hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Nicolas Liochon (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-6295) Possible performance improvement in client batch operations: presplit and send in background
Date Fri, 19 Apr 2013 13:33:16 GMT

    [ https://issues.apache.org/jira/browse/HBASE-6295?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13636364#comment-13636364
] 

Nicolas Liochon commented on HBASE-6295:
----------------------------------------

It seems that in this test, on AWS, we're limited by the bandwidth between the client and
the region server. The 25% is the time spent by the client waiting for an answer from the
servers.

This stack occurs sometimes with plain trunk and very often with 6295:

{noformat}
2013-04-19 09:22:45,991 WARN  [IPC Client (682317035) connection to ip-10-6-131-32.ec2.internal/10.6.131.32:60020
from root] ipc.HBaseClient (HBaseClient.java:run(664)) - IPC Client (682317035) connection
to ip-10-6-131-32.ec2.internal/10.6.131.32:60020 from root: unexpected exception receiving
call responses
java.lang.RuntimeException: java.lang.NullPointerException
	at org.apache.hadoop.hbase.ipc.HBaseClient$Connection.readResponse(HBaseClient.java:1017)
	at org.apache.hadoop.hbase.ipc.HBaseClient$Connection.run(HBaseClient.java:661)
Caused by: java.lang.NullPointerException
	at org.apache.hadoop.hbase.ipc.HBaseClient$Connection.readResponse(HBaseClient.java:1013)
	... 1 more
 1197 sec: 3411081 operations; 324,27 current ops/sec; [INSERT AverageLatency(us)=29332,6]

{noformat}

[~saint.ack@gmail.com], is this code changed / removed by the refactoring in progress in the
client?
                
> Possible performance improvement in client batch operations: presplit and send in background
> --------------------------------------------------------------------------------------------
>
>                 Key: HBASE-6295
>                 URL: https://issues.apache.org/jira/browse/HBASE-6295
>             Project: HBase
>          Issue Type: Improvement
>          Components: Client, Performance
>    Affects Versions: 0.95.2
>            Reporter: Nicolas Liochon
>            Assignee: Nicolas Liochon
>              Labels: noob
>         Attachments: 6295.v1.patch, 6295.v2.patch, 6295.v3.patch
>
>
> today batch algo is:
> {noformat}
> for Operation o: List<Op>{
>   add o to todolist
>   if todolist > maxsize or o last in list
>     split todolist per location
>     send split lists to region servers
>     clear todolist
>     wait
> }
> {noformat}
> We could:
> - create immediately the final object instead of an intermediate array
> - split per location immediately
> - instead of sending when the list as a whole is full, send it when there is enough data
for a single location
> It would be:
> {noformat}
> for Operation o: List<Op>{
>   get location
>   add o to todo location.todolist
>   if (location.todolist > maxLocationSize)
>     send location.todolist to region server 
>     clear location.todolist
>     // don't wait, continue the loop
> }
> send remaining
> wait
> {noformat}
> It's not trivial to write if you add error management: retried list must be shared with
the operations added in the todolist. But it's doable.
> It's interesting mainly for 'big' writes

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message