[
https://issues.apache.org/jira/browse/CASSANDRA-14983?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16815416#comment-16815416
]
Benedict commented on CASSANDRA-14983:
--------------------------------------
These are very valid points, thanks for the analysis. Both of these issues are
clearly bugs. Probably in real world scenarios they are rarely a major issue,
but that doesn't make either of them any less of a bug.
It seems like we should disable the behaviour entirely until we can guarantee
promptness of evaluation of the local read. Which probably will not happen for
several releases, when we can overhaul IO, and at this point we may have a
completely different threading model negating the optimisation. I don't think
it's worth trying to narrow the applicability further.
Good work, even if it is a shame to be true.
> Local reads potentially blocking remote reads
> ---------------------------------------------
>
> Key: CASSANDRA-14983
> URL: https://issues.apache.org/jira/browse/CASSANDRA-14983
> Project: Cassandra
> Issue Type: Bug
> Components: Consistency/Coordination
> Reporter: Marcus Olsson
> Assignee: Marcus Olsson
> Priority: Low
> Attachments: graph_local_read.html, graph_local_read_trunk.html,
> local_read_trace.log
>
>
> Since CASSANDRA-4718 there is a fast path allowing local requests to continue
> to [work in the same
> thread|https://github.com/apache/cassandra/blob/trunk/src/java/org/apache/cassandra/service/reads/AbstractReadExecutor.java#L157]
> rather than being sent over to the read stage.
> Based on the comment
> {code:java}
> // We delay the local (potentially blocking) read till the end to avoid
> stalling remote requests.
> {code}
> it seems like this should be performed last in the chain to avoid blocking
> remote requests but that does not seem to be the case when the local request
> is a data request. The digest request(s) are sent after the data requests are
> sent (and now the transient replica requests as well). When the fast path is
> used for local data/transient data requests this will block the next type of
> request from being sent away until the local read is finished and add
> additional latency to the request.
> In addition to this it seems like local requests are *always* data requests
> (might not be a problem), but the log message can say either ["digest" or
> "data"|https://github.com/apache/cassandra/blob/trunk/src/java/org/apache/cassandra/service/reads/AbstractReadExecutor.java#L156]
> as the type of request.
> I have tried to run performance measurements to see the impact of this in 3.0
> (by moving local requests to the end of ARE#executeAsync()) but I haven't
> seen any big difference yet. I'll continue to run some more tests to see if I
> can find a use case affected by this.
> Attaching a trace (3.0) where this happens. Reproduction:
> # Create a three node CCM cluster
> # Provision data with stress (rf=3)
> # In parallel:
> ## Start stress read run
> ## Run multiple manual read queries in cqlsh with tracing on and
> local_quorum (as this does not always happen)
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org
For additional commands, e-mail: commits-h...@cassandra.apache.org
