cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "sankalp kohli (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (CASSANDRA-9754) Make index info heap friendly for large CQL partitions
Date Wed, 08 Jul 2015 21:04:04 GMT

    [ https://issues.apache.org/jira/browse/CASSANDRA-9754?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14619368#comment-14619368
] 

sankalp kohli commented on CASSANDRA-9754:
------------------------------------------

If I am understanding it correctly, CASSANDRA-9738 will move the key cache off heap. This
will help as these IndexInfo objects won't be promoted as they won't be referenced by any
on heap map. 

However, we will still need to generate all these objects for each read whether it is in key
cache or not. With CASSANDRA-9738, on key cache hit, we will create new objects again in deserializing.


I think CASSANDRA-9738 is good but we can still optimize on reducing the objects created which
is currently promotional to the size of the CQL partition. 

> Make index info heap friendly for large CQL partitions
> ------------------------------------------------------
>
>                 Key: CASSANDRA-9754
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-9754
>             Project: Cassandra
>          Issue Type: Improvement
>            Reporter: sankalp kohli
>            Priority: Minor
>
>  Looking at a heap dump of 2.0 cluster, I found that majority of the objects are IndexInfo
and its ByteBuffers. This is specially bad in endpoints with large CQL partitions. If a CQL
partition is say 6,4GB, it will have 100K IndexInfo objects and 200K ByteBuffers. This will
create a lot of churn for GC. Can this be improved by not creating so many objects?



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

Mime
View raw message