hbase-default.xml

<configuration>
  <property>
    <name>hbase.rootdir</name>
    <value>hdfs://localhost:8020/hbase</value>
    <description>The directory shared by region servers and into
    which HBase persists.  The URL should be 'fully-qualified'
    to include the filesystem scheme.  For example, to specify the
    HDFS directory '/hbase' where the HDFS instance's namenode is
    running at namenode.example.org on port 9000, set this value to:
    hdfs://namenode.example.org:9000/hbase.  By default HBase writes
    into /tmp.  Change this configuration else all data will be lost
    on machine restart.
    </description>
  </property>
  <property>
    <name>hbase.master.port</name>
    <value>60000</value>
    <description>The port the HBase Master should bind to.</description>
  </property>
  <property>
    <name>hbase.cluster.distributed</name>
    <value>true</value>
    <description>The mode the cluster will be in. Possible values are
      false for standalone mode and true for distributed mode.  If
      false, startup will run all HBase and ZooKeeper daemons together
      in the one JVM.
    </description>
  </property>
  <property>
    <name>hbase.tmp.dir</name>
    <value>/home/vamshi/Documents/HBASE_SOFTWARE/hbase-0.90.4/hbase-${user.name}</value>
    <description>Temporary directory on the local filesystem.
    Change this setting to point to a location more permanent
    than '/tmp' (The '/tmp' directory is often cleared on
    machine restart).
    </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 a UI instance run.
    </description>
  </property>
  <property>
    <name>hbase.master.info.bindAddress</name>
    <value>0.0.0.0</value>
    <description>The bind address for the HBase Master web UI
    </description>
  </property>
  <property>
    <name>hbase.client.write.buffer</name>
    <value>2097152</value>
    <description>Default size of the HTable clien 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 a larger buffer size reduces the number of RPCs made.
    For an estimate of server-side memory-used, evaluate
    hbase.client.write.buffer * hbase.regionserver.handler.count
    </description>
  </property>
  <property>
    <name>hbase.regionserver.port</name>
    <value>60020</value>
    <description>The port the HBase RegionServer binds to.
    </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 RegionServer UI to run.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.info.port.auto</name>
    <value>false</value>
    <description>Whether or not the Master or RegionServer
    UI should search for a port to bind to. Enables automatic port
    search if hbase.regionserver.info.port is already in use.
    Useful for testing, turned off by default.
    </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>The RegionServer interface to use.
    Used by the client opening proxy to remote region server.
    </description>
  </property>
  <property>
    <name>hbase.client.pause</name>
    <value>1000</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>1</value>
    <description>Number of rows that will be fetched when calling next
    on a scanner if it is not served from (local, client) 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.
    Do not set this value such that the time between invocations is greater
    than the scanner timeout; i.e. hbase.regionserver.lease.period
    </description>
  </property>
  <property>
    <name>hbase.client.keyvalue.maxsize</name>
    <value>10485760</value>
    <description>Specifies the combined maximum allowed size of a KeyValue
    instance. This is to set an upper boundary for a single entry saved in a
    storage file. Since they cannot be split it helps avoiding that a region
    cannot be split any further because the data is too large. It seems wise
    to set this to a fraction of the maximum region size. Setting it to zero
    or less disables the check.
    </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 Master 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 Master
    in milliseconds.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.optionallogflushinterval</name>
    <value>1000</value>
    <description>Sync the HLog to the HDFS after this interval if it has not
    accumulated enough entries to trigger a sync. Default 1 second. Units:
    milliseconds.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.regionSplitLimit</name>
    <value>2147483647</value>
    <description>Limit for the number of regions after which no more region
    splitting should take place. This is not a hard limit for the number of
    regions but acts as a guideline for the regionserver to stop splitting after
    a certain limit. Default is set to MAX_INT; i.e. do not block splitting.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.logroll.period</name>
    <value>3600000</value>
    <description>Period at which we will roll the commit log regardless
    of how many edits it has.</description>
  </property>
  <property>
    <name>hbase.regionserver.hlog.reader.impl</name>
    <value>org.apache.hadoop.hbase.regionserver.wal.SequenceFileLogReader</value>
    <description>The HLog file reader implementation.</description>
  </property>
  <property>
    <name>hbase.regionserver.hlog.writer.impl</name>
    <value>org.apache.hadoop.hbase.regionserver.wal.SequenceFileLogWriter</value>
    <description>The HLog file writer implementation.</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 resevoir blocks of memory release on
    OOME so we can cleanup properly before server shutdown.
    </description>
  </property>
  <property>
    <name>hbase.zookeeper.dns.interface</name>
    <value>default</value>
    <description>The name of the Network Interface from which a ZooKeeper server
      should report its IP address.
    </description>
  </property>
  <property>
    <name>hbase.zookeeper.dns.nameserver</name>
    <value>default</value>
    <description>The host name or IP address of the name server (DNS)
      which a ZooKeeper server should use to determine the host name used by the
      master for communication and display purposes.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.dns.interface</name>
    <value>default</value>
    <description>The name of the Network Interface from which a region server
      should report its IP address.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.dns.nameserver</name>
    <value>default</value>
    <description>The host name or IP address of the name server (DNS)
      which a region server should use to determine the host name used by the
      master for communication and display purposes.
    </description>
  </property>
  <property>
    <name>hbase.master.dns.interface</name>
    <value>default</value>
    <description>The name of the Network Interface from which a master
      should report its IP address.
    </description>
  </property>
  <property>
    <name>hbase.master.dns.nameserver</name>
    <value>default</value>
    <description>The host name or IP address of the name server (DNS)
      which a master should use to determine the host name used
      for communication and display purposes.
    </description>
  </property>
  <property>
    <name>hbase.balancer.period
    </name>
    <value>300000</value>
    <description>Period at which the region balancer runs in the Master.
    </description>
  </property>
  <property>
    <name>hbase.regions.slop</name>
    <value>0</value>
    <description>Rebalance if any regionserver has average + (average * slop) regions.
    Default is 0% slop.
    </description>
  </property>
  <property>
    <name>hbase.master.logcleaner.ttl</name>
    <value>600000</value>
    <description>Maximum time a HLog can stay in the .oldlogdir directory,
    after which it will be cleaned by a Master thread.
    </description>
  </property>
  <property>
    <name>hbase.master.logcleaner.plugins</name>
    <value>org.apache.hadoop.hbase.master.TimeToLiveLogCleaner</value>
    <description>A comma-separated list of LogCleanerDelegate invoked by
    the LogsCleaner service. These WAL/HLog cleaners are called in order,
    so put the HLog cleaner that prunes the most HLog files in front. To
    implement your own LogCleanerDelegate, just put it in HBase's classpath
    and add the fully qualified class name here. Always add the above
    default log cleaners in the list.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.global.memstore.upperLimit</name>
    <value>0.4</value>
    <description>Maximum size of all memstores in a region server before new
      updates are blocked and flushes are forced. Defaults to 40% of heap
    </description>
  </property>
  <property>
    <name>hbase.regionserver.global.memstore.lowerLimit</name>
    <value>0.35</value>
    <description>When memstores are being forced to flush to make room in
      memory, keep flushing until we hit this mark. Defaults to 35% of heap.
      This value equal to hbase.regionserver.global.memstore.upperLimit causes
      the minimum possible flushing to occur when updates are blocked due to
      memstore limiting.
    </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 log roller.
    </description>
  </property>
  <property>
    <name>hbase.hregion.memstore.flush.size</name>
    <value>67108864</value>
    <description>
    Memstore will be flushed to disk if size of the memstore
    exceeds this number of bytes.  Value is checked by a thread that runs
    every hbase.server.thread.wakefrequency.
    </description>
  </property>
  <property>
    <name>hbase.hregion.preclose.flush.size</name>
    <value>5242880</value>
    <description>
      If the memstores in a region are this size or larger when we go
      to close, run a "pre-flush" to clear out memstores before we put up
      the region closed flag and take the region offline.  On close,
      a flush is run under the close flag to empty memory.  During
      this time the region is offline and we are not taking on any writes.
      If the memstore content is large, this flush could take a long time to
      complete.  The preflush is meant to clean out the bulk of the memstore
      before putting up the close flag and taking the region offline so the
      flush that runs under the close flag has little to do.
    </description>
  </property>
  <property>
    <name>hbase.hregion.memstore.block.multiplier</name>
    <value>2</value>
    <description>
    Block updates if memstore has hbase.hregion.block.memstore
    time hbase.hregion.flush.size bytes.  Useful preventing
    runaway memstore during spikes in update traffic.  Without an
    upper-bound, memstore 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.memstore.mslab.enabled</name>
    <value>false</value>
    <description>
      Experimental: Enables the MemStore-Local Allocation Buffer,
      a feature which works to prevent heap fragmentation under
      heavy write loads. This can reduce the frequency of stop-the-world
      GC pauses on large heaps.
    </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 memstore) 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.
    </description>
  </property>
  <property>
    <name>hbase.hstore.blockingStoreFiles</name>
    <value>7</value>
    <description>
    If more than this number of StoreFiles in any one Store
    (one StoreFile is written per flush of MemStore) then updates are
    blocked for this HRegion until a compaction is completed, or
    until hbase.hstore.blockingWaitTime has been exceeded.
    </description>
  </property>
  <property>
    <name>hbase.hstore.blockingWaitTime</name>
    <value>90000</value>
    <description>
    The time an HRegion will block updates for after hitting the StoreFile
    limit defined by hbase.hstore.blockingStoreFiles.
    After this time has elapsed, the HRegion will stop blocking updates even
    if a compaction has not been completed.  Default: 90 seconds.
    </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.
    Set to 0 to disable automated major compactions.
    </description>
  </property>
  <property>
    <name>hbase.mapreduce.hfileoutputformat.blocksize</name>
    <value>65536</value>
    <description>The mapreduce HFileOutputFormat writes storefiles/hfiles.
    This is the minimum hfile blocksize to emit.  Usually in hbase, writing
    hfiles, the blocksize is gotten from the table schema (HColumnDescriptor)
    but in the mapreduce outputformat context, we don't have access to the
    schema so get blocksize from Configuation.  The smaller you make
    the blocksize, the bigger your index and the less you fetch on a
    random-access.  Set the blocksize down if you have small cells and want
    faster random-access of individual cells.
    </description>
  </property>
  <property>
      <name>hfile.block.cache.size</name>
      <value>0.2</value>
      <description>
          Percentage of maximum heap (-Xmx setting) to allocate to block cache
          used by HFile/StoreFile. Default of 0.2 means allocate 20%.
          Set to 0 to disable.
      </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).
    Used by bloom filters.
    </description>
  </property>

  <!-- The following properties configure authentication information for
       HBase processes when using Kerberos security.  There are no default
       values, included here for documentation purposes -->
  <property>
    <name>hbase.master.keytab.file</name>
    <value></value>
    <description>Full path to the kerberos keytab file to use for logging in
    the configured HMaster server principal.
    </description>
  </property>
  <property>
    <name>hbase.master.kerberos.principal</name>
    <value></value>
    <description>Ex. "hbase/[email protected]".  The kerberos principal name
    that should be used to run the HMaster process.  The principal name should
    be in the form: user/hostname@DOMAIN.  If "_HOST" is used as the hostname
    portion, it will be replaced with the actual hostname of the running
    instance.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.keytab.file</name>
    <value></value>
    <description>Full path to the kerberos keytab file to use for logging in
    the configured HRegionServer server principal.
    </description>
  </property>
  <property>
    <name>hbase.regionserver.kerberos.principal</name>
    <value></value>
    <description>Ex. "hbase/[email protected]".  The kerberos principal name
    that should be used to run the HRegionServer process.  The principal name
    should be in the form: user/hostname@DOMAIN.  If "_HOST" is used as the
    hostname portion, it will be replaced with the actual hostname of the
    running instance.  An entry for this principal must exist in the file
    specified in hbase.regionserver.keytab.file
    </description>
  </property>
  <property>
    <name>zookeeper.session.timeout</name>
    <value>180000</value>
    <description>ZooKeeper session timeout.
      HBase passes this to the zk quorum as suggested maximum time for a
      session.  See http://hadoop.apache.org/zookeeper/docs/current/zookeeperProgrammers.html#ch_zkSessions
      "The client sends a requested timeout, the server responds with the
      timeout that it can give the client. "
      In milliseconds.
    </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 path 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>

  <!--
  The following three properties are used together to create the list of
  host:peer_port:leader_port quorum servers for ZooKeeper.
  -->
  <property>
    <name>hbase.zookeeper.quorum</name>
    <value>localhost</value>
    <description>Comma separated list of servers in the ZooKeeper Quorum.
    For example, "host1.mydomain.com,host2.mydomain.com,host3.mydomain.com".
    By default this is set to localhost for local and pseudo-distributed modes
    of operation. For a fully-distributed setup, this should be set to a full
    list of ZooKeeper quorum servers. If HBASE_MANAGES_ZK is set in hbase-env.sh
    this is the list of servers which we will start/stop ZooKeeper on.
    </description>
  </property>
  <property>
    <name>hbase.zookeeper.peerport</name>
    <value>2888</value>
    <description>Port used by ZooKeeper peers to talk to each other.
    See http://hadoop.apache.org/zookeeper/docs/r3.1.1/zookeeperStarted.html#sc_RunningReplicatedZooKeeper
    for more information.
    </description>
  </property>
  <property>
    <name>hbase.zookeeper.leaderport</name>
    <value>3888</value>
    <description>Port used by ZooKeeper for leader election.
    See http://hadoop.apache.org/zookeeper/docs/r3.1.1/zookeeperStarted.html#sc_RunningReplicatedZooKeeper
    for more information.
    </description>
  </property>
  <!-- End of properties used to generate ZooKeeper host:port quorum list. -->

  <!--
  Beginning of properties that are directly mapped from ZooKeeper's zoo.cfg.
  All properties with an "hbase.zookeeper.property." prefix are converted for
  ZooKeeper's configuration. Hence, if you want to add an option from zoo.cfg,
  e.g.  "initLimit=10" you would append the following to your configuration:
    <property>
      <name>hbase.zookeeper.property.initLimit</name>
      <value>10</value>
    </property>
  -->
  <property>
    <name>hbase.zookeeper.property.initLimit</name>
    <value>10</value>
    <description>Property from ZooKeeper's config zoo.cfg.
    The number of ticks that the initial synchronization phase can take.
    </description>
  </property>
  <property>
    <name>hbase.zookeeper.property.syncLimit</name>
    <value>5</value>
    <description>Property from ZooKeeper's config zoo.cfg.
    The number of ticks that can pass between sending a request and getting an
    acknowledgment.
    </description>
  </property>
  <property>
    <name>hbase.zookeeper.property.dataDir</name>
    <value>${hbase.tmp.dir}/zookeeper</value>
    <description>Property from ZooKeeper's config zoo.cfg.
    The directory where the snapshot is stored.
    </description>
  </property>
  <property>
    <name>hbase.zookeeper.property.clientPort</name>
    <value>2181</value>
    <description>Property from ZooKeeper's config zoo.cfg.
    The port at which the clients will connect.
    </description>
  </property>
  <property>
    <name>hbase.zookeeper.property.maxClientCnxns</name>
    <value>2000</value>
    <description>Property from ZooKeeper's config zoo.cfg.
    Limit on number of concurrent connections (at the socket level) that a
    single client, identified by IP address, may make to a single member of
    the ZooKeeper ensemble. Set high to avoid zk connection issues running
    standalone and pseudo-distributed.
    </description>
  </property>
  <!-- End of properties that are directly mapped from ZooKeeper's zoo.cfg -->
  <property>
    <name>hbase.rest.port</name>
    <value>8080</value>
    <description>The port for the HBase REST server.</description>
  </property>
  <property>
    <name>hbase.rest.readonly</name>
    <value>false</value>
    <description>
    Defines the mode the REST server will be started in. Possible values are:
    false: All HTTP methods are permitted - GET/PUT/POST/DELETE.
    true: Only the GET method is permitted.
    </description>
  </property>

  <property skipInDoc="true">
    <name>hbase.defaults.for.version</name>
    <value>@@@VERSION@@@</value>
    <description>
    This defaults file was compiled for version @@@VERSION@@@. This variable is used
    to make sure that a user doesn't have an old version of hbase-default.xml on the
    classpath.
    </description>
  </property>
</configuration>