[
https://issues.apache.org/jira/browse/HBASE-12031?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14150173#comment-14150173
]
stack commented on HBASE-12031:
-------------------------------
bq. HFileContext carries the information on some of the meta data about the
HFile - this is per HFile. FielReaderContext is per Reader (Scanner).
bq. Probably, yes but need a place (class) to move the actual read to.
Can it not be done inside existing model via changes to HFileBlock and/or
changes in scanners rather than doing this 'cross-cut'?
bq. Not all data from read ahead buffer should be cached in a general case.
Sharing some data between scanners in RA buffer is not a common case.
Tell me more about the use case then? Many scanners inside the same region but
they will not be scanning same files? RA buffers per scanner will need to be
accounted for so we can measure mem usage. Since we read in the block, why not
go via blockcache unless for sure it is one-shot only?
Will readahead be a scanner option?
Good stuff [~vrodionov]
> Parallel Scanners inside Region
> -------------------------------
>
> Key: HBASE-12031
> URL: https://issues.apache.org/jira/browse/HBASE-12031
> Project: HBase
> Issue Type: New Feature
> Components: Performance, Scanners
> Affects Versions: 0.98.6
> Reporter: Vladimir Rodionov
> Assignee: Vladimir Rodionov
> Fix For: 1.0.0, 2.0.0, 0.98.7, 0.99.1
>
> Attachments: HBASE-12031.2.patch, HBASE-12031.3.patch,
> HBASE-12031.patch, ParallelScannerDesign.pdf, hbase-12031-tests.tar.gz
>
>
> This JIRA to improve performance of multiple scanners running on a same
> region in parallel. The scenarios where we will get the performance benefits:
> * New TableInputFormat with input splits smaller than HBase Region.
> * Scanning during compaction (Compaction scanner and application scanner over
> the same Region).
> Some JIRAs related to this one:
> https://issues.apache.org/jira/browse/HBASE-7336
> https://issues.apache.org/jira/browse/HBASE-5979
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
