hadoop/hadoop-common-project/hadoop-common/src/main/resources/core-default.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.
-->

<!-- Do not modify this file directly.  Instead, copy entries that you -->
<!-- wish to modify from this file into core-site.xml and change them -->
<!-- there.  If core-site.xml does not already exist, create it.      -->

<configuration>

<!--- global properties -->

<property>
  <name>hadoop.common.configuration.version</name>
  <value>0.23.0</value>
  <description>version of this configuration file</description>
</property>

<property>
  <name>hadoop.tmp.dir</name>
  <value>/tmp/hadoop-${user.name}</value>
  <description>A base for other temporary directories.</description>
</property>

<property>
  <name>io.native.lib.available</name>
  <value>true</value>
  <description>Should native hadoop libraries, if present, be used.</description>
</property>

<property>
  <name>hadoop.http.filter.initializers</name>
  <value>org.apache.hadoop.http.lib.StaticUserWebFilter</value>
  <description>A comma separated list of class names. Each class in the list 
  must extend org.apache.hadoop.http.FilterInitializer. The corresponding 
  Filter will be initialized. Then, the Filter will be applied to all user 
  facing jsp and servlet web pages.  The ordering of the list defines the 
  ordering of the filters.</description>
</property>

<!--- security properties -->

<property>
  <name>hadoop.security.authorization</name>
  <value>false</value>
  <description>Is service-level authorization enabled?</description>
</property>

<property>
  <name>hadoop.security.authentication</name>
  <value>simple</value>
  <description>Possible values are simple (no authentication), and kerberos
  </description>
</property>

<property>
  <name>hadoop.security.group.mapping</name>
  <value>org.apache.hadoop.security.ShellBasedUnixGroupsMapping</value>
  <description>
    Class for user to group mapping (get groups for a given user) for ACL
  </description>
</property>

<property>
  <name>hadoop.security.groups.cache.secs</name>
  <value>300</value>
  <description>
    This is the config controlling the validity of the entries in the cache
    containing the user->group mapping. When this duration has expired,
    then the implementation of the group mapping provider is invoked to get
    the groups of the user and then cached back.
  </description>
</property>

<property>
  <name>hadoop.security.service.user.name.key</name>
  <value></value>
  <description>
    For those cases where the same RPC protocol is implemented by multiple
    servers, this configuration is required for specifying the principal
    name to use for the service when the client wishes to make an RPC call.
  </description>
</property>

<property>
  <name>hadoop.rpc.protection</name>
  <value>authentication</value>
  <description>This field sets the quality of protection for secured sasl 
      connections. Possible values are authentication, integrity and privacy.
      authentication means authentication only and no integrity or privacy; 
      integrity implies authentication and integrity are enabled; and privacy 
      implies all of authentication, integrity and privacy are enabled.
  </description>
</property>

<property>
  <name>hadoop.work.around.non.threadsafe.getpwuid</name>
  <value>false</value>
  <description>Some operating systems or authentication modules are known to
  have broken implementations of getpwuid_r and getpwgid_r, such that these
  calls are not thread-safe. Symptoms of this problem include JVM crashes
  with a stack trace inside these functions. If your system exhibits this
  issue, enable this configuration parameter to include a lock around the
  calls as a workaround.

  An incomplete list of some systems known to have this issue is available
  at http://wiki.apache.org/hadoop/KnownBrokenPwuidImplementations
  </description>
</property>

<property>
  <name>hadoop.kerberos.kinit.command</name>
  <value>kinit</value>
  <description>Used to periodically renew Kerberos credentials when provided
  to Hadoop. The default setting assumes that kinit is in the PATH of users
  running the Hadoop client. Change this to the absolute path to kinit if this
  is not the case.
  </description>
</property>

<!-- i/o properties -->
<property>
  <name>io.file.buffer.size</name>
  <value>4096</value>
  <description>The size of buffer for use in sequence files.
  The size of this buffer should probably be a multiple of hardware
  page size (4096 on Intel x86), and it determines how much data is
  buffered during read and write operations.</description>
</property>
  
<property>
  <name>io.bytes.per.checksum</name>
  <value>512</value>
  <description>The number of bytes per checksum.  Must not be larger than
  io.file.buffer.size.</description>
</property>

<property>
  <name>io.skip.checksum.errors</name>
  <value>false</value>
  <description>If true, when a checksum error is encountered while
  reading a sequence file, entries are skipped, instead of throwing an
  exception.</description>
</property>

<property>
  <name>io.compression.codecs</name>
  <value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec,org.apache.hadoop.io.compress.DeflateCodec,org.apache.hadoop.io.compress.SnappyCodec,org.apache.hadoop.io.compress.Lz4Codec</value>
  <description>A list of the compression codec classes that can be used 
               for compression/decompression.</description>
</property>

<property>
  <name>io.serializations</name>
  <value>org.apache.hadoop.io.serializer.WritableSerialization,org.apache.hadoop.io.serializer.avro.AvroSpecificSerialization,org.apache.hadoop.io.serializer.avro.AvroReflectSerialization</value>
  <description>A list of serialization classes that can be used for
  obtaining serializers and deserializers.</description>
</property>

<property>
  <name>io.seqfile.local.dir</name>
  <value>${hadoop.tmp.dir}/io/local</value>
  <description>The local directory where sequence file stores intermediate
  data files during merge.  May be a comma-separated list of
  directories on different devices in order to spread disk i/o.
  Directories that do not exist are ignored.
  </description>
</property>

<property>
  <name>io.map.index.skip</name>
  <value>0</value>
  <description>Number of index entries to skip between each entry.
  Zero by default. Setting this to values larger than zero can
  facilitate opening large MapFiles using less memory.</description>
</property>

<property>
  <name>io.map.index.interval</name>
  <value>128</value>
  <description>
    MapFile consist of two files - data file (tuples) and index file
    (keys). For every io.map.index.interval records written in the
    data file, an entry (record-key, data-file-position) is written
    in the index file. This is to allow for doing binary search later
    within the index file to look up records by their keys and get their
    closest positions in the data file.
  </description>
</property>

<!-- file system properties -->

<property>
  <name>fs.defaultFS</name>
  <value>file:///</value>
  <description>The name of the default file system.  A URI whose
  scheme and authority determine the FileSystem implementation.  The
  uri's scheme determines the config property (fs.SCHEME.impl) naming
  the FileSystem implementation class.  The uri's authority is used to
  determine the host, port, etc. for a filesystem.</description>
</property>

<property>
  <name>fs.default.name</name>
  <value>file:///</value>
  <description>Deprecated. Use (fs.defaultFS) property
  instead</description>
</property>

<property>
  <name>fs.trash.interval</name>
  <value>0</value>
  <description>Number of minutes after which the checkpoint
  gets deleted.
  If zero, the trash feature is disabled.
  </description>
</property>

<property>
  <name>fs.trash.checkpoint.interval</name>
  <value>0</value>
  <description>Number of minutes between trash checkpoints.
  Should be smaller or equal to fs.trash.interval.
  Every time the checkpointer runs it creates a new checkpoint 
  out of current and removes checkpoints created more than 
  fs.trash.interval minutes ago.
  </description>
</property>

<property>
  <name>fs.file.impl</name>
  <value>org.apache.hadoop.fs.LocalFileSystem</value>
  <description>The FileSystem for file: uris.</description>
</property>

<property>
  <name>fs.hdfs.impl</name>
  <value>org.apache.hadoop.hdfs.DistributedFileSystem</value>
  <description>The FileSystem for hdfs: uris.</description>
</property>

<property>
  <name>fs.viewfs.impl</name>
  <value>org.apache.hadoop.fs.viewfs.ViewFileSystem</value>
  <description>The FileSystem for view file system for viewfs: uris
  (ie client side mount table:).</description>
</property>

<property>
  <name>fs.AbstractFileSystem.file.impl</name>
  <value>org.apache.hadoop.fs.local.LocalFs</value>
  <description>The AbstractFileSystem for file: uris.</description>
</property>


<property>
  <name>fs.AbstractFileSystem.hdfs.impl</name>
  <value>org.apache.hadoop.fs.Hdfs</value>
  <description>The FileSystem for hdfs: uris.</description>
</property>

<property>
  <name>fs.AbstractFileSystem.viewfs.impl</name>
  <value>org.apache.hadoop.fs.viewfs.ViewFs</value>
  <description>The AbstractFileSystem for view file system for viewfs: uris
  (ie client side mount table:).</description>
</property>

<property>
  <name>fs.s3.impl</name>
  <value>org.apache.hadoop.fs.s3.S3FileSystem</value>
  <description>The FileSystem for s3: uris.</description>
</property>

<property>
  <name>fs.s3n.impl</name>
  <value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value>
  <description>The FileSystem for s3n: (Native S3) uris.</description>
</property>

<property>
  <name>fs.kfs.impl</name>
  <value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value>
  <description>The FileSystem for kfs: uris.</description>
</property>

<property>
  <name>fs.hftp.impl</name>
  <value>org.apache.hadoop.hdfs.HftpFileSystem</value>
</property>

<property>
  <name>fs.hsftp.impl</name>
  <value>org.apache.hadoop.hdfs.HsftpFileSystem</value>
</property>

<property>
  <name>fs.webhdfs.impl</name>
  <value>org.apache.hadoop.hdfs.web.WebHdfsFileSystem</value>
</property>

<property>
  <name>fs.ftp.impl</name>
  <value>org.apache.hadoop.fs.ftp.FTPFileSystem</value>
  <description>The FileSystem for ftp: uris.</description>
</property>

<property>
  <name>fs.ftp.host</name>
  <value>0.0.0.0</value>
  <description>FTP filesystem connects to this server</description>
</property>

<property>
  <name>fs.ftp.host.port</name>
  <value>21</value>
  <description>
    FTP filesystem connects to fs.ftp.host on this port
  </description>
</property>

<property>
  <name>fs.har.impl</name>
  <value>org.apache.hadoop.fs.HarFileSystem</value>
  <description>The filesystem for Hadoop archives. </description>
</property>

<property>
  <name>fs.har.impl.disable.cache</name>
  <value>true</value>
  <description>Don't cache 'har' filesystem instances.</description>
</property>

<property>
  <name>fs.df.interval</name>
  <value>60000</value>
  <description>Disk usage statistics refresh interval in msec.</description>
</property>

<property>
  <name>fs.s3.block.size</name>
  <value>67108864</value>
  <description>Block size to use when writing files to S3.</description>
</property>

<property>
  <name>fs.s3.buffer.dir</name>
  <value>${hadoop.tmp.dir}/s3</value>
  <description>Determines where on the local filesystem the S3 filesystem
  should store files before sending them to S3
  (or after retrieving them from S3).
  </description>
</property>

<property>
  <name>fs.s3.maxRetries</name>
  <value>4</value>
  <description>The maximum number of retries for reading or writing files to S3, 
  before we signal failure to the application.
  </description>
</property>

<property>
  <name>fs.s3.sleepTimeSeconds</name>
  <value>10</value>
  <description>The number of seconds to sleep between each S3 retry.
  </description>
</property>


<property>
  <name>fs.automatic.close</name>
  <value>true</value>
  <description>By default, FileSystem instances are automatically closed at program
  exit using a JVM shutdown hook. Setting this property to false disables this
  behavior. This is an advanced option that should only be used by server applications
  requiring a more carefully orchestrated shutdown sequence.
  </description>
</property>

<property>
  <name>fs.s3n.block.size</name>
  <value>67108864</value>
  <description>Block size to use when reading files using the native S3
  filesystem (s3n: URIs).</description>
</property>

<property>
  <name>io.seqfile.compress.blocksize</name>
  <value>1000000</value>
  <description>The minimum block size for compression in block compressed 
          SequenceFiles.
  </description>
</property>

<property>
  <name>io.seqfile.lazydecompress</name>
  <value>true</value>
  <description>Should values of block-compressed SequenceFiles be decompressed
          only when necessary.
  </description>
</property>

<property>
  <name>io.seqfile.sorter.recordlimit</name>
  <value>1000000</value>
  <description>The limit on number of records to be kept in memory in a spill 
          in SequenceFiles.Sorter
  </description>
</property>

 <property>
  <name>io.mapfile.bloom.size</name>
  <value>1048576</value>
  <description>The size of BloomFilter-s used in BloomMapFile. Each time this many
  keys is appended the next BloomFilter will be created (inside a DynamicBloomFilter).
  Larger values minimize the number of filters, which slightly increases the performance,
  but may waste too much space if the total number of keys is usually much smaller
  than this number.
  </description>
</property>

<property>
  <name>io.mapfile.bloom.error.rate</name>
  <value>0.005</value>
  <description>The rate of false positives in BloomFilter-s used in BloomMapFile.
  As this value decreases, the size of BloomFilter-s increases exponentially. This
  value is the probability of encountering false positives (default is 0.5%).
  </description>
</property>

<property>
  <name>hadoop.util.hash.type</name>
  <value>murmur</value>
  <description>The default implementation of Hash. Currently this can take one of the
  two values: 'murmur' to select MurmurHash and 'jenkins' to select JenkinsHash.
  </description>
</property>


<!-- ipc properties -->

<property>
  <name>ipc.client.idlethreshold</name>
  <value>4000</value>
  <description>Defines the threshold number of connections after which
               connections will be inspected for idleness.
  </description>
</property>

<property>
  <name>ipc.client.kill.max</name>
  <value>10</value>
  <description>Defines the maximum number of clients to disconnect in one go.
  </description>
</property>

<property>
  <name>ipc.client.connection.maxidletime</name>
  <value>10000</value>
  <description>The maximum time in msec after which a client will bring down the
               connection to the server.
  </description>
</property>

<property>
  <name>ipc.client.connect.max.retries</name>
  <value>10</value>
  <description>Indicates the number of retries a client will make to establish
               a server connection.
  </description>
</property>

<property>
  <name>ipc.server.listen.queue.size</name>
  <value>128</value>
  <description>Indicates the length of the listen queue for servers accepting
               client connections.
  </description>
</property>

<property>
  <name>ipc.server.tcpnodelay</name>
  <value>false</value>
  <description>Turn on/off Nagle's algorithm for the TCP socket connection on 
  the server. Setting to true disables the algorithm and may decrease latency
  with a cost of more/smaller packets. 
  </description>
</property>

<property>
  <name>ipc.client.tcpnodelay</name>
  <value>false</value>
  <description>Turn on/off Nagle's algorithm for the TCP socket connection on 
  the client. Setting to true disables the algorithm and may decrease latency
  with a cost of more/smaller packets. 
  </description>
</property>


<!-- Proxy Configuration -->

<property>
  <name>hadoop.rpc.socket.factory.class.default</name>
  <value>org.apache.hadoop.net.StandardSocketFactory</value>
  <description> Default SocketFactory to use. This parameter is expected to be
    formatted as "package.FactoryClassName".
  </description>
</property>

<property>
  <name>hadoop.rpc.socket.factory.class.ClientProtocol</name>
  <value></value>
  <description> SocketFactory to use to connect to a DFS. If null or empty, use
    hadoop.rpc.socket.class.default. This socket factory is also used by
    DFSClient to create sockets to DataNodes.
  </description>
</property>



<property>
  <name>hadoop.socks.server</name>
  <value></value>
  <description> Address (host:port) of the SOCKS server to be used by the
    SocksSocketFactory.
  </description>
</property>

<!-- Rack Configuration -->

<property>
	<name>net.topology.node.switch.mapping.impl</name>
  <value>org.apache.hadoop.net.ScriptBasedMapping</value>
  <description> The default implementation of the DNSToSwitchMapping. It
    invokes a script specified in net.topology.script.file.name to resolve
    node names. If the value for net.topology.script.file.name is not set, the
    default value of DEFAULT_RACK is returned for all node names.
  </description>
</property>

<property>
  <name>net.topology.script.file.name</name>
  <value></value>
  <description> The script name that should be invoked to resolve DNS names to
    NetworkTopology names. Example: the script would take host.foo.bar as an
    argument, and return /rack1 as the output.
  </description>
</property>

<property>
  <name>net.topology.script.number.args</name>
  <value>100</value>
  <description> The max number of args that the script configured with 
    net.topology.script.file.name should be run with. Each arg is an
    IP address.
  </description>
</property>

<!-- Local file system -->
<property>
  <name>file.stream-buffer-size</name>
  <value>4096</value>
  <description>The size of buffer to stream files.
  The size of this buffer should probably be a multiple of hardware
  page size (4096 on Intel x86), and it determines how much data is
  buffered during read and write operations.</description>
</property>

<property>
  <name>file.bytes-per-checksum</name>
  <value>512</value>
  <description>The number of bytes per checksum.  Must not be larger than
  file.stream-buffer-size</description>
</property>

<property>
  <name>file.client-write-packet-size</name>
  <value>65536</value>
  <description>Packet size for clients to write</description>
</property>

<property>
  <name>file.blocksize</name>
  <value>67108864</value>
  <description>Block size</description>
</property>

<property>
  <name>file.replication</name>
  <value>1</value>
  <description>Replication factor</description>
</property>

<!-- s3 File System -->

<property>
  <name>s3.stream-buffer-size</name>
  <value>4096</value>
  <description>The size of buffer to stream files.
  The size of this buffer should probably be a multiple of hardware
  page size (4096 on Intel x86), and it determines how much data is
  buffered during read and write operations.</description>
</property>

<property>
  <name>s3.bytes-per-checksum</name>
  <value>512</value>
  <description>The number of bytes per checksum.  Must not be larger than
  s3.stream-buffer-size</description>
</property>

<property>
  <name>s3.client-write-packet-size</name>
  <value>65536</value>
  <description>Packet size for clients to write</description>
</property>

<property>
  <name>s3.blocksize</name>
  <value>67108864</value>
  <description>Block size</description>
</property>

<property>
  <name>s3.replication</name>
  <value>3</value>
  <description>Replication factor</description>
</property>

<!-- s3native File System -->

<property>
  <name>s3native.stream-buffer-size</name>
  <value>4096</value>
  <description>The size of buffer to stream files.
  The size of this buffer should probably be a multiple of hardware
  page size (4096 on Intel x86), and it determines how much data is
  buffered during read and write operations.</description>
</property>

<property>
  <name>s3native.bytes-per-checksum</name>
  <value>512</value>
  <description>The number of bytes per checksum.  Must not be larger than
  s3native.stream-buffer-size</description>
</property>

<property>
  <name>s3native.client-write-packet-size</name>
  <value>65536</value>
  <description>Packet size for clients to write</description>
</property>

<property>
  <name>s3native.blocksize</name>
  <value>67108864</value>
  <description>Block size</description>
</property>

<property>
  <name>s3native.replication</name>
  <value>3</value>
  <description>Replication factor</description>
</property>

<!-- Kosmos File System -->

<property>
  <name>kfs.stream-buffer-size</name>
  <value>4096</value>
  <description>The size of buffer to stream files.
  The size of this buffer should probably be a multiple of hardware
  page size (4096 on Intel x86), and it determines how much data is
  buffered during read and write operations.</description>
</property>

<property>
  <name>kfs.bytes-per-checksum</name>
  <value>512</value>
  <description>The number of bytes per checksum.  Must not be larger than
  kfs.stream-buffer-size</description>
</property>

<property>
  <name>kfs.client-write-packet-size</name>
  <value>65536</value>
  <description>Packet size for clients to write</description>
</property>

<property>
  <name>kfs.blocksize</name>
  <value>67108864</value>
  <description>Block size</description>
</property>

<property>
  <name>kfs.replication</name>
  <value>3</value>
  <description>Replication factor</description>
</property>

<!-- FTP file system -->
<property>
  <name>ftp.stream-buffer-size</name>
  <value>4096</value>
  <description>The size of buffer to stream files.
  The size of this buffer should probably be a multiple of hardware
  page size (4096 on Intel x86), and it determines how much data is
  buffered during read and write operations.</description>
</property>

<property>
  <name>ftp.bytes-per-checksum</name>
  <value>512</value>
  <description>The number of bytes per checksum.  Must not be larger than
  ftp.stream-buffer-size</description>
</property>

<property>
  <name>ftp.client-write-packet-size</name>
  <value>65536</value>
  <description>Packet size for clients to write</description>
</property>

<property>
  <name>ftp.blocksize</name>
  <value>67108864</value>
  <description>Block size</description>
</property>

<property>
  <name>ftp.replication</name>
  <value>3</value>
  <description>Replication factor</description>
</property>

<!-- Tfile -->

<property>
  <name>tfile.io.chunk.size</name>
  <value>1048576</value>
  <description>
    Value chunk size 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 also
    TFile.Reader.Scanner.Entry.isValueLengthKnown()).
  </description>
</property>

<property>
  <name>tfile.fs.output.buffer.size</name>
  <value>262144</value>
  <description>
    Buffer size used for FSDataOutputStream in bytes.
  </description>
</property>

<property>
  <name>tfile.fs.input.buffer.size</name>
  <value>262144</value>
  <description>
    Buffer size used for FSDataInputStream in bytes.
  </description>
</property>

<!-- HTTP web-consoles Authentication -->

<property>
  <name>hadoop.http.authentication.type</name>
  <value>simple</value>
  <description>
    Defines authentication used for Oozie HTTP endpoint.
    Supported values are: simple | kerberos | #AUTHENTICATION_HANDLER_CLASSNAME#
  </description>
</property>

<property>
  <name>hadoop.http.authentication.token.validity</name>
  <value>36000</value>
  <description>
    Indicates how long (in seconds) an authentication token is valid before it has
    to be renewed.
  </description>
</property>

<property>
  <name>hadoop.http.authentication.signature.secret</name>
  <value>hadoop</value>
  <description>
    The signature secret for signing the authentication tokens.
    If not set a random secret is generated at startup time.
    The same secret should be used for JT/NN/DN/TT configurations.
  </description>
</property>

<property>
  <name>hadoop.http.authentication.cookie.domain</name>
  <value></value>
  <description>
    The domain to use for the HTTP cookie that stores the authentication token.
    In order to authentiation to work correctly across all Hadoop nodes web-consoles
    the domain must be correctly set.
    IMPORTANT: when using IP addresses, browsers ignore cookies with domain settings.
    For this setting to work properly all nodes in the cluster must be configured
    to generate URLs with hostname.domain names on it.
  </description>
</property>

<property>
  <name>hadoop.http.authentication.simple.anonymous.allowed</name>
  <value>true</value>
  <description>
    Indicates if anonymous requests are allowed when using 'simple' authentication.
  </description>
</property>

<property>
  <name>hadoop.http.authentication.kerberos.principal</name>
  <value>HTTP/localhost@LOCALHOST</value>
  <description>
    Indicates the Kerberos principal to be used for HTTP endpoint.
    The principal MUST start with 'HTTP/' as per Kerberos HTTP SPNEGO specification.
  </description>
</property>

<property>
  <name>hadoop.http.authentication.kerberos.keytab</name>
  <value>${user.home}/hadoop.keytab</value>
  <description>
    Location of the keytab file with the credentials for the principal.
    Referring to the same keytab file Oozie uses for its Kerberos credentials for Hadoop.
  </description>
</property>

</configuration>