You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hbase.apache.org by "Duo Zhang (JIRA)" <ji...@apache.org> on 2019/06/11 15:13:00 UTC
[jira] [Commented] (HBASE-22564) Compare performance number with
old sync client implementation
[ https://issues.apache.org/jira/browse/HBASE-22564?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16861128#comment-16861128 ]
Duo Zhang commented on HBASE-22564:
-----------------------------------
Set up a 5 node hbase cluster with the master code, and test it with both master client and HBASE-21512 client with PE. The number is not good, need to find out what's the problem.
The command is
{noformat}
./bin/hbase pe --presplit=10 --nomapred --rows=2000000 randomWrite 10 &>test.log </dev/null &
{noformat}
And the result for master client
{noformat}
2019-06-11 22:55:57,109 INFO [main] hbase.PerformanceEvaluation: [RandomWriteTest duration ] Min: 50539ms Max: 51925ms Avg: 51355ms
2019-06-11 22:55:57,109 INFO [main] hbase.PerformanceEvaluation: [ Avg latency (us)] 25
2019-06-11 22:55:57,109 INFO [main] hbase.PerformanceEvaluation: [ Avg TPS/QPS] 389465 row per second
{noformat}
And the result for HBASE-21512 client
{noformat}
2019-06-11 22:57:58,449 INFO [main] hbase.PerformanceEvaluation: [RandomWriteTest duration ] Min: 62140ms Max: 63839ms Avg: 62913ms
2019-06-11 22:57:58,449 INFO [main] hbase.PerformanceEvaluation: [ Avg latency (us)] 30
2019-06-11 22:57:58,449 INFO [main] hbase.PerformanceEvaluation: [ Avg TPS/QPS] 317916 row per second
{noformat}
> Compare performance number with old sync client implementation
> --------------------------------------------------------------
>
> Key: HBASE-22564
> URL: https://issues.apache.org/jira/browse/HBASE-22564
> Project: HBase
> Issue Type: Sub-task
> Reporter: Duo Zhang
> Priority: Major
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)