HADOOP-18810. Document missing a lot of properties in core-default.xml. (#5912) Contributed by WangYuanben.

Reviewed-by: Shilun Fan <slfan1989@apache.org>
Signed-off-by: Shilun Fan <slfan1989@apache.org>

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

@@ -73,6 +73,27 @@
   <description>Is service-level authorization enabled?</description>
 </property>
 
+<property>
+  <name>security.service.authorization.default.acl</name>
+  <value></value>
+  <description>
+    Define the default acl for the Hadoop service if the acl of Hadoop
+    service is not defined in hadoop-policy.xml. If not set, `*` is applied
+    meaning that all users are allowed to access the service. The list of
+    users and groups are both comma-separated list of names separated by
+    a space. Example: `user1,user2 group1,group2`.
+  </description>
+</property>
+
+<property>
+  <name>security.service.authorization.default.acl.blocked</name>
+  <value></value>
+  <description>
+    This property specifies the list of users and groups who are not
+    authorized to access Hadoop service.
+  </description>
+</property>
+
 <property>
   <name>hadoop.security.instrumentation.requires.admin</name>
   <value>false</value>
@@ -225,6 +246,17 @@
   </description>
 </property>
 
+<property>
+  <name>hadoop.security.group.mapping.ldap.ctx.factory.class</name>
+  <value></value>
+  <description>
+    Used to specify the fully qualified class name of the initial context
+    factory when connecting to an LDAP server. The default value is
+    "com.sun.jndi.ldap.LdapCtxFactory", but set to null now to avoid
+    LifecycleExecutionException with JDK 11(see HADOOP-15941).
+  </description>
+</property>
+
 <property>
   <name>hadoop.security.group.mapping.ldap.connection.timeout.ms</name>
   <value>60000</value>
@@ -803,7 +835,19 @@
 <property>
   <name>hadoop.token.files</name>
   <value></value>
-  <description>List of token cache files that have delegation tokens for hadoop service</description>
+  <description>
+    A comma-separated list of token cache files that have delegation tokens
+    for hadoop service
+  </description>
+</property>
+
+<property>
+  <name>hadoop.tokens</name>
+  <value></value>
+  <description>
+    A comma-separated list of delegation tokens from base64 encoding
+    for hadoop service.
+  </description>
 </property>
 
 <!-- i/o properties -->
@@ -855,6 +899,65 @@
   operate entirely in Java, specify "java-builtin".</description>
 </property>
 
+<property>
+  <name>io.compression.codec.lz4.buffersize</name>
+  <value>262144</value>
+  <description>
+    Internal buffer size for Lz4 compressor/decompressors.
+  </description>
+</property>
+
+<property>
+  <name>io.compression.codec.lz4.use.lz4hc</name>
+  <value>false</value>
+  <description>
+    Enable lz4hc(slow but with high compression ratio) for lz4 compression.
+  </description>
+</property>
+
+<property>
+  <name>io.compression.codec.lzo.buffersize</name>
+  <value>65536</value>
+  <description>
+    Internal buffer size for Lzo compressor/decompressors.
+  </description>
+</property>
+
+<property>
+  <name>io.compression.codec.lzo.class</name>
+  <value>org.apache.hadoop.io.compress.LzoCodec</value>
+  <description>
+    Codec class that implements Lzo compression algorithm.
+  </description>
+</property>
+
+<property>
+  <name>io.compression.codec.snappy.buffersize</name>
+  <value>262144</value>
+  <description>
+    Internal buffer size for Snappy compressor/decompressors.
+  </description>
+</property>
+
+<property>
+  <name>io.compression.codec.zstd.buffersize</name>
+  <value>0</value>
+  <description>
+    Indicate ZStandard buffer size. The default value 0 means use the
+    recommended zstd buffer size that the library recommends.
+  </description>
+</property>
+
+<property>
+  <name>io.compression.codec.zstd.level</name>
+  <value>3</value>
+  <description>
+    Indicate ZStandard compression level. The higher the compression level,
+    the higher the compression ratio and memory usage, but the slower the
+    compression and decompression speed.
+  </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>
@@ -1145,6 +1248,33 @@
   </description>
 </property>
 
+<property>
+  <name>fs.file.impl</name>
+  <value></value>
+  <description>
+    Specify the implementation class used for accessing the file system. It
+    is a fully qualified class name, including both the package name and the
+    class name.
+  </description>
+</property>
+
+<property>
+  <name>fs.creation.parallel.count</name>
+  <value>64</value>
+  <description>
+    This property sets a a semaphore to throttle the number of FileSystem
+    instances which can be created simultaneously. This is designed to reduce
+    the impact of many threads in an application calling FileSystem#get() on
+    a filesystem which takes time to instantiate -for example to an object
+    where HTTPS connections are set up during initialization. Many threads
+    trying to do this may create spurious delays by conflicting for access
+    to synchronized blocks, when simply limiting the parallelism diminishes
+    the conflict, so speeds up all threads trying to access the store. If a
+    service appears to be blocking on all threads initializing connections to
+    abfs, s3a or store, try a smaller (possibly significantly smaller) value.
+  </description>
+</property>
+
 <property>
   <name>fs.AbstractFileSystem.ftp.impl</name>
   <value>org.apache.hadoop.fs.ftp.FtpFs</value>
@@ -1231,6 +1361,22 @@
   </description>
 </property>
 
+<property>
+  <name>fs.iostatistics.logging.level</name>
+  <value>debug</value>
+  <description>
+    Logging level for IOStatistics.
+  </description>
+</property>
+
+<property>
+  <name>fs.iostatistics.thread.level.enabled</name>
+  <value>true</value>
+  <description>
+    Enable IOStatisticsContext support for thread level.
+  </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>
@@ -2230,6 +2376,13 @@ The switch to turn S3A auditing on or off.
 
 
 <!-- ipc properties -->
+<property>
+  <name>ipc.client.async.calls.max</name>
+  <value>100</value>
+  <description>
+    Define the maximum number of outstanding async calls.
+  </description>
+</property>
 
 <property>
   <name>ipc.client.idlethreshold</name>
@@ -2239,6 +2392,14 @@ The switch to turn S3A auditing on or off.
   </description>
 </property>
 
+<property>
+  <name>ipc.client.connection.idle-scan-interval.ms</name>
+  <value>10000</value>
+  <description>
+    Indicate how often the server scans for idle connections.
+  </description>
+</property>
+
 <property>
   <name>ipc.client.kill.max</name>
   <value>10</value>
@@ -2286,6 +2447,14 @@ The switch to turn S3A auditing on or off.
   </description>
 </property>
 
+<property>
+  <name>ipc.client.connect.max.retries.on.sasl</name>
+  <value>5</value>
+  <description>
+    The maximum retries on SASL connection failures in RPC client.
+  </description>
+</property>
+
 <property>
   <name>ipc.client.tcpnodelay</name>
   <value>true</value>
@@ -2329,6 +2498,14 @@ The switch to turn S3A auditing on or off.
   </description>
 </property>
 
+<property>
+  <name>ipc.server.tcpnodelay</name>
+  <value>true</value>
+  <description>
+    If true then disable Nagle's Algorithm.
+  </description>
+</property>
+
 <property>
   <name>ipc.server.handler.queue.size</name>
   <value>100</value>
@@ -2338,6 +2515,24 @@ The switch to turn S3A auditing on or off.
   </description>
 </property>
 
+<property>
+  <name>ipc.server.max.response.size</name>
+  <value>1048576</value>
+  <description>
+    The maximum size when large IPC handler response buffer is reset.
+  </description>
+</property>
+
+<property>
+  <name>ipc.server.metrics.update.runner.interval</name>
+  <value>5000</value>
+  <description>
+    To configure scheduling of server metrics update thread. This config is
+    used to indicate initial delay and delay between each execution of the
+    metric update runnable thread.
+  </description>
+</property>
+
 <property>
   <name>ipc.server.listen.queue.size</name>
   <value>256</value>
@@ -2363,6 +2558,22 @@ The switch to turn S3A auditing on or off.
   </description>
 </property>
 
+<property>
+  <name>ipc.server.read.connection-queue.size</name>
+  <value>100</value>
+  <description>
+    Number of pending connections that may be queued per socket reader.
+  </description>
+</property>
+
+<property>
+  <name>ipc.server.read.threadpool.size</name>
+  <value>1</value>
+  <description>
+    Indicates the number of threads in RPC server reading from the socket.
+  </description>
+</property>
+
 <property>
   <name>ipc.maximum.data.length</name>
   <value>134217728</value>
@@ -2392,6 +2603,14 @@ The switch to turn S3A auditing on or off.
   </description>
 </property>
 
+<property>
+  <name>callqueue.overflow.trigger.failover</name>
+  <value>false</value>
+  <description>
+    Enable callqueue overflow trigger failover for stateless servers.
+  </description>
+</property>
+
 <!-- FairCallQueue properties -->
 <!-- See FairCallQueue documentation for a table of all properties -->
 
@@ -2476,6 +2695,20 @@ The switch to turn S3A auditing on or off.
   </description>
 </property>
 
+<property>
+  <name>ipc.[port_number].callqueue.capacity.weights</name>
+  <value></value>
+  <description>
+    When FairCallQueue is enabled, user can specify capacity allocation
+    among all sub-queues via this property. The value of this config is
+    a comma-separated list of positive integers, each of which specifies
+    the weight associated with the sub-queue at that index. This list
+    length should be IPC scheduler priority levels, defined by
+    "scheduler.priority.levels". By default, each sub-queue is associated
+    with weight 1, i.e., all sub-queues are allocated with the same capacity.
+  </description>
+</property>
+
 <property>
   <name>ipc.[port_number].scheduler.priority.levels</name>
   <value>4</value>
@@ -2744,6 +2977,24 @@ The switch to turn S3A auditing on or off.
   </description>
 </property>
 
+<property>
+  <name>net.topology.configured.node.mapping</name>
+  <value></value>
+  <description>
+    Key to define the node mapping as a comma-delimited list of host=rack
+    mappings. e.g. host1=r1,host2=r1,host3=r2. Important: spaces not trimmed
+    and are considered significant.
+  </description>
+</property>
+
+<property>
+  <name>net.topology.dependency.script.file.name</name>
+  <value></value>
+  <description>
+    Key to the dependency script filename.
+  </description>
+</property>
+
 <!-- Local file system -->
 <property>
   <name>file.stream-buffer-size</name>
@@ -3274,6 +3525,17 @@ The switch to turn S3A auditing on or off.
   </description>
 </property>
 
+<property>
+  <name>hadoop.user.group.metrics.percentiles.intervals</name>
+  <value></value>
+  <description>
+    A comma-delimited list of integers denoting the desired rollover
+    intervals (in seconds) for percentile latency metrics on the Namenode
+    and Datanode for each user in the group. By default, percentile
+    latency metrics are disabled.
+  </description>
+</property>
+
 <property>
   <name>rpc.metrics.quantile.enable</name>
   <value>false</value>
@@ -3532,6 +3794,24 @@ The switch to turn S3A auditing on or off.
   </description>
 </property>
 
+<property>
+  <name>hadoop.security.kms.client.failover.max.retries</name>
+  <value></value>
+  <description>
+    Default value is the number of providers specified.
+  </description>
+</property>
+
+<property>
+  <name>hadoop.security.kerberos.ticket.cache.path</name>
+  <value></value>
+  <description>
+    Path to the Kerberos ticket cache.  Setting this will force
+    UserGroupInformation to use only this ticket cache file when
+    creating a FileSystem instance.
+  </description>
+</property>
+
  <property>
   <name>ipc.server.max.connections</name>
   <value>0</value>
@@ -3944,6 +4224,30 @@ The switch to turn S3A auditing on or off.
     </description>
   </property>
 
+  <property>
+    <name>hadoop.zk.server.principal</name>
+    <value></value>
+    <description>
+      Principal name for zookeeper servers.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.zk.kerberos.principal</name>
+    <value></value>
+    <description>
+      Kerberos principal name for zookeeper connection.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.zk.kerberos.keytab</name>
+    <value></value>
+    <description>
+      Kerberos keytab for zookeeper connection.
+    </description>
+  </property>
+
   <property>
     <name>hadoop.zk.ssl.keystore.location</name>
     <description>
@@ -3986,7 +4290,15 @@ The switch to turn S3A auditing on or off.
     <value>YARN,HDFS,NAMENODE,DATANODE,REQUIRED,SECURITY,KERBEROS,PERFORMANCE,CLIENT
       ,SERVER,DEBUG,DEPRECATED,COMMON,OPTIONAL</value>
     <description>
-      System tags to group related properties together.
+      A comma-separated list of system tags to group related properties together.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.tags.custom</name>
+    <value></value>
+    <description>
+      A comma-separated list of custom tags to group related properties together.
     </description>
   </property>
 

hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/conf/TestCommonConfigurationFields.java

@@ -157,6 +157,7 @@ public class TestCommonConfigurationFields extends TestConfigurationFieldsBase {
     xmlPropsToSkipCompare.add("ipc.[port_number].scheduler.impl");
     xmlPropsToSkipCompare.add("ipc.scheduler.impl");
     xmlPropsToSkipCompare.add("ipc.[port_number].scheduler.priority.levels");
+    xmlPropsToSkipCompare.add("ipc.[port_number].callqueue.capacity.weights");
     xmlPropsToSkipCompare.add(
         "ipc.[port_number].faircallqueue.multiplexer.weights");
     xmlPropsToSkipCompare.add("ipc.[port_number].identity-provider.impl");