[
https://issues.apache.org/jira/browse/ARTEMIS-3049?focusedWorklogId=530717&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-530717
]
ASF GitHub Bot logged work on ARTEMIS-3049:
-------------------------------------------
Author: ASF GitHub Bot
Created on: 04/Jan/21 15:00
Start Date: 04/Jan/21 15:00
Worklog Time Spent: 10m
Work Description: franz1981 commented on pull request #3393:
URL: https://github.com/apache/activemq-artemis/pull/3393#issuecomment-754024920
Despite my expectations, the results are NOT promising...
This PR
1 thread:
```
Benchmark (chunkSize) (size)
Mode Cnt Score Error Units
ConcurrentAppendOnlyChunkListLookupBenchmark.lookup 32 1000
thrpt 16 108968555.072 ± 135438.271 ops/s
ConcurrentAppendOnlyChunkListLookupBenchmark.lookup 32 10000
thrpt 16 105613840.728 ± 475604.647 ops/s
```
3 threads:
```
Benchmark (chunkSize) (size)
Mode Cnt Score Error Units
ConcurrentAppendOnlyChunkListLookupBenchmark.lookup 32 1000
thrpt 16 91693844.669 ± 29399345.167 ops/s
ConcurrentAppendOnlyChunkListLookupBenchmark.lookup 32 10000
thrpt 16 78520201.713 ± 3428526.469 ops/s
```
`master`
1 thread:
```
Benchmark (chunkSize) (size)
Mode Cnt Score Error Units
ConcurrentAppendOnlyChunkListLookupBenchmark.lookup 32 1000
thrpt 16 59747234.340 ± 1117878.317 ops/s
ConcurrentAppendOnlyChunkListLookupBenchmark.lookup 32 10000
thrpt 16 7699916.690 ± 36448.254 ops/s
```
3 threads:
```
Benchmark (chunkSize) (size)
Mode Cnt Score Error Units
ConcurrentAppendOnlyChunkListLookupBenchmark.lookup 32 1000
thrpt 16 181201564.143 ± 2457478.235 ops/s
ConcurrentAppendOnlyChunkListLookupBenchmark.lookup 32 10000
thrpt 16 23011863.725 ± 110276.468 ops/s
```
It shows that 3 consumers won't get the expected speedup and I suppose
that's due to the last accessed buffer miss.
----------------------------------------------------------------
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: 530717)
Time Spent: 0.5h (was: 20m)
> Reduce live page lookup cost
> ----------------------------
>
> Key: ARTEMIS-3049
> URL: https://issues.apache.org/jira/browse/ARTEMIS-3049
> Project: ActiveMQ Artemis
> Issue Type: Improvement
> Components: Broker
> Affects Versions: 2.16.0
> Reporter: Francesco Nigro
> Assignee: Francesco Nigro
> Priority: Major
> Time Spent: 0.5h
> Remaining Estimate: 0h
>
> LivePageCacheImpl::getMessage is performing a linked-list-like lookup that
> can be rather slow if compared to a O(1) lookup on ArrayList-like data
> structure.
> it's possible to speed it up by:
> # using a last accessed buffer cache on the append only chunked list used on
> LivePageCacheImpl, to speedup the most recent (& nearest) accesses
> # using an array with the fresh reloaded paged messages, in case of cache
> reload
> https://github.com/apache/activemq-artemis/pull/2494#issuecomment-455086939
> clearly show the issue with the current implementation.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
