Mailing-List: contact issues-help@hbase.apache.org; run by ezmlm
Precedence: bulk
Date: Mon, 16 Dec 2013 07:56:08 +0000 (UTC)
From: "Jingcheng Du (JIRA)" <jira@apache.org>
To: issues@hbase.apache.org
Message-ID: <JIRA.12684877.1387160288270.41336.1387180568806@arcas>
In-Reply-To: <JIRA.12684877.1387160288270@arcas>
References: <JIRA.12684877.1387160288270@arcas>
Subject: [jira] [Updated] (HBASE-10169) Batch coprocessor
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable


     [ https://issues.apache.org/jira/browse/HBASE-10169?page=3Dcom.atlassi=
an.jira.plugin.system.issuetabpanels:all-tabpanel ]

Jingcheng Du updated HBASE-10169:
---------------------------------

    Attachment: Batch Coprocessor Design Document.docx

> Batch coprocessor
> -----------------
>
>                 Key: HBASE-10169
>                 URL: https://issues.apache.org/jira/browse/HBASE-10169
>             Project: HBase
>          Issue Type: Sub-task
>          Components: Coprocessors
>    Affects Versions: 0.99.0
>            Reporter: Jingcheng Du
>            Assignee: Jingcheng Du
>         Attachments: Batch Coprocessor Design Document.docx, HBASE-10169.=
patch
>
>
> This is designed to improve the coprocessor invocation in the client side=
.=20
> Currently the coprocessor invocation is to send a call to each region. If=
 there=E2=80=99s one region server, and 100 regions are located in this ser=
ver, each coprocessor invocation will send 100 calls, each call uses a sing=
le thread in the client side. The threads will run out soon when the coproc=
essor invocations are heavy.=20
> In this design, all the calls to the same region server will be grouped i=
nto one in a single coprocessor invocation. This call will be spread into e=
ach region in the server side, and the results will be merged ahead in the =
server side before being returned to the client.


--
This message was sent by Atlassian JIRA
(v6.1.4#6159)