[
https://issues.apache.org/jira/browse/ARTEMIS-3045?focusedWorklogId=554627&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-554627
]
ASF GitHub Bot logged work on ARTEMIS-3045:
-------------------------------------------
Author: ASF GitHub Bot
Created on: 19/Feb/21 07:37
Start Date: 19/Feb/21 07:37
Worklog Time Spent: 10m
Work Description: franz1981 commented on pull request #3392:
URL: https://github.com/apache/activemq-artemis/pull/3392#issuecomment-781893787
Re the status of this PR, is done but I would like to:
- enforce not blocking ops on Artemis channel on Netty event loop
- save too many Runnable instances to be created (now > of the packets)
- [maybe] stop batching depending on time spent on the event loop (eg 100 ms
at max, although dangerous due to GC!)
The last 2 points could be the reason of the increased tail latency, because:
- bigger GC pauses due to the backlog of Runnables
- bigger replicated batches can delay reading backup responses and answering
back to clients (both share the same event loop)
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 554627)
Time Spent: 11h 50m (was: 11h 40m)
> ReplicationManager can batch sent replicated packets
> ----------------------------------------------------
>
> Key: ARTEMIS-3045
> URL: https://issues.apache.org/jira/browse/ARTEMIS-3045
> Project: ActiveMQ Artemis
> Issue Type: Improvement
> Reporter: Francesco Nigro
> Assignee: Francesco Nigro
> Priority: Major
> Time Spent: 11h 50m
> Remaining Estimate: 0h
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
