an {@link ApplicationId} to identify which application is + releasing the resource. +

    + +

    + Note: This method is an optimization and the client is not required to call + it for correctness. +

    + + @param applicationId ApplicationId of the application releasing the + resource + @param resourceKey the key (i.e. checksum) that identifies the resource]]> +     +     + + + + + + + + + + +     + + + + + + + + + + + + + + + + Obtain a {@link YarnClientApplication} for a new application, + which in turn contains the {@link ApplicationSubmissionContext} and + {@link org.apache.hadoop.yarn.api.protocolrecords.GetNewApplicationResponse} + objects. +

    + + @return {@link YarnClientApplication} built for a new application + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Submit a new application to YARN. It is a blocking call - it + will not return {@link ApplicationId} until the submitted application is + submitted successfully and accepted by the ResourceManager. +

    + +

    + Users should provide an {@link ApplicationId} as part of the parameter + {@link ApplicationSubmissionContext} when submitting a new application, + otherwise it will throw the {@link ApplicationIdNotProvidedException}. +

    + +

    This internally calls {@link ApplicationClientProtocol#submitApplication + (SubmitApplicationRequest)}, and after that, it internally invokes + {@link ApplicationClientProtocol#getApplicationReport + (GetApplicationReportRequest)} and waits till it can make sure that the + application gets properly submitted. If RM fails over or RM restart + happens before ResourceManager saves the application's state, + {@link ApplicationClientProtocol + #getApplicationReport(GetApplicationReportRequest)} will throw + the {@link ApplicationNotFoundException}. This API automatically resubmits + the application with the same {@link ApplicationSubmissionContext} when it + catches the {@link ApplicationNotFoundException}

    + + @param appContext + {@link ApplicationSubmissionContext} containing all the details + needed to submit a new application + @return {@link ApplicationId} of the accepted application + @throws YarnException + @throws IOException + @see #createApplication()]]> +     +     + + + + + + + Fail an application attempt identified by given ID. +

    + + @param applicationAttemptId + {@link ApplicationAttemptId} of the attempt to fail. + @throws YarnException + in case of errors or if YARN rejects the request due to + access-control restrictions. + @throws IOException + @see #getQueueAclsInfo()]]> +     +     + + + + + + + Kill an application identified by given ID. +

    + + @param applicationId + {@link ApplicationId} of the application that needs to be killed + @throws YarnException + in case of errors or if YARN rejects the request due to + access-control restrictions. + @throws IOException + @see #getQueueAclsInfo()]]> +     +     + + + + + + + + Kill an application identified by given ID. +

    + @param applicationId {@link ApplicationId} of the application that needs to + be killed + @param diagnostics for killing an application. + @throws YarnException in case of errors or if YARN rejects the request due + to access-control restrictions. + @throws IOException]]> +     +     + + + + + + + Get a report of the given Application. +

    + +

    + In secure mode, YARN verifies access to the application, queue + etc. before accepting the request. +

    + +

    + If the user does not have VIEW_APP access then the following + fields in the report will be set to stubbed values: +

      +
    • host - set to "N/A"
      • +
    • RPC port - set to -1
      • +
    • client token - set to "N/A"
      • +
    • diagnostics - set to "N/A"
      • +
    • tracking URL - set to "N/A"
      • +
    • original tracking URL - set to "N/A"
      • +
    • resource usage report - all values are -1
      • +
    + + @param appId + {@link ApplicationId} of the application that needs a report + @return application report + @throws YarnException + @throws IOException]]> +     +     + + + + + + + The AMRM token is required for AM to RM scheduling operations. For + managed Application Masters Yarn takes care of injecting it. For unmanaged + Applications Masters, the token must be obtained via this method and set + in the {@link org.apache.hadoop.security.UserGroupInformation} of the + current user. +

    + The AMRM token will be returned only if all the following conditions are + met: +

      +
    • the requester is the owner of the ApplicationMaster
      • +
    • the application master is an unmanaged ApplicationMaster
      • +
    • the application master is in ACCEPTED state
      • +
    + Else this method returns NULL. + + @param appId {@link ApplicationId} of the application to get the AMRM token + @return the AMRM token if available + @throws YarnException + @throws IOException]]> +     +     + + + + + + Get a report (ApplicationReport) of all Applications in the cluster. +

    + +

    + If the user does not have VIEW_APP access for an application + then the corresponding report will be filtered as described in + {@link #getApplicationReport(ApplicationId)}. +

    + + @return a list of reports of all running applications + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Get a report (ApplicationReport) of Applications + matching the given application types in the cluster. +

    + +

    + If the user does not have VIEW_APP access for an application + then the corresponding report will be filtered as described in + {@link #getApplicationReport(ApplicationId)}. +

    + + @param applicationTypes set of application types you are interested in + @return a list of reports of applications + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Get a report (ApplicationReport) of Applications matching the given + application states in the cluster. +

    + +

    + If the user does not have VIEW_APP access for an application + then the corresponding report will be filtered as described in + {@link #getApplicationReport(ApplicationId)}. +

    + + @param applicationStates set of application states you are interested in + @return a list of reports of applications + @throws YarnException + @throws IOException]]> +     +     + + + + + + + + Get a report (ApplicationReport) of Applications matching the given + application types and application states in the cluster. +

    + +

    + If the user does not have VIEW_APP access for an application + then the corresponding report will be filtered as described in + {@link #getApplicationReport(ApplicationId)}. +

    + + @param applicationTypes set of application types you are interested in + @param applicationStates set of application states you are interested in + @return a list of reports of applications + @throws YarnException + @throws IOException]]> +     +     + + + + + + + + + + Get a report (ApplicationReport) of Applications matching the given users, + queues, application types and application states in the cluster. If any of + the params is set to null, it is not used when filtering. +

    + +

    + If the user does not have VIEW_APP access for an application + then the corresponding report will be filtered as described in + {@link #getApplicationReport(ApplicationId)}. +

    + + @param queues set of queues you are interested in + @param users set of users you are interested in + @param applicationTypes set of application types you are interested in + @param applicationStates set of application states you are interested in + @return a list of reports of applications + @throws YarnException + @throws IOException]]> +     +     + + + + + + Get metrics ({@link YarnClusterMetrics}) about the cluster. +

    + + @return cluster metrics + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Get a report of nodes ({@link NodeReport}) in the cluster. +

    + + @param states The {@link NodeState}s to filter on. If no filter states are + given, nodes in all states will be returned. + @return A list of node reports + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Get a delegation token so as to be able to talk to YARN using those tokens. + + @param renewer + Address of the renewer who can renew these tokens when needed by + securely talking to YARN. + @return a delegation token ({@link Token}) that can be used to + talk to YARN + @throws YarnException + @throws IOException]]> + + + + + + + + + Get information ({@link QueueInfo}) about a given queue. +

    + + @param queueName + Name of the queue whose information is needed + @return queue information + @throws YarnException + in case of errors or if YARN rejects the request due to + access-control restrictions. + @throws IOException]]> +     +     + + + + + + Get information ({@link QueueInfo}) about all queues, recursively if there + is a hierarchy +

    + + @return a list of queue-information for all queues + @throws YarnException + @throws IOException]]> +     +     + + + + + + Get information ({@link QueueInfo}) about top level queues. +

    + + @return a list of queue-information for all the top-level queues + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Get information ({@link QueueInfo}) about all the immediate children queues + of the given queue +

    + + @param parent + Name of the queue whose child-queues' information is needed + @return a list of queue-information for all queues who are direct children + of the given parent queue. + @throws YarnException + @throws IOException]]> +     +     + + + + + + Get information about acls for current user on all the + existing queues. +

    + + @return a list of queue acls ({@link QueueUserACLInfo}) for + current user + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Get a report of the given ApplicationAttempt. +

    + +

    + In secure mode, YARN verifies access to the application, queue + etc. before accepting the request. +

    + + @param applicationAttemptId + {@link ApplicationAttemptId} of the application attempt that needs + a report + @return application attempt report + @throws YarnException + @throws ApplicationAttemptNotFoundException if application attempt + not found + @throws IOException]]> +     +     + + + + + + + Get a report of all (ApplicationAttempts) of Application in the cluster. +

    + + @param applicationId application id of the app + @return a list of reports for all application attempts for specified + application. + @throws YarnException + @throws IOException]]> +     +     + + + + + + + Get a report of the given Container. +

    + +

    + In secure mode, YARN verifies access to the application, queue + etc. before accepting the request. +

    + + @param containerId + {@link ContainerId} of the container that needs a report + @return container report + @throws YarnException + @throws ContainerNotFoundException if container not found. + @throws IOException]]> +     +     + + + + + + + Get a report of all (Containers) of ApplicationAttempt in the cluster. +

    + + @param applicationAttemptId application attempt id + @return a list of reports of all containers for specified application + attempts + @throws YarnException + @throws IOException]]> +     +     + + + + + + + + Attempts to move the given application to the given queue. +

    + + @param appId + Application to move. + @param queue + Queue to place it in to. + @throws YarnException + @throws IOException]]> +     +     + + + + + + Obtain a {@link GetNewReservationResponse} for a new reservation, + which contains the {@link ReservationId} object. +

    + + @return The {@link GetNewReservationResponse} containing a new + {@link ReservationId} object. + @throws YarnException if reservation cannot be created. + @throws IOException if reservation cannot be created.]]> +     +     + + + + + + + The interface used by clients to submit a new reservation to the + {@code ResourceManager}. +

    + +

    + The client packages all details of its request in a + {@link ReservationSubmissionRequest} object. This contains information + about the amount of capacity, temporal constraints, and gang needs. + Furthermore, the reservation might be composed of multiple stages, with + ordering dependencies among them. +

    + +

    + In order to respond, a new admission control component in the + {@code ResourceManager} performs an analysis of the resources that have + been committed over the period of time the user is requesting, verify that + the user requests can be fulfilled, and that it respect a sharing policy + (e.g., {@code CapacityOverTimePolicy}). Once it has positively determined + that the ReservationRequest is satisfiable the {@code ResourceManager} + answers with a {@link ReservationSubmissionResponse} that includes a + {@link ReservationId}. Upon failure to find a valid allocation the response + is an exception with the message detailing the reason of failure. +

    + +

    + The semantics guarantees that the {@link ReservationId} returned, + corresponds to a valid reservation existing in the time-range request by + the user. The amount of capacity dedicated to such reservation can vary + overtime, depending of the allocation that has been determined. But it is + guaranteed to satisfy all the constraint expressed by the user in the + {@link ReservationDefinition} +

    + + @param request request to submit a new Reservation + @return response contains the {@link ReservationId} on accepting the + submission + @throws YarnException if the reservation cannot be created successfully + @throws IOException]]> +     +     + + + + + + + The interface used by clients to update an existing Reservation. This is + referred to as a re-negotiation process, in which a user that has + previously submitted a Reservation. +

    + +

    + The allocation is attempted by virtually substituting all previous + allocations related to this Reservation with new ones, that satisfy the new + {@link ReservationDefinition}. Upon success the previous allocation is + atomically substituted by the new one, and on failure (i.e., if the system + cannot find a valid allocation for the updated request), the previous + allocation remains valid. +

    + + @param request to update an existing Reservation (the + {@link ReservationUpdateRequest} should refer to an existing valid + {@link ReservationId}) + @return response empty on successfully updating the existing reservation + @throws YarnException if the request is invalid or reservation cannot be + updated successfully + @throws IOException]]> +     +     + + + + + + + The interface used by clients to remove an existing Reservation. +

    + + @param request to remove an existing Reservation (the + {@link ReservationDeleteRequest} should refer to an existing valid + {@link ReservationId}) + @return response empty on successfully deleting the existing reservation + @throws YarnException if the request is invalid or reservation cannot be + deleted successfully + @throws IOException]]> +     +     + + + + + + + The interface used by clients to get the list of reservations in a plan. + The reservationId will be used to search for reservations to list if it is + provided. Otherwise, it will select active reservations within the + startTime and endTime (inclusive). +

    + + @param request to list reservations in a plan. Contains fields to select + String queue, ReservationId reservationId, long startTime, + long endTime, and a bool includeReservationAllocations. + + queue: Required. Cannot be null or empty. Refers to the + reservable queue in the scheduler that was selected when + creating a reservation submission + {@link ReservationSubmissionRequest}. + + reservationId: Optional. If provided, other fields will + be ignored. + + startTime: Optional. If provided, only reservations that + end after the startTime will be selected. This defaults + to 0 if an invalid number is used. + + endTime: Optional. If provided, only reservations that + start on or before endTime will be selected. This defaults + to Long.MAX_VALUE if an invalid number is used. + + includeReservationAllocations: Optional. Flag that + determines whether the entire reservation allocations are + to be returned. Reservation allocations are subject to + change in the event of re-planning as described by + {@link ReservationDefinition}. + + @return response that contains information about reservations that are + being searched for. + @throws YarnException if the request is invalid + @throws IOException if the request failed otherwise]]> +     +     + + + + + + The interface used by client to get node to labels mappings in existing cluster +

    + + @return node to labels mappings + @throws YarnException + @throws IOException]]> +     +     + + + + + + The interface used by client to get labels to nodes mapping + in existing cluster +

    + + @return node to labels mappings + @throws YarnException + @throws IOException]]> +     +     + + + + + + + The interface used by client to get labels to nodes mapping + for specified labels in existing cluster +

    + + @param labels labels for which labels to nodes mapping has to be retrieved + @return labels to nodes mappings for specific labels + @throws YarnException + @throws IOException]]> +     +     + + + + + + The interface used by client to get node labels in the cluster +

    + + @return cluster node labels collection + @throws YarnException when there is a failure in + {@link ApplicationClientProtocol} + @throws IOException when there is a failure in + {@link ApplicationClientProtocol}]]> +     +     + + + + + + + + The interface used by client to set priority of an application +

    + @param applicationId + @param priority + @return updated priority of an application. + @throws YarnException + @throws IOException]]> +     +     + + + + + + + + Signal a container identified by given ID. +

    + + @param containerId + {@link ContainerId} of the container that needs to be signaled + @param command the signal container command + @throws YarnException + @throws IOException]]> +     +     +     + + + + + + + + + + + +     + + + + + + + + + + + + + + + + Create a new instance of AMRMClientAsync.

    + + @param intervalMs heartbeat interval in milliseconds between AM and RM + @param callbackHandler callback handler that processes responses from + the ResourceManager]]> +     +     + + + + + + Create a new instance of AMRMClientAsync.

    + + @param client the AMRMClient instance + @param intervalMs heartbeat interval in milliseconds between AM and RM + @param callbackHandler callback handler that processes responses from + the ResourceManager]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + allocate + @param req Resource request]]> + + + + + + + + + + + + + allocate. + Any previous pending resource change request of the same container will be + removed. + + Application that calls this method is expected to maintain the + Containers that are returned from previous successful + allocations or resource changes. By passing in the existing container and a + target resource capability to this method, the application requests the + ResourceManager to change the existing resource allocation to the target + resource allocation. + + @param container The container returned from the last successful resource + allocation or resource change + @param capability The target resource capability of the container]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + check to return true for each 1000 ms. + See also {@link #waitFor(com.google.common.base.Supplier, int)} + and {@link #waitFor(com.google.common.base.Supplier, int, int)} + @param check]]> + + + + + + + + check to return true for each + checkEveryMillis ms. + See also {@link #waitFor(com.google.common.base.Supplier, int, int)} + @param check user defined checker + @param checkEveryMillis interval to call check]]> + + + + + + + + + check to return true for each + checkEveryMillis ms. In the main loop, this method will log + the message "waiting in main loop" for each logInterval times + iteration to confirm the thread is alive. + @param check user defined checker + @param checkEveryMillis interval to call check + @param logInterval interval to log for each]]> + + + + + + + + + + AMRMClientAsync handles communication with the ResourceManager + and provides asynchronous updates on events such as container allocations and + completions. It contains a thread that sends periodic heartbeats to the + ResourceManager. + + It should be used by implementing a CallbackHandler: + 
    + {@code
+ class MyCallbackHandler extends AMRMClientAsync.AbstractCallbackHandler {
+   public void onContainersAllocated(List containers) {
+     [run tasks on the containers]
+   }
+
+   public void onContainersUpdated(List containers) {
+     [determine if resource allocation of containers have been increased in
+      the ResourceManager, and if so, inform the NodeManagers to increase the
+      resource monitor/enforcement on the containers]
+   }
+
+   public void onContainersCompleted(List statuses) {
+     [update progress, check whether app is done]
+   }
+   
+   public void onNodesUpdated(List updated) {}
+   
+   public void onReboot() {}
+ }
+ }
+
    + + The client's lifecycle should be managed similarly to the following: + + 
    + {@code
+ AMRMClientAsync asyncClient = 
+     createAMRMClientAsync(appAttId, 1000, new MyCallbackhandler());
+ asyncClient.init(conf);
+ asyncClient.start();
+ RegisterApplicationMasterResponse response = asyncClient
+    .registerApplicationMaster(appMasterHostname, appMasterRpcPort,
+       appMasterTrackingUrl);
+ asyncClient.addContainerRequest(containerRequest);
+ [... wait for application to complete]
+ asyncClient.unregisterApplicationMaster(status, appMsg, trackingUrl);
+ asyncClient.stop();
+ }
+
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + NMClientAsync handles communication with all the NodeManagers + and provides asynchronous updates on getting responses from them. It + maintains a thread pool to communicate with individual NMs where a number of + worker threads process requests to NMs by using {@link NMClientImpl}. The max + size of the thread pool is configurable through + {@link YarnConfiguration#NM_CLIENT_ASYNC_THREAD_POOL_MAX_SIZE}. + + It should be used in conjunction with a CallbackHandler. For example + + 
    + {@code
+ class MyCallbackHandler extends NMClientAsync.AbstractCallbackHandler {
+   public void onContainerStarted(ContainerId containerId,
+       Map allServiceResponse) {
+     [post process after the container is started, process the response]
+   }
+
+   public void onContainerResourceIncreased(ContainerId containerId,
+       Resource resource) {
+     [post process after the container resource is increased]
+   }
+
+   public void onContainerStatusReceived(ContainerId containerId,
+       ContainerStatus containerStatus) {
+     [make use of the status of the container]
+   }
+
+   public void onContainerStopped(ContainerId containerId) {
+     [post process after the container is stopped]
+   }
+
+   public void onStartContainerError(
+       ContainerId containerId, Throwable t) {
+     [handle the raised exception]
+   }
+
+   public void onGetContainerStatusError(
+       ContainerId containerId, Throwable t) {
+     [handle the raised exception]
+   }
+
+   public void onStopContainerError(
+       ContainerId containerId, Throwable t) {
+     [handle the raised exception]
+   }
+ }
+ }
+
    + + The client's life-cycle should be managed like the following: + + 
    + {@code
+ NMClientAsync asyncClient = 
+     NMClientAsync.createNMClientAsync(new MyCallbackhandler());
+ asyncClient.init(conf);
+ asyncClient.start();
+ asyncClient.startContainer(container, containerLaunchContext);
+ [... wait for container being started]
+ asyncClient.getContainerStatus(container.getId(), container.getNodeId(),
+     container.getContainerToken());
+ [... handle the status in the callback instance]
+ asyncClient.stopContainer(container.getId(), container.getNodeId(),
+     container.getContainerToken());
+ [... wait for container being stopped]
+ asyncClient.stop();
+ }
+
    ]]> +     +     + +     + + + + + + + + + + + + + + + + + + + + + + + + + + +     diff --git a/hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Common_2.8.3.xml b/hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Common_2.8.3.xml new file mode 100644 index 00000000000..6826c2565f3 --- /dev/null +++ b/hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Common_2.8.3.xml @@ -0,0 +1,2665 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Type of proxy. + @return Proxy to the ResourceManager for the specified client protocol. + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Type information of the proxy + @return Proxy to the RM + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Send the information of a number of conceptual entities to the timeline + server. It is a blocking API. The method will not return until it gets the + response from the timeline server. +

    + + @param entities + the collection of {@link TimelineEntity} + @return the error information if the sent entities are not correctly stored + @throws IOException + @throws YarnException]]> +     +     + + + + + + + + + Send the information of a number of conceptual entities to the timeline + server. It is a blocking API. The method will not return until it gets the + response from the timeline server. + + This API is only for timeline service v1.5 +

    + + @param appAttemptId {@link ApplicationAttemptId} + @param groupId {@link TimelineEntityGroupId} + @param entities + the collection of {@link TimelineEntity} + @return the error information if the sent entities are not correctly stored + @throws IOException + @throws YarnException]]> +     +     + + + + + + + Send the information of a domain to the timeline server. It is a + blocking API. The method will not return until it gets the response from + the timeline server. +

    + + @param domain + an {@link TimelineDomain} object + @throws IOException + @throws YarnException]]> +     +     + + + + + + + + Send the information of a domain to the timeline server. It is a + blocking API. The method will not return until it gets the response from + the timeline server. + + This API is only for timeline service v1.5 +

    + + @param domain + an {@link TimelineDomain} object + @param appAttemptId {@link ApplicationAttemptId} + @throws IOException + @throws YarnException]]> +     +     + + + + + + + Get a delegation token so as to be able to talk to the timeline server in a + secure way. +

    + + @param renewer + Address of the renewer who can renew these tokens when needed by + securely talking to the timeline server + @return a delegation token ({@link Token}) that can be used to talk to the + timeline server + @throws IOException + @throws YarnException]]> +     +     + + + + + + + Renew a timeline delegation token. +

    + + @param timelineDT + the delegation token to renew + @return the new expiration time + @throws IOException + @throws YarnException]]> +     +     + + + + + + + Cancel a timeline delegation token. +

    + + @param timelineDT + the delegation token to cancel + @throws IOException + @throws YarnException]]> +     +     + + + +     + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + parameterized event of type T]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + InputStream to be checksumed + @return the message digest of the input stream + @throws IOException]]> + + + + + + + + + + + + SharedCacheChecksum object based on the configurable + algorithm implementation + (see yarn.sharedcache.checksum.algo.impl) + + @return SharedCacheChecksum object]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + The object type on which this state machine operates. + @param The state of the entity. + @param The external eventType to be handled. + @param The event object.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +     diff --git a/hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Server_Common_2.8.3.xml b/hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Server_Common_2.8.3.xml new file mode 100644 index 00000000000..f3191e46d52 --- /dev/null +++ b/hadoop-yarn-project/hadoop-yarn/dev-support/jdiff/Apache_Hadoop_YARN_Server_Common_2.8.3.xml @@ -0,0 +1,829 @@ + + + + + + + + + + + + + + + + + + + + + + + + true if the node is healthy, else false]]> + + + + + diagnostic health report of the node. + @return diagnostic health report of the node]]> + + + + + last timestamp at which the health report was received. + @return last timestamp at which the health report was received]]> + + + + + It includes information such as: +
      +
    • + An indicator of whether the node is healthy, as determined by the + health-check script. +
      • +
    • The previous time at which the health status was reported.
      • +
    • A diagnostic report on the health status.
      • +
    + + @see NodeReport + @see ApplicationClientProtocol#getClusterNodes(org.apache.hadoop.yarn.api.protocolrecords.GetClusterNodesRequest)]]> +     +     + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if the iteration has more elements.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +