big-data/hadoop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3d26717777
hadoop/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml

4351 lines
144 KiB
XML
Raw Blame History

<?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 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.rpc-address</name>
<value></value>
<description>
RPC address that handles all clients requests. In the case of HA/Federation where multiple namenodes exist,
the name service id is added to the name e.g. dfs.namenode.rpc-address.ns1
dfs.namenode.rpc-address.EXAMPLENAMESERVICE
The value of this property will take the form of nn-host1:rpc-port. The NameNode's default RPC port is 9820.
</description>
</property>
<property>
<name>dfs.namenode.rpc-bind-host</name>
<value></value>
<description>
The actual address the RPC server will bind to. If this optional address is
set, it overrides only the hostname portion of dfs.namenode.rpc-address.
It can also be specified per name node or name service for HA/Federation.
This is useful for making the name node listen on all interfaces by
setting it to 0.0.0.0.
</description>
</property>
<property>
<name>dfs.namenode.servicerpc-address</name>
<value></value>
<description>
RPC address for HDFS Services communication. BackupNode, Datanodes and all other services should be
connecting to this address if it is configured. In the case of HA/Federation where multiple namenodes exist,
the name service id is added to the name e.g. dfs.namenode.servicerpc-address.ns1
dfs.namenode.rpc-address.EXAMPLENAMESERVICE
The value of this property will take the form of nn-host1:rpc-port.
If the value of this property is unset the value of dfs.namenode.rpc-address will be used as the default.
</description>
</property>
<property>
<name>dfs.namenode.servicerpc-bind-host</name>
<value></value>
<description>
The actual address the service RPC server will bind to. If this optional address is
set, it overrides only the hostname portion of dfs.namenode.servicerpc-address.
It can also be specified per name node or name service for HA/Federation.
This is useful for making the name node listen on all interfaces by
setting it to 0.0.0.0.
</description>
</property>
<property>
<name>dfs.namenode.lifeline.rpc-address</name>
<value></value>
<description>
NameNode RPC lifeline address. This is an optional separate RPC address
that can be used to isolate health checks and liveness to protect against
resource exhaustion in the main RPC handler pool. In the case of
HA/Federation where multiple NameNodes exist, the name service ID is added
to the name e.g. dfs.namenode.lifeline.rpc-address.ns1. The value of this
property will take the form of nn-host1:rpc-port. If this property is not
defined, then the NameNode will not start a lifeline RPC server. By
default, the property is not defined.
</description>
</property>
<property>
<name>dfs.namenode.lifeline.rpc-bind-host</name>
<value></value>
<description>
The actual address the lifeline RPC server will bind to. If this optional
address is set, it overrides only the hostname portion of
dfs.namenode.lifeline.rpc-address. It can also be specified per name node
or name service for HA/Federation. This is useful for making the name node
listen on all interfaces by setting it to 0.0.0.0.
</description>
</property>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>0.0.0.0:9868</value>
<description>
The secondary namenode http server address and port.
</description>
</property>
<property>
<name>dfs.namenode.secondary.https-address</name>
<value>0.0.0.0:9869</value>
<description>
The secondary namenode HTTPS server address and port.
</description>
</property>
<property>
<name>dfs.datanode.address</name>
<value>0.0.0.0:9866</value>
<description>
The datanode server address and port for data transfer.
</description>
</property>
<property>
<name>dfs.datanode.http.address</name>
<value>0.0.0.0:9864</value>
<description>
The datanode http server address and port.
</description>
</property>
<property>
<name>dfs.datanode.ipc.address</name>
<value>0.0.0.0:9867</value>
<description>
The datanode ipc server address and port.
</description>
</property>
<property>
<name>dfs.datanode.handler.count</name>
<value>10</value>
<description>The number of server threads for the datanode.</description>
</property>
<property>
<name>dfs.namenode.http-address</name>
<value>0.0.0.0:9870</value>
<description>
The address and the base port where the dfs namenode web ui will listen on.
</description>
</property>
<property>
<name>dfs.namenode.http-bind-host</name>
<value></value>
<description>
The actual address the HTTP server will bind to. If this optional address
is set, it overrides only the hostname portion of dfs.namenode.http-address.
It can also be specified per name node or name service for HA/Federation.
This is useful for making the name node HTTP server listen on all
interfaces by setting it to 0.0.0.0.
</description>
</property>
<property>
<name>dfs.namenode.heartbeat.recheck-interval</name>
<value>300000</value>
<description>
This time decides the interval to check for expired datanodes.
With this value and dfs.heartbeat.interval, the interval of
deciding the datanode is stale or not is also calculated.
The unit of this configuration is millisecond.
</description>
</property>
<property>
<name>dfs.http.policy</name>
<value>HTTP_ONLY</value>
<description>Decide if HTTPS(SSL) is supported on HDFS
This configures the HTTP endpoint for HDFS daemons:
The following values are supported:
- HTTP_ONLY : Service is provided only on http
- HTTPS_ONLY : Service is provided only on https
- HTTP_AND_HTTPS : Service is provided both on http and https
</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.client.cached.conn.retry</name>
<value>3</value>
<description>The number of times the HDFS client will pull a socket from the
cache. Once this number is exceeded, the client will try to create a new
socket.
</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>0.0.0.0:9865</value>
<description>The datanode secure http server address and port.</description>
</property>
<property>
<name>dfs.namenode.https-address</name>
<value>0.0.0.0:9871</value>
<description>The namenode secure http server address and port.</description>
</property>
<property>
<name>dfs.namenode.https-bind-host</name>
<value></value>
<description>
The actual address the HTTPS server will bind to. If this optional address
is set, it overrides only the hostname portion of dfs.namenode.https-address.
It can also be specified per name node or name service for HA/Federation.
This is useful for making the name node HTTPS server listen on all
interfaces by setting it to 0.0.0.0.
</description>
</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. e.g. eth2. This setting may be required for some
multi-homed nodes where the DataNodes are assigned multiple hostnames
and it is desirable for the DataNodes to use a non-default hostname.
Prefer using hadoop.security.dns.interface over
dfs.datanode.dns.interface.
</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 its own host name.
Prefer using hadoop.security.dns.nameserver over
dfs.datanode.dns.nameserver.
</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.namenode.replication.considerLoad.factor</name>
<value>2.0</value>
<description>The factor by which a node's load can exceed the average
before being rejected for writes, only if considerLoad is true.
</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.
Specific storage type based reservation is also supported. The property can be followed with
corresponding storage types ([ssd]/[disk]/[archive]/[ram_disk]) for cluster with heterogeneous storage.
For example, reserved space for RAM_DISK storage can be configured using property
'dfs.datanode.du.reserved.ram_disk'. If specific storage type reservation is not configured
then dfs.datanode.du.reserved will be used.
</description>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file://${hadoop.tmp.dir}/dfs/name</value>
<description>Determines where on the local filesystem the DFS name node
should store the name table(fsimage). If this is a comma-delimited list
of directories then the name table is replicated in all of the
directories, for redundancy. </description>
</property>
<property>
<name>dfs.namenode.name.dir.restore</name>
<value>false</value>
<description>Set to true to enable NameNode to attempt recovering a
previously failed dfs.namenode.name.dir. When enabled, a recovery of any
failed directory is attempted during checkpoint.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.max-component-length</name>
<value>255</value>
<description>Defines the maximum number of bytes in UTF-8 encoding in each
component of a path. A value of 0 will disable the check.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.max-directory-items</name>
<value>1048576</value>
<description>Defines the maximum number of items that a directory may
contain. Cannot set the property to a value less than 1 or more than
6400000.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.min-block-size</name>
<value>1048576</value>
<description>Minimum block size in bytes, enforced by the Namenode at create
time. This prevents the accidental creation of files with tiny block
sizes (and thus many blocks), which can degrade
performance.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.max-blocks-per-file</name>
<value>1048576</value>
<description>Maximum number of blocks per file, enforced by the Namenode on
write. This prevents the creation of extremely large files which can
degrade performance.</description>
</property>
<property>
<name>dfs.namenode.edits.dir</name>
<value>${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.namenode.name.dir
</description>
</property>
<property>
<name>dfs.namenode.edits.dir.required</name>
<value></value>
<description>This should be a subset of dfs.namenode.edits.dir,
to ensure that the transaction (edits) file
in these places is always up-to-date.
</description>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value></value>
<description>A directory on shared storage between the multiple namenodes
in an HA cluster. This directory will be written by the active and read
by the standby in order to keep the namespaces synchronized. This directory
does not need to be listed in dfs.namenode.edits.dir above. It should be
left empty in a non-HA cluster.
</description>
</property>
<property>
<name>dfs.namenode.edits.journal-plugin.qjournal</name>
<value>org.apache.hadoop.hdfs.qjournal.client.QuorumJournalManager</value>
</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.
The value should be a single group name.
</description>
</property>
<property>
<name>dfs.cluster.administrators</name>
<value></value>
<description>ACL for the admins, this configuration is used to control
who can access the default servlets in the namenode, etc. The value
should be a comma separated list of users and groups. The user list
comes first and is separated by a space followed by the group list,
e.g. "user1,user2 group1,group2". Both users and groups are optional,
so "user1", " group1", "", "user1 group1", "user1,user2 group1,group2"
are all valid (note the leading space in " group1"). '*' grants access
to all users and groups, e.g. '*', '* ' and ' *' are all valid.
</description>
</property>
<property>
<name>dfs.namenode.acls.enabled</name>
<value>false</value>
<description>
Set to true to enable support for HDFS ACLs (Access Control Lists). By
default, ACLs are disabled. When ACLs are disabled, the NameNode rejects
all RPCs related to setting or getting ACLs.
</description>
</property>
<property>
<name>dfs.namenode.posix.acl.inheritance.enabled</name>
<value>false</value>
<description>
Set to true to enable POSIX style ACL inheritance. When it is enabled
and the create request comes from a compatible client, the NameNode
will apply default ACLs from the parent directory to the create mode
and ignore the client umask. If no default ACL found, it will apply the
client umask.
</description>
</property>
<property>
<name>dfs.namenode.lazypersist.file.scrub.interval.sec</name>
<value>300</value>
<description>
The NameNode periodically scans the namespace for LazyPersist files with
missing blocks and unlinks them from the namespace. This configuration key
controls the interval between successive scans. Set it to a negative value
to disable this behavior.
</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. The directories should be tagged
with corresponding storage types ([SSD]/[DISK]/[ARCHIVE]/[RAM_DISK]) for HDFS
storage policies. The default storage type will be DISK if the directory does
not have a storage type tagged explicitly. Directories that do not exist will
be created if local filesystem permission allows.
</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.namenode.maintenance.replication.min</name>
<value>1</value>
<description>Minimal live block replication in existence of maintenance mode.
</description>
</property>
<property>
<name>dfs.namenode.safemode.replication.min</name>
<value></value>
<description>
a separate minimum replication factor for calculating safe block count.
This is an expert level setting.
Setting this lower than the dfs.namenode.replication.min
is not recommend and/or dangerous for production setups.
When it's not set it takes value from dfs.namenode.replication.min
</description>
</property>
<property>
<name>dfs.blocksize</name>
<value>134217728</value>
<description>
The default block size for new files, in bytes.
You can use the following suffix (case insensitive):
k(kilo), m(mega), g(giga), t(tera), p(peta), e(exa) to specify the size (such as 128k, 512m, 1g, etc.),
Or provide complete size in bytes (such as 134217728 for 128 MB).
</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>true</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-wide property to enable/disable the feature.
When the cluster size is extremely small, e.g. 3 nodes or less, cluster
administrators may want to set the policy to NEVER in the default
configuration file or disable this feature. Otherwise, users may
experience an unusually high rate of pipeline failures since it is
impossible to find new datanodes for replacement.
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.client.block.write.replace-datanode-on-failure.best-effort</name>
<value>false</value>
<description>
This property is used only if the value of
dfs.client.block.write.replace-datanode-on-failure.enable is true.
Best effort means that the client will try to replace a failed datanode
in write pipeline (provided that the policy is satisfied), however, it
continues the write operation in case that the datanode replacement also
fails.
Suppose the datanode replacement fails.
false: An exception should be thrown so that the write will fail.
true : The write should be resumed with the remaining datandoes.
Note that setting this property to true allows writing to a pipeline
with a smaller number of datanodes. As a result, it increases the
probability of data loss.
</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>0s</value>
<description>
Delay for first block report in seconds. Support multiple time unit
suffix(case insensitive), as described in dfs.heartbeat.interval.
</description>
</property>
<property>
<name>dfs.blockreport.split.threshold</name>
<value>1000000</value>
<description>If the number of blocks on the DataNode is below this
threshold then it will send block reports for all Storage Directories
in a single message.
If the number of blocks exceeds this threshold then the DataNode will
send block reports for each Storage Directory in separate messages.
Set to zero to always split.
</description>
</property>
<property>
<name>dfs.namenode.max.full.block.report.leases</name>
<value>6</value>
<description>The maximum number of leases for full block reports that the
NameNode will issue at any given time. This prevents the NameNode from
being flooded with full block reports that use up all the RPC handler
threads. This number should never be more than the number of RPC handler
threads or less than 1.
</description>
</property>
<property>
<name>dfs.namenode.full.block.report.lease.length.ms</name>
<value>300000</value>
<description>
The number of milliseconds that the NameNode will wait before invalidating
a full block report lease. This prevents a crashed DataNode from
permanently using up a full block report lease.
</description>
</property>
<property>
<name>dfs.datanode.directoryscan.interval</name>
<value>21600s</value>
<description>Interval in seconds for Datanode to scan data directories and
reconcile the difference between blocks in memory and on the disk.
Support multiple time unit suffix(case insensitive), as described
in dfs.heartbeat.interval.
</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.directoryscan.throttle.limit.ms.per.sec</name>
<value>1000</value>
<description>The report compilation threads are limited to only running for
a given number of milliseconds per second, as configured by the
property. The limit is taken per thread, not in aggregate, e.g. setting
a limit of 100ms for 4 compiler threads will result in each thread being
limited to 100ms, not 25ms.
Note that the throttle does not interrupt the report compiler threads, so the
actual running time of the threads per second will typically be somewhat
higher than the throttle limit, usually by no more than 20%.
Setting this limit to 1000 disables compiler thread throttling. Only
values between 1 and 1000 are valid. Setting an invalid value will result
in the throttle being disabled and an error message being logged. 1000 is
the default setting.
</description>
</property>
<property>
<name>dfs.heartbeat.interval</name>
<value>3s</value>
<description>
Determines datanode heartbeat interval in seconds.
Can use the following suffix (case insensitive):
ms(millis), s(sec), m(min), h(hour), d(day)
to specify the time (such as 2s, 2m, 1h, etc.).
Or provide complete number in seconds (such as 30 for 30 seconds).
</description>
</property>
<property>
<name>dfs.datanode.lifeline.interval.seconds</name>
<value></value>
<description>
Sets the interval in seconds between sending DataNode Lifeline Protocol
messages from the DataNode to the NameNode. The value must be greater than
the value of dfs.heartbeat.interval. If this property is not defined, then
the default behavior is to calculate the interval as 3x the value of
dfs.heartbeat.interval. Note that normal heartbeat processing may cause the
DataNode to postpone sending lifeline messages if they are not required.
Under normal operations with speedy heartbeat processing, it is possible
that no lifeline messages will need to be sent at all. This property has no
effect if dfs.namenode.lifeline.rpc-address is not defined.
</description>
</property>
<property>
<name>dfs.namenode.handler.count</name>
<value>10</value>
<description>The number of Namenode RPC server threads that listen to
requests from clients.
If dfs.namenode.servicerpc-address is not configured then
Namenode RPC server threads listen to requests from all nodes.
</description>
</property>
<property>
<name>dfs.namenode.service.handler.count</name>
<value>10</value>
<description>The number of Namenode RPC server threads that listen to
requests from DataNodes and from all other non-client nodes.
dfs.namenode.service.handler.count will be valid only if
dfs.namenode.servicerpc-address is configured.
</description>
</property>
<property>
<name>dfs.namenode.lifeline.handler.ratio</name>
<value>0.10</value>
<description>
A ratio applied to the value of dfs.namenode.handler.count, which then
provides the number of RPC server threads the NameNode runs for handling the
lifeline RPC server. For example, if dfs.namenode.handler.count is 100, and
dfs.namenode.lifeline.handler.factor is 0.10, then the NameNode starts
100 * 0.10 = 10 threads for handling the lifeline RPC server. It is common
to tune the value of dfs.namenode.handler.count as a function of the number
of DataNodes in a cluster. Using this property allows for the lifeline RPC
server handler threads to be tuned automatically without needing to touch a
separate property. Lifeline message processing is lightweight, so it is
expected to require many fewer threads than the main NameNode RPC server.
This property is not used if dfs.namenode.lifeline.handler.count is defined,
which sets an absolute thread count. This property has no effect if
dfs.namenode.lifeline.rpc-address is not defined.
</description>
</property>
<property>
<name>dfs.namenode.lifeline.handler.count</name>
<value></value>
<description>
Sets an absolute number of RPC server threads the NameNode runs for handling
the DataNode Lifeline Protocol and HA health check requests from ZKFC. If
this property is defined, then it overrides the behavior of
dfs.namenode.lifeline.handler.ratio. By default, it is not defined. This
property has no effect if dfs.namenode.lifeline.rpc-address is not defined.
</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. Support multiple time unit suffix (case insensitive), as
described in dfs.heartbeat.interval.
</description>
</property>
<property>
<name>dfs.namenode.resource.check.interval</name>
<value>5000</value>
<description>
The interval in milliseconds at which the NameNode resource checker runs.
The checker calculates the number of the NameNode storage volumes whose
available spaces are more than dfs.namenode.resource.du.reserved, and
enters safemode if the number becomes lower than the minimum value
specified by dfs.namenode.resource.checked.volumes.minimum.
</description>
</property>
<property>
<name>dfs.namenode.resource.du.reserved</name>
<value>104857600</value>
<description>
The amount of space to reserve/require for a NameNode storage directory
in bytes. The default is 100MB.
</description>
</property>
<property>
<name>dfs.namenode.resource.checked.volumes</name>
<value></value>
<description>
A list of local directories for the NameNode resource checker to check in
addition to the local edits directories.
</description>
</property>
<property>
<name>dfs.namenode.resource.checked.volumes.minimum</name>
<value>1</value>
<description>
The minimum number of redundant NameNode storage volumes required.
</description>
</property>
<property>
<name>dfs.datanode.balance.bandwidthPerSec</name>
<value>10m</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. You can use the following
suffix (case insensitive):
k(kilo), m(mega), g(giga), t(tera), p(peta), e(exa)to specify the size
(such as 128k, 512m, 1g, etc.).
Or provide complete size in bytes (such as 134217728 for 128 MB).
</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.datanode.registration.ip-hostname-check</name>
<value>true</value>
<description>
If true (the default), then the namenode requires that a connecting
datanode's address must be resolved to a hostname. If necessary, a reverse
DNS lookup is performed. All attempts to register a datanode from an
unresolvable address are rejected.
It is recommended that this setting be left on to prevent accidental
registration of datanodes listed by hostname in the excludes file during a
DNS outage. Only set this to false in environments where there is no
infrastructure to support reverse DNS lookup.
</description>
</property>
<property>
<name>dfs.namenode.decommission.interval</name>
<value>30s</value>
<description>Namenode periodicity in seconds to check if decommission is
complete. Support multiple time unit suffix(case insensitive), as described
in dfs.heartbeat.interval.
</description>
</property>
<property>
<name>dfs.namenode.decommission.blocks.per.interval</name>
<value>500000</value>
<description>The approximate number of blocks to process per
decommission interval, as defined in dfs.namenode.decommission.interval.
</description>
</property>
<property>
<name>dfs.namenode.decommission.max.concurrent.tracked.nodes</name>
<value>100</value>
<description>
The maximum number of decommission-in-progress datanodes nodes that will be
tracked at one time by the namenode. Tracking a decommission-in-progress
datanode consumes additional NN memory proportional to the number of blocks
on the datnode. Having a conservative limit reduces the potential impact
of decomissioning a large number of nodes at once.
A value of 0 means no limit will be enforced.
</description>
</property>
<property>
<name>dfs.namenode.replication.interval</name>
<value>3s</value>
<description>The periodicity in seconds with which the namenode computes
replication work for datanodes. Support multiple time unit suffix(case insensitive),
as described in dfs.heartbeat.interval.
</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.namenode.block-placement-policy.default.prefer-local-node</name>
<value>true</value>
<description>Controls how the default block placement policy places
the first replica of a block. When true, it will prefer the node where
the client is running. When false, it will prefer a node in the same rack
as the client. Setting to false avoids situations where entire copies of
large files end up on a single node, thus creating hotspots.
</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.client.write.exclude.nodes.cache.expiry.interval.millis</name>
<value>600000</value>
<description>The maximum period to keep a DN in the excluded nodes list
at a client. After this period, in milliseconds, the previously excluded node(s) will
be removed automatically from the cache and will be considered good for block allocations
again. Useful to lower or raise in situations where you keep a file open for very long
periods (such as a Write-Ahead-Log (WAL) file) to make the writer tolerant to cluster maintenance
restarts. Defaults to 10 minutes.</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 directories then the edits is
replicated in all of the directories for redundancy.
Default value is same as dfs.namenode.checkpoint.dir
</description>
</property>
<property>
<name>dfs.namenode.checkpoint.period</name>
<value>3600s</value>
<description>
The number of seconds between two periodic checkpoints.
Support multiple time unit suffix(case insensitive), as described
in dfs.heartbeat.interval.
</description>
</property>
<property>
<name>dfs.namenode.checkpoint.txns</name>
<value>1000000</value>
<description>The Secondary NameNode or CheckpointNode will create a checkpoint
of the namespace every 'dfs.namenode.checkpoint.txns' transactions, regardless
of whether 'dfs.namenode.checkpoint.period' has expired.
</description>
</property>
<property>
<name>dfs.namenode.checkpoint.check.period</name>
<value>60s</value>
<description>The SecondaryNameNode and CheckpointNode will poll the NameNode
every 'dfs.namenode.checkpoint.check.period' seconds to query the number
of uncheckpointed transactions. Support multiple time unit suffix(case insensitive),
as described in dfs.heartbeat.interval.
</description>
</property>
<property>
<name>dfs.namenode.checkpoint.max-retries</name>
<value>3</value>
<description>The SecondaryNameNode retries failed checkpointing. If the
failure occurs while loading fsimage or replaying edits, the number of
retries is limited by this variable.
</description>
</property>
<property>
<name>dfs.namenode.checkpoint.check.quiet-multiplier</name>
<value>1.5</value>
<description>
Used to calculate the amount of time between retries when in the 'quiet' period
for creating checkpoints (active namenode already has an up-to-date image from another
checkpointer), so we wait a multiplier of the dfs.namenode.checkpoint.check.period before
retrying the checkpoint because another node likely is already managing the checkpoints,
allowing us to save bandwidth to transfer checkpoints that don't need to be used.
</description>
</property>
<property>
<name>dfs.namenode.num.checkpoints.retained</name>
<value>2</value>
<description>The number of image checkpoint files (fsimage_*) that will be retained by
the NameNode and Secondary NameNode in their storage directories. All edit
logs (stored on edits_* files) necessary to recover an up-to-date namespace from the oldest retained
checkpoint will also be retained.
</description>
</property>
<property>
<name>dfs.namenode.num.extra.edits.retained</name>
<value>1000000</value>
<description>The number of extra transactions which should be retained
beyond what is minimally necessary for a NN restart.
It does not translate directly to file's age, or the number of files kept,
but to the number of transactions (here "edits" means transactions).
One edit file may contain several transactions (edits).
During checkpoint, NameNode will identify the total number of edits to retain as extra by
checking the latest checkpoint transaction value, subtracted by the value of this property.
Then, it scans edits files to identify the older ones that don't include the computed range of
retained transactions that are to be kept around, and purges them subsequently.
The retainment can be useful for audit purposes or for an HA setup where a remote Standby Node may have
been offline for some time and need to have a longer backlog of retained
edits in order to start again.
Typically each edit is on the order of a few hundred bytes, so the default
of 1 million edits should be on the order of hundreds of MBs or low GBs.
NOTE: Fewer extra edits may be retained than value specified for this setting
if doing so would mean that more segments would be retained than the number
configured by dfs.namenode.max.extra.edits.segments.retained.
</description>
</property>
<property>
<name>dfs.namenode.max.extra.edits.segments.retained</name>
<value>10000</value>
<description>The maximum number of extra edit log segments which should be retained
beyond what is minimally necessary for a NN restart. When used in conjunction with
dfs.namenode.num.extra.edits.retained, this configuration property serves to cap
the number of extra edits files to a reasonable value.
</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.timeout</name>
<value>60000</value>
<description>
Socket timeout for image transfer in milliseconds. This timeout and the related
dfs.image.transfer.bandwidthPerSec parameter should be configured such
that normal image transfer can complete successfully.
This timeout prevents client hangs when the sender fails during
image transfer. This is socket timeout during image transfer.
</description>
</property>
<property>
<name>dfs.image.transfer.bandwidthPerSec</name>
<value>0</value>
<description>
Maximum bandwidth used for regular image transfers (instead of
bootstrapping the standby namenode), in bytes per second.
This can help keep normal namenode operations responsive during
checkpointing. The maximum bandwidth and timeout in
dfs.image.transfer.timeout should be set such that normal image
transfers can complete successfully.
A default value of 0 indicates that throttling is disabled.
The maximum bandwidth used for bootstrapping standby namenode is
configured with dfs.image.transfer-bootstrap-standby.bandwidthPerSec.
</description>
</property>
<property>
<name>dfs.image.transfer-bootstrap-standby.bandwidthPerSec</name>
<value>0</value>
<description>
Maximum bandwidth used for transferring image to bootstrap standby
namenode, in bytes per second.
A default value of 0 indicates that throttling is disabled. This default
value should be used in most cases, to ensure timely HA operations.
The maximum bandwidth used for regular image transfers is configured
with dfs.image.transfer.bandwidthPerSec.
</description>
</property>
<property>
<name>dfs.image.transfer.chunksize</name>
<value>65536</value>
<description>
Chunksize in bytes to upload the checkpoint.
Chunked streaming is used to avoid internal buffering of contents
of image file of huge size.
</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>
<property>
<name>dfs.datanode.scan.period.hours</name>
<value>504</value>
<description>
If this is positive, the DataNode will not scan any
individual block more than once in the specified scan period.
If this is negative, the block scanner is disabled.
If this is set to zero, then the default value of 504 hours
or 3 weeks is used. Prior versions of HDFS incorrectly documented
that setting this key to zero will disable the block scanner.
</description>
</property>
<property>
<name>dfs.block.scanner.volume.bytes.per.second</name>
<value>1048576</value>
<description>
If this is 0, the DataNode's block scanner will be disabled. If this
is positive, this is the number of bytes per second that the DataNode's
block scanner will try to scan from each volume.
</description>
</property>
<property>
<name>dfs.datanode.readahead.bytes</name>
<value>4194304</value>
<description>
While reading block files, if the Hadoop native libraries are available,
the datanode can use the posix_fadvise system call to explicitly
page data into the operating system buffer cache ahead of the current
reader's position. This can improve performance especially when
disks are highly contended.
This configuration specifies the number of bytes ahead of the current
read position which the datanode will attempt to read ahead. This
feature may be disabled by configuring this property to 0.
If the native libraries are not available, this configuration has no
effect.
</description>
</property>
<property>
<name>dfs.datanode.drop.cache.behind.reads</name>
<value>false</value>
<description>
In some workloads, the data read from HDFS is known to be significantly
large enough that it is unlikely to be useful to cache it in the
operating system buffer cache. In this case, the DataNode may be
configured to automatically purge all data from the buffer cache
after it is delivered to the client. This behavior is automatically
disabled for workloads which read only short sections of a block
(e.g HBase random-IO workloads).
This may improve performance for some workloads by freeing buffer
cache space usage for more cacheable data.
If the Hadoop native libraries are not available, this configuration
has no effect.
</description>
</property>
<property>
<name>dfs.datanode.drop.cache.behind.writes</name>
<value>false</value>
<description>
In some workloads, the data written to HDFS is known to be significantly
large enough that it is unlikely to be useful to cache it in the
operating system buffer cache. In this case, the DataNode may be
configured to automatically purge all data from the buffer cache
after it is written to disk.
This may improve performance for some workloads by freeing buffer
cache space usage for more cacheable data.
If the Hadoop native libraries are not available, this configuration
has no effect.
</description>
</property>
<property>
<name>dfs.datanode.sync.behind.writes</name>
<value>false</value>
<description>
If this configuration is enabled, the datanode will instruct the
operating system to enqueue all written data to the disk immediately
after it is written. This differs from the usual OS policy which
may wait for up to 30 seconds before triggering writeback.
This may improve performance for some workloads by smoothing the
IO profile for data written to disk.
If the Hadoop native libraries are not available, this configuration
has no effect.
</description>
</property>
<property>
<name>dfs.client.failover.max.attempts</name>
<value>15</value>
<description>
Expert only. The number of client failover attempts that should be
made before the failover is considered failed.
</description>
</property>
<property>
<name>dfs.client.failover.sleep.base.millis</name>
<value>500</value>
<description>
Expert only. The time to wait, in milliseconds, between failover
attempts increases exponentially as a function of the number of
attempts made so far, with a random factor of +/- 50%. This option
specifies the base value used in the failover calculation. The
first failover will retry immediately. The 2nd failover attempt
will delay at least dfs.client.failover.sleep.base.millis
milliseconds. And so on.
</description>
</property>
<property>
<name>dfs.client.failover.sleep.max.millis</name>
<value>15000</value>
<description>
Expert only. The time to wait, in milliseconds, between failover
attempts increases exponentially as a function of the number of
attempts made so far, with a random factor of +/- 50%. This option
specifies the maximum value to wait between failovers.
Specifically, the time between two failover attempts will not
exceed +/- 50% of dfs.client.failover.sleep.max.millis
milliseconds.
</description>
</property>
<property>
<name>dfs.client.failover.connection.retries</name>
<value>0</value>
<description>
Expert only. Indicates the number of retries a failover IPC client
will make to establish a server connection.
</description>
</property>
<property>
<name>dfs.client.failover.connection.retries.on.timeouts</name>
<value>0</value>
<description>
Expert only. The number of retry attempts a failover IPC client
will make on socket timeout when establishing a server connection.
</description>
</property>
<property>
<name>dfs.client.datanode-restart.timeout</name>
<value>30s</value>
<description>
Expert only. The time to wait, in seconds, from reception of an
datanode shutdown notification for quick restart, until declaring
the datanode dead and invoking the normal recovery mechanisms.
The notification is sent by a datanode when it is being shutdown
using the shutdownDatanode admin command with the upgrade option.
Support multiple time unit suffix(case insensitive), as described
in dfs.heartbeat.interval.
</description>
</property>
<property>
<name>dfs.nameservices</name>
<value></value>
<description>
Comma-separated list of nameservices.
</description>
</property>
<property>
<name>dfs.nameservice.id</name>
<value></value>
<description>
The ID of this nameservice. If the nameservice ID is not
configured or more than one nameservice is configured for
dfs.nameservices it is determined automatically by
matching the local node's address with the configured address.
</description>
</property>
<property>
<name>dfs.internal.nameservices</name>
<value></value>
<description>
Comma-separated list of nameservices that belong to this cluster.
Datanode will report to all the nameservices in this list. By default
this is set to the value of dfs.nameservices.
</description>
</property>
<property>
<name>dfs.ha.namenodes.EXAMPLENAMESERVICE</name>
<value></value>
<description>
The prefix for a given nameservice, contains a comma-separated
list of namenodes for a given nameservice (eg EXAMPLENAMESERVICE).
Unique identifiers for each NameNode in the nameservice, delimited by
commas. This will be used by DataNodes to determine all the NameNodes
in the cluster. For example, if you used “mycluster” as the nameservice
ID previously, and you wanted to use “nn1” and “nn2” as the individual
IDs of the NameNodes, you would configure a property
dfs.ha.namenodes.mycluster, and its value "nn1,nn2".
</description>
</property>
<property>
<name>dfs.ha.namenode.id</name>
<value></value>
<description>
The ID of this namenode. If the namenode ID is not configured it
is determined automatically by matching the local node's address
with the configured address.
</description>
</property>
<property>
<name>dfs.ha.log-roll.period</name>
<value>120s</value>
<description>
How often, in seconds, the StandbyNode should ask the active to
roll edit logs. Since the StandbyNode only reads from finalized
log segments, the StandbyNode will only be as up-to-date as how
often the logs are rolled. Note that failover triggers a log roll
so the StandbyNode will be up to date before it becomes active.
Support multiple time unit suffix(case insensitive), as described
in dfs.heartbeat.interval.
</description>
</property>
<property>
<name>dfs.ha.tail-edits.period</name>
<value>60s</value>
<description>
How often, in seconds, the StandbyNode should check for new
finalized log segments in the shared edits log.
Support multiple time unit suffix(case insensitive), as described
in dfs.heartbeat.interval.
</description>
</property>
<property>
<name>dfs.ha.tail-edits.namenode-retries</name>
<value>3</value>
<description>
Number of retries to use when contacting the namenode when tailing the log.
</description>
</property>
<property>
<name>dfs.ha.tail-edits.rolledits.timeout</name>
<value>60</value>
<description>The timeout in seconds of calling rollEdits RPC on Active NN.
</description>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>false</value>
<description>
Whether automatic failover is enabled. See the HDFS High
Availability documentation for details on automatic HA
configuration.
</description>
</property>
<property>
<name>dfs.client.use.datanode.hostname</name>
<value>false</value>
<description>Whether clients should use datanode hostnames when
connecting to datanodes.
</description>
</property>
<property>
<name>dfs.datanode.use.datanode.hostname</name>
<value>false</value>
<description>Whether datanodes should use datanode hostnames when
connecting to other datanodes for data transfer.
</description>
</property>
<property>
<name>dfs.client.local.interfaces</name>
<value></value>
<description>A comma separated list of network interface names to use
for data transfer between the client and datanodes. When creating
a connection to read from or write to a datanode, the client
chooses one of the specified interfaces at random and binds its
socket to the IP of that interface. Individual names may be
specified as either an interface name (eg "eth0"), a subinterface
name (eg "eth0:0"), or an IP address (which may be specified using
CIDR notation to match a range of IPs).
</description>
</property>
<property>
<name>dfs.datanode.shared.file.descriptor.paths</name>
<value>/dev/shm,/tmp</value>
<description>
A comma-separated list of paths to use when creating file descriptors that
will be shared between the DataNode and the DFSClient. Typically we use
/dev/shm, so that the file descriptors will not be written to disk.
Systems that don't have /dev/shm will fall back to /tmp by default.
</description>
</property>
<property>
<name>dfs.short.circuit.shared.memory.watcher.interrupt.check.ms</name>
<value>60000</value>
<description>
The length of time in milliseconds that the short-circuit shared memory
watcher will go between checking for java interruptions sent from other
threads. This is provided mainly for unit tests.
</description>
</property>
<property>
<name>dfs.namenode.kerberos.principal</name>
<value></value>
<description>
The NameNode service principal. This is typically set to
nn/_HOST@REALM.TLD. Each NameNode will substitute _HOST with its
own fully qualified hostname at startup. The _HOST placeholder
allows using the same configuration setting on both NameNodes
in an HA setup.
</description>
</property>
<property>
<name>dfs.namenode.keytab.file</name>
<value></value>
<description>
The keytab file used by each NameNode daemon to login as its
service principal. The principal name is configured with
dfs.namenode.kerberos.principal.
</description>
</property>
<property>
<name>dfs.datanode.kerberos.principal</name>
<value></value>
<description>
The DataNode service principal. This is typically set to
dn/_HOST@REALM.TLD. Each DataNode will substitute _HOST with its
own fully qualified hostname at startup. The _HOST placeholder
allows using the same configuration setting on all DataNodes.
</description>
</property>
<property>
<name>dfs.datanode.keytab.file</name>
<value></value>
<description>
The keytab file used by each DataNode daemon to login as its
service principal. The principal name is configured with
dfs.datanode.kerberos.principal.
</description>
</property>
<property>
<name>dfs.journalnode.kerberos.principal</name>
<value></value>
<description>
The JournalNode service principal. This is typically set to
jn/_HOST@REALM.TLD. Each JournalNode will substitute _HOST with its
own fully qualified hostname at startup. The _HOST placeholder
allows using the same configuration setting on all JournalNodes.
</description>
</property>
<property>
<name>dfs.journalnode.keytab.file</name>
<value></value>
<description>
The keytab file used by each JournalNode daemon to login as its
service principal. The principal name is configured with
dfs.journalnode.kerberos.principal.
</description>
</property>
<property>
<name>dfs.namenode.kerberos.internal.spnego.principal</name>
<value>${dfs.web.authentication.kerberos.principal}</value>
<description>
The server principal used by the NameNode for web UI SPNEGO
authentication when Kerberos security is enabled. This is
typically set to HTTP/_HOST@REALM.TLD The SPNEGO server principal
begins with the prefix HTTP/ by convention.
If the value is '*', the web server will attempt to login with
every principal specified in the keytab file
dfs.web.authentication.kerberos.keytab.
</description>
</property>
<property>
<name>dfs.journalnode.kerberos.internal.spnego.principal</name>
<value></value>
<description>
The server principal used by the JournalNode HTTP Server for
SPNEGO authentication when Kerberos security is enabled. This is
typically set to HTTP/_HOST@REALM.TLD. The SPNEGO server principal
begins with the prefix HTTP/ by convention.
If the value is '*', the web server will attempt to login with
every principal specified in the keytab file
dfs.web.authentication.kerberos.keytab.
For most deployments this can be set to ${dfs.web.authentication.kerberos.principal}
i.e use the value of dfs.web.authentication.kerberos.principal.
</description>
</property>
<property>
<name>dfs.secondary.namenode.kerberos.internal.spnego.principal</name>
<value>${dfs.web.authentication.kerberos.principal}</value>
<description>
The server principal used by the Secondary NameNode for web UI SPNEGO
authentication when Kerberos security is enabled. Like all other
Secondary NameNode settings, it is ignored in an HA setup.
If the value is '*', the web server will attempt to login with
every principal specified in the keytab file
dfs.web.authentication.kerberos.keytab.
</description>
</property>
<property>
<name>dfs.web.authentication.kerberos.principal</name>
<value></value>
<description>
The server principal used by the NameNode for WebHDFS SPNEGO
authentication.
Required when WebHDFS and security are enabled. In most secure clusters this
setting is also used to specify the values for
dfs.namenode.kerberos.internal.spnego.principal and
dfs.journalnode.kerberos.internal.spnego.principal.
</description>
</property>
<property>
<name>dfs.web.authentication.kerberos.keytab</name>
<value></value>
<description>
The keytab file for the principal corresponding to
dfs.web.authentication.kerberos.principal.
</description>
</property>
<property>
<name>dfs.namenode.kerberos.principal.pattern</name>
<value>*</value>
<description>
A client-side RegEx that can be configured to control
allowed realms to authenticate with (useful in cross-realm env.)
</description>
</property>
<property>
<name>dfs.namenode.avoid.read.stale.datanode</name>
<value>false</value>
<description>
Indicate whether or not to avoid reading from &quot;stale&quot; datanodes whose
heartbeat messages have not been received by the namenode
for more than a specified time interval. Stale datanodes will be
moved to the end of the node list returned for reading. See
dfs.namenode.avoid.write.stale.datanode for a similar setting for writes.
</description>
</property>
<property>
<name>dfs.namenode.avoid.write.stale.datanode</name>
<value>false</value>
<description>
Indicate whether or not to avoid writing to &quot;stale&quot; datanodes whose
heartbeat messages have not been received by the namenode
for more than a specified time interval. Writes will avoid using
stale datanodes unless more than a configured ratio
(dfs.namenode.write.stale.datanode.ratio) of datanodes are marked as
stale. See dfs.namenode.avoid.read.stale.datanode for a similar setting
for reads.
</description>
</property>
<property>
<name>dfs.namenode.stale.datanode.interval</name>
<value>30000</value>
<description>
Default time interval for marking a datanode as "stale", i.e., if
the namenode has not received heartbeat msg from a datanode for
more than this time interval, the datanode will be marked and treated
as "stale" by default. The stale interval cannot be too small since
otherwise this may cause too frequent change of stale states.
We thus set a minimum stale interval value (the default value is 3 times
of heartbeat interval) and guarantee that the stale interval cannot be less
than the minimum value. A stale data node is avoided during lease/block
recovery. It can be conditionally avoided for reads (see
dfs.namenode.avoid.read.stale.datanode) and for writes (see
dfs.namenode.avoid.write.stale.datanode).
</description>
</property>
<property>
<name>dfs.namenode.write.stale.datanode.ratio</name>
<value>0.5f</value>
<description>
When the ratio of number stale datanodes to total datanodes marked
is greater than this ratio, stop avoiding writing to stale nodes so
as to prevent causing hotspots.
</description>
</property>
<property>
<name>dfs.namenode.invalidate.work.pct.per.iteration</name>
<value>0.32f</value>
<description>
*Note*: Advanced property. Change with caution.
This determines the percentage amount of block
invalidations (deletes) to do over a single DN heartbeat
deletion command. The final deletion count is determined by applying this
percentage to the number of live nodes in the system.
The resultant number is the number of blocks from the deletion list
chosen for proper invalidation over a single heartbeat of a single DN.
Value should be a positive, non-zero percentage in float notation (X.Yf),
with 1.0f meaning 100%.
</description>
</property>
<property>
<name>dfs.namenode.replication.work.multiplier.per.iteration</name>
<value>2</value>
<description>
*Note*: Advanced property. Change with caution.
This determines the total amount of block transfers to begin in
parallel at a DN, for replication, when such a command list is being
sent over a DN heartbeat by the NN. The actual number is obtained by
multiplying this multiplier with the total number of live nodes in the
cluster. The result number is the number of blocks to begin transfers
immediately for, per DN heartbeat. This number can be any positive,
non-zero integer.
</description>
</property>
<property>
<name>nfs.server.port</name>
<value>2049</value>
<description>
Specify the port number used by Hadoop NFS.
</description>
</property>
<property>
<name>nfs.mountd.port</name>
<value>4242</value>
<description>
Specify the port number used by Hadoop mount daemon.
</description>
</property>
<property>
<name>nfs.dump.dir</name>
<value>/tmp/.hdfs-nfs</value>
<description>
This directory is used to temporarily save out-of-order writes before
writing to HDFS. For each file, the out-of-order writes are dumped after
they are accumulated to exceed certain threshold (e.g., 1MB) in memory.
One needs to make sure the directory has enough space.
</description>
</property>
<property>
<name>nfs.rtmax</name>
<value>1048576</value>
<description>This is the maximum size in bytes of a READ request
supported by the NFS gateway. If you change this, make sure you
also update the nfs mount's rsize(add rsize= # of bytes to the
mount directive).
</description>
</property>
<property>
<name>nfs.wtmax</name>
<value>1048576</value>
<description>This is the maximum size in bytes of a WRITE request
supported by the NFS gateway. If you change this, make sure you
also update the nfs mount's wsize(add wsize= # of bytes to the
mount directive).
</description>
</property>
<property>
<name>nfs.keytab.file</name>
<value></value>
<description>
*Note*: Advanced property. Change with caution.
This is the path to the keytab file for the hdfs-nfs gateway.
This is required when the cluster is kerberized.
</description>
</property>
<property>
<name>nfs.kerberos.principal</name>
<value></value>
<description>
*Note*: Advanced property. Change with caution.
This is the name of the kerberos principal. This is required when
the cluster is kerberized.It must be of this format:
nfs-gateway-user/nfs-gateway-host@kerberos-realm
</description>
</property>
<property>
<name>nfs.allow.insecure.ports</name>
<value>true</value>
<description>
When set to false, client connections originating from unprivileged ports
(those above 1023) will be rejected. This is to ensure that clients
connecting to this NFS Gateway must have had root privilege on the machine
where they're connecting from.
</description>
</property>
<property>
<name>hadoop.fuse.connection.timeout</name>
<value>300</value>
<description>
The minimum number of seconds that we'll cache libhdfs connection objects
in fuse_dfs. Lower values will result in lower memory consumption; higher
values may speed up access by avoiding the overhead of creating new
connection objects.
</description>
</property>
<property>
<name>hadoop.fuse.timer.period</name>
<value>5</value>
<description>
The number of seconds between cache expiry checks in fuse_dfs. Lower values
will result in fuse_dfs noticing changes to Kerberos ticket caches more
quickly.
</description>
</property>
<property>
<name>dfs.namenode.metrics.logger.period.seconds</name>
<value>600</value>
<description>
This setting controls how frequently the NameNode logs its metrics. The
logging configuration must also define one or more appenders for
NameNodeMetricsLog for the metrics to be logged.
NameNode metrics logging is disabled if this value is set to zero or
less than zero.
</description>
</property>
<property>
<name>dfs.datanode.metrics.logger.period.seconds</name>
<value>600</value>
<description>
This setting controls how frequently the DataNode logs its metrics. The
logging configuration must also define one or more appenders for
DataNodeMetricsLog for the metrics to be logged.
DataNode metrics logging is disabled if this value is set to zero or
less than zero.
</description>
</property>
<property>
<name>dfs.metrics.percentiles.intervals</name>
<value></value>
<description>
Comma-delimited set of integers denoting the desired rollover intervals
(in seconds) for percentile latency metrics on the Namenode and Datanode.
By default, percentile latency metrics are disabled.
</description>
</property>
<property>
<name>hadoop.user.group.metrics.percentiles.intervals</name>
<value></value>
<description>
A comma-separated list of the granularity in seconds for the metrics
which describe the 50/75/90/95/99th percentile latency for group resolution
in milliseconds.
By default, percentile latency metrics are disabled.
</description>
</property>
<property>
<name>dfs.encrypt.data.transfer</name>
<value>false</value>
<description>
Whether or not actual block data that is read/written from/to HDFS should
be encrypted on the wire. This only needs to be set on the NN and DNs,
clients will deduce this automatically. It is possible to override this setting
per connection by specifying custom logic via dfs.trustedchannel.resolver.class.
</description>
</property>
<property>
<name>dfs.encrypt.data.transfer.algorithm</name>
<value></value>
<description>
This value may be set to either "3des" or "rc4". If nothing is set, then
the configured JCE default on the system is used (usually 3DES.) It is
widely believed that 3DES is more cryptographically secure, but RC4 is
substantially faster.
Note that if AES is supported by both the client and server then this
encryption algorithm will only be used to initially transfer keys for AES.
(See dfs.encrypt.data.transfer.cipher.suites.)
</description>
</property>
<property>
<name>dfs.encrypt.data.transfer.cipher.suites</name>
<value></value>
<description>
This value may be either undefined or AES/CTR/NoPadding. If defined, then
dfs.encrypt.data.transfer uses the specified cipher suite for data
encryption. If not defined, then only the algorithm specified in
dfs.encrypt.data.transfer.algorithm is used. By default, the property is
not defined.
</description>
</property>
<property>
<name>dfs.encrypt.data.transfer.cipher.key.bitlength</name>
<value>128</value>
<description>
The key bitlength negotiated by dfsclient and datanode for encryption.
This value may be set to either 128, 192 or 256.
</description>
</property>
<property>
<name>dfs.trustedchannel.resolver.class</name>
<value></value>
<description>
TrustedChannelResolver is used to determine whether a channel
is trusted for plain data transfer. The TrustedChannelResolver is
invoked on both client and server side. If the resolver indicates
that the channel is trusted, then the data transfer will not be
encrypted even if dfs.encrypt.data.transfer is set to true. The
default implementation returns false indicating that the channel
is not trusted.
</description>
</property>
<property>
<name>dfs.data.transfer.protection</name>
<value></value>
<description>
A comma-separated list of SASL protection values used for secured
connections to the DataNode when reading or writing block data. 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. If
dfs.encrypt.data.transfer is set to true, then it supersedes the setting for
dfs.data.transfer.protection and enforces that all connections must use a
specialized encrypted SASL handshake. This property is ignored for
connections to a DataNode listening on a privileged port. In this case, it
is assumed that the use of a privileged port establishes sufficient trust.
</description>
</property>
<property>
<name>dfs.data.transfer.saslproperties.resolver.class</name>
<value></value>
<description>
SaslPropertiesResolver used to resolve the QOP used for a connection to the
DataNode when reading or writing block data. If not specified, the value of
hadoop.security.saslproperties.resolver.class is used as the default value.
</description>
</property>
<property>
<name>dfs.journalnode.rpc-address</name>
<value>0.0.0.0:8485</value>
<description>
The JournalNode RPC server address and port.
</description>
</property>
<property>
<name>dfs.journalnode.http-address</name>
<value>0.0.0.0:8480</value>
<description>
The address and port the JournalNode HTTP server listens on.
If the port is 0 then the server will start on a free port.
</description>
</property>
<property>
<name>dfs.journalnode.https-address</name>
<value>0.0.0.0:8481</value>
<description>
The address and port the JournalNode HTTPS server listens on.
If the port is 0 then the server will start on a free port.
</description>
</property>
<property>
<name>dfs.namenode.audit.loggers</name>
<value>default</value>
<description>
List of classes implementing audit loggers that will receive audit events.
These should be implementations of org.apache.hadoop.hdfs.server.namenode.AuditLogger.
The special value "default" can be used to reference the default audit
logger, which uses the configured log system. Installing custom audit loggers
may affect the performance and stability of the NameNode. Refer to the custom
logger's documentation for more details.
</description>
</property>
<property>
<name>dfs.datanode.available-space-volume-choosing-policy.balanced-space-threshold</name>
<value>10737418240</value> <!-- 10 GB -->
<description>
Only used when the dfs.datanode.fsdataset.volume.choosing.policy is set to
org.apache.hadoop.hdfs.server.datanode.fsdataset.AvailableSpaceVolumeChoosingPolicy.
This setting controls how much DN volumes are allowed to differ in terms of
bytes of free disk space before they are considered imbalanced. If the free
space of all the volumes are within this range of each other, the volumes
will be considered balanced and block assignments will be done on a pure
round robin basis.
</description>
</property>
<property>
<name>dfs.datanode.available-space-volume-choosing-policy.balanced-space-preference-fraction</name>
<value>0.75f</value>
<description>
Only used when the dfs.datanode.fsdataset.volume.choosing.policy is set to
org.apache.hadoop.hdfs.server.datanode.fsdataset.AvailableSpaceVolumeChoosingPolicy.
This setting controls what percentage of new block allocations will be sent
to volumes with more available disk space than others. This setting should
be in the range 0.0 - 1.0, though in practice 0.5 - 1.0, since there should
be no reason to prefer that volumes with less available disk space receive
more block allocations.
</description>
</property>
<property>
<name>dfs.namenode.edits.noeditlogchannelflush</name>
<value>false</value>
<description>
Specifies whether to flush edit log file channel. When set, expensive
FileChannel#force calls are skipped and synchronous disk writes are
enabled instead by opening the edit log file with RandomAccessFile("rws")
flags. This can significantly improve the performance of edit log writes
on the Windows platform.
Note that the behavior of the "rws" flags is platform and hardware specific
and might not provide the same level of guarantees as FileChannel#force.
For example, the write will skip the disk-cache on SAS and SCSI devices
while it might not on SATA devices. This is an expert level setting,
change with caution.
</description>
</property>
<property>
<name>dfs.client.cache.drop.behind.writes</name>
<value></value>
<description>
Just like dfs.datanode.drop.cache.behind.writes, this setting causes the
page cache to be dropped behind HDFS writes, potentially freeing up more
memory for other uses. Unlike dfs.datanode.drop.cache.behind.writes, this
is a client-side setting rather than a setting for the entire datanode.
If present, this setting will override the DataNode default.
If the native libraries are not available to the DataNode, this
configuration has no effect.
</description>
</property>
<property>
<name>dfs.client.cache.drop.behind.reads</name>
<value></value>
<description>
Just like dfs.datanode.drop.cache.behind.reads, this setting causes the
page cache to be dropped behind HDFS reads, potentially freeing up more
memory for other uses. Unlike dfs.datanode.drop.cache.behind.reads, this
is a client-side setting rather than a setting for the entire datanode. If
present, this setting will override the DataNode default.
If the native libraries are not available to the DataNode, this
configuration has no effect.
</description>
</property>
<property>
<name>dfs.client.cache.readahead</name>
<value></value>
<description>
When using remote reads, this setting causes the datanode to
read ahead in the block file using posix_fadvise, potentially decreasing
I/O wait times. Unlike dfs.datanode.readahead.bytes, this is a client-side
setting rather than a setting for the entire datanode. If present, this
setting will override the DataNode default.
When using local reads, this setting determines how much readahead we do in
BlockReaderLocal.
If the native libraries are not available to the DataNode, this
configuration has no effect.
</description>
</property>
<property>
<name>dfs.namenode.enable.retrycache</name>
<value>true</value>
<description>
This enables the retry cache on the namenode. Namenode tracks for
non-idempotent requests the corresponding response. If a client retries the
request, the response from the retry cache is sent. Such operations
are tagged with annotation @AtMostOnce in namenode protocols. It is
recommended that this flag be set to true. Setting it to false, will result
in clients getting failure responses to retried request. This flag must
be enabled in HA setup for transparent fail-overs.
The entries in the cache have expiration time configurable
using dfs.namenode.retrycache.expirytime.millis.
</description>
</property>
<property>
<name>dfs.namenode.retrycache.expirytime.millis</name>
<value>600000</value>
<description>
The time for which retry cache entries are retained.
</description>
</property>
<property>
<name>dfs.namenode.retrycache.heap.percent</name>
<value>0.03f</value>
<description>
This parameter configures the heap size allocated for retry cache
(excluding the response cached). This corresponds to approximately
4096 entries for every 64MB of namenode process java heap size.
Assuming retry cache entry expiration time (configured using
dfs.namenode.retrycache.expirytime.millis) of 10 minutes, this
enables retry cache to support 7 operations per second sustained
for 10 minutes. As the heap size is increased, the operation rate
linearly increases.
</description>
</property>
<property>
<name>dfs.client.mmap.enabled</name>
<value>true</value>
<description>
If this is set to false, the client won't attempt to perform memory-mapped reads.
</description>
</property>
<property>
<name>dfs.client.mmap.cache.size</name>
<value>256</value>
<description>
When zero-copy reads are used, the DFSClient keeps a cache of recently used
memory mapped regions. This parameter controls the maximum number of
entries that we will keep in that cache.
The larger this number is, the more file descriptors we will potentially
use for memory-mapped files. mmaped files also use virtual address space.
You may need to increase your ulimit virtual address space limits before
increasing the client mmap cache size.
Note that you can still do zero-copy reads when this size is set to 0.
</description>
</property>
<property>
<name>dfs.client.mmap.cache.timeout.ms</name>
<value>3600000</value>
<description>
The minimum length of time that we will keep an mmap entry in the cache
between uses. If an entry is in the cache longer than this, and nobody
uses it, it will be removed by a background thread.
</description>
</property>
<property>
<name>dfs.client.mmap.retry.timeout.ms</name>
<value>300000</value>
<description>
The minimum amount of time that we will wait before retrying a failed mmap
operation.
</description>
</property>
<property>
<name>dfs.client.short.circuit.replica.stale.threshold.ms</name>
<value>1800000</value>
<description>
The maximum amount of time that we will consider a short-circuit replica to
be valid, if there is no communication from the DataNode. After this time
has elapsed, we will re-fetch the short-circuit replica even if it is in
the cache.
</description>
</property>
<property>
<name>dfs.namenode.path.based.cache.block.map.allocation.percent</name>
<value>0.25</value>
<description>
The percentage of the Java heap which we will allocate to the cached blocks
map. The cached blocks map is a hash map which uses chained hashing.
Smaller maps may be accessed more slowly if the number of cached blocks is
large; larger maps will consume more memory.
</description>
</property>
<property>
<name>dfs.datanode.max.locked.memory</name>
<value>0</value>
<description>
The amount of memory in bytes to use for caching of block replicas in
memory on the datanode. The datanode's maximum locked memory soft ulimit
(RLIMIT_MEMLOCK) must be set to at least this value, else the datanode
will abort on startup.
By default, this parameter is set to 0, which disables in-memory caching.
If the native libraries are not available to the DataNode, this
configuration has no effect.
</description>
</property>
<property>
<name>dfs.namenode.list.cache.directives.num.responses</name>
<value>100</value>
<description>
This value controls the number of cache directives that the NameNode will
send over the wire in response to a listDirectives RPC.
</description>
</property>
<property>
<name>dfs.namenode.list.cache.pools.num.responses</name>
<value>100</value>
<description>
This value controls the number of cache pools that the NameNode will
send over the wire in response to a listPools RPC.
</description>
</property>
<property>
<name>dfs.namenode.path.based.cache.refresh.interval.ms</name>
<value>30000</value>
<description>
The amount of milliseconds between subsequent path cache rescans. Path
cache rescans are when we calculate which blocks should be cached, and on
what datanodes.
By default, this parameter is set to 30 seconds.
</description>
</property>
<property>
<name>dfs.namenode.path.based.cache.retry.interval.ms</name>
<value>30000</value>
<description>
When the NameNode needs to uncache something that is cached, or cache
something that is not cached, it must direct the DataNodes to do so by
sending a DNA_CACHE or DNA_UNCACHE command in response to a DataNode
heartbeat. This parameter controls how frequently the NameNode will
resend these commands.
</description>
</property>
<property>
<name>dfs.datanode.fsdatasetcache.max.threads.per.volume</name>
<value>4</value>
<description>
The maximum number of threads per volume to use for caching new data
on the datanode. These threads consume both I/O and CPU. This can affect
normal datanode operations.
</description>
</property>
<property>
<name>dfs.cachereport.intervalMsec</name>
<value>10000</value>
<description>
Determines cache reporting interval in milliseconds. After this amount of
time, the DataNode sends a full report of its cache state to the NameNode.
The NameNode uses the cache report to update its map of cached blocks to
DataNode locations.
This configuration has no effect if in-memory caching has been disabled by
setting dfs.datanode.max.locked.memory to 0 (which is the default).
If the native libraries are not available to the DataNode, this
configuration has no effect.
</description>
</property>
<property>
<name>dfs.namenode.edit.log.autoroll.multiplier.threshold</name>
<value>2.0</value>
<description>
Determines when an active namenode will roll its own edit log.
The actual threshold (in number of edits) is determined by multiplying
this value by dfs.namenode.checkpoint.txns.
This prevents extremely large edit files from accumulating on the active
namenode, which can cause timeouts during namenode startup and pose an
administrative hassle. This behavior is intended as a failsafe for when
the standby or secondary namenode fail to roll the edit log by the normal
checkpoint threshold.
</description>
</property>
<property>
<name>dfs.namenode.edit.log.autoroll.check.interval.ms</name>
<value>300000</value>
<description>
How often an active namenode will check if it needs to roll its edit log,
in milliseconds.
</description>
</property>
<property>
<name>dfs.webhdfs.user.provider.user.pattern</name>
<value>^[A-Za-z_][A-Za-z0-9._-]*[$]?$</value>
<description>
Valid pattern for user and group names for webhdfs, it must be a valid java regex.
</description>
</property>
<property>
<name>dfs.webhdfs.socket.connect-timeout</name>
<value>60s</value>
<description>
Socket timeout for connecting to WebHDFS servers. This prevents a
WebHDFS client from hanging if the server hostname is
misconfigured, or the server does not response before the timeout
expires. Value is followed by a unit specifier: ns, us, ms, s, m,
h, d for nanoseconds, microseconds, milliseconds, seconds,
minutes, hours, days respectively. Values should provide units,
but milliseconds are assumed.
</description>
</property>
<property>
<name>dfs.webhdfs.socket.read-timeout</name>
<value>60s</value>
<description>
Socket timeout for reading data from WebHDFS servers. This
prevents a WebHDFS client from hanging if the server stops sending
data. Value is followed by a unit specifier: ns, us, ms, s, m, h,
d for nanoseconds, microseconds, milliseconds, seconds, minutes,
hours, days respectively. Values should provide units,
but milliseconds are assumed.
</description>
</property>
<property>
<name>dfs.client.context</name>
<value>default</value>
<description>
The name of the DFSClient context that we should use. Clients that share
a context share a socket cache and short-circuit cache, among other things.
You should only change this if you don't want to share with another set of
threads.
</description>
</property>
<property>
<name>dfs.client.read.shortcircuit</name>
<value>false</value>
<description>
This configuration parameter turns on short-circuit local reads.
</description>
</property>
<property>
<name>dfs.client.socket.send.buffer.size</name>
<value>131072</value>
<description>
Socket send buffer size for a write pipeline in DFSClient side.
This may affect TCP connection throughput.
If it is set to zero or negative value,
no buffer size will be set explicitly,
thus enable tcp auto-tuning on some system.
</description>
</property>
<property>
<name>dfs.domain.socket.path</name>
<value></value>
<description>
Optional. This is a path to a UNIX domain socket that will be used for
communication between the DataNode and local HDFS clients.
If the string "_PORT" is present in this path, it will be replaced by the
TCP port of the DataNode.
</description>
</property>
<property>
<name>dfs.client.read.shortcircuit.skip.checksum</name>
<value>false</value>
<description>
If this configuration parameter is set,
short-circuit local reads will skip checksums.
This is normally not recommended,
but it may be useful for special setups.
You might consider using this
if you are doing your own checksumming outside of HDFS.
</description>
</property>
<property>
<name>dfs.client.read.shortcircuit.streams.cache.size</name>
<value>256</value>
<description>
The DFSClient maintains a cache of recently opened file descriptors.
This parameter controls the maximum number of file descriptors in the cache.
Setting this higher will use more file descriptors,
but potentially provide better performance on workloads
involving lots of seeks.
</description>
</property>
<property>
<name>dfs.client.read.shortcircuit.streams.cache.expiry.ms</name>
<value>300000</value>
<description>
This controls the minimum amount of time
file descriptors need to sit in the client cache context
before they can be closed for being inactive for too long.
</description>
</property>
<property>
<name>dfs.datanode.shared.file.descriptor.paths</name>
<value>/dev/shm,/tmp</value>
<description>
Comma separated paths to the directory on which
shared memory segments are created.
The client and the DataNode exchange information via
this shared memory segment.
It tries paths in order until creation of shared memory segment succeeds.
</description>
</property>
<property>
<name>dfs.namenode.audit.log.debug.cmdlist</name>
<value></value>
<description>
A comma separated list of NameNode commands that are written to the HDFS
namenode audit log only if the audit log level is debug.
</description>
</property>
<property>
<name>dfs.client.use.legacy.blockreader.local</name>
<value>false</value>
<description>
Legacy short-circuit reader implementation based on HDFS-2246 is used
if this configuration parameter is true.
This is for the platforms other than Linux
where the new implementation based on HDFS-347 is not available.
</description>
</property>
<property>
<name>dfs.block.local-path-access.user</name>
<value></value>
<description>
Comma separated list of the users allowed to open block files
on legacy short-circuit local read.
</description>
</property>
<property>
<name>dfs.client.domain.socket.data.traffic</name>
<value>false</value>
<description>
This control whether we will try to pass normal data traffic
over UNIX domain socket rather than over TCP socket
on node-local data transfer.
This is currently experimental and turned off by default.
</description>
</property>
<property>
<name>dfs.namenode.reject-unresolved-dn-topology-mapping</name>
<value>false</value>
<description>
If the value is set to true, then namenode will reject datanode
registration if the topology mapping for a datanode is not resolved and
NULL is returned (script defined by net.topology.script.file.name fails
to execute). Otherwise, datanode will be registered and the default rack
will be assigned as the topology path. Topology paths are important for
data resiliency, since they define fault domains. Thus it may be unwanted
behavior to allow datanode registration with the default rack if the
resolving topology failed.
</description>
</property>
<property>
<name>dfs.namenode.xattrs.enabled</name>
<value>true</value>
<description>
Whether support for extended attributes is enabled on the NameNode.
</description>
</property>
<property>
<name>dfs.namenode.fs-limits.max-xattrs-per-inode</name>
<value>32</value>
<description>
Maximum number of extended attributes per inode.
</description>
</property>
<property>
<name>dfs.namenode.fs-limits.max-xattr-size</name>
<value>16384</value>
<description>
The maximum combined size of the name and value of an extended attribute
in bytes. It should be larger than 0, and less than or equal to maximum
size hard limit which is 32768.
</description>
</property>
<property>
<name>dfs.client.slow.io.warning.threshold.ms</name>
<value>30000</value>
<description>The threshold in milliseconds at which we will log a slow
io warning in a dfsclient. By default, this parameter is set to 30000
milliseconds (30 seconds).
</description>
</property>
<property>
<name>dfs.datanode.slow.io.warning.threshold.ms</name>
<value>300</value>
<description>The threshold in milliseconds at which we will log a slow
io warning in a datanode. By default, this parameter is set to 300
milliseconds.
</description>
</property>
<property>
<name>dfs.namenode.lease-recheck-interval-ms</name>
<value>2000</value>
<description>During the release of lease a lock is hold that make any
operations on the namenode stuck. In order to not block them during
a too long duration we stop releasing lease after this max lock limit.
</description>
</property>
<property>
<name>dfs.namenode.max-lock-hold-to-release-lease-ms</name>
<value>25</value>
<description>During the release of lease a lock is hold that make any
operations on the namenode stuck. In order to not block them during
a too long duration we stop releasing lease after this max lock limit.
</description>
</property>
<property>
<name>dfs.namenode.write-lock-reporting-threshold-ms</name>
<value>1000</value>
<description>When a write lock is held on the namenode for a long time,
this will be logged as the lock is released. This sets how long the
lock must be held for logging to occur.
</description>
</property>
<property>
<name>dfs.namenode.read-lock-reporting-threshold-ms</name>
<value>5000</value>
<description>When a read lock is held on the namenode for a long time,
this will be logged as the lock is released. This sets how long the
lock must be held for logging to occur.
</description>
</property>
<property>
<name>dfs.namenode.startup.delay.block.deletion.sec</name>
<value>0</value>
<description>The delay in seconds at which we will pause the blocks deletion
after Namenode startup. By default it's disabled.
In the case a directory has large number of directories and files are
deleted, suggested delay is one hour to give the administrator enough time
to notice large number of pending deletion blocks and take corrective
action.
</description>
</property>
<property>
<name>dfs.datanode.block.id.layout.upgrade.threads</name>
<value>12</value>
<description>The number of threads to use when creating hard links from
current to previous blocks during upgrade of a DataNode to block ID-based
block layout (see HDFS-6482 for details on the layout).</description>
</property>
<property>
<name>dfs.namenode.list.encryption.zones.num.responses</name>
<value>100</value>
<description>When listing encryption zones, the maximum number of zones
that will be returned in a batch. Fetching the list incrementally in
batches improves namenode performance.
</description>
</property>
<property>
<name>dfs.namenode.edekcacheloader.interval.ms</name>
<value>1000</value>
<description>When KeyProvider is configured, the interval time of warming
up edek cache on NN starts up / becomes active. All edeks will be loaded
from KMS into provider cache. The edek cache loader will try to warm up the
cache until succeed or NN leaves active state.
</description>
</property>
<property>
<name>dfs.namenode.edekcacheloader.initial.delay.ms</name>
<value>3000</value>
<description>When KeyProvider is configured, the time delayed until the first
attempt to warm up edek cache on NN start up / become active.
</description>
</property>
<property>
<name>dfs.namenode.inotify.max.events.per.rpc</name>
<value>1000</value>
<description>Maximum number of events that will be sent to an inotify client
in a single RPC response. The default value attempts to amortize away
the overhead for this RPC while avoiding huge memory requirements for the
client and NameNode (1000 events should consume no more than 1 MB.)
</description>
</property>
<property>
<name>dfs.user.home.dir.prefix</name>
<value>/user</value>
<description>The directory to prepend to user name to get the user's
home direcotry.
</description>
</property>
<property>
<name>dfs.datanode.cache.revocation.timeout.ms</name>
<value>900000</value>
<description>When the DFSClient reads from a block file which the DataNode is
caching, the DFSClient can skip verifying checksums. The DataNode will
keep the block file in cache until the client is done. If the client takes
an unusually long time, though, the DataNode may need to evict the block
file from the cache anyway. This value controls how long the DataNode will
wait for the client to release a replica that it is reading without
checksums.
</description>
</property>
<property>
<name>dfs.datanode.cache.revocation.polling.ms</name>
<value>500</value>
<description>How often the DataNode should poll to see if the clients have
stopped using a replica that the DataNode wants to uncache.
</description>
</property>
<property>
<name>dfs.storage.policy.enabled</name>
<value>true</value>
<description>
Allow users to change the storage policy on files and directories.
</description>
</property>
<property>
<name>dfs.namenode.legacy-oiv-image.dir</name>
<value></value>
<description>Determines where to save the namespace in the old fsimage format
during checkpointing by standby NameNode or SecondaryNameNode. Users can
dump the contents of the old format fsimage by oiv_legacy command. If
the value is not specified, old format fsimage will not be saved in
checkpoint.
</description>
</property>
<property>
<name>dfs.namenode.top.enabled</name>
<value>true</value>
<description>Enable nntop: reporting top users on namenode
</description>
</property>
<property>
<name>dfs.namenode.top.window.num.buckets</name>
<value>10</value>
<description>Number of buckets in the rolling window implementation of nntop
</description>
</property>
<property>
<name>dfs.namenode.top.num.users</name>
<value>10</value>
<description>Number of top users returned by the top tool
</description>
</property>
<property>
<name>dfs.namenode.top.windows.minutes</name>
<value>1,5,25</value>
<description>comma separated list of nntop reporting periods in minutes
</description>
</property>
<property>
<name>dfs.webhdfs.ugi.expire.after.access</name>
<value>600000</value>
<description>How long in milliseconds after the last access
the cached UGI will expire. With 0, never expire.
</description>
</property>
<property>
<name>dfs.namenode.blocks.per.postponedblocks.rescan</name>
<value>10000</value>
<description>Number of blocks to rescan for each iteration of
postponedMisreplicatedBlocks.
</description>
</property>
<property>
<name>dfs.datanode.block-pinning.enabled</name>
<value>false</value>
<description>Whether pin blocks on favored DataNode.</description>
</property>
<property>
<name>dfs.client.block.write.locateFollowingBlock.initial.delay.ms</name>
<value>400</value>
<description>The initial delay (unit is ms) for locateFollowingBlock,
the delay time will increase exponentially(double) for each retry.
</description>
</property>
<property>
<name>dfs.ha.zkfc.nn.http.timeout.ms</name>
<value>20000</value>
<description>
The HTTP connection and read timeout value (unit is ms ) when DFS ZKFC
tries to get local NN thread dump after local NN becomes
SERVICE_NOT_RESPONDING or SERVICE_UNHEALTHY.
If it is set to zero, DFS ZKFC won't get local NN thread dump.
</description>
</property>
<property>
<name>dfs.ha.tail-edits.in-progress</name>
<value>false</value>
<description>
Whether enable standby namenode to tail in-progress edit logs.
Clients might want to turn it on when they want Standby NN to have
more up-to-date data.
</description>
</property>
<property>
<name>dfs.datanode.ec.reconstruction.stripedread.timeout.millis</name>
<value>5000</value>
<description>Datanode striped read timeout in milliseconds.
</description>
</property>
<property>
<name>dfs.datanode.ec.reconstruction.stripedread.threads</name>
<value>20</value>
<description>
Number of threads used by the Datanode to read striped block
during background reconstruction work.
</description>
</property>
<property>
<name>dfs.datanode.ec.reconstruction.stripedread.buffer.size</name>
<value>65536</value>
<description>Datanode striped read buffer size.
</description>
</property>
<property>
<name>dfs.datanode.ec.reconstruction.stripedblock.threads.size</name>
<value>8</value>
<description>
Number of threads used by the Datanode for background
reconstruction work.
</description>
</property>
<property>
<name>dfs.namenode.quota.init-threads</name>
<value>4</value>
<description>
The number of concurrent threads to be used in quota initialization. The
speed of quota initialization also affects the namenode fail-over latency.
If the size of name space is big, try increasing this.
</description>
</property>
<property>
<name>dfs.datanode.transfer.socket.send.buffer.size</name>
<value>131072</value>
<description>
Socket send buffer size for DataXceiver (mirroring packets to downstream
in pipeline). This may affect TCP connection throughput.
If it is set to zero or negative value, no buffer size will be set
explicitly, thus enable tcp auto-tuning on some system.
</description>
</property>
<property>
<name>dfs.datanode.transfer.socket.recv.buffer.size</name>
<value>131072</value>
<description>
Socket receive buffer size for DataXceiver (receiving packets from client
during block writing). This may affect TCP connection throughput.
If it is set to zero or negative value, no buffer size will be set
explicitly, thus enable tcp auto-tuning on some system.
</description>
</property>
<property>
<name>dfs.namenode.upgrade.domain.factor</name>
<value>${dfs.replication}</value>
<description>
This is valid only when block placement policy is set to
BlockPlacementPolicyWithUpgradeDomain. It defines the number of
unique upgrade domains any block's replicas should have.
When the number of replicas is less or equal to this value, the policy
ensures each replica has an unique upgrade domain. When the number of
replicas is greater than this value, the policy ensures the number of
unique domains is at least this value.
</description>
</property>
<property>
<name>dfs.ha.zkfc.port</name>
<value>8019</value>
<description>
RPC port for Zookeeper Failover Controller.
</description>
</property>
<property>
<name>dfs.datanode.bp-ready.timeout</name>
<value>20s</value>
<description>
The maximum wait time for datanode to be ready before failing the
received request. Setting this to 0 fails requests right away if the
datanode is not yet registered with the namenode. This wait time
reduces initial request failures after datanode restart.
Support multiple time unit suffix(case insensitive), as described
in dfs.heartbeat.interval.
</description>
</property>
<property>
<name>dfs.datanode.cached-dfsused.check.interval.ms</name>
<value>600000</value>
<description>
The interval check time of loading DU_CACHE_FILE in each volume.
When the cluster doing the rolling upgrade operations, it will
usually lead dfsUsed cache file of each volume expired and redo the
du operations in datanode and that makes datanode start slowly. Adjust
this property can make cache file be available for the time as you want.
</description>
</property>
<property>
<name>dfs.webhdfs.rest-csrf.enabled</name>
<value>false</value>
<description>
If true, then enables WebHDFS protection against cross-site request forgery
(CSRF). The WebHDFS client also uses this property to determine whether or
not it needs to send the custom CSRF prevention header in its HTTP requests.
</description>
</property>
<property>
<name>dfs.webhdfs.rest-csrf.custom-header</name>
<value>X-XSRF-HEADER</value>
<description>
The name of a custom header that HTTP requests must send when protection
against cross-site request forgery (CSRF) is enabled for WebHDFS by setting
dfs.webhdfs.rest-csrf.enabled to true. The WebHDFS client also uses this
property to determine whether or not it needs to send the custom CSRF
prevention header in its HTTP requests.
</description>
</property>
<property>
<name>dfs.webhdfs.rest-csrf.methods-to-ignore</name>
<value>GET,OPTIONS,HEAD,TRACE</value>
<description>
A comma-separated list of HTTP methods that do not require HTTP requests to
include a custom header when protection against cross-site request forgery
(CSRF) is enabled for WebHDFS by setting dfs.webhdfs.rest-csrf.enabled to
true. The WebHDFS client also uses this property to determine whether or
not it needs to send the custom CSRF prevention header in its HTTP requests.
</description>
</property>
<property>
<name>dfs.webhdfs.rest-csrf.browser-useragents-regex</name>
<value>^Mozilla.*,^Opera.*</value>
<description>
A comma-separated list of regular expressions used to match against an HTTP
request's User-Agent header when protection against cross-site request
forgery (CSRF) is enabled for WebHDFS by setting
dfs.webhdfs.reset-csrf.enabled to true. If the incoming User-Agent matches
any of these regular expressions, then the request is considered to be sent
by a browser, and therefore CSRF prevention is enforced. If the request's
User-Agent does not match any of these regular expressions, then the request
is considered to be sent by something other than a browser, such as scripted
automation. In this case, CSRF is not a potential attack vector, so
the prevention is not enforced. This helps achieve backwards-compatibility
with existing automation that has not been updated to send the CSRF
prevention header.
</description>
</property>
<property>
<name>dfs.xframe.enabled</name>
<value>true</value>
<description>
If true, then enables protection against clickjacking by returning
X_FRAME_OPTIONS header value set to SAMEORIGIN.
Clickjacking protection prevents an attacker from using transparent or
opaque layers to trick a user into clicking on a button
or link on another page.
</description>
</property>
<property>
<name>dfs.xframe.value</name>
<value>SAMEORIGIN</value>
<description>
This configration value allows user to specify the value for the
X-FRAME-OPTIONS. The possible values for this field are
DENY, SAMEORIGIN and ALLOW-FROM. Any other value will throw an
exception when namenode and datanodes are starting up.
</description>
</property>
<property>
<name>dfs.balancer.keytab.enabled</name>
<value>false</value>
<description>
Set to true to enable login using a keytab for Kerberized Hadoop.
</description>
</property>
<property>
<name>dfs.balancer.address</name>
<value>0.0.0.0:0</value>
<description>
The hostname used for a keytab based Kerberos login. Keytab based login
can be enabled with dfs.balancer.keytab.enabled.
</description>
</property>
<property>
<name>dfs.balancer.keytab.file</name>
<value></value>
<description>
The keytab file used by the Balancer to login as its
service principal. The principal name is configured with
dfs.balancer.kerberos.principal. Keytab based login can be
enabled with dfs.balancer.keytab.enabled.
</description>
</property>
<property>
<name>dfs.balancer.kerberos.principal</name>
<value></value>
<description>
The Balancer principal. This is typically set to
balancer/_HOST@REALM.TLD. The Balancer will substitute _HOST with its
own fully qualified hostname at startup. The _HOST placeholder
allows using the same configuration setting on different servers.
Keytab based login can be enabled with dfs.balancer.keytab.enabled.
</description>
</property>
<property>
<name>dfs.http.client.retry.policy.enabled</name>
<value>false</value>
<description>
If "true", enable the retry policy of WebHDFS client.
If "false", retry policy is turned off.
Enabling the retry policy can be quite useful while using WebHDFS to
copy large files between clusters that could timeout, or
copy files between HA clusters that could failover during the copy.
</description>
</property>
<property>
<name>dfs.http.client.retry.policy.spec</name>
<value>10000,6,60000,10</value>
<description>
Specify a policy of multiple linear random retry for WebHDFS client,
e.g. given pairs of number of retries and sleep time (n0, t0), (n1, t1),
..., the first n0 retries sleep t0 milliseconds on average,
the following n1 retries sleep t1 milliseconds on average, and so on.
</description>
</property>
<property>
<name>dfs.http.client.failover.max.attempts</name>
<value>15</value>
<description>
Specify the max number of failover attempts for WebHDFS client
in case of network exception.
</description>
</property>
<property>
<name>dfs.http.client.retry.max.attempts</name>
<value>10</value>
<description>
Specify the max number of retry attempts for WebHDFS client,
if the difference between retried attempts and failovered attempts is
larger than the max number of retry attempts, there will be no more
retries.
</description>
</property>
<property>
<name>dfs.http.client.failover.sleep.base.millis</name>
<value>500</value>
<description>
Specify the base amount of time in milliseconds upon which the
exponentially increased sleep time between retries or failovers
is calculated for WebHDFS client.
</description>
</property>
<property>
<name>dfs.http.client.failover.sleep.max.millis</name>
<value>15000</value>
<description>
Specify the upper bound of sleep time in milliseconds between
retries or failovers for WebHDFS client.
</description>
</property>
<property>
<name>dfs.namenode.hosts.provider.classname</name>
<value>org.apache.hadoop.hdfs.server.blockmanagement.HostFileManager</value>
<description>
The class that provides access for host files.
org.apache.hadoop.hdfs.server.blockmanagement.HostFileManager is used
by default which loads files specified by dfs.hosts and dfs.hosts.exclude.
If org.apache.hadoop.hdfs.server.blockmanagement.CombinedHostFileManager is
used, it will load the JSON file defined in dfs.hosts.
To change class name, nn restart is required. "dfsadmin -refreshNodes" only
refreshes the configuration files used by the class.
</description>
</property>
<property>
<name>datanode.https.port</name>
<value>50475</value>
<description>
HTTPS port for DataNode.
</description>
</property>
<property>
<name>dfs.balancer.dispatcherThreads</name>
<value>200</value>
<description>
Size of the thread pool for the HDFS balancer block mover.
dispatchExecutor
</description>
</property>
<property>
<name>dfs.balancer.movedWinWidth</name>
<value>5400000</value>
<description>
Window of time in ms for the HDFS balancer tracking blocks and its
locations.
</description>
</property>
<property>
<name>dfs.balancer.moverThreads</name>
<value>1000</value>
<description>
Thread pool size for executing block moves.
moverThreadAllocator
</description>
</property>
<property>
<name>dfs.balancer.max-size-to-move</name>
<value>10737418240</value>
<description>
Maximum number of bytes that can be moved by the balancer in a single
thread.
</description>
</property>
<property>
<name>dfs.balancer.getBlocks.min-block-size</name>
<value>10485760</value>
<description>
Minimum block threshold size in bytes to ignore when fetching a source's
block list.
</description>
</property>
<property>
<name>dfs.balancer.getBlocks.size</name>
<value>2147483648</value>
<description>
Total size in bytes of Datanode blocks to get when fetching a source's
block list.
</description>
</property>
<property>
<name>dfs.balancer.block-move.timeout</name>
<value>0</value>
<description>
Maximum amount of time in milliseconds for a block to move. If this is set
greater than 0, Balancer will stop waiting for a block move completion
after this time. In typical clusters, a 3 to 5 minute timeout is reasonable.
If timeout happens to a large proportion of block moves, this needs to be
increased. It could also be that too much work is dispatched and many nodes
are constantly exceeding the bandwidth limit as a result. In that case,
other balancer parameters might need to be adjusted.
It is disabled (0) by default.
</description>
</property>
<property>
<name>dfs.block.invalidate.limit</name>
<value>1000</value>
<description>
Limit on the list of invalidated block list kept by the Namenode.
</description>
</property>
<property>
<name>dfs.block.misreplication.processing.limit</name>
<value>10000</value>
<description>
Maximum number of blocks to process for initializing replication queues.
</description>
</property>
<property>
<name>dfs.block.placement.ec.classname</name>
<value>org.apache.hadoop.hdfs.server.blockmanagement.BlockPlacementPolicyRackFaultTolerant</value>
<description>
Placement policy class for striped files.
Defaults to BlockPlacementPolicyRackFaultTolerant.class
</description>
</property>
<property>
<name>dfs.block.replicator.classname</name>
<value>org.apache.hadoop.hdfs.server.blockmanagement.BlockPlacementPolicyDefault</value>
<description>
Class representing block placement policy for non-striped files.
There are four block placement policies currently being supported:
BlockPlacementPolicyDefault, BlockPlacementPolicyWithNodeGroup,
BlockPlacementPolicyRackFaultTolerant and BlockPlacementPolicyWithUpgradeDomain.
BlockPlacementPolicyDefault chooses the desired number of targets
for placing block replicas in a default way. BlockPlacementPolicyWithNodeGroup
places block replicas on environment with node-group layer. BlockPlacementPolicyRackFaultTolerant
places the replicas to more racks.
BlockPlacementPolicyWithUpgradeDomain places block replicas that honors upgrade domain policy.
The details of placing replicas are documented in the javadoc of the corresponding policy classes.
The default policy is BlockPlacementPolicyDefault, and the corresponding class is
org.apache.hadoop.hdfs.server.blockmanagement.BlockPlacementPolicyDefault.
</description>
</property>
<property>
<name>dfs.blockreport.incremental.intervalMsec</name>
<value>0</value>
<description>
If set to a positive integer, the value in ms to wait between sending
incremental block reports from the Datanode to the Namenode.
</description>
</property>
<property>
<name>dfs.checksum.type</name>
<value>CRC32C</value>
<description>
Checksum type
</description>
</property>
<property>
<name>dfs.client.block.write.locateFollowingBlock.retries</name>
<value>5</value>
<description>
Number of retries to use when finding the next block during HDFS writes.
</description>
</property>
<property>
<name>dfs.client.failover.proxy.provider</name>
<value></value>
<description>
The prefix (plus a required nameservice ID) for the class name of the
configured Failover proxy provider for the host. For more detailed
information, please consult the "Configuration Details" section of
the HDFS High Availability documentation.
</description>
</property>
<property>
<name>dfs.client.key.provider.cache.expiry</name>
<value>864000000</value>
<description>
DFS client security key cache expiration in milliseconds.
</description>
</property>
<property>
<name>dfs.client.max.block.acquire.failures</name>
<value>3</value>
<description>
Maximum failures allowed when trying to get block information from a specific datanode.
</description>
</property>
<property>
<name>dfs.client.read.prefetch.size</name>
<value></value>
<description>
The number of bytes for the DFSClient will fetch from the Namenode
during a read operation. Defaults to 10 * ${dfs.blocksize}.
</description>
</property>
<property>
<name>dfs.client.read.short.circuit.replica.stale.threshold.ms</name>
<value>1800000</value>
<description>
Threshold in milliseconds for read entries during short-circuit local reads.
</description>
</property>
<property>
<name>dfs.client.read.shortcircuit.buffer.size</name>
<value>1048576</value>
<description>
Buffer size in bytes for short-circuit local reads.
</description>
</property>
<property>
<name>dfs.client.replica.accessor.builder.classes</name>
<value></value>
<description>
Comma-separated classes for building ReplicaAccessor. If the classes
are specified, client will use external BlockReader that uses the
ReplicaAccessor built by the builder.
</description>
</property>
<property>
<name>dfs.client.retry.interval-ms.get-last-block-length</name>
<value>4000</value>
<description>
Retry interval in milliseconds to wait between retries in getting
block lengths from the datanodes.
</description>
</property>
<property>
<name>dfs.client.retry.max.attempts</name>
<value>10</value>
<description>
Max retry attempts for DFSClient talking to namenodes.
</description>
</property>
<property>
<name>dfs.client.retry.policy.enabled</name>
<value>false</value>
<description>
If true, turns on DFSClient retry policy.
</description>
</property>
<property>
<name>dfs.client.retry.policy.spec</name>
<value>10000,6,60000,10</value>
<description>
Set to pairs of timeouts and retries for DFSClient.
</description>
</property>
<property>
<name>dfs.client.retry.times.get-last-block-length</name>
<value>3</value>
<description>
Number of retries for calls to fetchLocatedBlocksAndGetLastBlockLength().
</description>
</property>
<property>
<name>dfs.client.retry.window.base</name>
<value>3000</value>
<description>
Base time window in ms for DFSClient retries. For each retry attempt,
this value is extended linearly (e.g. 3000 ms for first attempt and
first retry, 6000 ms for second retry, 9000 ms for third retry, etc.).
</description>
</property>
<property>
<name>dfs.client.socket-timeout</name>
<value>60000</value>
<description>
Default timeout value in milliseconds for all sockets.
</description>
</property>
<property>
<name>dfs.client.socketcache.capacity</name>
<value>16</value>
<description>
Socket cache capacity (in entries) for short-circuit reads.
</description>
</property>
<property>
<name>dfs.client.socketcache.expiryMsec</name>
<value>3000</value>
<description>
Socket cache expiration for short-circuit reads in msec.
</description>
</property>
<property>
<name>dfs.client.test.drop.namenode.response.number</name>
<value>0</value>
<description>
The number of Namenode responses dropped by DFSClient for each RPC call. Used
for testing the NN retry cache.
</description>
</property>
<property>
<name>dfs.client.hedged.read.threadpool.size</name>
<value>0</value>
<description>
Support 'hedged' reads in DFSClient. To enable this feature, set the parameter
to a positive number. The threadpool size is how many threads to dedicate
to the running of these 'hedged', concurrent reads in your client.
</description>
</property>
<property>
<name>dfs.client.hedged.read.threshold.millis</name>
<value>500</value>
<description>
Configure 'hedged' reads in DFSClient. This is the number of milliseconds
to wait before starting up a 'hedged' read.
</description>
</property>
<property>
<name>dfs.client.write.byte-array-manager.count-limit</name>
<value>2048</value>
<description>
The maximum number of arrays allowed for each array length.
</description>
</property>
<property>
<name>dfs.client.write.byte-array-manager.count-reset-time-period-ms</name>
<value>10000</value>
<description>
The time period in milliseconds that the allocation count for each array length is
reset to zero if there is no increment.
</description>
</property>
<property>
<name>dfs.client.write.byte-array-manager.count-threshold</name>
<value>128</value>
<description>
The count threshold for each array length so that a manager is created only after the
allocation count exceeds the threshold. In other words, the particular array length
is not managed until the allocation count exceeds the threshold.
</description>
</property>
<property>
<name>dfs.client.write.byte-array-manager.enabled</name>
<value>false</value>
<description>
If true, enables byte array manager used by DFSOutputStream.
</description>
</property>
<property>
<name>dfs.client.write.max-packets-in-flight</name>
<value>80</value>
<description>
The maximum number of DFSPackets allowed in flight.
</description>
</property>
<property>
<name>dfs.content-summary.limit</name>
<value>5000</value>
<description>
The maximum content summary counts allowed in one locking period. 0 or a negative number
means no limit (i.e. no yielding).
</description>
</property>
<property>
<name>dfs.content-summary.sleep-microsec</name>
<value>500</value>
<description>
The length of time in microseconds to put the thread to sleep, between reaquiring the locks
in content summary computation.
</description>
</property>
<property>
<name>dfs.data.transfer.client.tcpnodelay</name>
<value>true</value>
<description>
If true, set TCP_NODELAY to sockets for transferring data from DFS client.
</description>
</property>
<property>
<name>dfs.data.transfer.server.tcpnodelay</name>
<value>true</value>
<description>
If true, set TCP_NODELAY to sockets for transferring data between Datanodes.
</description>
</property>
<property>
<name>dfs.datanode.balance.max.concurrent.moves</name>
<value>50</value>
<description>
Maximum number of threads for Datanode balancer pending moves. This
value is reconfigurable via the "dfsadmin -reconfig" command.
</description>
</property>
<property>
<name>dfs.datanode.fsdataset.factory</name>
<value></value>
<description>
The class name for the underlying storage that stores replicas for a
Datanode. Defaults to
org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetFactory.
</description>
</property>
<property>
<name>dfs.datanode.fsdataset.volume.choosing.policy</name>
<value></value>
<description>
The class name of the policy for choosing volumes in the list of
directories. Defaults to
org.apache.hadoop.hdfs.server.datanode.fsdataset.RoundRobinVolumeChoosingPolicy.
If you would like to take into account available disk space, set the
value to
"org.apache.hadoop.hdfs.server.datanode.fsdataset.AvailableSpaceVolumeChoosingPolicy".
</description>
</property>
<property>
<name>dfs.datanode.hostname</name>
<value></value>
<description>
Optional. The hostname for the Datanode containing this
configuration file. Will be different for each machine.
Defaults to current hostname.
</description>
</property>
<property>
<name>dfs.datanode.lazywriter.interval.sec</name>
<value>60</value>
<description>
Interval in seconds for Datanodes for lazy persist writes.
</description>
</property>
<property>
<name>dfs.datanode.network.counts.cache.max.size</name>
<value>2147483647</value>
<description>
The maximum number of entries the datanode per-host network error
count cache may contain.
</description>
</property>
<property>
<name>dfs.datanode.oob.timeout-ms</name>
<value>1500,0,0,0</value>
<description>
Timeout value when sending OOB response for each OOB type, which are
OOB_RESTART, OOB_RESERVED1, OOB_RESERVED2, and OOB_RESERVED3,
respectively. Currently, only OOB_RESTART is used.
</description>
</property>
<property>
<name>dfs.datanode.parallel.volumes.load.threads.num</name>
<value></value>
<description>
Maximum number of threads to use for upgrading data directories.
The default value is the number of storage directories in the
DataNode.
</description>
</property>
<property>
<name>dfs.datanode.ram.disk.replica.tracker</name>
<value></value>
<description>
Name of the class implementing the RamDiskReplicaTracker interface.
Defaults to
org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.RamDiskReplicaLruTracker.
</description>
</property>
<property>
<name>dfs.datanode.restart.replica.expiration</name>
<value>50</value>
<description>
During shutdown for restart, the amount of time in seconds budgeted for
datanode restart.
</description>
</property>
<property>
<name>dfs.datanode.socket.reuse.keepalive</name>
<value>4000</value>
<description>
The window of time in ms before the DataXceiver closes a socket for a
single request. If a second request occurs within that window, the
socket can be reused.
</description>
</property>
<property>
<name>dfs.datanode.socket.write.timeout</name>
<value>480000</value>
<description>
Timeout in ms for clients socket writes to DataNodes.
</description>
</property>
<property>
<name>dfs.datanode.sync.behind.writes.in.background</name>
<value>false</value>
<description>
If set to true, then sync_file_range() system call will occur
asynchronously. This property is only valid when the property
dfs.datanode.sync.behind.writes is true.
</description>
</property>
<property>
<name>dfs.datanode.transferTo.allowed</name>
<value>true</value>
<description>
If false, break block transfers on 32-bit machines greater than
or equal to 2GB into smaller chunks.
</description>
</property>
<property>
<name>dfs.ha.fencing.methods</name>
<value></value>
<description>
A list of scripts or Java classes which will be used to fence
the Active NameNode during a failover. See the HDFS High
Availability documentation for details on automatic HA
configuration.
</description>
</property>
<property>
<name>dfs.ha.standby.checkpoints</name>
<value>true</value>
<description>
If true, a NameNode in Standby state periodically takes a checkpoint
of the namespace, saves it to its local storage and then upload to
the remote NameNode.
</description>
</property>
<property>
<name>dfs.ha.zkfc.port</name>
<value>8019</value>
<description>
The port number that the zookeeper failover controller RPC
server binds to.
</description>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/tmp/hadoop/dfs/journalnode/</value>
<description>
The directory where the journal edit files are stored.
</description>
</property>
<property>
<name>dfs.journalnode.kerberos.internal.spnego.principal</name>
<value></value>
<description>
Kerberos SPNEGO principal name used by the journal node.
</description>
</property>
<property>
<name>dfs.journalnode.kerberos.principal</name>
<value></value>
<description>
Kerberos principal name for the journal node.
</description>
</property>
<property>
<name>dfs.journalnode.keytab.file</name>
<value></value>
<description>
Kerberos keytab file for the journal node.
</description>
</property>
<property>
<name>dfs.ls.limit</name>
<value>1000</value>
<description>
Limit the number of files printed by ls. If less or equal to
zero, at most DFS_LIST_LIMIT_DEFAULT (= 1000) will be printed.
</description>
</property>
<property>
<name>dfs.mover.movedWinWidth</name>
<value>5400000</value>
<description>
The minimum time interval, in milliseconds, that a block can be
moved to another location again.
</description>
</property>
<property>
<name>dfs.mover.moverThreads</name>
<value>1000</value>
<description>
Configure the balancer's mover thread pool size.
</description>
</property>
<property>
<name>dfs.mover.retry.max.attempts</name>
<value>10</value>
<description>
The maximum number of retries before the mover consider the
move failed.
</description>
</property>
<property>
<name>dfs.mover.keytab.enabled</name>
<value>false</value>
<description>
Set to true to enable login using a keytab for Kerberized Hadoop.
</description>
</property>
<property>
<name>dfs.mover.address</name>
<value>0.0.0.0:0</value>
<description>
The hostname used for a keytab based Kerberos login. Keytab based login
can be enabled with dfs.mover.keytab.enabled.
</description>
</property>
<property>
<name>dfs.mover.keytab.file</name>
<value></value>
<description>
The keytab file used by the Mover to login as its
service principal. The principal name is configured with
dfs.mover.kerberos.principal. Keytab based login can be
enabled with dfs.mover.keytab.enabled.
</description>
</property>
<property>
<name>dfs.mover.kerberos.principal</name>
<value></value>
<description>
The Mover principal. This is typically set to
mover/_HOST@REALM.TLD. The Mover will substitute _HOST with its
own fully qualified hostname at startup. The _HOST placeholder
allows using the same configuration setting on different servers.
Keytab based login can be enabled with dfs.mover.keytab.enabled.
</description>
</property>
<property>
<name>dfs.namenode.audit.log.async</name>
<value>false</value>
<description>
If true, enables asynchronous audit log.
</description>
</property>
<property>
<name>dfs.namenode.audit.log.token.tracking.id</name>
<value>false</value>
<description>
If true, adds a tracking ID for all audit log events.
</description>
</property>
<property>
<name>dfs.namenode.available-space-block-placement-policy.balanced-space-preference-fraction</name>
<value>0.6</value>
<description>
Only used when the dfs.block.replicator.classname is set to
org.apache.hadoop.hdfs.server.blockmanagement.AvailableSpaceBlockPlacementPolicy.
Special value between 0 and 1, noninclusive. Increases chance of
placing blocks on Datanodes with less disk space used.
</description>
</property>
<property>
<name>dfs.namenode.backup.dnrpc-address</name>
<value></value>
<description>
Service RPC address for the backup Namenode.
</description>
</property>
<property>
<name>dfs.namenode.delegation.token.always-use</name>
<value>false</value>
<description>
For testing. Setting to true always allows the DT secret manager
to be used, even if security is disabled.
</description>
</property>
<property>
<name>dfs.namenode.edits.asynclogging</name>
<value>false</value>
<description>
If set to true, enables asynchronous edit logs in the Namenode. If set
to false, the Namenode uses the traditional synchronous edit logs.
</description>
</property>
<property>
<name>dfs.namenode.edits.dir.minimum</name>
<value>1</value>
<description>
dfs.namenode.edits.dir includes both required directories
(specified by dfs.namenode.edits.dir.required) and optional directories.
The number of usable optional directories must be greater than or equal
to this property. If the number of usable optional directories falls
below dfs.namenode.edits.dir.minimum, HDFS will issue an error.
This property defaults to 1.
</description>
</property>
<property>
<name>dfs.namenode.edits.journal-plugin</name>
<value></value>
<description>
When FSEditLog is creating JournalManagers from dfs.namenode.edits.dir,
and it encounters a URI with a schema different to "file" it loads the
name of the implementing class from
"dfs.namenode.edits.journal-plugin.[schema]". This class must implement
JournalManager and have a constructor which takes (Configuration, URI).
</description>
</property>
<property>
<name>dfs.namenode.file.close.num-committed-allowed</name>
<value>0</value>
<description>
Normally a file can only be closed with all its blocks are committed.
When this value is set to a positive integer N, a file can be closed
when N blocks are committed and the rest complete.
</description>
</property>
<property>
<name>dfs.namenode.inode.attributes.provider.class</name>
<value></value>
<description>
Name of class to use for delegating HDFS authorization.
</description>
</property>
<property>
<name>dfs.namenode.max-num-blocks-to-log</name>
<value>1000</value>
<description>
Puts a limit on the number of blocks printed to the log by the Namenode
after a block report.
</description>
</property>
<property>
<name>dfs.namenode.max.op.size</name>
<value>52428800</value>
<description>
Maximum opcode size in bytes.
</description>
</property>
<property>
<name>dfs.namenode.missing.checkpoint.periods.before.shutdown</name>
<value>3</value>
<description>
The number of checkpoint period windows (as defined by the property
dfs.namenode.checkpoint.period) allowed by the Namenode to perform
saving the namespace before shutdown.
</description>
</property>
<property>
<name>dfs.namenode.name.cache.threshold</name>
<value>10</value>
<description>
Frequently accessed files that are accessed more times than this
threshold are cached in the FSDirectory nameCache.
</description>
</property>
<property>
<name>dfs.namenode.replication.max-streams</name>
<value>2</value>
<description>
Hard limit for the number of highest-priority replication streams.
</description>
</property>
<property>
<name>dfs.namenode.replication.max-streams-hard-limit</name>
<value>4</value>
<description>
Hard limit for all replication streams.
</description>
</property>
<property>
<name>dfs.namenode.reconstruction.pending.timeout-sec</name>
<value>-1</value>
<description>
Timeout in seconds for block reconstruction. If this value is 0 or less,
then it will default to 5 minutes.
</description>
</property>
<property>
<name>dfs.namenode.stale.datanode.minimum.interval</name>
<value>3</value>
<description>
Minimum number of missed heartbeats intervals for a datanode to
be marked stale by the Namenode. The actual interval is calculated as
(dfs.namenode.stale.datanode.minimum.interval * dfs.heartbeat.interval)
in seconds. If this value is greater than the property
dfs.namenode.stale.datanode.interval, then the calculated value above
is used.
</description>
</property>
<property>
<name>dfs.namenode.storageinfo.defragment.timeout.ms</name>
<value>4</value>
<description>
Timeout value in ms for the StorageInfo compaction run.
</description>
</property>
<property>
<name>dfs.namenode.storageinfo.defragment.interval.ms</name>
<value>600000</value>
<description>
The thread for checking the StorageInfo for defragmentation will
run periodically. The time between runs is determined by this
property.
</description>
</property>
<property>
<name>dfs.namenode.storageinfo.defragment.ratio</name>
<value>0.75</value>
<description>
The defragmentation threshold for the StorageInfo.
</description>
</property>
<property>
<name>dfs.pipeline.ecn</name>
<value>false</value>
<description>
If true, allows ECN (explicit congestion notification) from the
Datanode.
</description>
</property>
<property>
<name>dfs.qjournal.accept-recovery.timeout.ms</name>
<value>120000</value>
<description>
Quorum timeout in milliseconds during accept phase of
recovery/synchronization for a specific segment.
</description>
</property>
<property>
<name>dfs.qjournal.finalize-segment.timeout.ms</name>
<value>120000</value>
<description>
Quorum timeout in milliseconds during finalizing for a specific
segment.
</description>
</property>
<property>
<name>dfs.qjournal.get-journal-state.timeout.ms</name>
<value>120000</value>
<description>
Timeout in milliseconds when calling getJournalState().
JournalNodes.
</description>
</property>
<property>
<name>dfs.qjournal.new-epoch.timeout.ms</name>
<value>120000</value>
<description>
Timeout in milliseconds when getting an epoch number for write
access to JournalNodes.
</description>
</property>
<property>
<name>dfs.qjournal.prepare-recovery.timeout.ms</name>
<value>120000</value>
<description>
Quorum timeout in milliseconds during preparation phase of
recovery/synchronization for a specific segment.
</description>
</property>
<property>
<name>dfs.qjournal.queued-edits.limit.mb</name>
<value>10</value>
<description>
Queue size in MB for quorum journal edits.
</description>
</property>
<property>
<name>dfs.qjournal.select-input-streams.timeout.ms</name>
<value>20000</value>
<description>
Timeout in milliseconds for accepting streams from JournalManagers.
</description>
</property>
<property>
<name>dfs.qjournal.start-segment.timeout.ms</name>
<value>20000</value>
<description>
Quorum timeout in milliseconds for starting a log segment.
</description>
</property>
<property>
<name>dfs.qjournal.write-txns.timeout.ms</name>
<value>20000</value>
<description>
Write timeout in milliseconds when writing to a quorum of remote
journals.
</description>
</property>
<property>
<name>dfs.quota.by.storage.type.enabled</name>
<value>true</value>
<description>
If true, enables quotas based on storage type.
</description>
</property>
<property>
<name>dfs.secondary.namenode.kerberos.principal</name>
<value></value>
<description>
Kerberos principal name for the Secondary NameNode.
</description>
</property>
<property>
<name>dfs.secondary.namenode.keytab.file</name>
<value></value>
<description>
Kerberos keytab file for the Secondary NameNode.
</description>
</property>
<property>
<name>dfs.web.authentication.filter</name>
<value>org.apache.hadoop.hdfs.web.AuthFilter</value>
<description>
Authentication filter class used for WebHDFS.
</description>
</property>
<property>
<name>dfs.web.authentication.simple.anonymous.allowed</name>
<value></value>
<description>
If true, allow anonymous user to access WebHDFS. Set to
false to disable anonymous authentication.
</description>
</property>
<property>
<name>dfs.web.ugi</name>
<value></value>
<description>
dfs.web.ugi is deprecated. Use hadoop.http.staticuser.user instead.
</description>
</property>
<property>
<name>dfs.webhdfs.netty.high.watermark</name>
<value>65535</value>
<description>
High watermark configuration to Netty for Datanode WebHdfs.
</description>
</property>
<property>
<name>dfs.webhdfs.netty.low.watermark</name>
<value>32768</value>
<description>
Low watermark configuration to Netty for Datanode WebHdfs.
</description>
</property>
<property>
<name>dfs.webhdfs.oauth2.access.token.provider</name>
<value></value>
<description>
Access token provider class for WebHDFS using OAuth2.
Defaults to org.apache.hadoop.hdfs.web.oauth2.ConfCredentialBasedAccessTokenProvider.
</description>
</property>
<property>
<name>dfs.webhdfs.oauth2.client.id</name>
<value></value>
<description>
Client id used to obtain access token with either credential or
refresh token.
</description>
</property>
<property>
<name>dfs.webhdfs.oauth2.enabled</name>
<value>false</value>
<description>
If true, enables OAuth2 in WebHDFS
</description>
</property>
<property>
<name>dfs.webhdfs.oauth2.refresh.url</name>
<value></value>
<description>
URL against which to post for obtaining bearer token with
either credential or refresh token.
</description>
</property>
<property>
<name>ssl.server.keystore.keypassword</name>
<value></value>
<description>
Keystore key password for HTTPS SSL configuration
</description>
</property>
<property>
<name>ssl.server.keystore.location</name>
<value></value>
<description>
Keystore location for HTTPS SSL configuration
</description>
</property>
<property>
<name>ssl.server.keystore.password</name>
<value></value>
<description>
Keystore password for HTTPS SSL configuration
</description>
</property>
<property>
<name>ssl.server.truststore.location</name>
<value></value>
<description>
Truststore location for HTTPS SSL configuration
</description>
</property>
<property>
<name>ssl.server.truststore.password</name>
<value></value>
<description>
Truststore password for HTTPS SSL configuration
</description>
</property>
<!--Disk baalncer properties-->
<property>
<name>dfs.disk.balancer.max.disk.throughputInMBperSec</name>
<value>10</value>
<description>Maximum disk bandwidth used by diskbalancer
during read from a source disk. The unit is MB/sec.
</description>
</property>
<property>
<name>dfs.disk.balancer.block.tolerance.percent</name>
<value>10</value>
<description>
When a disk balancer copy operation is proceeding, the datanode is still
active. So it might not be possible to move the exactly specified
amount of data. So tolerance allows us to define a percentage which
defines a good enough move.
</description>
</property>
<property>
<name>dfs.disk.balancer.max.disk.errors</name>
<value>5</value>
<description>
During a block move from a source to destination disk, we might
encounter various errors. This defines how many errors we can tolerate
before we declare a move between 2 disks (or a step) has failed.
</description>
</property>
<property>
<name>dfs.disk.balancer.enabled</name>
<value>false</value>
<description>
This enables the diskbalancer feature on a cluster. By default, disk
balancer is disabled.
</description>
</property>
<property>
<name>dfs.disk.balancer.plan.threshold.percent</name>
<value>10</value>
<description>
The percentage threshold value for volume Data Density in a plan.
If the absolute value of volume Data Density which is out of
threshold value in a node, it means that the volumes corresponding to
the disks should do the balancing in the plan. The default value is 10.
</description>
</property>
<property>
<name>dfs.lock.suppress.warning.interval</name>
<value>10s</value>
<description>Instrumentation reporting long critical sections will suppress
consecutive warnings within this interval.</description>
</property>
<property>
<name>httpfs.buffer.size</name>
<value>4096</value>
<description>
The size buffer to be used when creating or opening httpfs filesystem IO stream.
</description>
</property>
<property>
<name>dfs.webhdfs.use.ipc.callq</name>
<value>true</value>
<description>Enables routing of webhdfs calls through rpc
call queue</description>
</property>
<property>
<name>dfs.datanode.disk.check.min.gap</name>
<value>15m</value>
<description>
The minimum gap between two successive checks of the same DataNode
volume. This setting supports multiple time unit suffixes as described
in dfs.heartbeat.interval. If no suffix is specified then milliseconds
is assumed.
</description>
</property>
<property>
<name>dfs.datanode.disk.check.timeout</name>
<value>10m</value>
<description>
Maximum allowed time for a disk check to complete. If the check does
not complete within this time interval then the disk is declared as
failed. This setting supports multiple time unit suffixes as described
in dfs.heartbeat.interval. If no suffix is specified then milliseconds
is assumed.
</description>
</property>
</configuration>
Reference in New Issue View Git Blame Copy Permalink