| <?xml version="1.0"?> |
| |
| <!-- |
| 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. |
| --> |
| |
| <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> |
| |
| <!-- Do not modify this file directly. Instead, copy entries that you --> |
| <!-- wish to modify from this file into hdfs-site.xml and change them --> |
| <!-- there. If hdfs-site.xml does not already exist, create it. --> |
| |
| <configuration> |
| |
| <property> |
| <name>hadoop.hdfs.configuration.version</name> |
| <value>1</value> |
| <description>version of this configuration file</description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.logging.level</name> |
| <value>info</value> |
| <description>The logging level for dfs namenode. Other values are "dir"(trac |
| e namespace mutations), "block"(trace block under/over replications and block |
| creations/deletions), or "all".</description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.secondary.http-address</name> |
| <value>0.0.0.0:50090</value> |
| <description> |
| The secondary namenode http server address and port. |
| If the port is 0 then the server will start on a free port. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.address</name> |
| <value>0.0.0.0:50010</value> |
| <description> |
| The address where the datanode server will listen to. |
| If the port is 0 then the server will start on a free port. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.http.address</name> |
| <value>0.0.0.0:50075</value> |
| <description> |
| The datanode http server address and port. |
| If the port is 0 then the server will start on a free port. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.ipc.address</name> |
| <value>0.0.0.0:50020</value> |
| <description> |
| The datanode ipc server address and port. |
| If the port is 0 then the server will start on a free port. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.handler.count</name> |
| <value>3</value> |
| <description>The number of server threads for the datanode.</description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.http-address</name> |
| <value>0.0.0.0:50070</value> |
| <description> |
| The address and the base port where the dfs namenode web ui will listen on. |
| If the port is 0 then the server will start on a free port. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.https.enable</name> |
| <value>false</value> |
| <description>Decide if HTTPS(SSL) is supported on HDFS |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.client.https.need-auth</name> |
| <value>false</value> |
| <description>Whether SSL client certificate authentication is required |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.https.server.keystore.resource</name> |
| <value>ssl-server.xml</value> |
| <description>Resource file from which ssl server keystore |
| information will be extracted |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.client.https.keystore.resource</name> |
| <value>ssl-client.xml</value> |
| <description>Resource file from which ssl client keystore |
| information will be extracted |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.https.address</name> |
| <value>0.0.0.0:50475</value> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.https-address</name> |
| <value>0.0.0.0:50470</value> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.dns.interface</name> |
| <value>default</value> |
| <description>The name of the Network Interface from which a data node should |
| report its IP address. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.dns.nameserver</name> |
| <value>default</value> |
| <description>The host name or IP address of the name server (DNS) |
| which a DataNode should use to determine the host name used by the |
| NameNode for communication and display purposes. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.backup.address</name> |
| <value>0.0.0.0:50100</value> |
| <description> |
| The backup node server address and port. |
| If the port is 0 then the server will start on a free port. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.backup.http-address</name> |
| <value>0.0.0.0:50105</value> |
| <description> |
| The backup node http server address and port. |
| If the port is 0 then the server will start on a free port. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.replication.considerLoad</name> |
| <value>true</value> |
| <description>Decide if chooseTarget considers the target's load or not |
| </description> |
| </property> |
| <property> |
| <name>dfs.default.chunk.view.size</name> |
| <value>32768</value> |
| <description>The number of bytes to view for a file on the browser. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.du.reserved</name> |
| <value>0</value> |
| <description>Reserved space in bytes per volume. Always leave this much space free for non dfs use. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.name.dir</name> |
| <value>file://${hadoop.tmp.dir}/dfs/name</value> |
| <description>Determines where on the local filesystem the DFS name node |
| should store the name table(fsimage). If this is a comma-delimited list |
| of directories then the name table is replicated in all of the |
| directories, for redundancy. </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.fs-limits.max-component-length</name> |
| <value>0</value> |
| <description>Defines the maximum number of characters in each component |
| of a path. A value of 0 will disable the check.</description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.fs-limits.max-directory-items</name> |
| <value>0</value> |
| <description>Defines the maximum number of items that a directory may |
| contain. A value of 0 will disable the check.</description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.edits.dir</name> |
| <value>${dfs.namenode.name.dir}</value> |
| <description>Determines where on the local filesystem the DFS name node |
| should store the transaction (edits) file. If this is a comma-delimited list |
| of directories then the transaction file is replicated in all of the |
| directories, for redundancy. Default value is same as dfs.name.dir |
| </description> |
| </property> |
| <property> |
| <name>dfs.web.ugi</name> |
| <value>webuser,webgroup</value> |
| <description>The user account used by the web interface. |
| Syntax: USERNAME,GROUP1,GROUP2, ... |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.permissions.enabled</name> |
| <value>true</value> |
| <description> |
| If "true", enable permission checking in HDFS. |
| If "false", permission checking is turned off, |
| but all other behavior is unchanged. |
| Switching from one parameter value to the other does not change the mode, |
| owner or group of files or directories. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.permissions.superusergroup</name> |
| <value>supergroup</value> |
| <description>The name of the group of super-users.</description> |
| </property> |
| <!-- |
| <property> |
| <name>dfs.cluster.administrators</name> |
| <value>ACL for the admins</value> |
| <description>This configuration is used to control who can access the |
| default servlets in the namenode, etc. |
| </description> |
| </property> |
| --> |
| |
| <property> |
| <name>dfs.block.access.token.enable</name> |
| <value>false</value> |
| <description> |
| If "true", access tokens are used as capabilities for accessing datanodes. |
| If "false", no access tokens are checked on accessing datanodes. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.block.access.key.update.interval</name> |
| <value>600</value> |
| <description> |
| Interval in minutes at which namenode updates its access keys. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.block.access.token.lifetime</name> |
| <value>600</value> |
| <description>The lifetime of access tokens in minutes.</description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.data.dir</name> |
| <value>file://${hadoop.tmp.dir}/dfs/data</value> |
| <description>Determines where on the local filesystem an DFS data node |
| should store its blocks. If this is a comma-delimited |
| list of directories, then data will be stored in all named |
| directories, typically on different devices. |
| Directories that do not exist are ignored. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.data.dir.perm</name> |
| <value>700</value> |
| <description>Permissions for the directories on on the local filesystem where |
| the DFS data node store its blocks. The permissions can either be octal or |
| symbolic.</description> |
| </property> |
| |
| <property> |
| <name>dfs.replication</name> |
| <value>3</value> |
| <description>Default block replication. |
| The actual number of replications can be specified when the file is created. |
| The default is used if replication is not specified in create time. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.replication.max</name> |
| <value>512</value> |
| <description>Maximal block replication. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.replication.min</name> |
| <value>1</value> |
| <description>Minimal block replication. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.blocksize</name> |
| <value>67108864</value> |
| <description>The default block size for new files.</description> |
| </property> |
| |
| <property> |
| <name>dfs.client.block.write.retries</name> |
| <value>3</value> |
| <description>The number of retries for writing blocks to the data nodes, |
| before we signal failure to the application. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.client.block.write.replace-datanode-on-failure.enable</name> |
| <value>ture</value> |
| <description> |
| If there is a datanode/network failure in the write pipeline, |
| DFSClient will try to remove the failed datanode from the pipeline |
| and then continue writing with the remaining datanodes. As a result, |
| the number of datanodes in the pipeline is decreased. The feature is |
| to add new datanodes to the pipeline. |
| |
| This is a site-wise property to enable/disable the feature. |
| |
| See also dfs.client.block.write.replace-datanode-on-failure.policy |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.client.block.write.replace-datanode-on-failure.policy</name> |
| <value>DEFAULT</value> |
| <description> |
| This property is used only if the value of |
| dfs.client.block.write.replace-datanode-on-failure.enable is true. |
| |
| ALWAYS: always add a new datanode when an existing datanode is removed. |
| |
| NEVER: never add a new datanode. |
| |
| DEFAULT: |
| Let r be the replication number. |
| Let n be the number of existing datanodes. |
| Add a new datanode only if r is greater than or equal to 3 and either |
| (1) floor(r/2) is greater than or equal to n; or |
| (2) r is greater than n and the block is hflushed/appended. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.blockreport.intervalMsec</name> |
| <value>21600000</value> |
| <description>Determines block reporting interval in milliseconds.</description> |
| </property> |
| |
| <property> |
| <name>dfs.blockreport.initialDelay</name> <value>0</value> |
| <description>Delay for first block report in seconds.</description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.directoryscan.interval</name> |
| <value>21600</value> |
| <description>Interval in seconds for Datanode to scan data directories and |
| reconcile the difference between blocks in memory and on the disk. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.directoryscan.threads</name> |
| <value>1</value> |
| <description>How many threads should the threadpool used to compile reports |
| for volumes in parallel have. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.block.volume.choice.policy</name> |
| <value>org.apache.hadoop.hdfs.server.datanode.RoundRobinVolumesPolicy</value> |
| <description>The policy class to use to determine into which of the |
| datanode's available volumes a block must be written to. Default is a simple |
| round-robin policy that chooses volumes in a cyclic order. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.heartbeat.interval</name> |
| <value>3</value> |
| <description>Determines datanode heartbeat interval in seconds.</description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.handler.count</name> |
| <value>10</value> |
| <description>The number of server threads for the namenode.</description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.safemode.threshold-pct</name> |
| <value>0.999f</value> |
| <description> |
| Specifies the percentage of blocks that should satisfy |
| the minimal replication requirement defined by dfs.namenode.replication.min. |
| Values less than or equal to 0 mean not to wait for any particular |
| percentage of blocks before exiting safemode. |
| Values greater than 1 will make safe mode permanent. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.safemode.min.datanodes</name> |
| <value>0</value> |
| <description> |
| Specifies the number of datanodes that must be considered alive |
| before the name node exits safemode. |
| Values less than or equal to 0 mean not to take the number of live |
| datanodes into account when deciding whether to remain in safe mode |
| during startup. |
| Values greater than the number of datanodes in the cluster |
| will make safe mode permanent. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.safemode.extension</name> |
| <value>30000</value> |
| <description> |
| Determines extension of safe mode in milliseconds |
| after the threshold level is reached. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.balance.bandwidthPerSec</name> |
| <value>1048576</value> |
| <description> |
| Specifies the maximum amount of bandwidth that each datanode |
| can utilize for the balancing purpose in term of |
| the number of bytes per second. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.hosts</name> |
| <value></value> |
| <description>Names a file that contains a list of hosts that are |
| permitted to connect to the namenode. The full pathname of the file |
| must be specified. If the value is empty, all hosts are |
| permitted.</description> |
| </property> |
| |
| <property> |
| <name>dfs.hosts.exclude</name> |
| <value></value> |
| <description>Names a file that contains a list of hosts that are |
| not permitted to connect to the namenode. The full pathname of the |
| file must be specified. If the value is empty, no hosts are |
| excluded.</description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.max.objects</name> |
| <value>0</value> |
| <description>The maximum number of files, directories and blocks |
| dfs supports. A value of zero indicates no limit to the number |
| of objects that dfs supports. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.decommission.interval</name> |
| <value>30</value> |
| <description>Namenode periodicity in seconds to check if decommission is |
| complete.</description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.decommission.nodes.per.interval</name> |
| <value>5</value> |
| <description>The number of nodes namenode checks if decommission is complete |
| in each dfs.namenode.decommission.interval.</description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.replication.interval</name> |
| <value>3</value> |
| <description>The periodicity in seconds with which the namenode computes |
| repliaction work for datanodes. </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.accesstime.precision</name> |
| <value>3600000</value> |
| <description>The access time for HDFS file is precise upto this value. |
| The default value is 1 hour. Setting a value of 0 disables |
| access times for HDFS. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.plugins</name> |
| <value></value> |
| <description>Comma-separated list of datanode plug-ins to be activated. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.plugins</name> |
| <value></value> |
| <description>Comma-separated list of namenode plug-ins to be activated. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.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>dfs.bytes-per-checksum</name> |
| <value>512</value> |
| <description>The number of bytes per checksum. Must not be larger than |
| dfs.stream-buffer-size</description> |
| </property> |
| |
| <property> |
| <name>dfs.client-write-packet-size</name> |
| <value>65536</value> |
| <description>Packet size for clients to write</description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.checkpoint.dir</name> |
| <value>file://${hadoop.tmp.dir}/dfs/namesecondary</value> |
| <description>Determines where on the local filesystem the DFS secondary |
| name node should store the temporary images to merge. |
| If this is a comma-delimited list of directories then the image is |
| replicated in all of the directories for redundancy. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.checkpoint.edits.dir</name> |
| <value>${dfs.namenode.checkpoint.dir}</value> |
| <description>Determines where on the local filesystem the DFS secondary |
| name node should store the temporary edits to merge. |
| If this is a comma-delimited list of directoires then teh edits is |
| replicated in all of the directoires for redundancy. |
| Default value is same as dfs.namenode.checkpoint.dir |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.checkpoint.period</name> |
| <value>3600</value> |
| <description>The number of seconds between two periodic checkpoints. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.checkpoint.size</name> |
| <value>67108864</value> |
| <description>The size of the current edit log (in bytes) that triggers |
| a periodic checkpoint even if the dfs.namenode.checkpoint.period hasn't expired. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.delegation.key.update-interval</name> |
| <value>86400000</value> |
| <description>The update interval for master key for delegation tokens |
| in the namenode in milliseconds. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.delegation.token.max-lifetime</name> |
| <value>604800000</value> |
| <description>The maximum lifetime in milliseconds for which a delegation |
| token is valid. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.delegation.token.renew-interval</name> |
| <value>86400000</value> |
| <description>The renewal interval for delegation token in milliseconds. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.failed.volumes.tolerated</name> |
| <value>0</value> |
| <description>The number of volumes that are allowed to |
| fail before a datanode stops offering service. By default |
| any volume failure will cause a datanode to shutdown. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.image.compress</name> |
| <value>false</value> |
| <description>Should the dfs image be compressed? |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.image.compression.codec</name> |
| <value>org.apache.hadoop.io.compress.DefaultCodec</value> |
| <description>If the dfs image is compressed, how should they be compressed? |
| This has to be a codec defined in io.compression.codecs. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.image.transfer.bandwidthPerSec</name> |
| <value>0</value> |
| <description> |
| Specifies the maximum amount of bandwidth that can be utilized for image |
| transfer in term of the number of bytes per second. |
| A default value of 0 indicates that throttling is disabled. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.namenode.support.allow.format</name> |
| <value>true</value> |
| <description>Does HDFS namenode allow itself to be formatted? |
| You may consider setting this to false for any production |
| cluster, to avoid any possibility of formatting a running DFS. |
| </description> |
| </property> |
| |
| <property> |
| <name>dfs.datanode.max.transfer.threads</name> |
| <value>4096</value> |
| <description> |
| Specifies the maximum number of threads to use for transferring data |
| in and out of the DN. |
| </description> |
| </property> |
| |
| </configuration> |