Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance. Project price only 1 $
You can buy this project and download/modify it how often you want.
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
<!-- Do not modify this file directly. Instead, copy entries that you -->
<!-- wish to modify from this file into core-site.xml and change them -->
<!-- there. If core-site.xml does not already exist, create it. -->
<configuration>
<!--- global properties -->
<property>
<name>hadoop.common.configuration.version</name>
<value>3.0.0</value>
<description>version of this configuration file</description>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/tmp/hadoop-${user.name}</value>
<description>A base for other temporary directories.</description>
</property>
<property>
<name>hadoop.http.filter.initializers</name>
<value>org.apache.hadoop.http.lib.StaticUserWebFilter</value>
<description>A comma separated list of class names. Each class in the list
must extend org.apache.hadoop.http.FilterInitializer. The corresponding
Filter will be initialized. Then, the Filter will be applied to all user
facing jsp and servlet web pages. The ordering of the list defines the
ordering of the filters.</description>
</property>
<property>
<name>hadoop.http.idle_timeout.ms</name>
<value>60000</value>
<description>
NN/JN/DN Server connection timeout in milliseconds.
</description>
</property>
<!--- security properties -->
<property>
<name>hadoop.security.authorization</name>
<value>false</value>
<description>Is service-level authorization enabled?</description>
</property>
<property>
<name>hadoop.security.instrumentation.requires.admin</name>
<value>false</value>
<description>
Indicates if administrator ACLs are required to access
instrumentation servlets (JMX, METRICS, CONF, STACKS).
</description>
</property>
<property>
<name>hadoop.security.authentication</name>
<value>simple</value>
<description>Possible values are simple (no authentication), and kerberos
</description>
</property>
<property>
<name>hadoop.security.group.mapping</name>
<value>org.apache.hadoop.security.JniBasedUnixGroupsMappingWithFallback</value>
<description>
Class for user to group mapping (get groups for a given user) for ACL.
The default implementation,
org.apache.hadoop.security.JniBasedUnixGroupsMappingWithFallback,
will determine if the Java Native Interface (JNI) is available. If JNI is
available the implementation will use the API within hadoop to resolve a
list of groups for a user. If JNI is not available then the shell
implementation, ShellBasedUnixGroupsMapping, is used. This implementation
shells out to the Linux/Unix environment with the
<code>bash -c groups</code> command to resolve a list of groups for a user.
</description>
</property>
<property>
<name>hadoop.security.dns.interface</name>
<description>
The name of the Network Interface from which the service should determine
its host name for Kerberos login. e.g. eth2. In a multi-homed environment,
the setting can be used to affect the _HOST substitution in the service
Kerberos principal. If this configuration value is not set, the service
will use its default hostname as returned by
InetAddress.getLocalHost().getCanonicalHostName().
Most clusters will not require this setting.
</description>
</property>
<property>
<name>hadoop.security.dns.nameserver</name>
<description>
The host name or IP address of the name server (DNS) which a service Node
should use to determine its own host name for Kerberos Login. Requires
hadoop.security.dns.interface.
Most clusters will not require this setting.
</description>
</property>
<property>
<name>hadoop.security.dns.log-slow-lookups.enabled</name>
<value>false</value>
<description>
Time name lookups (via SecurityUtil) and log them if they exceed the
configured threshold.
</description>
</property>
<property>
<name>hadoop.security.dns.log-slow-lookups.threshold.ms</name>
<value>1000</value>
<description>
If slow lookup logging is enabled, this threshold is used to decide if a
lookup is considered slow enough to be logged.
</description>
</property>
<property>
<name>hadoop.security.groups.cache.secs</name>
<value>300</value>
<description>
This is the config controlling the validity of the entries in the cache
containing the user->group mapping. When this duration has expired,
then the implementation of the group mapping provider is invoked to get
the groups of the user and then cached back.
</description>
</property>
<property>
<name>hadoop.security.groups.negative-cache.secs</name>
<value>30</value>
<description>
Expiration time for entries in the the negative user-to-group mapping
caching, in seconds. This is useful when invalid users are retrying
frequently. It is suggested to set a small value for this expiration, since
a transient error in group lookup could temporarily lock out a legitimate
user.
Set this to zero or negative value to disable negative user-to-group caching.
</description>
</property>
<property>
<name>hadoop.security.groups.cache.warn.after.ms</name>
<value>5000</value>
<description>
If looking up a single user to group takes longer than this amount of
milliseconds, we will log a warning message.
</description>
</property>
<property>
<name>hadoop.security.groups.cache.background.reload</name>
<value>false</value>
<description>
Whether to reload expired user->group mappings using a background thread
pool. If set to true, a pool of
hadoop.security.groups.cache.background.reload.threads is created to
update the cache in the background.
</description>
</property>
<property>
<name>hadoop.security.groups.cache.background.reload.threads</name>
<value>3</value>
<description>
Only relevant if hadoop.security.groups.cache.background.reload is true.
Controls the number of concurrent background user->group cache entry
refreshes. Pending refresh requests beyond this value are queued and
processed when a thread is free.
</description>
</property>
<property>
<name>hadoop.security.groups.shell.command.timeout</name>
<value>0s</value>
<description>
Used by the ShellBasedUnixGroupsMapping class, this property controls how
long to wait for the underlying shell command that is run to fetch groups.
Expressed in seconds (e.g. 10s, 1m, etc.), if the running command takes
longer than the value configured, the command is aborted and the groups
resolver would return a result of no groups found. A value of 0s (default)
would mean an infinite wait (i.e. wait until the command exits on its own).
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.connection.timeout.ms</name>
<value>60000</value>
<description>
This property is the connection timeout (in milliseconds) for LDAP
operations. If the LDAP provider doesn't establish a connection within the
specified period, it will abort the connect attempt. Non-positive value
means no LDAP connection timeout is specified in which case it waits for the
connection to establish until the underlying network times out.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.read.timeout.ms</name>
<value>60000</value>
<description>
This property is the read timeout (in milliseconds) for LDAP
operations. If the LDAP provider doesn't get a LDAP response within the
specified period, it will abort the read attempt. Non-positive value
means no read timeout is specified in which case it waits for the response
infinitely.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.num.attempts</name>
<value>3</value>
<description>
This property is the number of attempts to be made for LDAP operations.
If this limit is exceeded, LdapGroupsMapping will return an empty
group list.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.num.attempts.before.failover</name>
<value>3</value>
<description>
This property is the number of attempts to be made for LDAP operations
using a single LDAP instance. If multiple LDAP servers are configured
and this number of failed operations is reached, we will switch to the
next LDAP server. The configuration for the overall number of attempts
will still be respected, failover will thus be performed only if this
property is less than hadoop.security.group.mapping.ldap.num.attempts.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.url</name>
<value></value>
<description>
The URL of the LDAP server(s) to use for resolving user groups when using
the LdapGroupsMapping user to group mapping. Supports configuring multiple
LDAP servers via a comma-separated list.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.ssl</name>
<value>false</value>
<description>
Whether or not to use SSL when connecting to the LDAP server.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.ssl.keystore</name>
<value></value>
<description>
File path to the SSL keystore that contains the SSL certificate required
by the LDAP server.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.ssl.keystore.password.file</name>
<value></value>
<description>
The path to a file containing the password of the LDAP SSL keystore. If
the password is not configured in credential providers and the property
hadoop.security.group.mapping.ldap.ssl.keystore.password is not set,
LDAPGroupsMapping reads password from the file.
IMPORTANT: This file should be readable only by the Unix user running
the daemons and should be a local file.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.ssl.keystore.password</name>
<value></value>
<description>
The password of the LDAP SSL keystore. this property name is used as an
alias to get the password from credential providers. If the password can
not be found and hadoop.security.credential.clear-text-fallback is true
LDAPGroupsMapping uses the value of this property for password.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.conversion.rule</name>
<value>none</value>
<description>
The rule is applied on the group names received from LDAP when
RuleBasedLdapGroupsMapping is configured.
Supported rules are "to_upper", "to_lower" and "none".
to_upper: This will convert all the group names to uppercase.
to_lower: This will convert all the group names to lowercase.
none: This will retain the source formatting, this is default value.
</description>
</property>
<property>
<name>hadoop.security.credential.clear-text-fallback</name>
<value>true</value>
<description>
true or false to indicate whether or not to fall back to storing credential
password as clear text. The default value is true. This property only works
when the password can't not be found from credential providers.
</description>
</property>
<property>
<name>hadoop.security.credential.provider.path</name>
<value></value>
<description>
A comma-separated list of URLs that indicates the type and
location of a list of providers that should be consulted.
</description>
</property>
<property>
<name>hadoop.security.credstore.java-keystore-provider.password-file</name>
<value></value>
<description>
The path to a file containing the custom password for all keystores
that may be configured in the provider path.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.ssl.truststore</name>
<value></value>
<description>
File path to the SSL truststore that contains the root certificate used to
sign the LDAP server's certificate. Specify this if the LDAP server's
certificate is not signed by a well known certificate authority.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.ssl.truststore.password.file</name>
<value></value>
<description>
The path to a file containing the password of the LDAP SSL truststore.
IMPORTANT: This file should be readable only by the Unix user running
the daemons.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.bind.users</name>
<value></value>
<description>
Aliases of users to be used to bind as when connecting to the LDAP
server(s). Each alias will have to have its distinguished name and
password specified through:
hadoop.security.group.mapping.ldap.bind.user
and a password configuration such as:
hadoop.security.group.mapping.ldap.bind.password.alias
For example, if:
hadoop.security.group.mapping.ldap.bind.users=alias1,alias2
then the following configuration is valid:
hadoop.security.group.mapping.ldap.bind.users.alias1.bind.user=bindUser1
hadoop.security.group.mapping.ldap.bind.users.alias1.bind.password.alias=
bindPasswordAlias1
hadoop.security.group.mapping.ldap.bind.users.alias2.bind.user=bindUser2
hadoop.security.group.mapping.ldap.bind.users.alias2.bind.password.alias=
bindPasswordAlias2
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.bind.user</name>
<value></value>
<description>
The distinguished name of the user to bind as when connecting to the LDAP
server. This may be left blank if the LDAP server supports anonymous binds.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.bind.password.alias</name>
<value></value>
<description>
The alias of the bind user to be used to get the password from credential
providers. If the alias is empty, property
hadoop.security.group.mapping.ldap.bind.password is used instead.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.bind.password.file</name>
<value></value>
<description>
The path to a file containing the password of the bind user. If
the password is not configured in credential providers and the property
hadoop.security.group.mapping.ldap.bind.password is not set,
LDAPGroupsMapping reads password from the file.
IMPORTANT: This file should be readable only by the Unix user running
the daemons and should be a local file.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.bind.password</name>
<value></value>
<description>
The password of the bind user. this property name is used as an
alias to get the password from credential providers. If the password can
not be found and hadoop.security.credential.clear-text-fallback is true
LDAPGroupsMapping uses the value of this property for password.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.base</name>
<value></value>
<description>
The search base for the LDAP connection. This is a distinguished name,
and will typically be the root of the LDAP directory.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.userbase</name>
<value></value>
<description>
The search base for the LDAP connection for user search query. This is a
distinguished name, and its the root of the LDAP directory for users.
If not set, hadoop.security.group.mapping.ldap.base is used.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.groupbase</name>
<value></value>
<description>
The search base for the LDAP connection for group search . This is a
distinguished name, and its the root of the LDAP directory for groups.
If not set, hadoop.security.group.mapping.ldap.base is used.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.search.filter.user</name>
<value>(&(objectClass=user)(sAMAccountName={0}))</value>
<description>
An additional filter to use when searching for LDAP users. The default will
usually be appropriate for Active Directory installations. If connecting to
an LDAP server with a non-AD schema, this should be replaced with
(&(objectClass=inetOrgPerson)(uid={0}). {0} is a special string used to
denote where the username fits into the filter.
If the LDAP server supports posixGroups, Hadoop can enable the feature by
setting the value of this property to "posixAccount" and the value of
the hadoop.security.group.mapping.ldap.search.filter.group property to
"posixGroup".
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.search.filter.group</name>
<value>(objectClass=group)</value>
<description>
An additional filter to use when searching for LDAP groups. This should be
changed when resolving groups against a non-Active Directory installation.
See the description of hadoop.security.group.mapping.ldap.search.filter.user
to enable posixGroups support.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.search.attr.memberof</name>
<value></value>
<description>
The attribute of the user object that identifies its group objects. By
default, Hadoop makes two LDAP queries per user if this value is empty. If
set, Hadoop will attempt to resolve group names from this attribute,
instead of making the second LDAP query to get group objects. The value
should be 'memberOf' for an MS AD installation.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.search.attr.member</name>
<value>member</value>
<description>
The attribute of the group object that identifies the users that are
members of the group. The default will usually be appropriate for
any LDAP installation.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.search.attr.group.name</name>
<value>cn</value>
<description>
The attribute of the group object that identifies the group name. The
default will usually be appropriate for all LDAP systems.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.search.group.hierarchy.levels</name>
<value>0</value>
<description>
The number of levels to go up the group hierarchy when determining
which groups a user is part of. 0 Will represent checking just the
group that the user belongs to. Each additional level will raise the
time it takes to execute a query by at most
hadoop.security.group.mapping.ldap.directory.search.timeout.
The default will usually be appropriate for all LDAP systems.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.posix.attr.uid.name</name>
<value>uidNumber</value>
<description>
The attribute of posixAccount to use when groups for membership.
Mostly useful for schemas wherein groups have memberUids that use an
attribute other than uidNumber.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.posix.attr.gid.name</name>
<value>gidNumber</value>
<description>
The attribute of posixAccount indicating the group id.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.ldap.directory.search.timeout</name>
<value>10000</value>
<description>
The attribute applied to the LDAP SearchControl properties to set a
maximum time limit when searching and awaiting a result.
Set to 0 if infinite wait period is desired.
Default is 10 seconds. Units in milliseconds.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.providers</name>
<value></value>
<description>
Comma separated of names of other providers to provide user to group
mapping. Used by CompositeGroupsMapping.
</description>
</property>
<property>
<name>hadoop.security.group.mapping.providers.combined</name>
<value>true</value>
<description>
true or false to indicate whether groups from the providers are combined or
not. The default value is true. If true, then all the providers will be
tried to get groups and all the groups are combined to return as the final
results. Otherwise, providers are tried one by one in the configured list
order, and if any groups are retrieved from any provider, then the groups
will be returned without trying the left ones.
</description>
</property>
<property>
<name>hadoop.security.service.user.name.key</name>
<value></value>
<description>
For those cases where the same RPC protocol is implemented by multiple
servers, this configuration is required for specifying the principal
name to use for the service when the client wishes to make an RPC call.
</description>
</property>
<property>
<name>fs.azure.user.agent.prefix</name>
<value>unknown</value>
<description>
WASB passes User-Agent header to the Azure back-end. The default value
contains WASB version, Java Runtime version, Azure Client library version,
and the value of the configuration option fs.azure.user.agent.prefix.
</description>
</property>
<property>
<name>hadoop.security.uid.cache.secs</name>
<value>14400</value>
<description>
This is the config controlling the validity of the entries in the cache
containing the userId to userName and groupId to groupName used by
NativeIO getFstat().
</description>
</property>
<property>
<name>hadoop.service.shutdown.timeout</name>
<value>30s</value>
<description>
Timeout to wait for each shutdown operation to complete.
If a hook takes longer than this time to complete, it will be interrupted,
so the service will shutdown. This allows the service shutdown
to recover from a blocked operation.
Some shutdown hooks may need more time than this, for example when
a large amount of data needs to be uploaded to an object store.
In this situation: increase the timeout.
The minimum duration of the timeout is 1 second, "1s".
</description>
</property>
<property>
<name>hadoop.rpc.protection</name>
<value>authentication</value>
<description>A comma-separated list of protection values for secured sasl
connections. Possible values are authentication, integrity and privacy.
authentication means authentication only and no integrity or privacy;
integrity implies authentication and integrity are enabled; and privacy
implies all of authentication, integrity and privacy are enabled.
hadoop.security.saslproperties.resolver.class can be used to override
the hadoop.rpc.protection for a connection at the server side.
</description>
</property>
<property>
<name>hadoop.security.saslproperties.resolver.class</name>
<value></value>
<description>SaslPropertiesResolver used to resolve the QOP used for a
connection. If not specified, the full set of values specified in
hadoop.rpc.protection is used while determining the QOP used for the
connection. If a class is specified, then the QOP values returned by
the class will be used while determining the QOP used for the connection.
</description>
</property>
<property>
<name>hadoop.security.sensitive-config-keys</name>
<value>
secret$
password$
ssl.keystore.pass$
fs.s3a.server-side-encryption.key
fs.s3a.*.server-side-encryption.key
fs.s3a.secret.key
fs.s3a.*.secret.key
fs.s3a.session.key
fs.s3a.*.session.key
fs.s3a.session.token
fs.s3a.*.session.token
fs.azure.account.key.*
fs.azure.oauth2.*
fs.adl.oauth2.*
credential$
oauth.*secret
oauth.*password
oauth.*token
hadoop.security.sensitive-config-keys
</value>
<description>A comma-separated or multi-line list of regular expressions to
match configuration keys that should be redacted where appropriate, for
example, when logging modified properties during a reconfiguration,
private credentials should not be logged.
</description>
</property>
<property>
<name>hadoop.workaround.non.threadsafe.getpwuid</name>
<value>true</value>
<description>Some operating systems or authentication modules are known to
have broken implementations of getpwuid_r and getpwgid_r, such that these
calls are not thread-safe. Symptoms of this problem include JVM crashes
with a stack trace inside these functions. If your system exhibits this
issue, enable this configuration parameter to include a lock around the
calls as a workaround.
An incomplete list of some systems known to have this issue is available
at http://wiki.apache.org/hadoop/KnownBrokenPwuidImplementations
</description>
</property>
<property>
<name>hadoop.kerberos.kinit.command</name>
<value>kinit</value>
<description>Used to periodically renew Kerberos credentials when provided
to Hadoop. The default setting assumes that kinit is in the PATH of users
running the Hadoop client. Change this to the absolute path to kinit if this
is not the case.
</description>
</property>
<property>
<name>hadoop.kerberos.min.seconds.before.relogin</name>
<value>60</value>
<description>The minimum time between relogin attempts for Kerberos, in
seconds.
</description>
</property>
<property>
<name>hadoop.kerberos.keytab.login.autorenewal.enabled</name>
<value>false</value>
<description>Used to enable automatic renewal of keytab based kerberos login.
By default the automatic renewal is disabled for keytab based kerberos login.
</description>
</property>
<property>
<name>hadoop.security.auth_to_local</name>
<value></value>
<description>Maps kerberos principals to local user names</description>
</property>
<property>
<name>hadoop.security.auth_to_local.mechanism</name>
<value>hadoop</value>
<description>The mechanism by which auth_to_local rules are evaluated.
If set to 'hadoop' it will not allow resulting local user names to have
either '@' or '/'. If set to 'MIT' it will follow MIT evaluation rules
and the restrictions of 'hadoop' do not apply.</description>
</property>
<property>
<name>hadoop.token.files</name>
<value></value>
<description>List of token cache files that have delegation tokens for hadoop service</description>
</property>
<!-- i/o properties -->
<property>
<name>io.file.buffer.size</name>
<value>4096</value>
<description>The size of buffer for use in sequence files.
The size of this buffer should probably be a multiple of hardware
page size (4096 on Intel x86), and it determines how much data is
buffered during read and write operations.</description>
</property>
<property>
<name>io.bytes.per.checksum</name>
<value>512</value>
<description>The number of bytes per checksum. Must not be larger than
io.file.buffer.size.</description>
</property>
<property>
<name>io.skip.checksum.errors</name>
<value>false</value>
<description>If true, when a checksum error is encountered while
reading a sequence file, entries are skipped, instead of throwing an
exception.</description>
</property>
<property>
<name>io.compression.codecs</name>
<value></value>
<description>A comma-separated list of the compression codec classes that can
be used for compression/decompression. In addition to any classes specified
with this property (which take precedence), codec classes on the classpath
are discovered using a Java ServiceLoader.</description>
</property>
<property>
<name>io.compression.codec.bzip2.library</name>
<value>system-native</value>
<description>The native-code library to be used for compression and
decompression by the bzip2 codec. This library could be specified
either by by name or the full pathname. In the former case, the
library is located by the dynamic linker, usually searching the
directories specified in the environment variable LD_LIBRARY_PATH.
The value of "system-native" indicates that the default system
library should be used. To indicate that the algorithm should
operate entirely in Java, specify "java-builtin".</description>
</property>
<property>
<name>io.serializations</name>
<value>org.apache.hadoop.io.serializer.WritableSerialization, org.apache.hadoop.io.serializer.avro.AvroSpecificSerialization, org.apache.hadoop.io.serializer.avro.AvroReflectSerialization</value>
<description>A list of serialization classes that can be used for
obtaining serializers and deserializers.</description>
</property>
<property>
<name>io.seqfile.local.dir</name>
<value>${hadoop.tmp.dir}/io/local</value>
<description>The local directory where sequence file stores intermediate
data files during merge. May be a comma-separated list of
directories on different devices in order to spread disk i/o.
Directories that do not exist are ignored.
</description>
</property>
<property>
<name>io.map.index.skip</name>
<value>0</value>
<description>Number of index entries to skip between each entry.
Zero by default. Setting this to values larger than zero can
facilitate opening large MapFiles using less memory.</description>
</property>
<property>
<name>io.map.index.interval</name>
<value>128</value>
<description>
MapFile consist of two files - data file (tuples) and index file
(keys). For every io.map.index.interval records written in the
data file, an entry (record-key, data-file-position) is written
in the index file. This is to allow for doing binary search later
within the index file to look up records by their keys and get their
closest positions in the data file.
</description>
</property>
<property>
<name>io.erasurecode.codec.rs.rawcoders</name>
<value>rs_native,rs_java</value>
<description>
Comma separated raw coder implementations for the rs codec. The earlier
factory is prior to followings in case of failure of creating raw coders.
</description>
</property>
<property>
<name>io.erasurecode.codec.rs-legacy.rawcoders</name>
<value>rs-legacy_java</value>
<description>
Comma separated raw coder implementations for the rs-legacy codec. The earlier
factory is prior to followings in case of failure of creating raw coders.
</description>
</property>
<property>
<name>io.erasurecode.codec.xor.rawcoders</name>
<value>xor_native,xor_java</value>
<description>
Comma separated raw coder implementations for the xor codec. The earlier
factory is prior to followings in case of failure of creating raw coders.
</description>
</property>
<!-- file system properties -->
<property>
<name>fs.defaultFS</name>
<value>file:///</value>
<description>The name of the default file system. A URI whose
scheme and authority determine the FileSystem implementation. The
uri's scheme determines the config property (fs.SCHEME.impl) naming
the FileSystem implementation class. The uri's authority is used to
determine the host, port, etc. for a filesystem.</description>
</property>
<property>
<name>fs.default.name</name>
<value>file:///</value>
<description>Deprecated. Use (fs.defaultFS) property
instead</description>
</property>
<property>
<name>fs.trash.interval</name>
<value>0</value>
<description>Number of minutes after which the checkpoint
gets deleted. If zero, the trash feature is disabled.
This option may be configured both on the server and the
client. If trash is disabled server side then the client
side configuration is checked. If trash is enabled on the
server side then the value configured on the server is
used and the client configuration value is ignored.
</description>
</property>
<property>
<name>fs.trash.checkpoint.interval</name>
<value>0</value>
<description>Number of minutes between trash checkpoints.
Should be smaller or equal to fs.trash.interval. If zero,
the value is set to the value of fs.trash.interval.
Every time the checkpointer runs it creates a new checkpoint
out of current and removes checkpoints created more than
fs.trash.interval minutes ago.
</description>
</property>
<property>
<name>fs.protected.directories</name>
<value></value>
<description>A comma-separated list of directories which cannot
be deleted or renamed even by the superuser unless they are empty. This
setting can be used to guard important system directories
against accidental deletion due to administrator error.
</description>
</property>
<property>
<name>fs.AbstractFileSystem.file.impl</name>
<value>org.apache.hadoop.fs.local.LocalFs</value>
<description>The AbstractFileSystem for file: uris.</description>
</property>
<property>
<name>fs.AbstractFileSystem.har.impl</name>
<value>org.apache.hadoop.fs.HarFs</value>
<description>The AbstractFileSystem for har: uris.</description>
</property>
<property>
<name>fs.AbstractFileSystem.hdfs.impl</name>
<value>org.apache.hadoop.fs.Hdfs</value>
<description>The FileSystem for hdfs: uris.</description>
</property>
<property>
<name>fs.AbstractFileSystem.viewfs.impl</name>
<value>org.apache.hadoop.fs.viewfs.ViewFs</value>
<description>The AbstractFileSystem for view file system for viewfs: uris
(ie client side mount table:).</description>
</property>
<property>
<name>fs.viewfs.rename.strategy</name>
<value>SAME_MOUNTPOINT</value>
<description>Allowed rename strategy to rename between multiple mountpoints.
Allowed values are SAME_MOUNTPOINT,SAME_TARGET_URI_ACROSS_MOUNTPOINT and
SAME_FILESYSTEM_ACROSS_MOUNTPOINT.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.hdfs.impl</name>
<value>org.apache.hadoop.hdfs.DistributedFileSystem</value>
<description>The DistributedFileSystem for view file system overload scheme
when child file system and ViewFSOverloadScheme's schemes are hdfs.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.s3a.impl</name>
<value>org.apache.hadoop.fs.s3a.S3AFileSystem</value>
<description>The S3AFileSystem for view file system overload scheme when
child file system and ViewFSOverloadScheme's schemes are s3a.</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.ofs.impl</name>
<value>org.apache.hadoop.fs.ozone.RootedOzoneFileSystem</value>
<description>The RootedOzoneFileSystem for view file system overload scheme
when child file system and ViewFSOverloadScheme's schemes are ofs.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.o3fs.impl</name>
<value>org.apache.hadoop.fs.ozone.OzoneFileSystem</value>
<description>The OzoneFileSystem for view file system overload scheme when
child file system and ViewFSOverloadScheme's schemes are o3fs.</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.ftp.impl</name>
<value>org.apache.hadoop.fs.ftp.FTPFileSystem</value>
<description>The FTPFileSystem for view file system overload scheme when
child file system and ViewFSOverloadScheme's schemes are ftp.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.webhdfs.impl</name>
<value>org.apache.hadoop.hdfs.web.WebHdfsFileSystem</value>
<description>The WebHdfsFileSystem for view file system overload scheme when
child file system and ViewFSOverloadScheme's schemes are webhdfs.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.swebhdfs.impl</name>
<value>org.apache.hadoop.hdfs.web.SWebHdfsFileSystem</value>
<description>The SWebHdfsFileSystem for view file system overload scheme when
child file system and ViewFSOverloadScheme's schemes are swebhdfs.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.file.impl</name>
<value>org.apache.hadoop.fs.LocalFileSystem</value>
<description>The LocalFileSystem for view file system overload scheme when
child file system and ViewFSOverloadScheme's schemes are file.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.abfs.impl</name>
<value>org.apache.hadoop.fs.azurebfs.AzureBlobFileSystem</value>
<description>The AzureBlobFileSystem for view file system overload scheme
when child file system and ViewFSOverloadScheme's schemes are abfs.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.abfss.impl</name>
<value>org.apache.hadoop.fs.azurebfs.SecureAzureBlobFileSystem</value>
<description>The SecureAzureBlobFileSystem for view file system overload
scheme when child file system and ViewFSOverloadScheme's schemes are abfss.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.wasb.impl</name>
<value>org.apache.hadoop.fs.azure.NativeAzureFileSystem</value>
<description>The NativeAzureFileSystem for view file system overload scheme
when child file system and ViewFSOverloadScheme's schemes are wasb.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.swift.impl</name>
<value>org.apache.hadoop.fs.swift.snative.SwiftNativeFileSystem</value>
<description>The SwiftNativeFileSystem for view file system overload scheme
when child file system and ViewFSOverloadScheme's schemes are swift.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.oss.impl</name>
<value>org.apache.hadoop.fs.aliyun.oss.AliyunOSSFileSystem</value>
<description>The AliyunOSSFileSystem for view file system overload scheme
when child file system and ViewFSOverloadScheme's schemes are oss.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.http.impl</name>
<value>org.apache.hadoop.fs.http.HttpFileSystem</value>
<description>The HttpFileSystem for view file system overload scheme
when child file system and ViewFSOverloadScheme's schemes are http.
</description>
</property>
<property>
<name>fs.viewfs.overload.scheme.target.https.impl</name>
<value>org.apache.hadoop.fs.http.HttpsFileSystem</value>
<description>The HttpsFileSystem for view file system overload scheme
when child file system and ViewFSOverloadScheme's schemes are https.
</description>
</property>
<property>
<name>fs.AbstractFileSystem.ftp.impl</name>
<value>org.apache.hadoop.fs.ftp.FtpFs</value>
<description>The FileSystem for Ftp: uris.</description>
</property>
<property>
<name>fs.ftp.impl</name>
<value>org.apache.hadoop.fs.ftp.FTPFileSystem</value>
<description>The implementation class of the FTP FileSystem</description>
</property>
<property>
<name>fs.AbstractFileSystem.webhdfs.impl</name>
<value>org.apache.hadoop.fs.WebHdfs</value>
<description>The FileSystem for webhdfs: uris.</description>
</property>
<property>
<name>fs.AbstractFileSystem.swebhdfs.impl</name>
<value>org.apache.hadoop.fs.SWebHdfs</value>
<description>The FileSystem for swebhdfs: uris.</description>
</property>
<property>
<name>fs.ftp.host</name>
<value>0.0.0.0</value>
<description>FTP filesystem connects to this server</description>
</property>
<property>
<name>fs.ftp.host.port</name>
<value>21</value>
<description>
FTP filesystem connects to fs.ftp.host on this port
</description>
</property>
<property>
<name>fs.ftp.data.connection.mode</name>
<value>ACTIVE_LOCAL_DATA_CONNECTION_MODE</value>
<description>Set the FTPClient's data connection mode based on configuration.
Valid values are ACTIVE_LOCAL_DATA_CONNECTION_MODE,
PASSIVE_LOCAL_DATA_CONNECTION_MODE and PASSIVE_REMOTE_DATA_CONNECTION_MODE.
</description>
</property>
<property>
<name>fs.ftp.transfer.mode</name>
<value>BLOCK_TRANSFER_MODE</value>
<description>
Set FTP's transfer mode based on configuration. Valid values are
STREAM_TRANSFER_MODE, BLOCK_TRANSFER_MODE and COMPRESSED_TRANSFER_MODE.
</description>
</property>
<property>
<name>fs.ftp.timeout</name>
<value>0</value>
<description>
FTP filesystem's timeout in seconds.
</description>
</property>
<property>
<name>fs.df.interval</name>
<value>60000</value>
<description>Disk usage statistics refresh interval in msec.</description>
</property>
<property>
<name>fs.du.interval</name>
<value>600000</value>
<description>File space usage statistics refresh interval in msec.</description>
</property>
<property>
<name>fs.swift.impl</name>
<value>org.apache.hadoop.fs.swift.snative.SwiftNativeFileSystem</value>
<description>The implementation class of the OpenStack Swift Filesystem</description>
</property>
<property>
<name>fs.automatic.close</name>
<value>true</value>
<description>By default, FileSystem instances are automatically closed at program
exit using a JVM shutdown hook. Setting this property to false disables this
behavior. This is an advanced option that should only be used by server applications
requiring a more carefully orchestrated shutdown sequence.
</description>
</property>
<property>
<name>fs.s3a.access.key</name>
<description>AWS access key ID used by S3A file system. Omit for IAM role-based or provider-based authentication.</description>
</property>
<property>
<name>fs.s3a.secret.key</name>
<description>AWS secret key used by S3A file system. Omit for IAM role-based or provider-based authentication.</description>
</property>
<property>
<name>fs.s3a.aws.credentials.provider</name>
<value>
org.apache.hadoop.fs.s3a.TemporaryAWSCredentialsProvider,
org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider,
com.amazonaws.auth.EnvironmentVariableCredentialsProvider,
org.apache.hadoop.fs.s3a.auth.IAMInstanceCredentialsProvider
</value>
<description>
Comma-separated class names of credential provider classes which implement
com.amazonaws.auth.AWSCredentialsProvider.
When S3A delegation tokens are not enabled, this list will be used
to directly authenticate with S3 and DynamoDB services.
When S3A Delegation tokens are enabled, depending upon the delegation
token binding it may be used
to communicate wih the STS endpoint to request session/role
credentials.
These are loaded and queried in sequence for a valid set of credentials.
Each listed class must implement one of the following means of
construction, which are attempted in order:
* a public constructor accepting java.net.URI and
org.apache.hadoop.conf.Configuration,
* a public constructor accepting org.apache.hadoop.conf.Configuration,
* a public static method named getInstance that accepts no
arguments and returns an instance of
com.amazonaws.auth.AWSCredentialsProvider, or
* a public default constructor.
Specifying org.apache.hadoop.fs.s3a.AnonymousAWSCredentialsProvider allows
anonymous access to a publicly accessible S3 bucket without any credentials.
Please note that allowing anonymous access to an S3 bucket compromises
security and therefore is unsuitable for most use cases. It can be useful
for accessing public data sets without requiring AWS credentials.
If unspecified, then the default list of credential provider classes,
queried in sequence, is:
* org.apache.hadoop.fs.s3a.TemporaryAWSCredentialsProvider: looks
for session login secrets in the Hadoop configuration.
* org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider:
Uses the values of fs.s3a.access.key and fs.s3a.secret.key.
* com.amazonaws.auth.EnvironmentVariableCredentialsProvider: supports
configuration of AWS access key ID and secret access key in
environment variables named AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY,
and AWS_SESSION_TOKEN as documented in the AWS SDK.
* org.apache.hadoop.fs.s3a.auth.IAMInstanceCredentialsProvider: picks up
IAM credentials of any EC2 VM or AWS container in which the process is running.
</description>
</property>
<property>
<name>fs.s3a.session.token</name>
<description>Session token, when using org.apache.hadoop.fs.s3a.TemporaryAWSCredentialsProvider
as one of the providers.
</description>
</property>
<property>
<name>fs.s3a.security.credential.provider.path</name>
<value />
<description>
Optional comma separated list of credential providers, a list
which is prepended to that set in hadoop.security.credential.provider.path
</description>
</property>
<property>
<name>fs.s3a.assumed.role.arn</name>
<value />
<description>
AWS ARN for the role to be assumed.
Required if the fs.s3a.aws.credentials.provider contains
org.apache.hadoop.fs.s3a.AssumedRoleCredentialProvider
</description>
</property>
<property>
<name>fs.s3a.assumed.role.session.name</name>
<value />
<description>
Session name for the assumed role, must be valid characters according to
the AWS APIs.
Only used if AssumedRoleCredentialProvider is the AWS credential provider.
If not set, one is generated from the current Hadoop/Kerberos username.
</description>
</property>
<property>
<name>fs.s3a.assumed.role.policy</name>
<value/>
<description>
JSON policy to apply to the role.
Only used if AssumedRoleCredentialProvider is the AWS credential provider.
</description>
</property>
<property>
<name>fs.s3a.assumed.role.session.duration</name>
<value>30m</value>
<description>
Duration of assumed roles before a refresh is attempted.
Used when session tokens are requested.
Range: 15m to 1h
</description>
</property>
<property>
<name>fs.s3a.assumed.role.sts.endpoint</name>
<value/>
<description>
AWS Security Token Service Endpoint.
If unset, uses the default endpoint.
Only used if AssumedRoleCredentialProvider is the AWS credential provider.
Used by the AssumedRoleCredentialProvider and in Session and Role delegation
tokens.
</description>
</property>
<property>
<name>fs.s3a.assumed.role.sts.endpoint.region</name>
<value></value>
<description>
AWS Security Token Service Endpoint's region;
Needed if fs.s3a.assumed.role.sts.endpoint points to an endpoint
other than the default one and the v4 signature is used.
Used by the AssumedRoleCredentialProvider and in Session and Role delegation
tokens.
</description>
</property>
<property>
<name>fs.s3a.assumed.role.credentials.provider</name>
<value>org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider</value>
<description>
List of credential providers to authenticate with the STS endpoint and
retrieve short-lived role credentials.
Only used if AssumedRoleCredentialProvider is the AWS credential provider.
If unset, uses "org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider".
</description>
</property>
<property>
<name>fs.s3a.delegation.tokens.enabled</name>
<value>false</value>
<description></description>
</property>
<property>
<name>fs.s3a.delegation.token.binding</name>
<value></value>
<description>
The name of a class to provide delegation tokens support in S3A.
If unset: delegation token support is disabled.
Note: for job submission to actually collect these tokens,
Kerberos must be enabled.
Options are:
org.apache.hadoop.fs.s3a.auth.delegation.SessionTokenBinding
org.apache.hadoop.fs.s3a.auth.delegation.FullCredentialsTokenBinding
and org.apache.hadoop.fs.s3a.auth.delegation.RoleTokenBinding
</description>
</property>
<property>
<name>fs.s3a.connection.maximum</name>
<value>48</value>
<description>Controls the maximum number of simultaneous connections to S3.
This must be bigger than the value of fs.s3a.threads.max so as to stop
threads being blocked waiting for new HTTPS connections.
Why not equal? The AWS SDK transfer manager also uses these connections.
</description>
</property>
<property>
<name>fs.s3a.connection.ssl.enabled</name>
<value>true</value>
<description>Enables or disables SSL connections to AWS services.
Also sets the default port to use for the s3a proxy settings,
when not explicitly set in fs.s3a.proxy.port.</description>
</property>
<property>
<name>fs.s3a.endpoint</name>
<description>AWS S3 endpoint to connect to. An up-to-date list is
provided in the AWS Documentation: regions and endpoints. Without this
property, the standard region (s3.amazonaws.com) is assumed.
</description>
</property>
<property>
<name>fs.s3a.path.style.access</name>
<value>false</value>
<description>Enable S3 path style access ie disabling the default virtual hosting behaviour.
Useful for S3A-compliant storage providers as it removes the need to set up DNS for virtual hosting.
</description>
</property>
<property>
<name>fs.s3a.proxy.host</name>
<description>Hostname of the (optional) proxy server for S3 connections.</description>
</property>
<property>
<name>fs.s3a.proxy.port</name>
<description>Proxy server port. If this property is not set
but fs.s3a.proxy.host is, port 80 or 443 is assumed (consistent with
the value of fs.s3a.connection.ssl.enabled).</description>
</property>
<property>
<name>fs.s3a.proxy.username</name>
<description>Username for authenticating with proxy server.</description>
</property>
<property>
<name>fs.s3a.proxy.password</name>
<description>Password for authenticating with proxy server.</description>
</property>
<property>
<name>fs.s3a.proxy.domain</name>
<description>Domain for authenticating with proxy server.</description>
</property>
<property>
<name>fs.s3a.proxy.workstation</name>
<description>Workstation for authenticating with proxy server.</description>
</property>
<property>
<name>fs.s3a.attempts.maximum</name>
<value>20</value>
<description>How many times we should retry commands on transient errors.</description>
</property>
<property>
<name>fs.s3a.connection.establish.timeout</name>
<value>5000</value>
<description>Socket connection setup timeout in milliseconds.</description>
</property>
<property>
<name>fs.s3a.connection.timeout</name>
<value>200000</value>
<description>Socket connection timeout in milliseconds.</description>
</property>
<property>
<name>fs.s3a.socket.send.buffer</name>
<value>8192</value>
<description>Socket send buffer hint to amazon connector. Represented in bytes.</description>
</property>
<property>
<name>fs.s3a.socket.recv.buffer</name>
<value>8192</value>
<description>Socket receive buffer hint to amazon connector. Represented in bytes.</description>
</property>
<property>
<name>fs.s3a.paging.maximum</name>
<value>5000</value>
<description>How many keys to request from S3 when doing
directory listings at a time.</description>
</property>
<property>
<name>fs.s3a.threads.max</name>
<value>64</value>
<description>The total number of threads available in the filesystem for data
uploads *or any other queued filesystem operation*.</description>
</property>
<property>
<name>fs.s3a.threads.keepalivetime</name>
<value>60</value>
<description>Number of seconds a thread can be idle before being
terminated.</description>
</property>
<property>
<name>fs.s3a.max.total.tasks</name>
<value>32</value>
<description>The number of operations which can be queued for execution.
This is in addition to the number of active threads in fs.s3a.threads.max.
</description>
</property>
<property>
<name>fs.s3a.executor.capacity</name>
<value>16</value>
<description>The maximum number of submitted tasks which is a single
operation (e.g. rename(), delete()) may submit simultaneously for
execution -excluding the IO-heavy block uploads, whose capacity
is set in "fs.s3a.fast.upload.active.blocks"
All tasks are submitted to the shared thread pool whose size is
set in "fs.s3a.threads.max"; the value of capacity should be less than that
of the thread pool itself, as the goal is to stop a single operation
from overloading that thread pool.
</description>
</property>
<property>
<name>fs.s3a.multipart.size</name>
<value>64M</value>
<description>How big (in bytes) to split upload or copy operations up into.
A suffix from the set {K,M,G,T,P} may be used to scale the numeric value.
</description>
</property>
<property>
<name>fs.s3a.multipart.threshold</name>
<value>128M</value>
<description>How big (in bytes) to split upload or copy operations up into.
This also controls the partition size in renamed files, as rename() involves
copying the source file(s).
A suffix from the set {K,M,G,T,P} may be used to scale the numeric value.
</description>
</property>
<property>
<name>fs.s3a.multiobjectdelete.enable</name>
<value>true</value>
<description>When enabled, multiple single-object delete requests are replaced by
a single 'delete multiple objects'-request, reducing the number of requests.
Beware: legacy S3-compatible object stores might not support this request.
</description>
</property>
<property>
<name>fs.s3a.acl.default</name>
<description>Set a canned ACL for newly created and copied objects. Value may be Private,
PublicRead, PublicReadWrite, AuthenticatedRead, LogDeliveryWrite, BucketOwnerRead,
or BucketOwnerFullControl.</description>
</property>
<property>
<name>fs.s3a.multipart.purge</name>
<value>false</value>
<description>True if you want to purge existing multipart uploads that may not have been
completed/aborted correctly. The corresponding purge age is defined in
fs.s3a.multipart.purge.age.
If set, when the filesystem is instantiated then all outstanding uploads
older than the purge age will be terminated -across the entire bucket.
This will impact multipart uploads by other applications and users. so should
be used sparingly, with an age value chosen to stop failed uploads, without
breaking ongoing operations.
</description>
</property>
<property>
<name>fs.s3a.multipart.purge.age</name>
<value>86400</value>
<description>Minimum age in seconds of multipart uploads to purge
on startup if "fs.s3a.multipart.purge" is true
</description>
</property>
<property>
<name>fs.s3a.server-side-encryption-algorithm</name>
<description>Specify a server-side encryption algorithm for s3a: file system.
Unset by default. It supports the following values: 'AES256' (for SSE-S3),
'SSE-KMS' and 'SSE-C'.
</description>
</property>
<property>
<name>fs.s3a.server-side-encryption.key</name>
<description>Specific encryption key to use if fs.s3a.server-side-encryption-algorithm
has been set to 'SSE-KMS' or 'SSE-C'. In the case of SSE-C, the value of this property
should be the Base64 encoded key. If you are using SSE-KMS and leave this property empty,
you'll be using your default's S3 KMS key, otherwise you should set this property to
the specific KMS key id.
</description>
</property>
<property>
<name>fs.s3a.signing-algorithm</name>
<description>Override the default signing algorithm so legacy
implementations can still be used</description>
</property>
<property>
<name>fs.s3a.block.size</name>
<value>32M</value>
<description>Block size to use when reading files using s3a: file system.
A suffix from the set {K,M,G,T,P} may be used to scale the numeric value.
</description>
</property>
<property>
<name>fs.s3a.buffer.dir</name>
<value>${hadoop.tmp.dir}/s3a</value>
<description>Comma separated list of directories that will be used to buffer file
uploads to.</description>
</property>
<property>
<name>fs.s3a.fast.upload.buffer</name>
<value>disk</value>
<description>
The buffering mechanism to for data being written.
Values: disk, array, bytebuffer.
"disk" will use the directories listed in fs.s3a.buffer.dir as
the location(s) to save data prior to being uploaded.
"array" uses arrays in the JVM heap
"bytebuffer" uses off-heap memory within the JVM.
Both "array" and "bytebuffer" will consume memory in a single stream up to the number
of blocks set by:
fs.s3a.multipart.size * fs.s3a.fast.upload.active.blocks.
If using either of these mechanisms, keep this value low
The total number of threads performing work across all threads is set by
fs.s3a.threads.max, with fs.s3a.max.total.tasks values setting the number of queued
work items.
</description>
</property>
<property>
<name>fs.s3a.fast.upload.active.blocks</name>
<value>4</value>
<description>
Maximum Number of blocks a single output stream can have
active (uploading, or queued to the central FileSystem
instance's pool of queued operations.
This stops a single stream overloading the shared thread pool.
</description>
</property>
<property>
<name>fs.s3a.readahead.range</name>
<value>64K</value>
<description>Bytes to read ahead during a seek() before closing and
re-opening the S3 HTTP connection. This option will be overridden if
any call to setReadahead() is made to an open stream.
A suffix from the set {K,M,G,T,P} may be used to scale the numeric value.
</description>
</property>
<property>
<name>fs.s3a.user.agent.prefix</name>
<value></value>
<description>
Sets a custom value that will be prepended to the User-Agent header sent in
HTTP requests to the S3 back-end by S3AFileSystem. The User-Agent header
always includes the Hadoop version number followed by a string generated by
the AWS SDK. An example is "User-Agent: Hadoop 2.8.0, aws-sdk-java/1.10.6".
If this optional property is set, then its value is prepended to create a
customized User-Agent. For example, if this configuration property was set
to "MyApp", then an example of the resulting User-Agent would be
"User-Agent: MyApp, Hadoop 2.8.0, aws-sdk-java/1.10.6".
</description>
</property>
<property>
<name>fs.s3a.metadatastore.authoritative</name>
<value>false</value>
<description>
When true, allow MetadataStore implementations to act as source of
truth for getting file status and directory listings. Even if this
is set to true, MetadataStore implementations may choose not to
return authoritative results. If the configured MetadataStore does
not support being authoritative, this setting will have no effect.
</description>
</property>
<property>
<name>fs.s3a.metadatastore.metadata.ttl</name>
<value>15m</value>
<description>
This value sets how long an entry in a MetadataStore is valid.
</description>
</property>
<property>
<name>fs.s3a.metadatastore.impl</name>
<value>org.apache.hadoop.fs.s3a.s3guard.NullMetadataStore</value>
<description>
Fully-qualified name of the class that implements the MetadataStore
to be used by s3a. The default class, NullMetadataStore, has no
effect: s3a will continue to treat the backing S3 service as the one
and only source of truth for file and directory metadata.
</description>
</property>
<property>
<name>fs.s3a.metadatastore.fail.on.write.error</name>
<value>true</value>
<description>
When true (default), FileSystem write operations generate
org.apache.hadoop.fs.s3a.MetadataPersistenceException if the metadata
cannot be saved to the metadata store. When false, failures to save to
metadata store are logged at ERROR level, but the overall FileSystem
write operation succeeds.
</description>
</property>
<property>
<name>fs.s3a.s3guard.cli.prune.age</name>
<value>86400000</value>
<description>
Default age (in milliseconds) after which to prune metadata from the
metadatastore when the prune command is run. Can be overridden on the
command-line.
</description>
</property>
<property>
<name>fs.s3a.impl</name>
<value>org.apache.hadoop.fs.s3a.S3AFileSystem</value>
<description>The implementation class of the S3A Filesystem</description>
</property>
<property>
<name>fs.s3a.s3guard.ddb.region</name>
<value></value>
<description>
AWS DynamoDB region to connect to. An up-to-date list is
provided in the AWS Documentation: regions and endpoints. Without this
property, the S3Guard will operate table in the associated S3 bucket region.
</description>
</property>
<property>
<name>fs.s3a.s3guard.ddb.table</name>
<value></value>
<description>
The DynamoDB table name to operate. Without this property, the respective
S3 bucket name will be used.
</description>
</property>
<property>
<name>fs.s3a.s3guard.ddb.table.create</name>
<value>false</value>
<description>
If true, the S3A client will create the table if it does not already exist.
</description>
</property>
<property>
<name>fs.s3a.s3guard.ddb.table.capacity.read</name>
<value>0</value>
<description>
Provisioned throughput requirements for read operations in terms of capacity
units for the DynamoDB table. This config value will only be used when
creating a new DynamoDB table.
If set to 0 (the default), new tables are created with "per-request" capacity.
If a positive integer is provided for this and the write capacity, then
a table with "provisioned capacity" will be created.
You can change the capacity of an existing provisioned-capacity table
through the "s3guard set-capacity" command.
</description>
</property>
<property>
<name>fs.s3a.s3guard.ddb.table.capacity.write</name>
<value>0</value>
<description>
Provisioned throughput requirements for write operations in terms of
capacity units for the DynamoDB table.
If set to 0 (the default), new tables are created with "per-request" capacity.
Refer to related configuration option fs.s3a.s3guard.ddb.table.capacity.read
</description>
</property>
<property>
<name>fs.s3a.s3guard.ddb.table.sse.enabled</name>
<value>false</value>
<description>
Whether server-side encryption (SSE) is enabled or disabled on the table.
By default it's disabled, meaning SSE is set to AWS owned CMK.
</description>
</property>
<property>
<name>fs.s3a.s3guard.ddb.table.sse.cmk</name>
<value/>
<description>
The KMS Customer Master Key (CMK) used for the KMS encryption on the table.
To specify a CMK, this config value can be its key ID, Amazon Resource Name
(ARN), alias name, or alias ARN. Users only need to provide this config if
the key is different from the default DynamoDB KMS Master Key, which is
alias/aws/dynamodb.
</description>
</property>
<property>
<name>fs.s3a.s3guard.ddb.max.retries</name>
<value>9</value>
<description>
Max retries on throttled/incompleted DynamoDB operations
before giving up and throwing an IOException.
Each retry is delayed with an exponential
backoff timer which starts at 100 milliseconds and approximately
doubles each time. The minimum wait before throwing an exception is
sum(100, 200, 400, 800, .. 100*2^N-1 ) == 100 * ((2^N)-1)
</description>
</property>
<property>
<name>fs.s3a.s3guard.ddb.throttle.retry.interval</name>
<value>100ms</value>
<description>
Initial interval to retry after a request is throttled events;
the back-off policy is exponential until the number of retries of
fs.s3a.s3guard.ddb.max.retries is reached.
</description>
</property>
<property>
<name>fs.s3a.s3guard.ddb.background.sleep</name>
<value>25ms</value>
<description>
Length (in milliseconds) of pause between each batch of deletes when
pruning metadata. Prevents prune operations (which can typically be low
priority background operations) from overly interfering with other I/O
operations.
</description>
</property>
<property>
<name>fs.s3a.retry.limit</name>
<value>7</value>
<description>
Number of times to retry any repeatable S3 client request on failure,
excluding throttling requests and S3Guard inconsistency resolution.
</description>
</property>
<property>
<name>fs.s3a.retry.interval</name>
<value>500ms</value>
<description>
Initial retry interval when retrying operations for any reason other
than S3 throttle errors and S3Guard inconsistency resolution.
</description>
</property>
<property>
<name>fs.s3a.retry.throttle.limit</name>
<value>20</value>
<description>
Number of times to retry any throttled request.
</description>
</property>
<property>
<name>fs.s3a.retry.throttle.interval</name>
<value>100ms</value>
<description>
Initial between retry attempts on throttled requests, +/- 50%. chosen at random.
i.e. for an intial value of 3000ms, the initial delay would be in the range 1500ms to 4500ms.
Backoffs are exponential; again randomness is used to avoid the thundering heard problem.
500ms is the default value used by the AWS S3 Retry policy.
</description>
</property>
<property>
<name>fs.s3a.s3guard.consistency.retry.limit</name>
<value>7</value>
<description>
Number of times to retry attempts to read/open/copy files when
S3Guard believes a specific version of the file to be available,
but the S3 request does not find any version of a file, or a different
version.
</description>
</property>
<property>
<name>fs.s3a.s3guard.consistency.retry.interval</name>
<value>2s</value>
<description>
Initial interval between attempts to retry operations while waiting for S3
to become consistent with the S3Guard data.
An exponential back-off is used here: every failure doubles the delay.
</description>
</property>
<property>
<name>fs.s3a.committer.name</name>
<value>file</value>
<description>
Committer to create for output to S3A, one of:
"file", "directory", "partitioned", "magic".
</description>
</property>
<property>
<name>fs.s3a.committer.magic.enabled</name>
<value>true</value>
<description>
Enable support in the S3A filesystem for the "Magic" committer.
</description>
</property>
<property>
<name>fs.s3a.committer.threads</name>
<value>8</value>
<description>
Number of threads in committers for parallel operations on files
(upload, commit, abort, delete...)
</description>
</property>
<property>
<name>fs.s3a.committer.staging.tmp.path</name>
<value>tmp/staging</value>
<description>
Path in the cluster filesystem for temporary data.
This is for HDFS, not the local filesystem.
It is only for the summary data of each file, not the actual
data being committed.
Using an unqualified path guarantees that the full path will be
generated relative to the home directory of the user creating the job,
hence private (assuming home directory permissions are secure).
</description>
</property>
<property>
<name>fs.s3a.committer.staging.unique-filenames</name>
<value>true</value>
<description>
Option for final files to have a unique name through job attempt info,
or the value of fs.s3a.committer.staging.uuid
When writing data with the "append" conflict option, this guarantees
that new data will not overwrite any existing data.
</description>
</property>
<property>
<name>fs.s3a.committer.staging.conflict-mode</name>
<value>append</value>
<description>
Staging committer conflict resolution policy.
Supported: "fail", "append", "replace".
</description>
</property>
<property>
<name>fs.s3a.committer.abort.pending.uploads</name>
<value>true</value>
<description>
Should the committers abort all pending uploads to the destination
directory?
Set to false if more than one job is writing to the same directory tree.
</description>
</property>
<property>
<name>fs.s3a.select.enabled</name>
<value>true</value>
<description>Is S3 Select enabled?</description>
</property>
<property>
<name>fs.s3a.select.input.csv.comment.marker</name>
<value>#</value>
<description>In S3 Select queries: the marker for comment lines in CSV files</description>
</property>
<property>
<name>fs.s3a.select.input.csv.record.delimiter</name>
<value>\n</value>
<description>In S3 Select queries over CSV files: the record delimiter.
\t is remapped to the TAB character, \r to CR \n to newline. \\ to \
and \" to "
</description>
</property>
<property>
<name>fs.s3a.select.input.csv.field.delimiter</name>
<value>,</value>
<description>In S3 Select queries over CSV files: the field delimiter.
\t is remapped to the TAB character, \r to CR \n to newline. \\ to \
and \" to "
</description>
</property>
<property>
<name>fs.s3a.select.input.csv.quote.character</name>
<value>"</value>
<description>In S3 Select queries over CSV files: quote character.
\t is remapped to the TAB character, \r to CR \n to newline. \\ to \
and \" to "
</description>
</property>
<property>
<name>fs.s3a.select.input.csv.quote.escape.character</name>
<value>\\</value>
<description>In S3 Select queries over CSV files: quote escape character.
\t is remapped to the TAB character, \r to CR \n to newline. \\ to \
and \" to "
</description>
</property>
<property>
<name>fs.s3a.select.input.csv.header</name>
<value>none</value>
<description>In S3 Select queries over CSV files: what is the role of the header? One of "none", "ignore" and "use"</description>
</property>
<property>
<name>fs.s3a.select.input.compression</name>
<value>none</value>
<description>In S3 Select queries, the source compression
algorithm. One of: "none" and "gzip"</description>
</property>
<property>
<name>fs.s3a.select.output.csv.quote.fields</name>
<value>always</value>
<description>
In S3 Select queries: should fields in generated CSV Files be quoted?
One of: "always", "asneeded".
</description>
</property>
<property>
<name>fs.s3a.select.output.csv.quote.character</name>
<value>"</value>
<description>
In S3 Select queries: the quote character for generated CSV Files.
</description>
</property>
<property>
<name>fs.s3a.select.output.csv.quote.escape.character</name>
<value>\\</value>
<description>
In S3 Select queries: the quote escape character for generated CSV Files.
</description>
</property>
<property>
<name>fs.s3a.select.output.csv.record.delimiter</name>
<value>\n</value>
<description>
In S3 Select queries: the record delimiter for generated CSV Files.
</description>
</property>
<property>
<name>fs.s3a.select.output.csv.field.delimiter</name>
<value>,</value>
<description>
In S3 Select queries: the field delimiter for generated CSV Files.
</description>
</property>
<property>
<name>fs.s3a.select.errors.include.sql</name>
<value>false</value>
<description>
Include the SQL statement in errors: this is useful for development but
may leak security and Personally Identifying Information in production,
so must be disabled there.
</description>
</property>
<property>
<name>fs.AbstractFileSystem.s3a.impl</name>
<value>org.apache.hadoop.fs.s3a.S3A</value>
<description>The implementation class of the S3A AbstractFileSystem.</description>
</property>
<property>
<name>fs.s3a.list.version</name>
<value>2</value>
<description>
Select which version of the S3 SDK's List Objects API to use. Currently
support 2 (default) and 1 (older API).
</description>
</property>
<property>
<name>fs.s3a.connection.request.timeout</name>
<value>0</value>
<description>
Time out on HTTP requests to the AWS service; 0 means no timeout.
Measured in seconds; the usual time suffixes are all supported
Important: this is the maximum duration of any AWS service call,
including upload and copy operations. If non-zero, it must be larger
than the time to upload multi-megabyte blocks to S3 from the client,
and to rename many-GB files. Use with care.
Values that are larger than Integer.MAX_VALUE milliseconds are
converged to Integer.MAX_VALUE milliseconds
</description>
</property>
<property>
<name>fs.s3a.etag.checksum.enabled</name>
<value>false</value>
<description>
Should calls to getFileChecksum() return the etag value of the remote
object.
WARNING: if enabled, distcp operations between HDFS and S3 will fail unless
-skipcrccheck is set.
</description>
</property>
<property>
<name>fs.s3a.change.detection.source</name>
<value>etag</value>
<description>
Select which S3 object attribute to use for change detection.
Currently support 'etag' for S3 object eTags and 'versionid' for
S3 object version IDs. Use of version IDs requires object versioning to be
enabled for each S3 bucket utilized. Object versioning is disabled on
buckets by default. When version ID is used, the buckets utilized should
have versioning enabled before any data is written.
</description>
</property>
<property>
<name>fs.s3a.change.detection.mode</name>
<value>server</value>
<description>
Determines how change detection is applied to alert to inconsistent S3
objects read during or after an overwrite. Value 'server' indicates to apply
the attribute constraint directly on GetObject requests to S3. Value 'client'
means to do a client-side comparison of the attribute value returned in the
response. Value 'server' would not work with third-party S3 implementations
that do not support these constraints on GetObject. Values 'server' and
'client' generate RemoteObjectChangedException when a mismatch is detected.
Value 'warn' works like 'client' but generates only a warning. Value 'none'
will ignore change detection completely.
</description>
</property>
<property>
<name>fs.s3a.change.detection.version.required</name>
<value>true</value>
<description>
Determines if S3 object version attribute defined by
fs.s3a.change.detection.source should be treated as required. If true and the
referred attribute is unavailable in an S3 GetObject response,
NoVersionAttributeException is thrown. Setting to 'true' is encouraged to
avoid potential for inconsistent reads with third-party S3 implementations or
against S3 buckets that have object versioning disabled.
</description>
</property>
<property>
<name>fs.s3a.ssl.channel.mode</name>
<value>default_jsse</value>
<description>
If secure connections to S3 are enabled, configures the SSL
implementation used to encrypt connections to S3. Supported values are:
"default_jsse", "default_jsse_with_gcm", "default", and "openssl".
"default_jsse" uses the Java Secure Socket Extension package (JSSE).
However, when running on Java 8, the GCM cipher is removed from the list
of enabled ciphers. This is due to performance issues with GCM in Java 8.
"default_jsse_with_gcm" uses the JSSE with the default list of cipher
suites. "default_jsse_with_gcm" is equivalent to the behavior prior to
this feature being introduced. "default" attempts to use OpenSSL rather
than the JSSE for SSL encryption, if OpenSSL libraries cannot be loaded,
it falls back to the "default_jsse" behavior. "openssl" attempts to use
OpenSSL as well, but fails if OpenSSL libraries cannot be loaded.
</description>
</property>
<!-- Azure file system properties -->
<property>
<name>fs.AbstractFileSystem.wasb.impl</name>
<value>org.apache.hadoop.fs.azure.Wasb</value>
<description>AbstractFileSystem implementation class of wasb://</description>
</property>
<property>
<name>fs.AbstractFileSystem.wasbs.impl</name>
<value>org.apache.hadoop.fs.azure.Wasbs</value>
<description>AbstractFileSystem implementation class of wasbs://</description>
</property>
<property>
<name>fs.wasb.impl</name>
<value>org.apache.hadoop.fs.azure.NativeAzureFileSystem</value>
<description>The implementation class of the Native Azure Filesystem</description>
</property>
<property>
<name>fs.wasbs.impl</name>
<value>org.apache.hadoop.fs.azure.NativeAzureFileSystem$Secure</value>
<description>The implementation class of the Secure Native Azure Filesystem</description>
</property>
<property>
<name>fs.azure.secure.mode</name>
<value>false</value>
<description>
Config flag to identify the mode in which fs.azure.NativeAzureFileSystem needs
to run under. Setting it "true" would make fs.azure.NativeAzureFileSystem use
SAS keys to communicate with Azure storage.
</description>
</property>
<property>
<name>fs.abfs.impl</name>
<value>org.apache.hadoop.fs.azurebfs.AzureBlobFileSystem</value>
<description>The implementation class of the Azure Blob Filesystem</description>
</property>
<property>
<name>fs.abfss.impl</name>
<value>org.apache.hadoop.fs.azurebfs.SecureAzureBlobFileSystem</value>
<description>The implementation class of the Secure Azure Blob Filesystem</description>
</property>
<property>
<name>fs.AbstractFileSystem.abfs.impl</name>
<value>org.apache.hadoop.fs.azurebfs.Abfs</value>
<description>AbstractFileSystem implementation class of abfs://</description>
</property>
<property>
<name>fs.AbstractFileSystem.abfss.impl</name>
<value>org.apache.hadoop.fs.azurebfs.Abfss</value>
<description>AbstractFileSystem implementation class of abfss://</description>
</property>
<property>
<name>fs.azure.local.sas.key.mode</name>
<value>false</value>
<description>
Works in conjuction with fs.azure.secure.mode. Setting this config to true
results in fs.azure.NativeAzureFileSystem using the local SAS key generation
where the SAS keys are generating in the same process as fs.azure.NativeAzureFileSystem.
If fs.azure.secure.mode flag is set to false, this flag has no effect.
</description>
</property>
<property>
<name>fs.azure.sas.expiry.period</name>
<value>90d</value>
<description>
The default value to be used for expiration period for SAS keys generated.
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.).
</description>
</property>
<property>
<name>fs.azure.authorization</name>
<value>false</value>
<description>
Config flag to enable authorization support in WASB. Setting it to "true" enables
authorization support to WASB. Currently WASB authorization requires a remote service
to provide authorization that needs to be specified via fs.azure.authorization.remote.service.url
configuration
</description>
</property>
<property>
<name>fs.azure.authorization.caching.enable</name>
<value>true</value>
<description>
Config flag to enable caching of authorization results and saskeys in WASB.
This flag is relevant only when fs.azure.authorization is enabled.
</description>
</property>
<property>
<name>fs.azure.saskey.usecontainersaskeyforallaccess</name>
<value>true</value>
<description>
Use container saskey for access to all blobs within the container.
Blob-specific saskeys are not used when this setting is enabled.
This setting provides better performance compared to blob-specific saskeys.
</description>
</property>
<property>
<name>io.seqfile.compress.blocksize</name>
<value>1000000</value>
<description>The minimum block size for compression in block compressed
SequenceFiles.
</description>
</property>
<property>
<name>io.mapfile.bloom.size</name>
<value>1048576</value>
<description>The size of BloomFilter-s used in BloomMapFile. Each time this many
keys is appended the next BloomFilter will be created (inside a DynamicBloomFilter).
Larger values minimize the number of filters, which slightly increases the performance,
but may waste too much space if the total number of keys is usually much smaller
than this number.
</description>
</property>
<property>
<name>io.mapfile.bloom.error.rate</name>
<value>0.005</value>
<description>The rate of false positives in BloomFilter-s used in BloomMapFile.
As this value decreases, the size of BloomFilter-s increases exponentially. This
value is the probability of encountering false positives (default is 0.5%).
</description>
</property>
<property>
<name>hadoop.util.hash.type</name>
<value>murmur</value>
<description>The default implementation of Hash. Currently this can take one of the
two values: 'murmur' to select MurmurHash and 'jenkins' to select JenkinsHash.
</description>
</property>
<!-- ipc properties -->
<property>
<name>ipc.client.idlethreshold</name>
<value>4000</value>
<description>Defines the threshold number of connections after which
connections will be inspected for idleness.
</description>
</property>
<property>
<name>ipc.client.kill.max</name>
<value>10</value>
<description>Defines the maximum number of clients to disconnect in one go.
</description>
</property>
<property>
<name>ipc.client.connection.maxidletime</name>
<value>10000</value>
<description>The maximum time in msec after which a client will bring down the
connection to the server.
</description>
</property>
<property>
<name>ipc.client.connect.max.retries</name>
<value>10</value>
<description>Indicates the number of retries a client will make to establish
a server connection.
</description>
</property>
<property>
<name>ipc.client.connect.retry.interval</name>
<value>1000</value>
<description>Indicates the number of milliseconds a client will wait for
before retrying to establish a server connection.
</description>
</property>
<property>
<name>ipc.client.connect.timeout</name>
<value>20000</value>
<description>Indicates the number of milliseconds a client will wait for the
socket to establish a server connection.
</description>
</property>
<property>
<name>ipc.client.connect.max.retries.on.timeouts</name>
<value>45</value>
<description>Indicates the number of retries a client will make on socket timeout
to establish a server connection.
</description>
</property>
<property>
<name>ipc.client.tcpnodelay</name>
<value>true</value>
<description>Use TCP_NODELAY flag to bypass Nagle's algorithm transmission delays.
</description>
</property>
<property>
<name>ipc.client.low-latency</name>
<value>false</value>
<description>Use low-latency QoS markers for IPC connections.
</description>
</property>
<property>
<name>ipc.client.ping</name>
<value>true</value>
<description>Send a ping to the server when timeout on reading the response,
if set to true. If no failure is detected, the client retries until at least
a byte is read or the time given by ipc.client.rpc-timeout.ms is passed.
</description>
</property>
<property>
<name>ipc.ping.interval</name>
<value>60000</value>
<description>Timeout on waiting response from server, in milliseconds.
The client will send ping when the interval is passed without receiving bytes,
if ipc.client.ping is set to true.
</description>
</property>
<property>
<name>ipc.client.rpc-timeout.ms</name>
<value>0</value>
<description>Timeout on waiting response from server, in milliseconds.
If ipc.client.ping is set to true and this rpc-timeout is greater than
the value of ipc.ping.interval, the effective value of the rpc-timeout is
rounded up to multiple of ipc.ping.interval.
</description>
</property>
<property>
<name>ipc.server.listen.queue.size</name>
<value>256</value>
<description>Indicates the length of the listen queue for servers accepting
client connections.
</description>
</property>
<property>
<name>ipc.server.log.slow.rpc</name>
<value>false</value>
<description>This setting is useful to troubleshoot performance issues for
various services. If this value is set to true then we log requests that
fall into 99th percentile as well as increment RpcSlowCalls counter.
</description>
</property>
<property>
<name>ipc.maximum.data.length</name>
<value>134217728</value>
<description>This indicates the maximum IPC message length (bytes) that can be
accepted by the server. Messages larger than this value are rejected by the
immediately to avoid possible OOMs. This setting should rarely need to be
changed.
</description>
</property>
<property>
<name>ipc.maximum.response.length</name>
<value>134217728</value>
<description>This indicates the maximum IPC message length (bytes) that can be
accepted by the client. Messages larger than this value are rejected
immediately to avoid possible OOMs. This setting should rarely need to be
changed. Set to 0 to disable.
</description>
</property>
<property>
<name>ipc.server.reuseaddr</name>
<value>true</value>
<description>Enables the SO_REUSEADDR TCP option on the server.
Useful if BindException often prevents a certain service to be restarted
because the server side is stuck in TIME_WAIT state.
</description>
</property>
<!-- FairCallQueue properties -->
<!-- See FairCallQueue documentation for a table of all properties -->
<!-- [port_number] is the port used by the IPC server to be configured. -->
<!-- For example, ipc.8020.callqueue.impl will adjust the call queue -->
<!-- implementation for the IPC server running at port 8020. -->
<!-- Typically, [port_number] is configured to be the NameNode RPC port, -->
<!-- i.e. port number in dfs.namenode.rpc-address, or port number in -->
<!-- fs.defaultFS if dfs.namenode.rpc-address is not explicitly configured. -->
<property>
<name>ipc.[port_number].backoff.enable</name>
<value>false</value>
<description>Whether or not to enable client backoff when a queue is full.
</description>
</property>
<property>
<name>ipc.[port_number].callqueue.impl</name>
<value>java.util.concurrent.LinkedBlockingQueue</value>
<description>The fully qualified name of a class to use as the implementation
of a call queue. The default implementation is
java.util.concurrent.LinkedBlockingQueue (FIFO queue).
Use org.apache.hadoop.ipc.FairCallQueue for the Fair Call Queue.
</description>
</property>
<property>
<name>ipc.[port_number].scheduler.impl</name>
<value>org.apache.hadoop.ipc.DefaultRpcScheduler</value>
<description>The fully qualified name of a class to use as the
implementation of the scheduler. The default implementation is
org.apache.hadoop.ipc.DefaultRpcScheduler (no-op scheduler) when not using
FairCallQueue. If using FairCallQueue, defaults to
org.apache.hadoop.ipc.DecayRpcScheduler. Use
org.apache.hadoop.ipc.DecayRpcScheduler in conjunction with the Fair Call
Queue.
</description>
</property>
<property>
<name>ipc.[port_number].scheduler.priority.levels</name>
<value>4</value>
<description>How many priority levels to use within the scheduler and call
queue. This property applies to RpcScheduler and CallQueue.
</description>
</property>
<property>
<name>ipc.[port_number].faircallqueue.multiplexer.weights</name>
<value>8,4,2,1</value>
<description>How much weight to give to each priority queue. This should be
a comma-separated list of length equal to the number of priority levels.
Weights descend by a factor of 2 (e.g., for 4 levels: 8,4,2,1).
This property applies to WeightedRoundRobinMultiplexer.
</description>
</property>
<property>
<name>ipc.[port_number].identity-provider.impl</name>
<value>org.apache.hadoop.ipc.UserIdentityProvider</value>
<description>The identity provider mapping user requests to their identity.
This property applies to DecayRpcScheduler.
</description>
</property>
<property>
<name>ipc.[port_number].cost-provider.impl</name>
<value>org.apache.hadoop.ipc.DefaultCostProvider</value>
<description>The cost provider mapping user requests to their cost. To
enable determination of cost based on processing time, use
org.apache.hadoop.ipc.WeightedTimeCostProvider.
This property applies to DecayRpcScheduler.
</description>
</property>
<property>
<name>ipc.[port_number].decay-scheduler.period-ms</name>
<value>5000</value>
<description>How frequently the decay factor should be applied to the
operation counts of users. Higher values have less overhead, but respond
less quickly to changes in client behavior.
This property applies to DecayRpcScheduler.
</description>
</property>
<property>
<name>ipc.[port_number].decay-scheduler.decay-factor</name>
<value>0.5</value>
<description>When decaying the operation counts of users, the multiplicative
decay factor to apply. Higher values will weight older operations more
strongly, essentially giving the scheduler a longer memory, and penalizing
heavy clients for a longer period of time.
This property applies to DecayRpcScheduler.
</description>
</property>
<property>
<name>ipc.[port_number].decay-scheduler.thresholds</name>
<value>13,25,50</value>
<description>The client load threshold, as an integer percentage, for each
priority queue. Clients producing less load, as a percent of total
operations, than specified at position i will be given priority i. This
should be a comma-separated list of length equal to the number of priority
levels minus 1 (the last is implicitly 100).
Thresholds ascend by a factor of 2 (e.g., for 4 levels: 13,25,50).
This property applies to DecayRpcScheduler.
</description>
</property>
<property>
<name>ipc.[port_number].decay-scheduler.backoff.responsetime.enable</name>
<value>false</value>
<description>Whether or not to enable the backoff by response time feature.
This property applies to DecayRpcScheduler.
</description>
</property>
<property>
<name>ipc.[port_number].decay-scheduler.backoff.responsetime.thresholds</name>
<value>10s,20s,30s,40s</value>
<description>The response time thresholds, as time durations, for each
priority queue. If the average response time for a queue is above this
threshold, backoff will occur in lower priority queues. This should be a
comma-separated list of length equal to the number of priority levels.
Threshold increases by 10s per level (e.g., for 4 levels: 10s,20s,30s,40s)
This property applies to DecayRpcScheduler.
</description>
</property>
<property>
<name>ipc.[port_number].decay-scheduler.metrics.top.user.count</name>
<value>10</value>
<description>The number of top (i.e., heaviest) users to emit metric
information about. This property applies to DecayRpcScheduler.
</description>
</property>
<property>
<name>ipc.[port_number].weighted-cost.lockshared</name>
<value>10</value>
<description>The weight multiplier to apply to the time spent in the
processing phase which holds a shared (read) lock.
This property applies to WeightedTimeCostProvider.
</description>
</property>
<property>
<name>ipc.[port_number].weighted-cost.lockexclusive</name>
<value>100</value>
<description>The weight multiplier to apply to the time spent in the
processing phase which holds an exclusive (write) lock.
This property applies to WeightedTimeCostProvider.
</description>
</property>
<property>
<name>ipc.[port_number].weighted-cost.handler</name>
<value>1</value>
<description>The weight multiplier to apply to the time spent in the
HANDLER phase which do not involve holding a lock.
See org.apache.hadoop.ipc.ProcessingDetails.Timing for more details on
this phase. This property applies to WeightedTimeCostProvider.
</description>
</property>
<property>
<name>ipc.[port_number].weighted-cost.lockfree</name>
<value>1</value>
<description>The weight multiplier to apply to the time spent in the
LOCKFREE phase which do not involve holding a lock.
See org.apache.hadoop.ipc.ProcessingDetails.Timing for more details on
this phase. This property applies to WeightedTimeCostProvider.
</description>
</property>
<property>
<name>ipc.[port_number].weighted-cost.response</name>
<value>1</value>
<description>The weight multiplier to apply to the time spent in the
RESPONSE phase which do not involve holding a lock.
See org.apache.hadoop.ipc.ProcessingDetails.Timing for more details on
this phase. This property applies to WeightedTimeCostProvider.
</description>
</property>
<!-- Proxy Configuration -->
<property>
<name>hadoop.security.impersonation.provider.class</name>
<value></value>
<description>A class which implements ImpersonationProvider interface, used to
authorize whether one user can impersonate a specific user.
If not specified, the DefaultImpersonationProvider will be used.
If a class is specified, then that class will be used to determine
the impersonation capability.
</description>
</property>
<property>
<name>hadoop.rpc.socket.factory.class.default</name>
<value>org.apache.hadoop.net.StandardSocketFactory</value>
<description> Default SocketFactory to use. This parameter is expected to be
formatted as "package.FactoryClassName".
</description>
</property>
<property>
<name>hadoop.rpc.socket.factory.class.ClientProtocol</name>
<value></value>
<description> SocketFactory to use to connect to a DFS. If null or empty, use
hadoop.rpc.socket.class.default. This socket factory is also used by
DFSClient to create sockets to DataNodes.
</description>
</property>
<property>
<name>hadoop.socks.server</name>
<value></value>
<description> Address (host:port) of the SOCKS server to be used by the
SocksSocketFactory.
</description>
</property>
<!-- Topology Configuration -->
<property>
<name>net.topology.node.switch.mapping.impl</name>
<value>org.apache.hadoop.net.ScriptBasedMapping</value>
<description> The default implementation of the DNSToSwitchMapping. It
invokes a script specified in net.topology.script.file.name to resolve
node names. If the value for net.topology.script.file.name is not set, the
default value of DEFAULT_RACK is returned for all node names.
</description>
</property>
<property>
<name>net.topology.impl</name>
<value>org.apache.hadoop.net.NetworkTopology</value>
<description> The default implementation of NetworkTopology which is classic three layer one.
</description>
</property>
<property>
<name>net.topology.script.file.name</name>
<value></value>
<description> The script name that should be invoked to resolve DNS names to
NetworkTopology names. Example: the script would take host.foo.bar as an
argument, and return /rack1 as the output.
</description>
</property>
<property>
<name>net.topology.script.number.args</name>
<value>100</value>
<description> The max number of args that the script configured with
net.topology.script.file.name should be run with. Each arg is an
IP address.
</description>
</property>
<property>
<name>net.topology.table.file.name</name>
<value></value>
<description> The file name for a topology file, which is used when the
net.topology.node.switch.mapping.impl property is set to
org.apache.hadoop.net.TableMapping. The file format is a two column text
file, with columns separated by whitespace. The first column is a DNS or
IP address and the second column specifies the rack where the address maps.
If no entry corresponding to a host in the cluster is found, then
/default-rack is assumed.
</description>
</property>
<!-- Local file system -->
<property>
<name>file.stream-buffer-size</name>
<value>4096</value>
<description>The size of buffer to stream files.
The size of this buffer should probably be a multiple of hardware
page size (4096 on Intel x86), and it determines how much data is
buffered during read and write operations.</description>
</property>
<property>
<name>file.bytes-per-checksum</name>
<value>512</value>
<description>The number of bytes per checksum. Must not be larger than
file.stream-buffer-size</description>
</property>
<property>
<name>file.client-write-packet-size</name>
<value>65536</value>
<description>Packet size for clients to write</description>
</property>
<property>
<name>file.blocksize</name>
<value>67108864</value>
<description>Block size</description>
</property>
<property>
<name>file.replication</name>
<value>1</value>
<description>Replication factor</description>
</property>
<!-- FTP file system -->
<property>
<name>ftp.stream-buffer-size</name>
<value>4096</value>
<description>The size of buffer to stream files.
The size of this buffer should probably be a multiple of hardware
page size (4096 on Intel x86), and it determines how much data is
buffered during read and write operations.</description>
</property>
<property>
<name>ftp.bytes-per-checksum</name>
<value>512</value>
<description>The number of bytes per checksum. Must not be larger than
ftp.stream-buffer-size</description>
</property>
<property>
<name>ftp.client-write-packet-size</name>
<value>65536</value>
<description>Packet size for clients to write</description>
</property>
<property>
<name>ftp.blocksize</name>
<value>67108864</value>
<description>Block size</description>
</property>
<property>
<name>ftp.replication</name>
<value>3</value>
<description>Replication factor</description>
</property>
<!-- Tfile -->
<property>
<name>tfile.io.chunk.size</name>
<value>1048576</value>
<description>
Value chunk size in bytes. Default to
1MB. Values of the length less than the chunk size is
guaranteed to have known value length in read time (See also
TFile.Reader.Scanner.Entry.isValueLengthKnown()).
</description>
</property>
<property>
<name>tfile.fs.output.buffer.size</name>
<value>262144</value>
<description>
Buffer size used for FSDataOutputStream in bytes.
</description>
</property>
<property>
<name>tfile.fs.input.buffer.size</name>
<value>262144</value>
<description>
Buffer size used for FSDataInputStream in bytes.
</description>
</property>
<!-- HTTP web-consoles Authentication -->
<property>
<name>hadoop.http.authentication.type</name>
<value>simple</value>
<description>
Defines authentication used for Oozie HTTP endpoint.
Supported values are: simple | kerberos | #AUTHENTICATION_HANDLER_CLASSNAME#
</description>
</property>
<property>
<name>hadoop.http.authentication.token.validity</name>
<value>36000</value>
<description>
Indicates how long (in seconds) an authentication token is valid before it has
to be renewed.
</description>
</property>
<property>
<name>hadoop.http.authentication.signature.secret.file</name>
<value>${user.home}/hadoop-http-auth-signature-secret</value>
<description>
The signature secret for signing the authentication tokens.
A different secret should be used for each service.
</description>
</property>
<property>
<name>hadoop.http.authentication.cookie.domain</name>
<value></value>
<description>
The domain to use for the HTTP cookie that stores the authentication token.
In order to authentiation to work correctly across all Hadoop nodes web-consoles
the domain must be correctly set.
IMPORTANT: when using IP addresses, browsers ignore cookies with domain settings.
For this setting to work properly all nodes in the cluster must be configured
to generate URLs with hostname.domain names on it.
</description>
</property>
<property>
<name>hadoop.http.authentication.simple.anonymous.allowed</name>
<value>true</value>
<description>
Indicates if anonymous requests are allowed when using 'simple' authentication.
</description>
</property>
<property>
<name>hadoop.http.authentication.kerberos.principal</name>
<value>HTTP/_HOST@LOCALHOST</value>
<description>
Indicates the Kerberos principal to be used for HTTP endpoint.
The principal MUST start with 'HTTP/' as per Kerberos HTTP SPNEGO specification.
</description>
</property>
<property>
<name>hadoop.http.authentication.kerberos.keytab</name>
<value>${user.home}/hadoop.keytab</value>
<description>
Location of the keytab file with the credentials for the principal.
Referring to the same keytab file Oozie uses for its Kerberos credentials for Hadoop.
</description>
</property>
<property>
<name>hadoop.http.authentication.kerberos.endpoint.whitelist</name>
<value></value>
<description>
The comma-separated list of the endpoints that skips Kerberos
authentication. The endpoint must start with '/' and must not
contain special characters afterwards. This parameter is for
the monitoring tools that do not support Kerberos authentication.
Administrator must configure this parameter very carefully
because it allows unauthenticated access to the daemons.
</description>
</property>
<!-- HTTP CORS support -->
<property>
<name>hadoop.http.cross-origin.enabled</name>
<value>false</value>
<description>Enable/disable the cross-origin (CORS) filter.</description>
</property>
<property>
<name>hadoop.http.cross-origin.allowed-origins</name>
<value>*</value>
<description>Comma separated list of origins that are allowed for web services
needing cross-origin (CORS) support. If a value in the list contains an
asterix (*), a regex pattern, escaping any dots ('.' -> '\.') and replacing
the asterix such that it captures any characters ('*' -> '.*'), is generated.
Values prefixed with 'regex:' are interpreted directly as regular expressions,
e.g. use the expression 'regex:https?:\/\/foo\.bar:([0-9]+)?' to allow any
origin using the 'http' or 'https' protocol in the domain 'foo.bar' on any
port. The use of simple wildcards ('*') is discouraged, and only available for
backward compatibility.</description>
</property>
<property>
<name>hadoop.http.cross-origin.allowed-methods</name>
<value>GET,POST,HEAD</value>
<description>Comma separated list of methods that are allowed for web
services needing cross-origin (CORS) support.</description>
</property>
<property>
<name>hadoop.http.cross-origin.allowed-headers</name>
<value>X-Requested-With,Content-Type,Accept,Origin</value>
<description>Comma separated list of headers that are allowed for web
services needing cross-origin (CORS) support.</description>
</property>
<property>
<name>hadoop.http.cross-origin.max-age</name>
<value>1800</value>
<description>The number of seconds a pre-flighted request can be cached
for web services needing cross-origin (CORS) support.</description>
</property>
<property>
<name>dfs.ha.fencing.methods</name>
<value></value>
<description>
List of fencing methods to use for service fencing. May contain
builtin methods (eg shell and sshfence) or user-defined method.
</description>
</property>
<property>
<name>dfs.ha.fencing.ssh.connect-timeout</name>
<value>30000</value>
<description>
SSH connection timeout, in milliseconds, to use with the builtin
sshfence fencer.
</description>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value></value>
<description>
The SSH private key files to use with the builtin sshfence fencer.
</description>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<description>
A list of ZooKeeper server addresses, separated by commas, that are
to be used by the ZKFailoverController in automatic failover.
</description>
</property>
<property>
<name>ha.zookeeper.session-timeout.ms</name>
<value>10000</value>
<description>
The session timeout to use when the ZKFC connects to ZooKeeper.
Setting this value to a lower value implies that server crashes
will be detected more quickly, but risks triggering failover too
aggressively in the case of a transient error or network blip.
</description>
</property>
<property>
<name>ha.zookeeper.parent-znode</name>
<value>/hadoop-ha</value>
<description>
The ZooKeeper znode under which the ZK failover controller stores
its information. Note that the nameservice ID is automatically
appended to this znode, so it is not normally necessary to
configure this, even in a federated environment.
</description>
</property>
<property>
<name>ha.zookeeper.acl</name>
<value>world:anyone:rwcda</value>
<description>
A comma-separated list of ZooKeeper ACLs to apply to the znodes
used by automatic failover. These ACLs are specified in the same
format as used by the ZooKeeper CLI.
If the ACL itself contains secrets, you may instead specify a
path to a file, prefixed with the '@' symbol, and the value of
this configuration will be loaded from within.
</description>
</property>
<property>
<name>ha.zookeeper.auth</name>
<value></value>
<description>
A comma-separated list of ZooKeeper authentications to add when
connecting to ZooKeeper. These are specified in the same format
as used by the "addauth" command in the ZK CLI. It is
important that the authentications specified here are sufficient
to access znodes with the ACL specified in ha.zookeeper.acl.
If the auths contain secrets, you may instead specify a
path to a file, prefixed with the '@' symbol, and the value of
this configuration will be loaded from within.
</description>
</property>
<!-- Static Web User Filter properties. -->
<property>
<name>hadoop.http.staticuser.user</name>
<value>dr.who</value>
<description>
The user name to filter as, on static web filters
while rendering content. An example use is the HDFS
web UI (user to be used for browsing files).
</description>
</property>
<!-- SSLFactory configuration -->
<property>
<name>hadoop.ssl.keystores.factory.class</name>
<value>org.apache.hadoop.security.ssl.FileBasedKeyStoresFactory</value>
<description>
The keystores factory to use for retrieving certificates.
</description>
</property>
<property>
<name>hadoop.ssl.require.client.cert</name>
<value>false</value>
<description>Whether client certificates are required</description>
</property>
<property>
<name>hadoop.ssl.hostname.verifier</name>
<value>DEFAULT</value>
<description>
The hostname verifier to provide for HttpsURLConnections.
Valid values are: DEFAULT, STRICT, STRICT_IE6, DEFAULT_AND_LOCALHOST and
ALLOW_ALL
</description>
</property>
<property>
<name>hadoop.ssl.server.conf</name>
<value>ssl-server.xml</value>
<description>
Resource file from which ssl server keystore information will be extracted.
This file is looked up in the classpath, typically it should be in Hadoop
conf/ directory.
</description>
</property>
<property>
<name>hadoop.ssl.client.conf</name>
<value>ssl-client.xml</value>
<description>
Resource file from which ssl client keystore information will be extracted
This file is looked up in the classpath, typically it should be in Hadoop
conf/ directory.
</description>
</property>
<property>
<name>hadoop.ssl.enabled</name>
<value>false</value>
<description>
Deprecated. Use dfs.http.policy and yarn.http.policy instead.
</description>
</property>
<property>
<name>hadoop.ssl.enabled.protocols</name>
<value>TLSv1.2</value>
<description>
The supported SSL protocols. The parameter will only be used from
DatanodeHttpServer.
Starting from Hadoop 3.3.0, TLSv1.3 is supported with Java 11 Runtime.
</description>
</property>
<property>
<name>hadoop.jetty.logs.serve.aliases</name>
<value>true</value>
<description>
Enable/Disable aliases serving from jetty
</description>
</property>
<property>
<name>fs.permissions.umask-mode</name>
<value>022</value>
<description>
The umask used when creating files and directories.
Can be in octal or in symbolic. Examples are:
"022" (octal for u=rwx,g=r-x,o=r-x in symbolic),
or "u=rwx,g=rwx,o=" (symbolic for 007 in octal).
</description>
</property>
<!-- ha properties -->
<property>
<name>ha.health-monitor.connect-retry-interval.ms</name>
<value>1000</value>
<description>
How often to retry connecting to the service.
</description>
</property>
<property>
<name>ha.health-monitor.check-interval.ms</name>
<value>1000</value>
<description>
How often to check the service.
</description>
</property>
<property>
<name>ha.health-monitor.sleep-after-disconnect.ms</name>
<value>1000</value>
<description>
How long to sleep after an unexpected RPC error.
</description>
</property>
<property>
<name>ha.health-monitor.rpc.connect.max.retries</name>
<value>1</value>
<description>
The number of retries on connect error when establishing RPC proxy
connection to NameNode, used for monitorHealth() calls.
</description>
</property>
<property>
<name>ha.health-monitor.rpc-timeout.ms</name>
<value>45000</value>
<description>
Timeout for the actual monitorHealth() calls.
</description>
</property>
<property>
<name>ha.failover-controller.new-active.rpc-timeout.ms</name>
<value>60000</value>
<description>
Timeout that the FC waits for the new active to become active
</description>
</property>
<property>
<name>ha.failover-controller.graceful-fence.rpc-timeout.ms</name>
<value>5000</value>
<description>
Timeout that the FC waits for the old active to go to standby
</description>
</property>
<property>
<name>ha.failover-controller.graceful-fence.connection.retries</name>
<value>1</value>
<description>
FC connection retries for graceful fencing
</description>
</property>
<property>
<name>ha.failover-controller.active-standby-elector.zk.op.retries</name>
<value>3</value>
<description>
The number of zookeeper operation retry times in ActiveStandbyElector
</description>
</property>
<property>
<name>ha.failover-controller.cli-check.rpc-timeout.ms</name>
<value>20000</value>
<description>
Timeout that the CLI (manual) FC waits for monitorHealth, getServiceState
</description>
</property>
<property>
<name>ipc.client.fallback-to-simple-auth-allowed</name>
<value>false</value>
<description>
When a client is configured to attempt a secure connection, but attempts to
connect to an insecure server, that server may instruct the client to
switch to SASL SIMPLE (unsecure) authentication. This setting controls
whether or not the client will accept this instruction from the server.
When false (the default), the client will not allow the fallback to SIMPLE
authentication, and will abort the connection.
</description>
</property>
<property>
<name>fs.client.resolve.remote.symlinks</name>
<value>true</value>
<description>
Whether to resolve symlinks when accessing a remote Hadoop filesystem.
Setting this to false causes an exception to be thrown upon encountering
a symlink. This setting does not apply to local filesystems, which
automatically resolve local symlinks.
</description>
</property>
<property>
<name>nfs.exports.allowed.hosts</name>
<value>* rw</value>
<description>
By default, the export can be mounted by any client. The value string
contains machine name and access privilege, separated by whitespace
characters. The machine name format can be a single host, a Java regular
expression, or an IPv4 address. The access privilege uses rw or ro to
specify read/write or read-only access of the machines to exports. If the
access privilege is not provided, the default is read-only. Entries are separated by ";".
For example: "192.168.0.0/22 rw ; host.*\.example\.com ; host1.test.org ro;".
Only the NFS gateway needs to restart after this property is updated.
</description>
</property>
<property>
<name>hadoop.user.group.static.mapping.overrides</name>
<value>dr.who=;</value>
<description>
Static mapping of user to groups. This will override the groups if
available in the system for the specified user. In other words, groups
look-up will not happen for these users, instead groups mapped in this
configuration will be used.
Mapping should be in this format.
user1=group1,group2;user2=;user3=group2;
Default, "dr.who=;" will consider "dr.who" as user without groups.
</description>
</property>
<property>
<name>rpc.metrics.quantile.enable</name>
<value>false</value>
<description>
Setting this property to true and rpc.metrics.percentiles.intervals
to a comma-separated list of the granularity in seconds, the
50/75/90/95/99th percentile latency for rpc queue/processing time in
milliseconds are added to rpc metrics.
</description>
</property>
<property>
<name>rpc.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 rpc queue/processing
time. The metrics are outputted if rpc.metrics.quantile.enable is set to
true.
</description>
</property>
<property>
<name>hadoop.security.crypto.codec.classes.EXAMPLECIPHERSUITE</name>
<value></value>
<description>
The prefix for a given crypto codec, contains a comma-separated
list of implementation classes for a given crypto codec (eg EXAMPLECIPHERSUITE).
The first implementation will be used if available, others are fallbacks.
</description>
</property>
<property>
<name>hadoop.security.crypto.codec.classes.aes.ctr.nopadding</name>
<value>org.apache.hadoop.crypto.OpensslAesCtrCryptoCodec, org.apache.hadoop.crypto.JceAesCtrCryptoCodec</value>
<description>
Comma-separated list of crypto codec implementations for AES/CTR/NoPadding.
The first implementation will be used if available, others are fallbacks.
</description>
</property>
<property>
<name>hadoop.security.crypto.cipher.suite</name>
<value>AES/CTR/NoPadding</value>
<description>
Cipher suite for crypto codec.
</description>
</property>
<property>
<name>hadoop.security.crypto.jce.provider</name>
<value></value>
<description>
The JCE provider name used in CryptoCodec.
</description>
</property>
<property>
<name>hadoop.security.crypto.jceks.key.serialfilter</name>
<description>
Enhanced KeyStore Mechanisms in JDK 8u171 introduced jceks.key.serialFilter.
If jceks.key.serialFilter is configured, the JCEKS KeyStore uses it during
the deserialization of the encrypted Key object stored inside a
SecretKeyEntry.
If jceks.key.serialFilter is not configured it will cause an error when
recovering keystore file in KeyProviderFactory when recovering key from
keystore file using JDK 8u171 or newer. The filter pattern uses the same
format as jdk.serialFilter.
The value of this property will be used as the following:
1. The value of jceks.key.serialFilter system property takes precedence
over the value of this property.
2. In the absence of jceks.key.serialFilter system property the value of
this property will be set as the value of jceks.key.serialFilter.
3. If the value of this property and jceks.key.serialFilter system
property has not been set, org.apache.hadoop.crypto.key.KeyProvider
sets a default value for jceks.key.serialFilter.
</description>
</property>
<property>
<name>hadoop.security.crypto.buffer.size</name>
<value>8192</value>
<description>
The buffer size used by CryptoInputStream and CryptoOutputStream.
</description>
</property>
<property>
<name>hadoop.security.java.secure.random.algorithm</name>
<value>SHA1PRNG</value>
<description>
The java secure random algorithm.
</description>
</property>
<property>
<name>hadoop.security.secure.random.impl</name>
<value>org.apache.hadoop.crypto.random.OpensslSecureRandom</value>
<description>
Implementation of secure random.
</description>
</property>
<property>
<name>hadoop.security.random.device.file.path</name>
<value>/dev/urandom</value>
<description>
OS security random device file path.
</description>
</property>
<property>
<name>hadoop.security.key.provider.path</name>
<description>
The KeyProvider to use when managing zone keys, and interacting with
encryption keys when reading and writing to an encryption zone.
For hdfs clients, the provider path will be same as namenode's
provider path.
</description>
</property>
<property>
<name>hadoop.security.key.default.bitlength</name>
<value>128</value>
<description>
The length (bits) of keys we want the KeyProvider to produce. Key length
defines the upper-bound on an algorithm's security, ideally, it would
coincide with the lower-bound on an algorithm's security.
</description>
</property>
<property>
<name>hadoop.security.key.default.cipher</name>
<value>AES/CTR/NoPadding</value>
<description>
This indicates the algorithm that be used by KeyProvider for generating
key, and will be converted to CipherSuite when creating encryption zone.
</description>
</property>
<property>
<name>fs.har.impl.disable.cache</name>
<value>true</value>
<description>Don't cache 'har' filesystem instances.</description>
</property>
<!--- KMSClientProvider configurations -->
<property>
<name>hadoop.security.kms.client.authentication.retry-count</name>
<value>1</value>
<description>
Number of time to retry connecting to KMS on authentication failure
</description>
</property>
<property>
<name>hadoop.security.kms.client.encrypted.key.cache.size</name>
<value>500</value>
<description>
Size of the EncryptedKeyVersion cache Queue for each key
</description>
</property>
<property>
<name>hadoop.security.kms.client.encrypted.key.cache.low-watermark</name>
<value>0.3f</value>
<description>
If size of the EncryptedKeyVersion cache Queue falls below the
low watermark, this cache queue will be scheduled for a refill
</description>
</property>
<property>
<name>hadoop.security.kms.client.encrypted.key.cache.num.refill.threads</name>
<value>2</value>
<description>
Number of threads to use for refilling depleted EncryptedKeyVersion
cache Queues
</description>
</property>
<property>
<name>hadoop.security.kms.client.encrypted.key.cache.expiry</name>
<value>43200000</value>
<description>
Cache expiry time for a Key, after which the cache Queue for this
key will be dropped. Default = 12hrs
</description>
</property>
<property>
<name>hadoop.security.kms.client.timeout</name>
<value>60</value>
<description>
Sets value for KMS client connection timeout, and the read timeout
to KMS servers.
</description>
</property>
<property>
<name>hadoop.security.kms.client.failover.sleep.base.millis</name>
<value>100</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 hadoop.security.client.failover.sleep.base.millis
milliseconds. And so on.
</description>
</property>
<property>
<name>hadoop.security.kms.client.failover.sleep.max.millis</name>
<value>2000</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 hadoop.security.client.failover.sleep.max.millis
milliseconds.
</description>
</property>
<property>
<name>ipc.server.max.connections</name>
<value>0</value>
<description>The maximum number of concurrent connections a server is allowed
to accept. If this limit is exceeded, incoming connections will first fill
the listen queue and then may go to an OS-specific listen overflow queue.
The client may fail or timeout, but the server can avoid running out of file
descriptors using this feature. 0 means no limit.
</description>
</property>
<!-- YARN registry -->
<property>
<name>hadoop.registry.zk.root</name>
<value>/registry</value>
<description>
The root zookeeper node for the registry
</description>
</property>
<property>
<name>hadoop.registry.zk.session.timeout.ms</name>
<value>60000</value>
<description>
Zookeeper session timeout in milliseconds
</description>
</property>
<property>
<name>hadoop.registry.zk.connection.timeout.ms</name>
<value>15000</value>
<description>
Zookeeper connection timeout in milliseconds
</description>
</property>
<property>
<name>hadoop.registry.zk.retry.times</name>
<value>5</value>
<description>
Zookeeper connection retry count before failing
</description>
</property>
<property>
<name>hadoop.registry.zk.retry.interval.ms</name>
<value>1000</value>
<description>
</description>
</property>
<property>
<name>hadoop.registry.zk.retry.ceiling.ms</name>
<value>60000</value>
<description>
Zookeeper retry limit in milliseconds, during
exponential backoff.
This places a limit even
if the retry times and interval limit, combined
with the backoff policy, result in a long retry
period
</description>
</property>
<property>
<name>hadoop.registry.zk.quorum</name>
<value>localhost:2181</value>
<description>
List of hostname:port pairs defining the
zookeeper quorum binding for the registry
</description>
</property>
<property>
<name>hadoop.registry.secure</name>
<value>false</value>
<description>
Key to set if the registry is secure. Turning it on
changes the permissions policy from "open access"
to restrictions on kerberos with the option of
a user adding one or more auth key pairs down their
own tree.
</description>
</property>
<property>
<name>hadoop.registry.system.acls</name>
<value>sasl:yarn@, sasl:mapred@, sasl:hdfs@</value>
<description>
A comma separated list of Zookeeper ACL identifiers with
system access to the registry in a secure cluster.
These are given full access to all entries.
If there is an "@" at the end of a SASL entry it
instructs the registry client to append the default kerberos domain.
</description>
</property>
<property>
<name>hadoop.registry.kerberos.realm</name>
<value></value>
<description>
The kerberos realm: used to set the realm of
system principals which do not declare their realm,
and any other accounts that need the value.
If empty, the default realm of the running process
is used.
If neither are known and the realm is needed, then the registry
service/client will fail.
</description>
</property>
<property>
<name>hadoop.registry.jaas.context</name>
<value>Client</value>
<description>
Key to define the JAAS context. Used in secure
mode
</description>
</property>
<property>
<name>hadoop.shell.missing.defaultFs.warning</name>
<value>false</value>
<description>
Enable hdfs shell commands to display warnings if (fs.defaultFS) property
is not set.
</description>
</property>
<property>
<name>hadoop.shell.safely.delete.limit.num.files</name>
<value>100</value>
<description>Used by -safely option of hadoop fs shell -rm command to avoid
accidental deletion of large directories. When enabled, the -rm command
requires confirmation if the number of files to be deleted is greater than
this limit. The default limit is 100 files. The warning is disabled if
the limit is 0 or the -safely is not specified in -rm command.
</description>
</property>
<property>
<name>fs.client.htrace.sampler.classes</name>
<value></value>
<description>The class names of the HTrace Samplers to use for Hadoop
filesystem clients.
</description>
</property>
<property>
<name>hadoop.htrace.span.receiver.classes</name>
<value></value>
<description>The class names of the Span Receivers to use for Hadoop.
</description>
</property>
<property>
<name>hadoop.http.logs.enabled</name>
<value>true</value>
<description>
Enable the "/logs" endpoint on all Hadoop daemons, which serves local
logs, but may be considered a security risk due to it listing the contents
of a directory.
</description>
</property>
<property>
<name>fs.client.resolve.topology.enabled</name>
<value>false</value>
<description>Whether the client machine will use the class specified by
property net.topology.node.switch.mapping.impl to compute the network
distance between itself and remote machines of the FileSystem. Additional
properties might need to be configured depending on the class specified
in net.topology.node.switch.mapping.impl. For example, if
org.apache.hadoop.net.ScriptBasedMapping is used, a valid script file
needs to be specified in net.topology.script.file.name.
</description>
</property>
<!-- Azure Data Lake File System Configurations -->
<property>
<name>fs.adl.impl</name>
<value>org.apache.hadoop.fs.adl.AdlFileSystem</value>
</property>
<property>
<name>fs.AbstractFileSystem.adl.impl</name>
<value>org.apache.hadoop.fs.adl.Adl</value>
</property>
<property>
<name>adl.feature.ownerandgroup.enableupn</name>
<value>false</value>
<description>
When true : User and Group in FileStatus/AclStatus response is
represented as user friendly name as per Azure AD profile.
When false (default) : User and Group in FileStatus/AclStatus
response is represented by the unique identifier from Azure AD
profile (Object ID as GUID).
For optimal performance, false is recommended.
</description>
</property>
<property>
<name>fs.adl.oauth2.access.token.provider.type</name>
<value>ClientCredential</value>
<description>
Defines Azure Active Directory OAuth2 access token provider type.
Supported types are ClientCredential, RefreshToken, MSI, DeviceCode,
and Custom.
The ClientCredential type requires property fs.adl.oauth2.client.id,
fs.adl.oauth2.credential, and fs.adl.oauth2.refresh.url.
The RefreshToken type requires property fs.adl.oauth2.client.id and
fs.adl.oauth2.refresh.token.
The MSI type reads optional property fs.adl.oauth2.msi.port, if specified.
The DeviceCode type requires property
fs.adl.oauth2.devicecode.clientapp.id.
The Custom type requires property fs.adl.oauth2.access.token.provider.
</description>
</property>
<property>
<name>fs.adl.oauth2.client.id</name>
<value></value>
<description>The OAuth2 client id.</description>
</property>
<property>
<name>fs.adl.oauth2.credential</name>
<value></value>
<description>The OAuth2 access key.</description>
</property>
<property>
<name>fs.adl.oauth2.refresh.url</name>
<value></value>
<description>The OAuth2 token endpoint.</description>
</property>
<property>
<name>fs.adl.oauth2.refresh.token</name>
<value></value>
<description>The OAuth2 refresh token.</description>
</property>
<property>
<name>fs.adl.oauth2.access.token.provider</name>
<value></value>
<description>
The class name of the OAuth2 access token provider.
</description>
</property>
<property>
<name>fs.adl.oauth2.msi.port</name>
<value></value>
<description>
The localhost port for the MSI token service. This is the port specified
when creating the Azure VM. The default, if this setting is not specified,
is 50342.
Used by MSI token provider.
</description>
</property>
<property>
<name>fs.adl.oauth2.devicecode.clientapp.id</name>
<value></value>
<description>
The app id of the AAD native app in whose context the auth request
should be made.
Used by DeviceCode token provider.
</description>
</property>
<property>
<name>adl.http.timeout</name>
<value>-1</value>
<description>
Base timeout (in milliseconds) for HTTP requests from the ADL SDK. Values
of zero or less cause the SDK default to be used instead.
</description>
</property>
<property>
<name>adl.ssl.channel.mode</name>
<value></value>
<description>
Valid inputs are OpenSSL, Default_JSE and Default (case insensitive).
If config is missing or is invalid, SSL Channel mode will be set to Default.
When OpenSSL, SSL socket connections are created in OpenSSL mode.
When Default_JSE, SSL socket connections are created in the default JSE mode.
When Default, SSL socket connections are attempted with OpenSSL
and will fallback to Default_JSE mode if OpenSSL is not available at runtime.
</description>
</property>
<!-- Azure Data Lake File System Configurations Ends Here-->
<property>
<name>hadoop.caller.context.enabled</name>
<value>false</value>
<description>When the feature is enabled, additional fields are written into
name-node audit log records for auditing coarse granularity operations.
</description>
</property>
<property>
<name>hadoop.caller.context.max.size</name>
<value>128</value>
<description>The maximum bytes a caller context string can have. If the
passed caller context is longer than this maximum bytes, client will
truncate it before sending to server. Note that the server may have a
different maximum size, and will truncate the caller context to the
maximum size it allows.
</description>
</property>
<property>
<name>hadoop.caller.context.signature.max.size</name>
<value>40</value>
<description>
The caller's signature (optional) is for offline validation. If the
signature exceeds the maximum allowed bytes in server, the caller context
will be abandoned, in which case the caller context will not be recorded
in audit logs.
</description>
</property>
<!-- SequenceFile's Sorter properties -->
<property>
<name>seq.io.sort.mb</name>
<value>100</value>
<description>
The total amount of buffer memory to use while sorting files,
while using SequenceFile.Sorter, in megabytes. By default,
gives each merge stream 1MB, which should minimize seeks.
</description>
</property>
<property>
<name>seq.io.sort.factor</name>
<value>100</value>
<description>
The number of streams to merge at once while sorting
files using SequenceFile.Sorter.
This determines the number of open file handles.
</description>
</property>
<property>
<name>hadoop.zk.address</name>
<!--value>127.0.0.1:2181</value-->
<description>Host:Port of the ZooKeeper server to be used.
</description>
</property>
<property>
<name>hadoop.zk.num-retries</name>
<value>1000</value>
<description>Number of tries to connect to ZooKeeper.</description>
</property>
<property>
<name>hadoop.zk.retry-interval-ms</name>
<value>1000</value>
<description>Retry interval in milliseconds when connecting to ZooKeeper.
</description>
</property>
<property>
<name>hadoop.zk.timeout-ms</name>
<value>10000</value>
<description>ZooKeeper session timeout in milliseconds. Session expiration
is managed by the ZooKeeper cluster itself, not by the client. This value is
used by the cluster to determine when the client's session expires.
Expirations happens when the cluster does not hear from the client within
the specified session timeout period (i.e. no heartbeat).</description>
</property>
<property>
<name>hadoop.zk.acl</name>
<value>world:anyone:rwcda</value>
<description>ACL's to be used for ZooKeeper znodes.</description>
</property>
<property>
<name>hadoop.zk.auth</name>
<description>
Specify the auths to be used for the ACL's specified in hadoop.zk.acl.
This takes a comma-separated list of authentication mechanisms, each of the
form 'scheme:auth' (the same syntax used for the 'addAuth' command in
the ZK CLI).
</description>
</property>
<property>
<name>hadoop.system.tags</name>
<value>YARN,HDFS,NAMENODE,DATANODE,REQUIRED,SECURITY,KERBEROS,PERFORMANCE,CLIENT
,SERVER,DEBUG,DEPRECATED,COMMON,OPTIONAL</value>
<description>
Deprecated. Please use hadoop.tags.system instead.
</description>
</property>
<property>
<name>hadoop.tags.system</name>
<value>YARN,HDFS,NAMENODE,DATANODE,REQUIRED,SECURITY,KERBEROS,PERFORMANCE,CLIENT
,SERVER,DEBUG,DEPRECATED,COMMON,OPTIONAL</value>
<description>
System tags to group related properties together.
</description>
</property>
<property>
<name>ipc.client.bind.wildcard.addr</name>
<value>false</value>
<description>When set to true Clients will bind socket to wildcard
address. (i.e 0.0.0.0)
</description>
</property>
<property>
<name>hadoop.domainname.resolver.impl</name>
<value>org.apache.hadoop.net.DNSDomainNameResolver</value>
<description>The implementation of DomainNameResolver used for service (NameNodes,
RBF Routers etc) discovery. The default implementation
org.apache.hadoop.net.DNSDomainNameResolver returns all IP addresses associated
with the input domain name of the services by querying the underlying DNS.
</description>
</property>
<property>
<name>dfs.client.ignore.namenode.default.kms.uri</name>
<value>false</value>
<description>
Ignore KMS default URI returned from NameNode.
When set to true, kms uri is searched in the following order:
1. If there is a mapping in Credential's secrets map for namenode uri.
2. Fallback to local conf. (i.e hadoop.security.key.provider.path)
If client choose to ignore KMS uri provided by NameNode then client
should set KMS URI using 'hadoop.security.key.provider.path' to access
the right KMS for encrypted files.
</description>
</property>
<property>
<name>hadoop.prometheus.endpoint.enabled</name>
<value>false</value>
<description>
If set to true, prometheus compatible metric page on the HTTP servers
is enabled via '/prom' endpoint.
</description>
</property>
<property>
<name>fs.getspaceused.classname</name>
<value></value>
<description>
The class that can tell estimate much space is used in a directory.
There are four impl classes that being supported:
org.apache.hadoop.fs.DU(default), org.apache.hadoop.fs.WindowsGetSpaceUsed
org.apache.hadoop.fs.DFCachingGetSpaceUsed and
org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.ReplicaCachingGetSpaceUsed.
And the ReplicaCachingGetSpaceUsed impl class only used in HDFS module.
</description>
</property>
<property>
<name>fs.getspaceused.jitterMillis</name>
<value>60000</value>
<description>
fs space usage statistics refresh jitter in msec.
</description>
</property>
<property>
<name>hadoop.http.sni.host.check.enabled</name>
<value>false</value>
<description>
Enable Server Name Indication (SNI) host check for HTTPS enabled server.
</description>
</property>
<property>
<name>hadoop.metrics.jvm.use-thread-mxbean</name>
<value>false</value>
<description>
Whether or not ThreadMXBean is used for getting thread info in JvmMetrics,
ThreadGroup approach is preferred for better performance.
</description>
</property>
</configuration>
