You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@cassandra.apache.org by "Lorina Poland (Jira)" <ji...@apache.org> on 2020/06/26 18:04:00 UTC
[jira] [Assigned] (CASSANDRA-14816) Add Operating System Specific
Setup Documentation for Cassandra
[ https://issues.apache.org/jira/browse/CASSANDRA-14816?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Lorina Poland reassigned CASSANDRA-14816:
-----------------------------------------
Assignee: Lorina Poland
> Add Operating System Specific Setup Documentation for Cassandra
> ---------------------------------------------------------------
>
> Key: CASSANDRA-14816
> URL: https://issues.apache.org/jira/browse/CASSANDRA-14816
> Project: Cassandra
> Issue Type: Improvement
> Components: Documentation/Website
> Reporter: Joey Lynch
> Assignee: Lorina Poland
> Priority: Low
>
> There are a number of operating system tunings that can vastly improve Cassandra's performance on Linux in particular things like:
> # Setting {{/sys/block/${DEVICE}/queue/read_ahead_kb}} to something more reasonable like 32
> # Setting the qdisc on modern linux to something better like {{tc-fq}} with {{bbr}}
> # Setting {{nofile}} ulimits properly and {{fs.file-max}}
> # Potentially raising {{vm.max_map_count}} even higher than the default debian package does
> # Using raid instead of jbod
> # Mounting /tmp on a tmpfs and turning back on {{PerfDisableSharedMem}}
> And many more ... I think many of the recommendations from [Amy Tobey's|https://tobert.github.io/pages/als-cassandra-21-tuning-guide.html] 2.1 guide may still be pretty relevant.
> Perhaps we can document some of these in the website's Operations section?
--
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