You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@cassandra.apache.org by "Jon Haddad (Jira)" <ji...@apache.org> on 2020/03/04 00:17:00 UTC
[jira] [Updated] (CASSANDRA-15619) Counter tables should use a 4KB
chunk length by default
[ https://issues.apache.org/jira/browse/CASSANDRA-15619?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Jon Haddad updated CASSANDRA-15619:
-----------------------------------
Change Category: Operability
Complexity: Low Hanging Fruit
Status: Open (was: Triage Needed)
> Counter tables should use a 4KB chunk length by default
> -------------------------------------------------------
>
> Key: CASSANDRA-15619
> URL: https://issues.apache.org/jira/browse/CASSANDRA-15619
> Project: Cassandra
> Issue Type: Improvement
> Components: Feature/Counters
> Reporter: Jon Haddad
> Priority: Normal
>
> One of the issues I found when using counters is throughput gets significantly limited due to the default chunk length. When tuning from 64 to 4, I saw a massive improvement in both throughput and latency.
> Our default chunk length is 16, which is fine for general purpose tables, but since tables with counters are special purpose we should give users this optimization automatically.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@cassandra.apache.org
For additional commands, e-mail: commits-help@cassandra.apache.org