[ 
https://issues.apache.org/jira/browse/HDFS-13274?focusedWorklogId=793926&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-793926
 ]

ASF GitHub Bot logged work on HDFS-13274:
-----------------------------------------

                Author: ASF GitHub Bot
            Created on: 21/Jul/22 20:25
            Start Date: 21/Jul/22 20:25
    Worklog Time Spent: 10m 
      Work Description: goiri commented on code in PR #4531:
URL: https://github.com/apache/hadoop/pull/4531#discussion_r927072119


##########
hadoop-hdfs-project/hadoop-hdfs-rbf/src/main/java/org/apache/hadoop/hdfs/server/federation/router/RBFConfigKeys.java:
##########
@@ -135,6 +135,13 @@ public class RBFConfigKeys extends 
CommonConfigurationKeysPublic {
       FEDERATION_ROUTER_PREFIX + "connection.clean.ms";
   public static final long DFS_ROUTER_NAMENODE_CONNECTION_CLEAN_MS_DEFAULT =
       TimeUnit.SECONDS.toMillis(10);
+  public static final String DFS_ROUTER_NAMENODE_ENABLE_MULTIPLE_SOCKET_KEY =
+      FEDERATION_ROUTER_PREFIX + "enable.multiple.socket";
+  public static final boolean 
DFS_ROUTER_NAMENODE_ENABLE_MULTIPLE_SOCKET_DEFAULT

Review Comment:
   Actually this fits in one line.



##########
hadoop-hdfs-project/hadoop-hdfs-rbf/src/main/resources/hdfs-rbf-default.xml:
##########
@@ -134,6 +134,30 @@
     </description>
   </property>
 
+  <property>
+    <name>dfs.federation.router.enable.multiple.socket</name>
+    <value>false</value>
+    <description>
+      If enable multiple downstream socket or not. If true, ConnectionPool
+      will use a new socket when creating a new connection for the same user,
+      and RouterRPCClient will get a better throughput. It's best used with
+      dfs.federation.router.max.concurrency.per.connection together to get
+      a better throughput with fewer sockets.
+    </description>
+  </property>
+
+  <property>
+    <name>dfs.federation.router.max.concurrency.per.connection</name>
+    <value>1</value>
+    <description>
+      The maximum number of requests that a connection can handle concurrently.
+      It's best used with dfs.federation.router.enable.multiple.socket 
together.

Review Comment:
   If dfs.federation.router.enable.multiple.socket=false does it even take 
effect?
   Can we also give an example or a rule of thumb to what value would be good 
(moderate is a little ambiguous)?





Issue Time Tracking
-------------------

    Worklog Id:     (was: 793926)
    Time Spent: 3.5h  (was: 3h 20m)

> RBF: Extend RouterRpcClient to use multiple sockets
> ---------------------------------------------------
>
>                 Key: HDFS-13274
>                 URL: https://issues.apache.org/jira/browse/HDFS-13274
>             Project: Hadoop HDFS
>          Issue Type: Sub-task
>            Reporter: Íñigo Goiri
>            Assignee: Íñigo Goiri
>            Priority: Major
>              Labels: pull-request-available
>          Time Spent: 3.5h
>  Remaining Estimate: 0h
>
> HADOOP-13144 introduces the ability to create multiple connections for the 
> same user and use different sockets. The RouterRpcClient should use this 
> approach to get a better throughput.



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to