cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Ryan McGuire (JIRA)" <j...@apache.org>
Subject [jira] [Comment Edited] (CASSANDRA-7282) Faster Memtable map
Date Thu, 21 Aug 2014 04:10:46 GMT

    [ https://issues.apache.org/jira/browse/CASSANDRA-7282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14104970#comment-14104970
] 

Ryan McGuire edited comment on CASSANDRA-7282 at 8/21/14 4:10 AM:
------------------------------------------------------------------

Thanks Benedict, I tried it with those new settings. Still using memtable_cleanup_threshold
of 0.5 :

http://riptano.github.io/cassandra_performance/graph_v3/graph.html?stats=stats.7282.3.json

Getting a bit more interesting now, not sure what's up with that first read and then the drop.

EDIT: a second run of this shows similar results: http://riptano.github.io/cassandra_performance/graph_v3/graph.html?stats=stats.7282.3-redo.json&metric=op_rate&operation=2_read&smoothing=1&show_aggregates=true&xmin=0&xmax=389.62&ymin=0&ymax=196953.9

I'll try scaling up memtable_cleanup_threshold again.


was (Author: enigmacurry):
Thanks Benedict, I tried it with those new settings. Still using memtable_cleanup_threshold
of 0.5 :

http://riptano.github.io/cassandra_performance/graph_v3/graph.html?stats=stats.7282.3.json

Getting a bit more interesting now, not sure what's up with that first read and then the drop.

I'll try scaling up memtable_cleanup_threshold again.

> Faster Memtable map
> -------------------
>
>                 Key: CASSANDRA-7282
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-7282
>             Project: Cassandra
>          Issue Type: Improvement
>          Components: Core
>            Reporter: Benedict
>            Assignee: Benedict
>              Labels: performance
>             Fix For: 3.0
>
>
> 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
(v6.2#6252)

Mime
View raw message