cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Pavel Yaskevich (JIRA)" <>
Subject [jira] [Commented] (CASSANDRA-4937) CRAR improvements (object cache + CompressionMetadata chunk offset storage moved off-heap).
Date Fri, 11 Jan 2013 04:38:13 GMT


Pavel Yaskevich commented on CASSANDRA-4937:

bq. Shouldn't we just take out cache-skipping on [C]RAR entirely then?

Sorry, we probably had some communication issues, that is exactly what I propose and what
attached patch does :) I can make separate one that just removes page skiping from read path
and does it only when SSTable life ends.

bq. Why does this work better than the old mincore approach we tried?

Basically because it doesn't try to be smart about anything, it just preheats first page of
each row listed in that cache which gives a room for adoptive readahead.

> CRAR improvements (object cache + CompressionMetadata chunk offset storage moved off-heap).
> -------------------------------------------------------------------------------------------
>                 Key: CASSANDRA-4937
>                 URL:
>             Project: Cassandra
>          Issue Type: Improvement
>            Reporter: Pavel Yaskevich
>            Assignee: Pavel Yaskevich
>             Fix For: 1.2.1
>         Attachments: CASSANDRA-4937.patch
> After good amount of testing on one of the clusters it was found that in order to improve
read latency we need to minimize allocation rate that compression involves, that minimizes
GC (as well as heap usage) and substantially decreases latency on read heavy workloads. 
> I have also discovered that RAR skip cache harms performance in situation when reads
are done in parallel with compaction working with relatively big SSTable files (few GB and
more). The attached patch removes possibility to skip cache from compressed files (I can also
add changes to RAR to remove skip cache functionality as a separate patch). 

This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see:

View raw message