ignite-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Ilya Lantukh (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (IGNITE-3014) Optimize GridDhtPartitionTopologyImpl#localPartition()
Date Wed, 27 Apr 2016 23:26:12 GMT

    [ https://issues.apache.org/jira/browse/IGNITE-3014?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15261183#comment-15261183
] 

Ilya Lantukh commented on IGNITE-3014:
--------------------------------------

Optimizations are implemented, but they caused GridCacheStopSelfTest to fail sometimes with
a wierd error:
"java.lang.AssertionError: Transaction does not own lock for update" at org.apache.ignite.internal.processors.cache.GridCacheMapEntry.innerSet(GridCacheMapEntry.java:1138).
It doesn't happen in current master branch and I still don't have a clear understanding of
the reason behind it.

> Optimize GridDhtPartitionTopologyImpl#localPartition()
> ------------------------------------------------------
>
>                 Key: IGNITE-3014
>                 URL: https://issues.apache.org/jira/browse/IGNITE-3014
>             Project: Ignite
>          Issue Type: Improvement
>            Reporter: Ilya Lantukh
>            Assignee: Ilya Lantukh
>              Labels: performance
>
> This method is called at least once for every cache operation on each node.
> It was partially optimized in https://issues.apache.org/jira/browse/IGNITE-2948.
> It seems that we can reduce time spent in that method even further by removing excessive
RW locks and using volatile read/write instead.



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

Mime
View raw message