[
https://issues.apache.org/jira/browse/HBASE-12590?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Weichen Ye updated HBASE-12590:
-------------------------------
Description:
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 regions 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 other 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 for a long time.
2, Configuration
Add three new configuration
hbase.mapreduce.input.autobalance = true means enabling the “auto balance” in
HBase-MapReduce jobs. The default value is false.
hbase.mapreduce.input.autobalance.maxskewratio= 3 (default is 3). If a region
size is larger than 3x average region size, treat the region as
“proportionately too large”.
hbase.table.row.textkey = 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 default value
is true.
If (region size >= average size*ratio) : cut the region into two MR input
splits
If (average size <= region size < average size*ratio) : one region as one 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/#
was:
1, Motivation
In production environment, data skew is a very common case. A HBase table
always contains a lot of small regions and several large regions. Small regions
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 larger then the other 99
regions. When we run a job with the table as input, 99 mappers will be
completed very quickly, and we need to wait for the last mapper for a long time.
2, Configuration
Add two new configuration.
hbase.mapreduce.split.autobalance = true means enabling the “auto balance” in
HBase-MapReduce jobs. The default value is false.
hbase.mapreduce.split.targetsize = 1073741824 (default 1GB). The target size of
mapreduce splits.
If a region size is large than the target size, cut the region into two
split.If the sum of several small continuous region size less than the target
size, combine these regions into one split.
Example:
In attachment
Welcome to the Review Board.
https://reviews.apache.org/r/28494/diff/#
> 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
> (Version2).pdf, A Solution for Data Skew in HBase-MapReduce Job
> (Version3).pdf, HBASE-12590-v3.patch, HBase-12590-v1.patch,
> HBase-12590-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 regions
> 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 other 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 for a
> long time.
> 2, Configuration
> Add three new configuration
> hbase.mapreduce.input.autobalance = true means enabling the “auto balance” in
> HBase-MapReduce jobs. The default value is false.
> hbase.mapreduce.input.autobalance.maxskewratio= 3 (default is 3). If a region
> size is larger than 3x average region size, treat the region as
> “proportionately too large”.
> hbase.table.row.textkey = 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 default
> value is true.
> If (region size >= average size*ratio) : cut the region into two MR input
> splits
> If (average size <= region size < average size*ratio) : one region as one 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)
