hbase/conf/hbase-default.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
/**
 * Copyright 2007 The Apache Software Foundation
 *
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
-->
<configuration>
  <property>
    <name>hbase.rootdir</name>
    <value>file:///tmp/hbase-${user.name}/hbase</value>
    <description>The directory shared by region servers.
    Should be fully-qualified to include the filesystem to use.
    E.g: hdfs://NAMENODE_SERVER:PORT/HBASE_ROOTDIR
    </description>
  </property>
  <property>
    <name>run.distributed</name>
    <value>false</value>
    <description>Enable this to run a distributed HBase. When this is disabled
    (the default) HBase runs all processes on the current host in a local mode.
    </description>
  </property>
  <property>
    <name>hbase.master.hostname</name>
    <value>localhost</value>
    <description>The host that the HBase master runs at.</description>
  </property>
  <property>
    <name>hbase.master.port</name>
    <value>60000</value>
    <description>The port master should bind to.</description>
  </property>
  <property>
    <name>hbase.tmp.dir</name>
    <value>/tmp/hbase-${user.name}</value>
    <description>Temporary directory on the local filesystem.</description>
  </property>
  <property>
    <name>hbase.master.info.port</name>
    <value>60010</value>
    <description>The port for the hbase master web UI
    Set to -1 if you do not want the info server to run.
    </description>
  </property>
  <property>
    <name>hbase.master.info.bindAddress</name>
    <value>0.0.0.0</value>
    <description>The address for the hbase master web UI
    </description>
  </property>
  <property>
    <name>hbase.client.write.buffer</name>
    <value>2097152</value>
    <description>Size of the write buffer in bytes. A bigger buffer takes more
    memory -- on both the client and server side since server instantiates
    the passed write buffer to process it -- but reduces the number of RPC.  
    For an estimate of server-side memory-used, evaluate
    hbase.client.write.buffer * hbase.regionserver.handler.count
    </description>
  </property>
  <property>
    <name>hbase.master.meta.thread.rescanfrequency</name>
    <value>60000</value>
    <description>How long the HMaster sleeps (in milliseconds) between scans of
    the root and meta tables.
    </description>
  </property>
  <property>
    <name>hbase.master.lease.period</name>
    <value>120000</value>
    <description>HMaster server lease period in milliseconds. Default is
    120 seconds.  Region servers must report in within this period else
    they are considered dead.  On loaded cluster, may need to up this
    period.</description>
  </property>
  <property>
    <name>hbase.regionserver</name>
    <value>0.0.0.0:60020</value>
    <description>The host and port a HBase region server runs at.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.dns.interface</name>
    <value>default</value>
    <description>Name of the network interface which a regionserver
    should use to determine it's "real" IP address.  This lookup
    prevents strings like "localhost" and "127.0.0.1" from being
    reported back to the master.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.info.port</name>
    <value>60030</value>
    <description>The port for the hbase regionserver web UI
    Set to -1 if you do not want the info server to run.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.info.bindAddress</name>
    <value>0.0.0.0</value>
    <description>The address for the hbase regionserver web UI
    </description>
  </property>
  <property>
    <name>hbase.regionserver.class</name>
    <value>org.apache.hadoop.hbase.ipc.HRegionInterface</value>
    <description>An interface that is assignable to HRegionInterface.  Used in HClient for
    opening proxy to remote region server.
    </description>
  </property>
  <property>
    <name>hbase.client.pause</name>
    <value>2000</value>
    <description>General client pause value.  Used mostly as value to wait
    before running a retry of a failed get, region lookup, etc.</description>
  </property>
  <property>
    <name>hbase.client.retries.number</name>
    <value>10</value>
    <description>Maximum retries.  Used as maximum for all retryable
    operations such as fetching of the root region from root region
    server, getting a cell's value, starting a row update, etc.
    Default: 10.
    </description>
  </property>
  <property>
    <name>hbase.client.scanner.caching</name>
    <value>30</value>
    <description>Number of rows that will be fetched when calling next
    on a scanner if it is not served from memory. Higher caching values
    will enable faster scanners but will eat up more memory and some
    calls of next may take longer and longer times when the cache is empty.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.lease.period</name>
    <value>60000</value>
    <description>HRegion server lease period in milliseconds. Default is
    60 seconds. Clients must report in within this period else they are
    considered dead.</description>
  </property>
  <property>
    <name>hbase.regionserver.handler.count</name>
    <value>10</value>
    <description>Count of RPC Server instances spun up on RegionServers
    Same property is used by the HMaster for count of master handlers.
    Default is 10.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.msginterval</name>
    <value>3000</value>
    <description>Interval between messages from the RegionServer to HMaster
    in milliseconds.  Default is 3 seconds.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.maxlogentries</name>
    <value>100000</value>
    <description>Rotate the HRegion HLogs when count of entries exceeds this
    value.  Default: 100,000.  Value is checked by a thread that runs every
    hbase.server.thread.wakefrequency.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.flushlogentries</name>
    <value>100</value>
    <description>Sync the HLog to the HDFS when it has accumulated this many
    entries. Default 100. Value is checked on every HLog.append
    </description>
  </property>
  <property>
    <name>hbase.regionserver.optionallogflushinterval</name>
    <value>10000</value>
    <description>Sync the HLog to the HDFS after this interval if it has not
    accumulated enough entries to trigger a sync. Default 10 seconds. Units:
    milliseconds.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.hlog.blocksize</name>
    <value>1048576</value>
    <description>Block size for HLog files. To minimize potential data loss,
    the size should be (avg key length) * (avg value length) * flushlogentries.
    Default 1MB.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.thread.splitcompactcheckfrequency</name>
    <value>20000</value>
    <description>How often a region server runs the split/compaction check.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.nbreservationblocks</name>
    <value>4</value>
    <description>The number of reservation blocks which are used to prevent
    unstable region servers caused by an OOME.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.globalMemcache.upperLimit</name>
    <value>0.4</value>
    <description>Maximum size of all memcaches in a region server before new 
      updates are blocked and flushes are forced. Defaults to 40% of heap.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.globalMemcache.lowerLimit</name>
    <value>0.25</value>
    <description>When memcaches are being forced to flush to make room in
      memory, keep flushing until we hit this mark. Defaults to 30% of heap. 
      This value equal to hbase.regionserver.globalmemcache.upperLimit causes
      the minimum possible flushing to occur when updates are blocked due to 
      memcache limiting.
    </description>
  </property>  
  <property>
    <name>hbase.hbasemaster.maxregionopen</name>
    <value>120000</value>
    <description>Period to wait for a region open.  If regionserver
    takes longer than this interval, assign to a new regionserver.
    </description>
  </property>
  <property>
    <name>hbase.regions.percheckin</name>
    <value>10</value>
    <description>Maximum number of regions that can be assigned in a single go
    to a region server.
    </description>
  </property>
  <property>
    <name>hbase.server.thread.wakefrequency</name>
    <value>10000</value>
    <description>Time to sleep in between searches for work (in milliseconds).
    Used as sleep interval by service threads such as META scanner and log roller.
    </description>
  </property>
  <property>
    <name>hbase.hregion.memcache.flush.size</name>
    <value>67108864</value>
    <description>
    A HRegion memcache will be flushed to disk if size of the memcache
    exceeds this number of bytes.  Value is checked by a thread that runs
    every hbase.server.thread.wakefrequency.  
    </description>
  </property>
  <property>
    <name>hbase.hregion.memcache.block.multiplier</name>
    <value>2</value>
    <description>
    Block updates if memcache has hbase.hregion.block.memcache
    time hbase.hregion.flush.size bytes.  Useful preventing
    runaway memcache during spikes in update traffic.  Without an
    upper-bound, memcache fills such that when it flushes the
    resultant flush files take a long time to compact or split, or
    worse, we OOME.
    </description>
  </property>
  <property>
    <name>hbase.hregion.max.filesize</name>
    <value>268435456</value>
    <description>
    Maximum HStoreFile size. If any one of a column families' HStoreFiles has
    grown to exceed this value, the hosting HRegion is split in two.
    Default: 256M.
    </description>
  </property>
  <property>
    <name>hbase.hstore.compactionThreshold</name>
    <value>3</value>
    <description>
    If more than this number of HStoreFiles in any one HStore
    (one HStoreFile is written per flush of memcache) then a compaction
    is run to rewrite all HStoreFiles files as one.  Larger numbers
    put off compaction but when it runs, it takes longer to complete.
    During a compaction, updates cannot be flushed to disk.  Long
    compactions require memory sufficient to carry the logging of
    all updates across the duration of the compaction.
    
    If too large, clients timeout during compaction.
    </description>
  </property>
  <property>
    <name>hbase.hstore.compaction.max</name>
    <value>10</value>
    <description>Max number of HStoreFiles to compact per 'minor' compaction.
    </description>
  </property>
  <property>
    <name>hbase.hregion.majorcompaction</name>
    <value>86400000</value>
    <description>The time (in miliseconds) between 'major' compactions of all
    HStoreFiles in a region.  Default: 1 day.
    </description>
  </property>
  <property>
    <name>hbase.regions.slop</name>
    <value>0.1</value>
    <description>Rebalance if regionserver has average + (average * slop) regions.
    Default is 10% slop.
    </description>
  </property>
  <property>
    <name>hbase.io.index.interval</name>
    <value>128</value>
    <description>The interval at which we record offsets in hbase
    store files/mapfiles.  Default for stock mapfiles is 128.  Index
    files are read into memory.  If there are many of them, could prove
    a burden.  If so play with the hadoop io.map.index.skip property and
    skip every nth index member when reading back the index into memory.
    Downside to high index interval is lowered access times.
    </description>
  </property>
  <property>
    <name>hfile.min.blocksize.size</name>
    <value>65536</value>
    <description>Minimum store file block size.  The smaller you make this, the
    bigger your index and the less you fetch on a random-access.  Set size down
    if you have small cells and want faster random-access of individual cells.
    </description>
  </property>
  <property>
    <name>hfile.min.blocksize.size</name>
    <value>65536</value>
    <description>Minimum store file block size.  The smaller you make this, the
    bigger your index and the less you fetch on a random-access.  Set size down
    if you have small cells and want faster random-access of individual cells.
    </description>
  </property>
  <property>
    <name>hfile.min.blocksize.size</name>
    <value>65536</value>
    <description>Minimum store file block size.  The smaller you make this, the
    bigger your index and the less you fetch on a random-access.  Set size down
    if you have small cells and want faster random-access of individual cells.
    </description>
  </property>
  <property>
    <name>hbase.io.seqfile.compression.type</name>
    <value>NONE</value>
    <description>The compression type for hbase sequencefile.Writers
    such as hlog.
    </description>
  </property>
  <property>
    <name>hbase.hstore.blockCache.blockSize</name>
    <value>16384</value>
    <description>The size of each block in the block cache.
    Enable blockcaching on a per column family basis; see the BLOCKCACHE setting
    in HColumnDescriptor.  Blocks are kept in a java Soft Reference cache so are
    let go when high pressure on memory.  Block caching is not enabled by default.
    </description>
  </property>
  <property>
    <name>hbase.hash.type</name>
    <value>murmur</value>
    <description>The hashing algorithm for use in HashFunction. Two values are
    supported now: murmur (MurmurHash) and jenkins (JenkinsHash).
    </description>
  </property>
  <property>
    <name>zookeeper.session.timeout</name>
    <value>10000</value>
    <description>ZooKeeper session timeout. This option is not used by HBase
      directly, it is for the internals of ZooKeeper. HBase merely passes it in
      whenever a connection is established to ZooKeeper. It is used by ZooKeeper
      for hearbeats. In milliseconds.
    </description>
  </property>
  <property>
    <name>zookeeper.retries</name>
    <value>5</value>
    <description>How many times to retry connections to ZooKeeper. Used for
      reading/writing root region location, checking/writing out of safe mode.
      Used together with ${zookeeper.pause} in an exponential backoff fashion
      when making queries to ZooKeeper.
    </description>
  </property>
  <property>
    <name>zookeeper.pause</name>
    <value>2000</value>
    <description>Sleep time between retries to ZooKeeper. In milliseconds. Used
      together with ${zookeeper.retries} in an exponential backoff fashion when
      making queries to ZooKeeper.
    </description>
  </property>
  <property>
    <name>zookeeper.znode.parent</name>
    <value>/hbase</value>
    <description>Root ZNode for HBase in ZooKeeper. All of HBase's ZooKeeper
      files that are configured with a relative path will go under this node.
      By default, all of HBase's ZooKeeper file patsh are configured with a
      relative path, so they will all go under this directory unless changed.
    </description>
  </property>
  <property>
    <name>zookeeper.znode.rootserver</name>
    <value>root-region-server</value>
    <description>Path to ZNode holding root region location. This is written by
      the master and read by clients and region servers. If a relative path is
      given, the parent folder will be ${zookeeper.znode.parent}. By default,
      this means the root location is stored at /hbase/root-region-server.
    </description>
  </property>
  <property>
    <name>zookeeper.znode.safemode</name>
    <value>safe-mode</value>
    <description>Path to ephemeral ZNode signifying cluster is out of safe mode.
      This is created by the master when scanning is done. Clients wait for this
      node before querying the cluster. If a relative path is given, the parent
      folder will be ${zookeeper.znode.parent}. By default, this means the safe
      mode flag is stored at /hbase/safe-mode.
    </description>
  </property>
</configuration>