Mailing-List: contact issues-help@hbase.apache.org; run by ezmlm
Precedence: bulk
Date: Wed, 17 Dec 2014 09:43:14 +0000 (UTC)
From: "Weichen Ye (JIRA)" <jira@apache.org>
To: issues@hbase.apache.org
Message-ID: <JIRA.12758108.1417053514000.42170.1418809394618@Atlassian.JIRA>
In-Reply-To: <JIRA.12758108.1417053514000@Atlassian.JIRA>
References: <JIRA.12758108.1417053514000@Atlassian.JIRA>
 <JIRA.12758108.1417053514565@arcas>
Subject: [jira] [Updated] (HBASE-12590) A solution for data skew in
 HBase-Mapreduce Job
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable


     [ https://issues.apache.org/jira/browse/HBASE-12590?page=3Dcom.atlassi=
an.jira.plugin.system.issuetabpanels:all-tabpanel ]

Weichen Ye updated HBASE-12590:
-------------------------------
    Attachment: HBASE-12590-v4.patch

> A solution for data skew in HBase-Mapreduce Job
> -----------------------------------------------
>
>                 Key: HBASE-12590
>                 URL: https://issues.apache.org/jira/browse/HBASE-12590
>             Project: HBase
>          Issue Type: Improvement
>          Components: mapreduce
>            Reporter: Weichen Ye
>         Attachments: A Solution for Data Skew in HBase-MapReduce Job (Ver=
sion2).pdf, A Solution for Data Skew in HBase-MapReduce Job (Version3).pdf,=
 HBASE-12590-v3.patch, HBASE-12590-v4.patch, HBase-12590-v1.patch, HBase-12=
590-v2.patch
>
>
> 1, Motivation
> In production environment, data skew is a very common case. A HBase table=
 may contains a lot of small regions and several large regions. Small regio=
ns waste a lot of computing resources. If we use a job to scan a table with=
 3000 small regions, we need a job with 3000 mappers. Large regions always =
block the job. If in a 100-region table, one region is far large then the o=
ther 99 regions. When we run a job with the table as input, 99 mappers will=
 be completed very quickly, and then we need to wait for the last mapper fo=
r a long time.
> 2, Configuration
> Add three new configuration=20
> hbase.mapreduce.input.autobalance =3D true means enabling the =E2=80=9Cau=
to balance=E2=80=9D in HBase-MapReduce jobs. The default value is false.=20
> hbase.mapreduce.input.autobalance.maxskewratio=3D 3 (default is 3). If a =
region size is larger than 3x average region size, treat the region as =E2=
=80=9Cproportionately too large=E2=80=9D.
> hbase.table.row.textkey  =3D true means the row key is text. False means =
binary row key. It is used to find the mid row key in large region. The def=
ault value is true.=20
> If (region size >=3D average size*ratio) :  cut the region into two MR in=
put splits
> If (average size <=3D region size < average size*ratio) : one region as o=
ne MR input split
> If (sum of several continuous regions size < average size): combine these=
 regions into one MR input split.
> Example:
> In attachment
> Welcome to the Review Board.
> https://reviews.apache.org/r/28494/diff/#


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