You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@cassandra.apache.org by "C. Scott Andreas (JIRA)" <ji...@apache.org> on 2018/11/19 02:25:01 UTC
[jira] [Updated] (CASSANDRA-12028) Proposal to change concurrent_*
and native_transport_max_threads defaults
[ https://issues.apache.org/jira/browse/CASSANDRA-12028?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
C. Scott Andreas updated CASSANDRA-12028:
-----------------------------------------
Component/s: Configuration
> Proposal to change concurrent_* and native_transport_max_threads defaults
> -------------------------------------------------------------------------
>
> Key: CASSANDRA-12028
> URL: https://issues.apache.org/jira/browse/CASSANDRA-12028
> Project: Cassandra
> Issue Type: Improvement
> Components: Configuration
> Reporter: Robert Stupp
> Priority: Minor
>
> The current recommendations in c.yaml regarding {{concurrent_reads/writes/counter_writes/materialized_view_writes}} and {{native_transport_max_threads}} feel oversized.
> While working on some load/stress tests, reducing these to the number of CPUs and also lowering {{native_transport_max_threads}} to 2xCPUs had no influence to the actual performance but reduced the risk of allocating too many threads when a node ran into a longer GC and requests against that node piled up.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@cassandra.apache.org
For additional commands, e-mail: commits-help@cassandra.apache.org