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-14186) Read mvcc vlong optimization
Date Wed, 05 Aug 2015 04:10:05 GMT

    [ https://issues.apache.org/jira/browse/HBASE-14186?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14654779#comment-14654779
] 

Anoop Sam John commented on HBASE-14186:
----------------------------------------

bq.Is it possible, that we could come in here and there'd only be a short amount to read so
we'd skip the SIZEOF_INT parens? if so, the shift by 16 bits in the second paren would be
not needed (might not be a problem if left shifting 0)
Yes shifting 0 is not a problem apart from this is an unwanted op.  But I think it is ok.
  The mvcc will be either 0 or some larger value with more than 4 bytes.

> Read mvcc vlong optimization
> ----------------------------
>
>                 Key: HBASE-14186
>                 URL: https://issues.apache.org/jira/browse/HBASE-14186
>             Project: HBase
>          Issue Type: Sub-task
>          Components: Scanners
>            Reporter: Anoop Sam John
>            Assignee: Anoop Sam John
>             Fix For: 2.0.0
>
>         Attachments: HBASE-14186.patch
>
>
> {code}
> for (int idx = 0; idx < remaining; idx++) {
>   byte b = blockBuffer.getByteAfterPosition(offsetFromPos + idx);
>   i = i << 8;
>   i = i | (b & 0xFF);
> }
> {code}
> Doing the read as in case of BIG_ENDIAN.
> After HBASE-12600, we tend to keep the mvcc and so byte by byte read looks eating up
lot of CPU time. (In my test HFileReaderImpl#_readMvccVersion comes on top in terms of hot
methods). We can optimize here by reading 4 or 2 bytes in one shot when the length of the
vlong is more than 4 bytes. We will in turn use UnsafeAccess methods which handles ENDIAN.



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

Mime
View raw message