<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>hadoop.hdfs.configuration.version</name>
<value>1</value>
<description>version of this configuration file</description>
</property>
<property>
<name>dfs.namenode.logging.level</name>
<value>info</value>
<description>
The logging level for dfs namenode. Other values are "dir" (trace
namespace mutations), "block" (trace block under/over replications
and block creations/deletions), or "all".
</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.
</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.secondary.http-address</name>
<value>0.0.0.0:50090</value>
<description>
The secondary namenode http server address and port.
</description>
</property>
<property>
<name>dfs.namenode.secondary.https-address</name>
<value>0.0.0.0:50091</value>
<description>
The secondary namenode HTTPS server address and port.
</description>
</property>
<property>
<name>dfs.datanode.address</name>
<value>0.0.0.0:50010</value>
<description>
The datanode server address and port for data transfer.
</description>
</property>
<property>
<name>dfs.datanode.http.address</name>
<value>0.0.0.0:50075</value>
<description>
The datanode http server address and port.
</description>
</property>
<property>
<name>dfs.datanode.ipc.address</name>
<value>0.0.0.0:50020</value>
<description>
The datanode ipc server address and port.
</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>0.0.0.0:50070</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 adress 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.https.enable</name>
<value>false</value>
<description>
Deprecated. Use "dfs.http.policy" instead.
</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>0.0.0.0:50475</value>
<description>The datanode secure http server address and port.</description>
</property>
<property>
<name>dfs.namenode.https-address</name>
<value>0.0.0.0:50470</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 adress 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.
</description>
</property>
<property>
<name>dfs.datanode.dns.nameserver</name>
<value>default</value>
<description>The host name or IP address of the name server (DNS)
which a DataNode should use to determine the host name used by the
NameNode for communication and display purposes.
</description>
</property>
<property>
<name>dfs.namenode.backup.address</name>
<value>0.0.0.0:50100</value>
<description>
The backup node server address and port.
If the port is 0 then the server will start on a free port.
</description>
</property>
<property>
<name>dfs.namenode.backup.http-address</name>
<value>0.0.0.0:50105</value>
<description>
The backup node http server address and port.
If the port is 0 then the server will start on a free port.
</description>
</property>
<property>
<name>dfs.namenode.replication.considerLoad</name>
<value>true</value>
<description>Decide if chooseTarget considers the target's load or not
</description>
</property>
<property>
<name>dfs.default.chunk.view.size</name>
<value>32768</value>
<description>The number of bytes to view for a file on the browser.
</description>
</property>
<property>
<name>dfs.datanode.du.reserved</name>
<value>0</value>
<description>Reserved space in bytes per volume. Always leave this much space free for non dfs use.
</description>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file://${hadoop.tmp.dir}/dfs/name</value>
<description>Determines where on the local filesystem the DFS name node
should store the name table(fsimage). If this is a comma-delimited list
of directories then the name table is replicated in all of the
directories, for redundancy. </description>
</property>
<property>
<name>dfs.namenode.name.dir.restore</name>
<value>false</value>
<description>Set to true to enable NameNode to attempt recovering a
previously failed dfs.namenode.name.dir. When enabled, a recovery of any
failed directory is attempted during checkpoint.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.max-component-length</name>
<value>255</value>
<description>Defines the maximum number of bytes in UTF-8 encoding in each
component of a path. A value of 0 will disable the check.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.max-directory-items</name>
<value>1048576</value>
<description>Defines the maximum number of items that a directory may
contain. A value of 0 will disable the check.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.min-block-size</name>
<value>1048576</value>
<description>Minimum block size in bytes, enforced by the Namenode at create
time. This prevents the accidental creation of files with tiny block
sizes (and thus many blocks), which can degrade
performance.</description>
</property>
<property>
<name>dfs.namenode.fs-limits.max-blocks-per-file</name>
<value>1048576</value>
<description>Maximum number of blocks per file, enforced by the Namenode on
write. This prevents the creation of extremely large files which can
degrade performance.</description>
</property>
<property>
<name>dfs.namenode.edits.dir</name>
<value>${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.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.</description>
</property>
<!--
<property>
<name>dfs.cluster.administrators</name>
<value>ACL for the admins</value>
<description>This configuration is used to control who can access the
default servlets in the namenode, etc.
</description>
</property>
-->
<property>
<name>dfs.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.block.access.token.enable</name>
<value>false</value>
<description>
If "true", access tokens are used as capabilities for accessing datanodes.
If "false", no access tokens are checked on accessing datanodes.
</description>
</property>
<property>
<name>dfs.block.access.key.update.interval</name>
<value>600</value>
<description>
Interval in minutes at which namenode updates its access keys.
</description>
</property>
<property>
<name>dfs.block.access.token.lifetime</name>
<value>600</value>
<description>The lifetime of access tokens in minutes.</description>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file://${hadoop.tmp.dir}/dfs/data</value>
<description>Determines where on the local filesystem an DFS data node
should store its blocks. If this is a comma-delimited
list of directories, then data will be stored in all named
directories, typically on different devices.
Directories that do not exist are ignored.
</description>
</property>
<property>
<name>dfs.datanode.data.dir.perm</name>
<value>700</value>
<description>Permissions for the directories on on the local filesystem where
the DFS data node store its blocks. The permissions can either be octal or
symbolic.</description>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
<description>Default block replication.
The actual number of replications can be specified when the file is created.
The default is used if replication is not specified in create time.
</description>
</property>
<property>
<name>dfs.replication.max</name>
<value>512</value>
<description>Maximal block replication.
</description>
</property>
<property>
<name>dfs.namenode.replication.min</name>
<value>1</value>
<description>Minimal block replication.
</description>
</property>
<property>
<name>dfs.blocksize</name>
<value>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.blockreport.intervalMsec</name>
<value>21600000</value>
<description>Determines block reporting interval in milliseconds.</description>
</property>
<property>
<name>dfs.blockreport.initialDelay</name> <value>0</value>
<description>Delay for first block report in seconds.</description>
</property>
<property>
<name>dfs.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.datanode.directoryscan.interval</name>
<value>21600</value>
<description>Interval in seconds for Datanode to scan data directories and
reconcile the difference between blocks in memory and on the disk.
</description>
</property>
<property>
<name>dfs.datanode.directoryscan.threads</name>
<value>1</value>
<description>How many threads should the threadpool used to compile reports
for volumes in parallel have.
</description>
</property>
<property>
<name>dfs.heartbeat.interval</name>
<value>3</value>
<description>Determines datanode heartbeat interval in seconds.</description>
</property>
<property>
<name>dfs.namenode.handler.count</name>
<value>10</value>
<description>The number of server threads for the namenode.</description>
</property>
<property>
<name>dfs.namenode.safemode.threshold-pct</name>
<value>0.999f</value>
<description>
Specifies the percentage of blocks that should satisfy
the minimal replication requirement defined by dfs.namenode.replication.min.
Values less than or equal to 0 mean not to wait for any particular
percentage of blocks before exiting safemode.
Values greater than 1 will make safe mode permanent.
</description>
</property>
<property>
<name>dfs.namenode.safemode.min.datanodes</name>
<value>0</value>
<description>
Specifies the number of datanodes that must be considered alive
before the name node exits safemode.
Values less than or equal to 0 mean not to take the number of live
datanodes into account when deciding whether to remain in safe mode
during startup.
Values greater than the number of datanodes in the cluster
will make safe mode permanent.
</description>
</property>
<property>
<name>dfs.namenode.safemode.extension</name>
<value>30000</value>
<description>
Determines extension of safe mode in milliseconds
after the threshold level is reached.
</description>
</property>
<property>
<name>dfs.datanode.balance.bandwidthPerSec</name>
<value>1048576</value>
<description>
Specifies the maximum amount of bandwidth that each datanode
can utilize for the balancing purpose in term of
the number of bytes per second.
</description>
</property>
<property>
<name>dfs.hosts</name>
<value></value>
<description>Names a file that contains a list of hosts that are
permitted to connect to the namenode. The full pathname of the file
must be specified. If the value is empty, all hosts are
permitted.</description>
</property>
<property>
<name>dfs.hosts.exclude</name>
<value></value>
<description>Names a file that contains a list of hosts that are
not permitted to connect to the namenode. The full pathname of the
file must be specified. If the value is empty, no hosts are
excluded.</description>
</property>
<property>
<name>dfs.namenode.max.objects</name>
<value>0</value>
<description>The maximum number of files, directories and blocks
dfs supports. A value of zero indicates no limit to the number
of objects that dfs supports.
</description>
</property>
<property>
<name>dfs.namenode.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>30</value>
<description>Namenode periodicity in seconds to check if decommission is
complete.</description>
</property>
<property>
<name>dfs.namenode.decommission.nodes.per.interval</name>
<value>5</value>
<description>The number of nodes namenode checks if decommission is complete
in each dfs.namenode.decommission.interval.</description>
</property>
<property>
<name>dfs.namenode.replication.interval</name>
<value>3</value>
<description>The periodicity in seconds with which the namenode computes
repliaction work for datanodes. </description>
</property>
<property>
<name>dfs.namenode.accesstime.precision</name>
<value>3600000</value>
<description>The access time for HDFS file is precise upto this value.
The default value is 1 hour. Setting a value of 0 disables
access times for HDFS.
</description>
</property>
<property>
<name>dfs.datanode.plugins</name>
<value></value>
<description>Comma-separated list of datanode plug-ins to be activated.
</description>
</property>
<property>
<name>dfs.namenode.plugins</name>
<value></value>
<description>Comma-separated list of namenode plug-ins to be activated.
</description>
</property>
<property>
<name>dfs.stream-buffer-size</name>
<value>4096</value>
<description>The size of buffer to stream files.
The size of this buffer should probably be a multiple of hardware
page size (4096 on Intel x86), and it determines how much data is
buffered during read and write operations.</description>
</property>
<property>
<name>dfs.bytes-per-checksum</name>
<value>512</value>
<description>The number of bytes per checksum. Must not be larger than
dfs.stream-buffer-size</description>
</property>
<property>
<name>dfs.client-write-packet-size</name>
<value>65536</value>
<description>Packet size for clients to write</description>
</property>
<property>
<name>dfs.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 directoires then teh edits is
replicated in all of the directoires for redundancy.
Default value is same as dfs.namenode.checkpoint.dir
</description>
</property>
<property>
<name>dfs.namenode.checkpoint.period</name>
<value>3600</value>
<description>The number of seconds between two periodic checkpoints.
</description>
</property>
<property>
<name>dfs.namenode.checkpoint.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>60</value>
<description>The SecondaryNameNode and CheckpointNode will poll the NameNode
every 'dfs.namenode.checkpoint.check.period' seconds to query the number
of uncheckpointed transactions.
</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.num.checkpoints.retained</name>
<value>2</value>
<description>The number of image checkpoint files that will be retained by
the NameNode and Secondary NameNode in their storage directories. All edit
logs 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. This 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 tranfer.
</description>
</property>
<property>
<name>dfs.image.transfer.bandwidthPerSec</name>
<value>0</value>
<description>
Maximum bandwidth used for image transfer 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.
</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.readahead.bytes</name>
<value>4193404</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 spage 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 spage 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>30</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.
</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.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).
</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>120</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.
</description>
</property>
<property>
<name>dfs.ha.tail-edits.period</name>
<value>60</value>
<description>
How often, in seconds, the StandbyNode should check for new
finalized log segments in the shared edits log.
</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.support.append</name>
<value>true</value>
<description>
Does HDFS allow appends to files?
</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.internal.spnego.principal</name>
<value>${dfs.web.authentication.kerberos.principal}</value>
</property>
<property>
<name>dfs.secondary.namenode.kerberos.internal.spnego.principal</name>
<value>${dfs.web.authentication.kerberos.principal}</value>
</property>
<property>
<name>dfs.namenode.avoid.read.stale.datanode</name>
<value>false</value>
<description>
Indicate whether or not to avoid reading from "stale" 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 "stale" 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>dfs.webhdfs.enabled</name>
<value>true</value>
<description>
Enable WebHDFS (REST API) in Namenodes and Datanodes.
</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.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>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.
</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.datanode.hdfs-blocks-metadata.enabled</name>
<value>false</value>
<description>
Boolean which enables backend datanode-side support for the experimental DistributedFileSystem#getFileVBlockStorageLocations API.
</description>
</property>
<property>
<name>dfs.client.file-block-storage-locations.num-threads</name>
<value>10</value>
<description>
Number of threads used for making parallel RPCs in DistributedFileSystem#getFileBlockStorageLocations().
</description>
</property>
<property>
<name>dfs.client.file-block-storage-locations.timeout.millis</name>
<value>1000</value>
<description>
Timeout (in milliseconds) for the parallel RPCs made in DistributedFileSystem#getFileBlockStorageLocations().
</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.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.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 size of that 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.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 allowd 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.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.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.
</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>
</configuration>
转载于:https://my.oschina.net/darionyaphet/blog/412948