[
https://issues.apache.org/jira/browse/CASSANDRA-7282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16534146#comment-16534146
]
Benedict commented on CASSANDRA-7282:
-------------------------------------
Thanks. I'm surprised, and will dig into this a little more myself.
However, we have to be careful with these microbenchmarks. The whole state
fits in L1 cache here, but there's a good chance this will not be hot in L1 in
live operation, given how poor our general cache usage is; it's certainly less
likely with the tree approach (given it is much larger in memory). So if the
scores are similar (which they are), I would still prefer the array variant.
Still, it should be outright faster, so I'll take a look and see if I can
figure out why you're seeing this behaviour.
> Faster Memtable map
> -------------------
>
> Key: CASSANDRA-7282
> URL: https://issues.apache.org/jira/browse/CASSANDRA-7282
> Project: Cassandra
> Issue Type: Improvement
> Reporter: Benedict
> Assignee: Michael Burman
> Priority: Major
> Labels: performance
> Fix For: 4.x
>
> Attachments: jasobrown-sample-run.txt, profile.yaml, reads.svg,
> run1.svg, writes.svg
>
>
> Currently we maintain a ConcurrentSkipLastMap of DecoratedKey -> Partition in
> our memtables. Maintaining this is an O(lg(n)) operation; since the vast
> majority of users use a hash partitioner, it occurs to me we could maintain a
> hybrid ordered list / hash map. The list would impose the normal order on the
> collection, but a hash index would live alongside as part of the same data
> structure, simply mapping into the list and permitting O(1) lookups and
> inserts.
> I've chosen to implement this initial version as a linked-list node per item,
> but we can optimise this in future by storing fatter nodes that permit a
> cache-line's worth of hashes to be checked at once, further reducing the
> constant factor costs for lookups.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org
For additional commands, e-mail: commits-h...@cassandra.apache.org
