[
https://issues.apache.org/jira/browse/CASSANDRA-5549?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13867396#comment-13867396
]
Jonathan Ellis commented on CASSANDRA-5549:
-------------------------------------------
bq. I should mention that I hope to introduce a patch next week that relies on
most of these things we'll be stripping out
I get that, but it's good hygiene to keep things self contained (and I don't
have to review it until then :).
bq. It's also not trivial to design a test that tells you for sure that it
does/doesn't
How good are you at reading JIT assembly? :)
But if it's not critical then I'm definitely partial to this form as being
easier to understand.
> Remove Table.switchLock
> -----------------------
>
> Key: CASSANDRA-5549
> URL: https://issues.apache.org/jira/browse/CASSANDRA-5549
> Project: Cassandra
> Issue Type: Bug
> Reporter: Jonathan Ellis
> Assignee: Benedict
> Labels: performance
> Fix For: 2.1
>
> Attachments: 5549-removed-switchlock.png, 5549-sunnyvale.png
>
>
> As discussed in CASSANDRA-5422, Table.switchLock is a bottleneck on the write
> path. ReentrantReadWriteLock is not lightweight, even if there is no
> contention per se between readers and writers of the lock (in Cassandra,
> memtable updates and switches).
--
This message was sent by Atlassian JIRA
(v6.1.5#6160)
