hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "stack (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (HBASE-15241) Blockcache only loads 100k blocks from a file
Date Wed, 10 Feb 2016 00:45:18 GMT

     [ https://issues.apache.org/jira/browse/HBASE-15241?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

stack updated HBASE-15241:
--------------------------
    Description: We can only load 100k blocks from a file. If 256Gs of SSD and blocks are
4k in size to align with SSD block read, and you want it all in cache, the 100k  limit gets
in the way (The 100k may be absolute limit... checking. In UI I see 100k only). There is a
configuration which lets you up the number per file, hbase.ui.blockcache.by.file.max. This
helps.  (was: We can only load 100k blocks from a file. If 256Gs of SSD and blocks are 4k
in size to align with SSD block read, and you want it all in cache, the 100k  limit gets in
the way (The 100k may be absolute limit... checking. In UI I see 100k only).)

> Blockcache only loads 100k blocks from a file
> ---------------------------------------------
>
>                 Key: HBASE-15241
>                 URL: https://issues.apache.org/jira/browse/HBASE-15241
>             Project: HBase
>          Issue Type: Sub-task
>          Components: BucketCache
>            Reporter: stack
>
> We can only load 100k blocks from a file. If 256Gs of SSD and blocks are 4k in size to
align with SSD block read, and you want it all in cache, the 100k  limit gets in the way (The
100k may be absolute limit... checking. In UI I see 100k only). There is a configuration which
lets you up the number per file, hbase.ui.blockcache.by.file.max. This helps.



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

Mime
View raw message