app-packages/hbase-win/configuration/hbase-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
/**
 * 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>hdfs://localhost:8020/apps/hbase/data</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.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.master.port</name>
    <value>60000</value>
    <description>The port the HBase Master should bind to.</description>
  </property>
  <property>
    <name>hbase.tmp.dir</name>
    <value>/hadoop/hbase</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.local.dir</name>
    <value>${hbase.tmp.dir}/local</value>
    <description>Directory on the local filesystem to be used as a local storage
    </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.master.info.port</name>
    <value>60010</value>
    <description>The port for the HBase Master web UI.</description>
  </property>
  <property>
    <name>hbase.regionserver.info.port</name>
    <value>60030</value>
    <description>The port for the HBase RegionServer web UI.</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.handler.count</name>
    <value>60</value>
    <description>Count of RPC Listener 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.hregion.majorcompaction</name>
    <value>86400000</value>
    <description>The time (in milliseconds) 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.regionserver.global.memstore.lowerLimit</name>
    <value>0.38</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.hregion.memstore.block.multiplier</name>
    <value>2</value>
    <description>Block updates if memstore has hbase.hregion.memstore.block.multiplier
    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.flush.size</name>
    <value>134217728</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.memstore.mslab.enabled</name>
    <value>true</value>
    <description>
      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>10737418240</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: 1G.
    </description>
  </property>
  <property>
    <name>hbase.client.scanner.caching</name>
    <value>100</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>zookeeper.session.timeout</name>
    <value>30000</value>
    <description>ZooKeeper session timeout.
      HBase passes this to the zk quorum as suggested maximum time for a
      session (This setting becomes zookeeper's 'maxSessionTimeout').  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>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.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.flush.retries.number</name>
    <value>120</value>
    <description>
    The number of times the region flush operation will be retried.
    </description>
  </property>
  
  <property>
    <name>hbase.hstore.blockingStoreFiles</name>
    <value>10</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>hfile.block.cache.size</name>
    <value>0.40</value>
    <description>
        Percentage of maximum heap (-Xmx setting) to allocate to block cache
        used by HFile/StoreFile. Default of 0.25 means allocate 25%.
        Set to 0 to disable but it's not recommended.
    </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>/etc/security/keytabs/hbase.service.keytab</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>hbase/_HOST@EXAMPLE.COM</value>
    <description>Ex. "hbase/_HOST@EXAMPLE.COM".  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>/etc/security/keytabs/hbase.service.keytab</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>hbase/_HOST@EXAMPLE.COM</value>
    <description>Ex. "hbase/_HOST@EXAMPLE.COM".  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>

  <!-- Additional configuration specific to HBase security -->
  <property>
    <name>hbase.superuser</name>
    <value>hbase</value>
    <description>List of users or groups (comma-separated), who are allowed
    full privileges, regardless of stored ACLs, across the cluster.
    Only used when HBase security is enabled.
    </description>
  </property>

  <property>
    <name>hbase.security.authentication</name>
    <value>simple</value>
    <description>  Controls whether or not secure authentication is enabled for HBase. Possible values are 'simple'
      (no authentication), and 'kerberos'.
    </description>
  </property>

  <property>
    <name>hbase.security.authorization</name>
    <value>false</value>
    <description>Enables HBase authorization. Set the value of this property to false to disable HBase authorization.
    </description>
  </property>

  <property>
    <name>hbase.coprocessor.region.classes</name>
    <value></value>
    <description>A comma-separated list of Coprocessors that are loaded by
    default on all tables. For any override coprocessor method, these classes
    will be called in order. After implementing your own Coprocessor, just put
    it in HBase's classpath and add the fully qualified class name here.
    A coprocessor can also be loaded on demand by setting HTableDescriptor.
    </description>
  </property>

  <property>
    <name>hbase.coprocessor.master.classes</name>
    <value></value>
    <description>A comma-separated list of
      org.apache.hadoop.hbase.coprocessor.MasterObserver coprocessors that are
      loaded by default on the active HMaster process. For any implemented
      coprocessor methods, the listed classes will be called in order. After
      implementing your own MasterObserver, just put it in HBase's classpath
      and add the fully qualified class name here.
    </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>

  <!--
  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>
  <!-- End of properties used to generate ZooKeeper host:port quorum list. -->

  <property>
    <name>hbase.zookeeper.useMulti</name>
    <value>true</value>
    <description>Instructs HBase to make use of ZooKeeper's multi-update functionality.
    This allows certain ZooKeeper operations to complete more quickly and prevents some issues
    with rare Replication failure scenarios (see the release note of HBASE-2611 for an example).·
    IMPORTANT: only set this to true if all ZooKeeper servers in the cluster are on version 3.4+
    and will not be downgraded.  ZooKeeper versions before 3.4 do not support multi-update and will
    not fail gracefully if multi-update is invoked (see ZOOKEEPER-1495).
    </description>
  </property>
  <property>
    <name>zookeeper.znode.parent</name>
    <value>/hbase-unsecure</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>hbase.defaults.for.version.skip</name>
    <value>true</value>
    <description>Disables version verification.</description>
  </property>

  <property>
    <name>dfs.domain.socket.path</name>
    <value>/var/lib/hadoop-hdfs/dn_socket</value>
    <description>Path to domain socket.</description>
  </property>

</configuration>