From a299146b6d9ed3c558f7d4e5bc33d492362faffd Mon Sep 17 00:00:00 2001 From: "Vinod Kumar Vavilapalli (I am also known as @tshooter.)" Date: Fri, 19 Aug 2016 19:08:53 -0700 Subject: [PATCH] HADOOP-13428. Fixed hadoop-common build files to generate jdiff by working around a jdiff-bug. Contributed by Wangda Tan. (cherry picked from commit 99603e902244f17b04cfd55122f47355d070b588) --- .../dev-support/jdiff-workaround.patch | 98 + .../jdiff/Apache_Hadoop_Common_2.7.2.xml | 46648 ++++++++++++++++ hadoop-common-project/hadoop-common/pom.xml | 2 + hadoop-project-dist/pom.xml | 44 +- 4 files changed, 46789 insertions(+), 3 deletions(-) create mode 100644 hadoop-common-project/hadoop-common/dev-support/jdiff-workaround.patch create mode 100644 hadoop-common-project/hadoop-common/dev-support/jdiff/Apache_Hadoop_Common_2.7.2.xml diff --git a/hadoop-common-project/hadoop-common/dev-support/jdiff-workaround.patch b/hadoop-common-project/hadoop-common/dev-support/jdiff-workaround.patch new file mode 100644 index 00000000000..8f87d4092bc --- /dev/null +++ b/hadoop-common-project/hadoop-common/dev-support/jdiff-workaround.patch @@ -0,0 +1,98 @@ +diff --git a/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/metrics2/MetricsSystem.java b/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/metrics2/MetricsSystem.java +index a277abd..ed7c709 100644 +--- a/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/metrics2/MetricsSystem.java ++++ b/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/metrics2/MetricsSystem.java +@@ -43,18 +43,6 @@ + public abstract MetricsSystem init(String prefix); + + /** +- * Register a metrics source +- * @param 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 +- */ +- public abstract T register(String name, String desc, T source); +- +- /** + * Unregister a metrics source + * @param name of the source. This is the name you use to call register() + */ +@@ -77,18 +65,19 @@ + */ + @InterfaceAudience.Private + public abstract MetricsSource getSource(String name); ++ + + /** +- * Register a metrics sink +- * @param the type of the sink +- * @param sink to register +- * @param name of the sink. Must be unique. +- * @param desc the description of the sink +- * @return the sink ++ * Register a metrics source ++ * @param 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 + */ +- public abstract +- T register(String name, String desc, T sink); ++ public abstract T register(String name, String desc, T source); + + /** + * Register a callback interface for JMX events +diff --git a/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/metrics2/impl/MetricsSystemImpl.java b/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/metrics2/impl/MetricsSystemImpl.java +index 6986edb..eeea81f 100644 +--- a/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/metrics2/impl/MetricsSystemImpl.java ++++ b/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/metrics2/impl/MetricsSystemImpl.java +@@ -270,27 +270,6 @@ void registerSource(String name, String desc, MetricsSource source) { + LOG.debug("Registered source "+ name); + } + +- @Override public synchronized +- T register(final String name, final String description, final T sink) { +- LOG.debug(name +", "+ description); +- if (allSinks.containsKey(name)) { +- LOG.warn("Sink "+ name +" already exists!"); +- return sink; +- } +- allSinks.put(name, sink); +- if (config != null) { +- registerSink(name, description, sink); +- } +- // We want to re-register the sink to pick up new config +- // when the metrics system restarts. +- register(name, new AbstractCallback() { +- @Override public void postStart() { +- register(name, description, sink); +- } +- }); +- return sink; +- } +- + synchronized void registerSink(String name, String desc, MetricsSink sink) { + checkNotNull(config, "config"); + MetricsConfig conf = sinkConfigs.get(name); +diff --git a/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/metrics2/impl/TestGangliaMetrics.java b/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/metrics2/impl/TestGangliaMetrics.java +index c19d238..f8412f1 100644 +--- a/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/metrics2/impl/TestGangliaMetrics.java ++++ b/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/metrics2/impl/TestGangliaMetrics.java +@@ -130,8 +130,8 @@ public void testTagsForPrefix() throws Exception { + GangliaMetricsTestHelper.setDatagramSocket(gsink31, mockds31); + + // register the sinks +- ms.register("gsink30", "gsink30 desc", gsink30); +- ms.register("gsink31", "gsink31 desc", gsink31); ++ //ms.register("gsink30", "gsink30 desc", gsink30); ++ //ms.register("gsink31", "gsink31 desc", gsink31); + ms.publishMetricsNow(); // publish the metrics + + ms.stop(); diff --git a/hadoop-common-project/hadoop-common/dev-support/jdiff/Apache_Hadoop_Common_2.7.2.xml b/hadoop-common-project/hadoop-common/dev-support/jdiff/Apache_Hadoop_Common_2.7.2.xml new file mode 100644 index 00000000000..5ef99b22770 --- /dev/null +++ b/hadoop-common-project/hadoop-common/dev-support/jdiff/Apache_Hadoop_Common_2.7.2.xml @@ -0,0 +1,46648 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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. + 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.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + KeyProviderExtension implementation providing a short lived + cache for KeyVersions and Metadatato avoid burst + of requests to hit the underlying KeyProvider.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + KeyVersion material of the latest key version + of the key and is encrypted using the same cipher. +

+ NOTE: The generated key is not stored by the KeyProvider + + @param encryptionKeyName + The latest KeyVersion of this key's material will be encrypted. + @return EncryptedKeyVersion with the generated key material, the version + name is 'EEK' (for Encrypted Encryption Key) + @throws IOException + thrown if the key material could not be generated + @throws GeneralSecurityException + thrown if the key material could not be encrypted because of a + cryptographic issue.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + The alternative to this is using the same IV for both the encryption key + and the encrypted key. Even a simple symmetric transformation like this + improves security by avoiding IV re-use. IVs will also be fairly unique + among different EEKs. + + @param encryptedKeyIV of the encrypted key (i.e. {@link + #getEncryptedKeyIv()}) + @return IV for the encryption key]]> + + + + + + + + + + + + + + + + + + + + + KeyProviderDelegationTokenExtension using a given + {@link KeyProvider}. +

+ If the given KeyProvider implements the + {@link DelegationTokenExtension} interface the KeyProvider + itself will provide the extension functionality, otherwise a default + extension implementation will be used. + + @param keyProvider KeyProvider to use to create the + KeyProviderDelegationTokenExtension extension. + @return a KeyProviderDelegationTokenExtension instance + using the given KeyProvider.]]> + + + + + + + + + + + + + + + + Credentials object if it is not already present, + @param renewer the user allowed to renew the delegation tokens + @param credentials cache in which to add new delegation tokens + @return list of new delegation tokens + @throws IOException thrown if IOException if an IO error occurs.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + NULL if + a provider for the specified URI scheme could not be found. + @throws IOException thrown if the provider failed to initialize.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @/ + + where : + - PROTO = http or https + - AUTHORITY = [:] + - HOSTS = [;] + - HOSTNAME = string + - PORT = integer + + If multiple hosts are provider, the Factory will create a + {@link LoadBalancingKMSClientProvider} that round-robins requests + across the provided list of hosts.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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 combination is not valid and will result in + {@link HadoopIllegalArgumentException}: +
    +
  1. APPEND|OVERWRITE
    2. +
  2. CREATE|APPEND|OVERWRITE
    3. +
]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + absOrFqPath is not supported. + @throws IOExcepton 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]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + *** 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, ...); +
    • ... +
    ]]> + + + + + + + + + + + + + + f is + not supported + + 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 + pathPattern 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]]> + + + + + + + + + + files 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]]> + + + + + + + + + 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: character a must be + lexicographically less than or equal to character b. + +

    +

    [^a] +
    Matches a single char 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 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 AccessControlException If access is denied + @throws UnsupportedFileSystemException If file system for + pathPattern 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]]> +     +     + + + + + + + + pathPattern 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]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + dst already exists + @throws FileNotFoundException If src does not exist + @throws ParentNotDirectoryException If parent of dst is not + a directory + @throws UnsupportedFileSystemException If file system for + src or 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 + + RuntimeExceptions: + @throws InvalidPathException If path dst is invalid]]> + + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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 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.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @return har]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + path is invalid]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @return file]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if and only if pathname + should be included]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + only to the given + valid time. + + @param mtime the modification time to set (only if greater than zero). + @param atime currently ignored. + @throws IOException if setting the last modified time fails.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + true if the iteration has more elements. + + @return true if the iterator has more elements. + @throws IOException if any IO error occurs]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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]]> +     +     + + + + + + + @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.default.name< = 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/ ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Zookeeper disconnects can happen due to network issues or loss of + Zookeeper quorum. Thus enterNeutralMode can be used to guard against + split-brain issues. In such situations it might be prudent to call + becomeStandby too. However, such state change operations might be + expensive and enterNeutralMode can help guard against doing that for + transient issues.]]> + + + + + + + + + + + + + + + + + The application will be notified with a callback only on state changes + (i.e. there will never be successive calls to becomeActive without an + intermediate call to enterNeutralMode).
    + The callbacks will be running on Zookeeper client library threads. The + application should return from these callbacks quickly so as not to impede + Zookeeper client library performance and notifications. The app will + typically remember the state change and return from the callback. It will + then proceed with implementing actions around that state change. It is + possible to be called back again while these actions are in flight and the + app should handle this scenario.]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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. {@see HAServiceStatus} + + @throws AccessControlException + if access is denied. + @throws IOException + if other errors happen]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + shell(/path/to/my/script.sh arg1 arg2 ...) +
    + The string between '(' and ')' is passed directly to a bash shell + (cmd.exe on Windows) and may not include any closing parentheses.

    + + The shell command will be run with an environment set up to contain + all of the current Hadoop configuration variables, with the '_' character + replacing any '.' characters in the configuration keys.

    + + If the shell command returns an exit code of 0, the fencing is + determined to be successful. If it returns any other exit code, the + fencing was not successful and the next fencing method in the list + will be attempted.

    + + Note: this fencing method does not implement any timeout. + If timeouts are necessary, they should be implemented in the shell + script itself (eg by forking a subshell to kill its parent in + some number of seconds).]]> + + + + + + + + + + + + + + + + + + + + + + fuser to kill the process listening on the service's + TCP port. This is more accurate than using "jps" since it doesn't + require parsing, and will work even if there are multiple service + processes running on the same machine.

    + It returns a successful status code if: +

      +
    • fuser indicates it successfully killed a process, or +
    • nc -z indicates that nothing is listening on the target port +
    +

    + This fencing mechanism is configured as following in the fencing method + list: + sshfence([[username][:ssh-port]]) + where the optional argument specifies the username and port to use + with ssh. +

    + In order to achieve passwordless SSH, the operator must also configure + dfs.ha.fencing.ssh.private-key-files to point to an + SSH key that has passphrase-less access to the given username and host.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + hadoop.http.filter.initializers. + +

      +
    • StaticUserWebFilter - An authorization plugin that makes all +users a static configured user. +
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + nth value.]]> + + + + + + + + + + + + + + + + + + + + + nth value in the file.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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}.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + key and + val. Returns true if such a pair exists and false when at + the end of the map]]> + + + + + + + + + + + + + + + + key or if it does not exist, at the first entry + after the named key. + +- * @param key - key that we're trying to find +- * @param val - data value if key is found +- * @return - the key that was the closest match or null if eof.]]> + + + + + + + + + key does not exist, return + the first entry that falls just before the key. Otherwise, + return the record that sorts just after. + @return - the key that was the closest match or null if eof.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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]]> +     + + + + + + + before + closing the related file descriptor. + + It is safe to use even if the readahead request has already + been fulfilled.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + An example of such an attack is: +
      +
    1. Malicious user removes his task's syslog file, and puts a link to the + jobToken file of a target user.
      2. +
    2. Malicious user tries to open the syslog file via the servlet on the + tasktracker.
      3. +
    3. The tasktracker is unaware of the symlink, and simply streams the contents + of the jobToken file. The malicious user can now access potentially sensitive + map outputs, etc. of the target user's job.
      4. +
    + A similar attack is possible involving task log truncation, but in that case + due to an insecure write to a file. +
    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + = 0. Otherwise, + the length is not available. + @return The opened stream. + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + key, skipping its + value. True if another entry exists, and false at end of file.]]> + + + + + + + + key and + val. Returns true if such a pair exists and false when at + end of file]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + The position passed must be a position returned by {@link + SequenceFile.Writer#getLength()} when writing this file. To seek to an arbitrary + position, use {@link SequenceFile.Reader#sync(long)}.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + SegmentDescriptor + @param segments the list of SegmentDescriptors + @param tmpDir the directory to write temporary files into + @return RawKeyValueIterator + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + For best performance, applications should make sure that the {@link + Writable#readFields(DataInput)} implementation of their keys is + very efficient. In particular, it should avoid allocating memory.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This always returns a synchronized position. In other words, + immediately after calling {@link SequenceFile.Reader#seek(long)} with a position + returned by this method, {@link SequenceFile.Reader#next(Writable)} may be called. However + the key may be earlier in the file than key last written when this + method was called (e.g., with block-compression, it may be the first key + in the block that was being written when this method was called).]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + key. Returns + true if such a key exists and false when at the end of the set.]]> + + + + + + + key. + Returns key, or null if no match exists.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + .lz4.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + .snappy.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +

  • "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.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + entry of the TFile. + @param endKey + End key of the scan. If null, scan up to the last entry + of the TFile. + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Use {@link Scanner#atEnd()} to test whether the cursor is at the end + location of the scanner. +

    + Use {@link Scanner#advance()} to move the cursor to the next key-value + pair (or end if none exists). Use seekTo methods ( + {@link Scanner#seekTo(byte[])} or + {@link Scanner#seekTo(byte[], int, int)}) to seek to any arbitrary + location in the covered range (including backward seeking). Use + {@link Scanner#rewind()} to seek back to the beginning of the scanner. + Use {@link Scanner#seekToEnd()} to seek to the end of the scanner. +

    + Actual keys and values may be obtained through {@link Scanner.Entry} + object, which is obtained through {@link Scanner#entry()}.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +

  • Algorithmic comparator: binary comparators that is language + independent. Currently, only "memcmp" is supported. +
  • Language-specific comparator: binary comparators that can + only be constructed in specific language. For Java, the syntax + is "jclass:", followed by the class name of the RawComparator. + Currently, we only support RawComparators that can be + constructed through the default constructor (with no + parameters). Parameterized RawComparators such as + {@link WritableComparator} or + {@link JavaSerializationComparator} may not be directly used. + One should write a wrapper class that inherits from such classes + and use its default constructor to perform proper + initialization. + + @param conf + The configuration object. + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + If an exception is thrown, the TFile will be in an inconsistent + state. The only legitimate call after that would be close]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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. +

    ]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This servlet generally will be placed under the /jmx URL for each + HttpServer. It provides read only + access to JMX metrics. The optional qry parameter + may be used to query only a subset of the JMX Beans. This query + functionality is provided through the + {@link MBeanServer#queryNames(ObjectName, javax.management.QueryExp)} + method. +

    + For example http://.../jmx?qry=Hadoop:* will return + all hadoop metrics exposed through JMX. +

    + The optional get parameter is used to query an specific + attribute of a JMX bean. The format of the URL is + http://.../jmx?get=MXBeanName::AttributeName +

    + For example + + http://../jmx?get=Hadoop:service=NameNode,name=NameNodeInfo::ClusterId + will return the cluster id of the namenode mxbean. +

    + If the qry or the get parameter is not formatted + correctly then a 400 BAD REQUEST http response code will be returned. +

    + If a resouce such as a mbean or attribute can not be found, + a 404 SC_NOT_FOUND http response code will be returned. +

    + The return format is JSON and in the form +

    + 

    +  {
+    "beans" : [
+      {
+        "name":"bean-name"
+        ...
+      }
+    ]
+  }
+
    +

    + The servlet attempts to convert the the JMXBeans into JSON. Each + bean's attributes will be converted to a JSON object member. + + If the attribute is a boolean, a number, a string, or an array + it will be converted to the JSON equivalent. + + If the value is a {@link CompositeData} then it will be converted + to a JSON object with the keys as the name of the JSON member and + the value is converted following these same rules. + + If the value is a {@link TabularData} then it will be converted + to an array of the {@link CompositeData} elements that it contains. + + All other objects will be converted to a string and output as such. + + The bean's name and modelerType will be returned for all beans.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +

  • Every event is a standalone JSON clause
    • +
  • Time is published as a time_t event since 1/1/1970 + -this is the fastest to generate.
    • +
  • An ISO date is generated, but this is cached and will only be accurate to within a second
    • +
  • the stack trace is included as an array
    • + + + A simple log event will resemble the following + 
    +     {"name":"test","time":1318429136789,"date":"2011-10-12 15:18:56,789","level":"INFO","thread":"main","message":"test message"}
+
    + + An event with an error will contain data similar to that below (which has been reformatted to be multi-line). + + 
    +     {
+     "name":"testException",
+     "time":1318429136789,
+     "date":"2011-10-12 15:18:56,789",
+     "level":"INFO",
+     "thread":"quoted\"",
+     "message":"new line\n and {}",
+     "exceptionclass":"java.net.NoRouteToHostException",
+     "stack":[
+         "java.net.NoRouteToHostException: that box caught fire 3 years ago",
+         "\tat org.apache.hadoop.log.TestLog4Json.testException(TestLog4Json.java:49)",
+         "\tat sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)",
+         "\tat sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)",
+         "\tat sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)",
+         "\tat java.lang.reflect.Method.invoke(Method.java:597)",
+         "\tat junit.framework.TestCase.runTest(TestCase.java:168)",
+         "\tat junit.framework.TestCase.runBare(TestCase.java:134)",
+         "\tat junit.framework.TestResult$1.protect(TestResult.java:110)",
+         "\tat junit.framework.TestResult.runProtected(TestResult.java:128)",
+         "\tat junit.framework.TestResult.run(TestResult.java:113)",
+         "\tat junit.framework.TestCase.run(TestCase.java:124)",
+         "\tat junit.framework.TestSuite.runTest(TestSuite.java:232)",
+         "\tat junit.framework.TestSuite.run(TestSuite.java:227)",
+         "\tat org.junit.internal.runners.JUnit38ClassRunner.run(JUnit38ClassRunner.java:83)",
+         "\tat org.apache.maven.surefire.junit4.JUnit4TestSet.execute(JUnit4TestSet.java:59)",
+         "\tat org.apache.maven.surefire.suite.AbstractDirectoryTestSuite.executeTestSet(AbstractDirectoryTestSuite.java:120)",
+         "\tat org.apache.maven.surefire.suite.AbstractDirectoryTestSuite.execute(AbstractDirectoryTestSuite.java:145)",
+         "\tat org.apache.maven.surefire.Surefire.run(Surefire.java:104)",
+         "\tat sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)",
+         "\tat sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)",
+         "\tat sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)",
+         "\tat java.lang.reflect.Method.invoke(Method.java:597)",
+         "\tat org.apache.maven.surefire.booter.SurefireBooter.runSuitesInProcess(SurefireBooter.java:290)",
+         "\tat org.apache.maven.surefire.booter.SurefireBooter.main(SurefireBooter.java:1017)"
+         ]
+     }
+
    ]]> +     + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + + + + + + + + + + + +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.

    ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + update + and remove().]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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 + @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]]> + + + + + + + + + + + + the actual type of the source object + @param source object to register + @return the source object + @exception MetricsException]]> + + + + + + + + the type of the sink + @param sink to register + @param name of the sink. Must be unique. + @param desc the description of the sink + @return the sink + @exception MetricsException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ,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.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Propagates to hadoop-auth AuthenticationFilter configuration all Hadoop + configuration properties prefixed with "hadoop.http.authentication." + + @param container The filter container + @param conf Configuration for run-time parameters]]> + + + + + + + + + It enables anonymous access, simple/speudo and Kerberos HTTP SPNEGO + authentication for Hadoop JobTracker, NameNode, DataNodes and + TaskTrackers. +

    + Refer to the core-default.xml file, after the comment + 'HTTP Authentication' for details on the configuration options. + All related configuration properties have 'hadoop.http.authentication.' + as prefix.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + mapping + and mapping]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + % hadoop credential create alias [-provider providerPath] + % hadoop credential list [-provider providerPath] + % hadoop credential delete alias [-provider providerPath] [-f] + + @param args + @return 0 if the argument(s) were recognized, 1 otherwise + @throws IOException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Note: Java doesn't appear able to extract international characters + from the SubjectAlts. It can only extract international characters + from the CN field. +

    + (Or maybe the version of OpenSSL I'm using to test isn't storing the + international characters correctly in the SubjectAlts?). + + @param cert X509Certificate + @return Array of SubjectALT DNS names stored in the certificate.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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.]]> +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Features: +
      +
    • mixing of '-' (dash) and '.' (dot) separators,
      • +
    • transition between characters and digits also constitutes a separator: + 1.0alpha1 => [1, 0, alpha, 1]
      • +
    • unlimited number of version components,
      • +
    • version components in the text can be digits or strings,
      • +
    • strings are checked for well-known qualifiers and the qualifier ordering is used for version ordering. + Well-known qualifiers (case insensitive) are:
        +
      • alpha or a
        • +
      • beta or b
        • +
      • milestone or m
        • +
      • rc or cr
        • +
      • snapshot
        • +
      • (the empty string) or ga or final
        • +
      • sp
        • +
      + Unknown qualifiers are considered after known qualifiers, with lexical order (always case insensitive), +
      • +
    • a dash usually precedes a qualifier, and is always less important than something preceded with a dot.
      • +

    + + @see "Versioning" on Maven Wiki]]> +     +     + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + This can be used for testing + @return contents of the MachineList]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + the static class to find + @param the parent class of the array + @param cls the dynamic class to find + @param opts the list of options to look through + @return the first option that matches + @throws IOException]]> + + + + + + + the type of options + @param oldOpts the old options + @param newOpts the new options + @return a new array of options]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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.]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ShellCommandExecutorshould be used in cases where the output + of the command needs no explicit parsing and where the command, working + directory and the environment remains unchanged. The output of the command + is stored as-is and is expected to be small.]]> + + + + + + + + ShutdownHookManager singleton. + + @return ShutdownHookManager singleton.]]> + + + + + + + Runnable + @param priority priority of the shutdownHook.]]> + + + + + + + + + + + + + + + + + + + + + ShutdownHookManager enables running shutdownHook + in a deterministic order, higher priority first. +

    + The JVM runs ShutdownHooks in a non-deterministic order or in parallel. + This class registers a single JVM shutdownHook and run all the + shutdownHooks registered to it (to this class) in order based on their + priority.]]> + + + + + + + + + + + true if the thread is successfully interrupted, + false otherwise + @throws InterruptedException]]> + + + + + + + true if the thread is successfully interrupted, + false otherwise + @throws InterruptedException]]> + + + + + + + true if the service is terminated, + false otherwise + @throws InterruptedException]]> + + + + + + + + true if the service is terminated, + false otherwise + @throws InterruptedException]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 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
+         JobClient.runJob(job);
+         return 0;
+       }
+
+       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-common-project/hadoop-common/pom.xml b/hadoop-common-project/hadoop-common/pom.xml index c804fcaaffc..09f630cf9da 100644 --- a/hadoop-common-project/hadoop-common/pom.xml +++ b/hadoop-common-project/hadoop-common/pom.xml @@ -33,6 +33,7 @@ common true + true ../etc/hadoop wsce-site.xml @@ -493,6 +494,7 @@ src/test/resources/test.har/_masterindex src/test/resources/test.har/part-0 src/test/resources/javakeystoreprovider.password + dev-support/jdiff-workaround.patch diff --git a/hadoop-project-dist/pom.xml b/hadoop-project-dist/pom.xml index b2e2c4f9139..c6cff924d3d 100644 --- a/hadoop-project-dist/pom.xml +++ b/hadoop-project-dist/pom.xml @@ -158,7 +158,7 @@ false - 2.6.0 + 2.7.2 -unstable @@ -171,7 +171,7 @@ org.apache.maven.plugins maven-javadoc-plugin - + javadoc @@ -239,6 +239,26 @@ org.apache.maven.plugins maven-antrun-plugin + + + + pre-site + prepare-package + + run + + + + + + + + + + + + site prepare-package @@ -247,7 +267,6 @@ - @@ -300,6 +319,25 @@ + + + + post-site + prepare-package + + run + + + + + + + + + + + +