hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Yu Li (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-14969) Add throughput controller for flush
Date Mon, 01 Feb 2016 09:22:39 GMT

    [ https://issues.apache.org/jira/browse/HBASE-14969?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15125993#comment-15125993
] 

Yu Li commented on HBASE-14969:
-------------------------------

It was my fault not making the test robust enough, sorry sir [~stack].

Thanks for the quick action [~Apache9]. I think we also need to include the {{assertEquals}}
check in {{testFlushThroughputTuning}} into the try clause to make sure the minicluster will
be shutdown at end of the case:
{code}
    assertEquals(10L * 1024 * 1024,
      ((PressureAwareThroughputController) TEST_UTIL.getMiniHBaseCluster().getRegionServer(0)
          .getFlushThroughputController()).getMaxThroughput(), EPSILON);
    Connection conn = ConnectionFactory.createConnection(conf);
    try {
      HTableDescriptor htd = new HTableDescriptor(tableName);
      htd.addFamily(new HColumnDescriptor(family));
{code}

Let me prepare an addendum for you to review.

> Add throughput controller for flush
> -----------------------------------
>
>                 Key: HBASE-14969
>                 URL: https://issues.apache.org/jira/browse/HBASE-14969
>             Project: HBase
>          Issue Type: Improvement
>          Components: regionserver
>    Affects Versions: 2.0.0, 1.3.0
>            Reporter: Yu Li
>            Assignee: Yu Li
>             Fix For: 2.0.0, 1.3.0
>
>         Attachments: HBASE-14969.branch-1.patch, HBASE-14969.patch, HBASE-14969_v10.patch,
HBASE-14969_v2.patch, HBASE-14969_v3.patch, HBASE-14969_v4.patch, HBASE-14969_v5.patch, HBASE-14969_v6.patch,
HBASE-14969_v9.patch, fd78628_9909808_compat_report.html, load-nothrottling.log, load-throttling.log
>
>
> In HBASE-8329 we added a throughput controller for compaction, to avoid spike caused
by huge IO pressure like network/disk overflow. However, even with this control on, we are
still observing disk utils near 100%, and by analysis we think this is caused by flush, especially
when we increase the setting of {{hbase.hstore.flusher.count}}
> In this JIRA, we propose to add throughput control feature for flush, as a supplement
of HBASE-8329 to better control IO pressure.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message