incubator-cassandra-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Jason Rutherglen <jason.rutherg...@gmail.com>
Subject Re: Avoiding the system IO cache for compaction
Date Wed, 03 Aug 2011 04:53:14 GMT
Looks like there were issues with the native parts.  Mike McCandless
notes this in [1].  If we reuse the Lucene code, I think it'll work
for Cassandra.

1. https://issues.apache.org/jira/browse/LUCENE-2500

On Tue, Aug 2, 2011 at 9:42 PM, Jonathan Ellis <jbellis@gmail.com> wrote:
> Tried and failed. https://issues.apache.org/jira/browse/CASSANDRA-1902
>
> On Tue, Aug 2, 2011 at 11:24 PM, Jason Rutherglen
> <jason.rutherglen@gmail.com> wrote:
>> Cassandra 'compacts' the way Lucene 'merges' segments.  One
>> interesting new feature built into Lucene is [1] which avoids loading
>> the source files into the system IO cache on compaction / merge.
>>
>> Perhaps Cassandra already has this feature?
>>
>> 1. https://builds.apache.org/job/Lucene-trunk/javadoc/all/org/apache/lucene/store/DirectIOLinuxDirectory.html
>>
>
>
>
> --
> Jonathan Ellis
> Project Chair, Apache Cassandra
> co-founder of DataStax, the source for professional Cassandra support
> http://www.datastax.com
>

Mime
View raw message