[
https://issues.apache.org/jira/browse/CASSANDRA-47?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13062709#comment-13062709
]
Pavel Yaskevich commented on CASSANDRA-47:
------------------------------------------
bq. I haven't had any luck seeing actual compression with this patch... is
there a manual step to enable it? On OSX, the patch slowed the server down to a
crawl, but did not result in compression. Performance seems to be reasonable on
Linux, but without any effect: running bin/stress -S 1024 -n 1000000 -C 250 -V
resulted in 3.3 GB of data.
As I wrote previously - right now on linux you can see compressed data size by
running ls with ahs and taking a size in blocks, because current
implementations uses file holes (reserves free space for the future chunk
changes). I'm currently working on the way to eliminate that need.
> SSTable compression
> -------------------
>
> Key: CASSANDRA-47
> URL: https://issues.apache.org/jira/browse/CASSANDRA-47
> Project: Cassandra
> Issue Type: New Feature
> Components: Core
> Reporter: Jonathan Ellis
> Assignee: Pavel Yaskevich
> Labels: compression
> Fix For: 1.0
>
> Attachments: CASSANDRA-47.patch, snappy-java-1.0.3-rc4.jar
>
>
> We should be able to do SSTable compression which would trade CPU for I/O
> (almost always a good trade).
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
