cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "T Jake Luciani (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (CASSANDRA-9365) Prioritize compactions based on read activity
Date Tue, 12 May 2015 20:38:01 GMT

     [ https://issues.apache.org/jira/browse/CASSANDRA-9365?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

T Jake Luciani updated CASSANDRA-9365:
--------------------------------------
    Description: 
The main purpose of compaction is to keep reads fast by consolidating tables together to avoid
merging on read.

In a cluster with many tables we currently treat all pending compaction as equal.  When in
reality we may only be reading mainly from one of the tables.

Rather than FIFO we should prioritize access to the compactors based on read activity. SStables
per read might be a good metric.  Also, we would need to be sure to be fair to other tables
over time.  This would be a way to skew the work towards the tables who need compaction the
most.

It might also be nice to offer a nodetool command to kill specific compaction jobs in progress
that are not important under load.

  was:
The main purpose of compaction is to keep reads fast by consolidating tables together to avoid
merging on read.

In a cluster with many tables we currently treat all pending compaction as equal.  When in
reality we may only be reading mainly from one of the tables.

Rather than FIFO we should prioritize access to the compactors based on read activity. 

It might also be nice to offer a nodetool command to kill specific compaction jobs in progress
that are not important under load.


> Prioritize compactions based on read activity
> ---------------------------------------------
>
>                 Key: CASSANDRA-9365
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-9365
>             Project: Cassandra
>          Issue Type: Improvement
>            Reporter: T Jake Luciani
>             Fix For: 3.x
>
>
> The main purpose of compaction is to keep reads fast by consolidating tables together
to avoid merging on read.
> In a cluster with many tables we currently treat all pending compaction as equal.  When
in reality we may only be reading mainly from one of the tables.
> Rather than FIFO we should prioritize access to the compactors based on read activity.
SStables per read might be a good metric.  Also, we would need to be sure to be fair to other
tables over time.  This would be a way to skew the work towards the tables who need compaction
the most.
> It might also be nice to offer a nodetool command to kill specific compaction jobs in
progress that are not important under load.



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

Mime
View raw message