[
https://issues.apache.org/jira/browse/COUCHDB-2724?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14603704#comment-14603704
]
Adam Kocoloski commented on COUCHDB-2724:
-----------------------------------------
This code seems to be pretty well ready to go, but the reason I haven't
submitted the PRs is because I'm not able to reproduce [~tonysun83]'s results
on a build of master running a `./dev/run` cluster on my laptop -- the
throughput is approximately the same with or without the patch. Maybe there
needs to be some network latency involved, not sure, but we should get the
details of the benchmark squared away here.
> Batch rows in streaming responses to improve throughput
> -------------------------------------------------------
>
> Key: COUCHDB-2724
> URL: https://issues.apache.org/jira/browse/COUCHDB-2724
> Project: CouchDB
> Issue Type: Improvement
> Security Level: public(Regular issues)
> Components: Database Core, HTTP Interface
> Reporter: Adam Kocoloski
> Assignee: Adam Kocoloski
>
> [~tonysun83] showed me some profiling of the {{_changes}} feed which
> indicated that the coordinator process was spending about 1/3 of its time
> executing inside {{send_delayed_chunk}}. We can reduce the number of
> invocations of this function by buffering individual rows until we reach a
> (configurable) threshold for sending the data out the wire.
> We'll of course want to be careful about continuous feeds; if we're in the
> "slow drip" portion of the feed we'll obviously want to emit right away
> instead of adding latency unnecessarily.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
