[
https://issues.apache.org/jira/browse/CASSANDRA-1035?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12862292#action_12862292
]
Jonathan Ellis commented on CASSANDRA-1035:
-------------------------------------------
I don't think scheduling of MUTATION-STAGE can solve this; if a user or app is
pouring enough ops in to affect QOS of others, then it's going to cause
backpressure which is of necessity per-node not per-user-or-app.
I think there would need to be some kind of rate-limiting at the coordinator
node instead, since that's the only place you can backpressure user-or-app
instead of entire peer nodes.
> Implement User/Keyspace throughput Scheduler
> --------------------------------------------
>
> Key: CASSANDRA-1035
> URL: https://issues.apache.org/jira/browse/CASSANDRA-1035
> Project: Cassandra
> Issue Type: Improvement
> Reporter: Stu Hood
>
> To support multiple applications on top of a single Cassandra cluster (and to
> protect against badly behaving clients) having a very simple scheduler for
> MUTATION-STAGE and READ-STAGE would be very beneficial.
> Since all tasks are short lived, a sufficient scheduler would probably only
> need to manage the queue of incoming requests, and weight them based on an
> assigned ID. The ID could be dynamically determined by using ip, userid or
> keyspace for instance, and then each Runnable would be assigned an ID.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
