cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Joshua McKenzie (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (CASSANDRA-7282) Faster Memtable map
Date Sat, 13 Sep 2014 19:59:34 GMT

    [ https://issues.apache.org/jira/browse/CASSANDRA-7282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14132924#comment-14132924
] 

Joshua McKenzie commented on CASSANDRA-7282:
--------------------------------------------

{quote}
does factor in to the decision
{quote}
{quote}
1) what workloads / portions of workloads are affected;
{quote}
That's what I was referring to.

To be clear: I'm not saying we shouldn't use the container or that I'm against it in any way,
 I'm just re-iterating that we need to be clear as to which use-cases and configurations we
expect this to help with (which you've done) and weigh that relative to the added risk of
untested code and the added complexity associated with the change.

> 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
>
>         Attachments: 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
(v6.3.4#6332)

Mime
View raw message