[
https://issues.apache.org/jira/browse/HBASE-15716?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15262438#comment-15262438
]
stack commented on HBASE-15716:
-------------------------------
Ok. Putting this aside for now. We could apply a patch that changes the HashMap
from Concurrent to plain HashMap for some benefit since it always accessed
under a synchronize block but it is the synchronization that is the way of our
being able to scale up our random reads. Need to figure way to do without it.
Will be back.
> HRegion#RegionScannerImpl scannerReadPoints synchronization costs
> -----------------------------------------------------------------
>
> Key: HBASE-15716
> URL: https://issues.apache.org/jira/browse/HBASE-15716
> Project: HBase
> Issue Type: Bug
> Components: Performance
> Reporter: stack
> Assignee: stack
> Attachments: 15716.prune.synchronizations.patch,
> 15716.prune.synchronizations.v3.patch, 15716.prune.synchronizations.v4.patch,
> 15716.prune.synchronizations.v4.patch, Screen Shot 2016-04-26 at 2.05.45
> PM.png, Screen Shot 2016-04-26 at 2.06.14 PM.png, Screen Shot 2016-04-26 at
> 2.07.06 PM.png, Screen Shot 2016-04-26 at 2.25.26 PM.png, Screen Shot
> 2016-04-26 at 6.02.29 PM.png, Screen Shot 2016-04-27 at 9.49.35 AM.png,
> current-branch-1.vs.NoSynchronization.vs.Patch.png, hits.png,
> remove_cslm.patch
>
>
> Here is a [~lhofhansl] special.
> When we construct the region scanner, we get our read point and then store it
> with the scanner instance in a Region scoped CSLM. This is done under a
> synchronize on the CSLM.
> This synchronize on a region-scoped Map creating region scanners is the
> outstanding point of lock contention according to flight recorder (My work
> load is workload c, random reads).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
