[
https://issues.apache.org/jira/browse/HBASE-17747?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15923529#comment-15923529
]
stack commented on HBASE-17747:
-------------------------------
[~Apache9] have a point . You running this in prod [~carp84]? If the soft
reference queues do not get enough servicing then yeah, they can back up
keeping a hold on references. If you are running this in prod with loads of
churn, would be good to know. On other hand, having this go in here now before
we cut hbase2 means we should find out if it is an issue before we get around
to making a release. It is pretty obvious when the queue-clearing gets
backed-up.
> Support both weak and soft object pool
> --------------------------------------
>
> Key: HBASE-17747
> URL: https://issues.apache.org/jira/browse/HBASE-17747
> Project: HBase
> Issue Type: Improvement
> Affects Versions: 2.0
> Reporter: Yu Li
> Assignee: Yu Li
> Fix For: 2.0
>
> Attachments: HBASE-17747.patch, HBASE-17747.v2.patch,
> HBASE-17747.v3.patch
>
>
> During YCSB testing on embedded mode after HBASE-17744, we found that under
> high read load GC is quite severe even with offheap L2 cache. After some
> investigation, we found it's caused by using weak reference in
> {{IdReadWriteLock}}. In embedded mode the read is so quick that the lock
> might already get promoted to the old generation when the weak reference is
> cleared, which causes dirty card table (old reference get removed and new
> lock object set into {{referenceCache}}, see {{WeakObjectPool#get}}) thus
> slowing YGC. In distributed mode there'll also be more lock object created
> with weak reference than soft reference that slowing down the processing.
> So we proposed to use soft reference for this {{IdReadWriteLock}} used in
> cache, which won't get cleared until JVM memory is not enough, and could
> resolve the issue mentioned above. What's more, we propose to extend the
> {{WeakObjectPool}} to be more generate to support both weak and soft
> reference.
> Note that the GC issue only emerges under embedded mode with DirectOperator,
> in which case all costs on the wire is removed thus produces extremely high
> concurrency.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
