[
https://issues.apache.org/jira/browse/ACCUMULO-1755?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15163437#comment-15163437
]
Dave Marion edited comment on ACCUMULO-1755 at 2/24/16 6:07 PM:
----------------------------------------------------------------
We could solve this by:
1. Making MutationSet.mutations a ConcurrentHashMap
2. Making MutationSet.memoryUsed an AtomicLong
3. Not synchronizing on access to TabletServerBatchWriter.mutations
4. Changing TabletServerBatchWriter.mutations to an AtomicReference so that it
is safe to swap it out in startProcessing()
5. In startProcessing(), swap in a new MutationSet then add the mutations from
the previous MutationSet to the writer.
was (Author: dlmarion):
We could solve this by:
1. Making MutationSet.mutations a ConcurrentHashMap
2. Not synchronizing on access to TabletServerBatchWriter.mutations
3. Changing TabletServerBatchWriter.mutations to an AtomicReference so that it
is safe to swap it out in startProcessing()
4. In startProcessing(), swap in a new MutationSet then add the mutations from
the previous MutationSet to the writer.
> BatchWriter blocks all addMutation calls while binning mutations
> ----------------------------------------------------------------
>
> Key: ACCUMULO-1755
> URL: https://issues.apache.org/jira/browse/ACCUMULO-1755
> Project: Accumulo
> Issue Type: Improvement
> Components: client
> Reporter: Adam Fuchs
>
> Through code inspection, we found that the BatchWriter bins mutations inside
> of a synchronized block that covers calls to addMutation. Binning potentially
> involves lookups of tablet metadata and processes a fair amount of
> information. We will get better parallelism if we can either unlock the lock
> while binning, dedicate another thread to do the binning, or use one of the
> send threads to do the binning.
> This has not been verified empirically yet, so there is not yet any profiling
> info to indicate the level of improvement that we should expect. Profiling
> and repeatable demonstration of this performance bottleneck should be the
> first step on this ticket.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
