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

Switch to Threaded View
HBase, mail # user - How to speed up Scan -- please help


Copy link to this message
-
Re: How to speed up Scan -- please help
Andrey Stepachev 2010-09-13, 19:06
vmstat should be taken while you are scanning.
it can show you, what you host is doing.
where you bottleneck: in cpu, or in disk io.

compression status can be found in hbase shell
by issuing describe 'tablename' and look at
COMPRESSION parameter, or you can
look at description of table in hbase web
interface.

2010/9/13 Jian Lu <[EMAIL PROTECTED]>:
> How to tell if I'm using gzip family?
>
> Below is the output from vmstat 1:
>
> procs -----------memory---------- ---swap-- -----io---- --system-- -----cpu------
>  r  b   swpd   free   buff  cache   si   so    bi    bo   in   cs us sy id wa st
>  0  0      0 489068 153664 2789984    0    0     0     1    0    0  0  0 100  0  0
>  0  0      0 489068 153664 2789984    0    0     0     0 1049  155  0  0 100  0  0
>  0  0      0 489068 153664 2789984    0    0     0     0 1019  152  0  0 100  0  0
>  0  0      0 489068 153664 2789984    0    0     0     0 1047  182  0  0 100  0  0
>  0  0      0 489068 153664 2789984    0    0     0    96 1035  176  0  0 90 10  0
>
>
> Jack.
>