hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Anoop Sam John (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-15314) Allow more than one backing file in bucketcache
Date Thu, 10 Mar 2016 13:02:41 GMT

    [ https://issues.apache.org/jira/browse/HBASE-15314?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15189247#comment-15189247
] 

Anoop Sam John commented on HBASE-15314:
----------------------------------------

So in order to have the clear randomness while filling in files itself, we may have to have
all sized buckets (we have by def 14 buckets of diff sizes) in all files.  The buckets allocation
in entire BC's capacity (offset of each bucket being decided) and allocation for each of the
HFile block happens at an upper layer to IOEngine impl (BucketAllocator)..  I feel this will
be a much bigger change.  Can we do that as a follow on issue?
In read case we will have randomness mostly.. That depends on which blocks we will read..

> Allow more than one backing file in bucketcache
> -----------------------------------------------
>
>                 Key: HBASE-15314
>                 URL: https://issues.apache.org/jira/browse/HBASE-15314
>             Project: HBase
>          Issue Type: Sub-task
>          Components: BucketCache
>            Reporter: stack
>            Assignee: Amal Joshy
>         Attachments: HBASE-15314.patch
>
>
> Allow bucketcache use more than just one backing file: e.g. chassis has more than one
SSD in it.



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

Mime
View raw message