hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Hiroshi Ikeda (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-14479) Apply the Leader/Followers pattern to RpcServer's Reader
Date Mon, 26 Oct 2015 07:38:27 GMT

    [ https://issues.apache.org/jira/browse/HBASE-14479?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14973862#comment-14973862
] 

Hiroshi Ikeda commented on HBASE-14479:
---------------------------------------

That's interesting.

I don't know details about YCSB, but does it use multiple connections? The selectors without
the patch consume more CPU time than the selector with the patch.

Park/unpark in the semaphore with the patch consumes non-trivial CPU time. The semaphore releases
a permit for each connection to read, but there might be actually well context switches to
wake up threads with overhead of park/unpark compared to cost of their tasks.

> Apply the Leader/Followers pattern to RpcServer's Reader
> --------------------------------------------------------
>
>                 Key: HBASE-14479
>                 URL: https://issues.apache.org/jira/browse/HBASE-14479
>             Project: HBase
>          Issue Type: Improvement
>          Components: IPC/RPC, Performance
>            Reporter: Hiroshi Ikeda
>            Assignee: Hiroshi Ikeda
>            Priority: Minor
>         Attachments: HBASE-14479-V2 (1).patch, HBASE-14479-V2.patch, HBASE-14479-V2.patch,
HBASE-14479.patch, flamegraph-19152.svg, flamegraph-32667.svg, gc.png, gets.png, io.png, median.png
>
>
> {{RpcServer}} uses multiple selectors to read data for load distribution, but the distribution
is just done by round-robin. It is uncertain, especially for long run, whether load is equally
divided and resources are used without being wasted.
> Moreover, multiple selectors may cause excessive context switches which give priority
to low latency (while we just add the requests to queues), and it is possible to reduce throughput
of the whole server.



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

Mime
View raw message