[
https://issues.apache.org/jira/browse/ARTEMIS-2224?focusedWorklogId=185652&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-185652
]
ASF GitHub Bot logged work on ARTEMIS-2224:
-------------------------------------------
Author: ASF GitHub Bot
Created on: 16/Jan/19 09:25
Start Date: 16/Jan/19 09:25
Worklog Time Spent: 10m
Work Description: franz1981 commented on issue #2494: ARTEMIS-2224 Reduce
contention on LivePageCacheImpl
URL: https://github.com/apache/activemq-artemis/pull/2494#issuecomment-454709952
@qihongxu
What is worrying me is this
> at most time it obtained a 3k~6k tps
If the same test (same configuration) is performed using just 1 consumer I'm
expecting (best case scenario) that it would have (3k-6k)/200 tps if:
1. the tps are dependent by the most demanding operation in the CPU
flamegraph you've posted
ie `ConcurrentAppendOnlyList:.get(index)`
2. the `ConcurrentAppendOnlyList:.get(index)` can now happen in parallel and
assuming to have 200 threads available it means a 200 x speedup
I suppose that 2 can't be true, so it really depends on the number of
cores/threads available to execute such queries to `LivePageCache` IF such
queries are performed in parallel.
Do you have any idea of what's happening here? Which assumptions are
correct/wrong?
Just guessing is this whole process could be made much better/scalable just
answering those questions :+1:
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on 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: 185652)
Time Spent: 1h 40m (was: 1.5h)
> Reduce contention on LivePageCacheImpl
> --------------------------------------
>
> Key: ARTEMIS-2224
> URL: https://issues.apache.org/jira/browse/ARTEMIS-2224
> Project: ActiveMQ Artemis
> Issue Type: Improvement
> Components: Broker
> Affects Versions: 2.7.0
> Reporter: Francesco Nigro
> Assignee: Francesco Nigro
> Priority: Major
> Time Spent: 1h 40m
> Remaining Estimate: 0h
>
> Has been measured that LIvePageCacheImpl operations are a source of
> contention on producer side while paging.
> This contention decrease the scalability of the broker in an evident way
> while using topics, because the page cache is been accessed concurrently by
> several producers to ack transactions while the messages are being appended.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
