cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jonathan Ellis (JIRA)" <j...@apache.org>
Subject [jira] Commented: (CASSANDRA-2252) off-heap memtables
Date Sun, 27 Feb 2011 04:30:59 GMT

    [ https://issues.apache.org/jira/browse/CASSANDRA-2252?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12999878#comment-12999878
] 

Jonathan Ellis commented on CASSANDRA-2252:
-------------------------------------------

I'll look deeper later, but one quick comment:

bq. Original uses JNA for direct memory access, alternate uses ByteBuffer.allocateDirect

allocateDirect pointers are not freed until CMS runs finalizers, so this could result in much
larger space used than intended.

The JNA-based code isn't perfect though either, I've seen heisenbug segfaults.  I'm sure it's
fixable though.

> off-heap memtables
> ------------------
>
>                 Key: CASSANDRA-2252
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-2252
>             Project: Cassandra
>          Issue Type: Improvement
>            Reporter: Jonathan Ellis
>            Assignee: Jonathan Ellis
>             Fix For: 0.8
>
>         Attachments: 0001-add-MemtableAllocator.txt, 0002-add-off-heap-MemtableAllocator-support.txt,
2252-alternate-v1.tgz
>
>
> The memtable design practically actively fights Java's GC design.  Todd Lipcon gave a
good explanation over on HBASE-3455.

-- 
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

Mime
View raw message