Home | About | Sematext search-lucene.com search-hadoop.com
 Search Hadoop and all its subprojects:

Switch to Plain View
HBase, mail # user - HBase random read performance


+
Ankit Jain 2013-04-13, 05:31
+
Ted Yu 2013-04-13, 15:16
+
Adrien Mogenet 2013-04-13, 16:00
+
Harsh J 2013-04-13, 17:02
+
Jean-Marc Spaggiari 2013-04-14, 21:58
+
Anoop Sam John 2013-04-15, 10:17
+
Rishabh Agrawal 2013-04-15, 10:42
+
Ankit Jain 2013-04-15, 10:53
+
谢良 2013-04-15, 11:41
+
Ankit Jain 2013-04-15, 13:04
+
Doug Meil 2013-04-15, 13:21
+
Ted Yu 2013-04-15, 13:30
+
Ted Yu 2013-04-15, 14:13
+
Ted Yu 2013-04-15, 17:03
+
lars hofhansl 2013-04-16, 14:55
+
Liu, Raymond 2013-04-16, 07:49
+
Nicolas Liochon 2013-04-16, 08:22
+
Jean-Marc Spaggiari 2013-04-16, 11:01
+
Michel Segel 2013-04-17, 12:33
+
Håvard Wahl Kongsgård 2013-04-14, 22:19
Copy link to this message
-
Re: HBase random read performance
Mohammad Tariq 2013-04-14, 22:39
Hello Ankit,

   How exactly are you trying to fetch the data?Some tips to enhance the
reads could be :
Use of scan caching.
Good rowkey design.
Use of block cache.
Properly closing HTable and ResultScanner.
Use of bloom filters.
Use of Filters to limit the search.
Proper use of compression.
Use JBOD disk configuration instead of a single big disk. It'll increase
the disk I/O resulting into faster data access.

You might also find the below specified links useful :
http://software.intel.com/en-us/articles/hadoop-and-hbase-optimization-for-read-intensive-search-applications
http://www.packtpub.com/article/hbase-basic-performance-tuning

HTH

Warm Regards,
Tariq
https://mtariq.jux.com/
cloudfront.blogspot.com
On Mon, Apr 15, 2013 at 3:49 AM, Håvard Wahl Kongsgård <
[EMAIL PROTECTED]> wrote:

> you setup is rather basic with 8gb memory per server. You should run
> hadoop/hbase on better hardware than this.
>
> On Sat, Apr 13, 2013 at 7:31 AM, Ankit Jain <[EMAIL PROTECTED]>
> wrote:
> > Hi All,
> >
> > We are using HBase 0.94.5 and Hadoop 1.0.4.
> >
> > We have HBase cluster of 5 nodes(5 regionservers and 1 master node). Each
> > regionserver has 8 GB RAM.
> >
> > We have loaded 25 millions records in HBase table, regions are pre-split
> > into 16 regions and all the regions are equally loaded.
> >
> > We are getting very low random read performance while performing multi
> get
> > from HBase.
> >
> > We are passing random 10000 row-keys as input, while HBase is taking
> around
> > 17 secs to return 10000 records.
> >
> > Please suggest some tuning to increase HBase read performance.
> >
> > Thanks,
> > Ankit Jain
> > iLabs
> >
> >
> >
> > --
> > Thanks,
> > Ankit Jain
>
>
>
> --
> Håvard Wahl Kongsgård
> Data Scientist
> Faculty of Medicine &
> Department of Mathematical Sciences
> NTNU
>
> http://havard.dbkeeping.com/
>
+
Ted Yu 2013-07-08, 12:49