You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@ignite.apache.org by "Ksenia Rybakova (JIRA)" <ji...@apache.org> on 2017/07/06 11:59:00 UTC
[jira] [Updated] (IGNITE-5547) Slow streaming and long running
transactions while load test with 500 logical caches
[ https://issues.apache.org/jira/browse/IGNITE-5547?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Ksenia Rybakova updated IGNITE-5547:
------------------------------------
Description:
Load config:
- CacheRandomOperation benchmark
- Caches:
atomic partitioned cache
2 tx partitioned caches
2 atomic partitioned onheap caches
2 atomic replicated onheap caches
2 tx partitioned onheap caches
2 tx replicated onheap caches
3 partitioned atomic indexed caches
30 groups with 10 partitioned caches each (atomic and tx, total 300 logical caches)
20 groups with 10 replicated caches each (atomic and tx, total 200 logical caches)
- Preload amount: 10K-30K entries per cache
- Key range: 20K
- Persistent store is enabled (long running transactions are reproduced with disabled PDS as well)
- 32 server nodes (4 nodes per phisical host), 5 client nodes (2 of 5 failed due to benchmark problems)
Preloading took 50 minutes that is too long for configured preloading amount.
Warmup took an hour instead of configured 5 minutes (possibly because of long running transaction), and operations are also slowed down.
Complete configs are attached.
was:
Load config:
- CacheRandomOperation benchmark
- Caches:
atomic partitioned cache
2 tx partitioned caches
2 atomic partitioned onheap caches
2 atomic replicated onheap caches
2 tx partitioned onheap caches
2 tx replicated onheap caches
3 partitioned atomic indexed caches
30 groups with 10 partitioned caches each (atomic and tx, total 300 logical caches)
20 groups with 10 replicated caches each (atomic and tx, total 200 logical caches)
- Preload amount: 10K-30K entries per cache
- Key range: 20K
- Persistent store is enabled
- 32 server nodes (4 nodes per phisical host), 5 client nodes (2 of 5 failed due to benchmark problems)
Preloading took 50 minutes that is too long for configured preloading amount.
Warmup took an hour instead of configured 5 minutes (possibly because of long running transaction), and operations are also slowed down.
Complete configs are attached.
> Slow streaming and long running transactions while load test with 500 logical caches
> ------------------------------------------------------------------------------------
>
> Key: IGNITE-5547
> URL: https://issues.apache.org/jira/browse/IGNITE-5547
> Project: Ignite
> Issue Type: Bug
> Affects Versions: 2.1
> Reporter: Ksenia Rybakova
> Attachments: ignite-base-load-config.xml, run-load.properties, run-load.xml
>
>
> Load config:
> - CacheRandomOperation benchmark
> - Caches:
> atomic partitioned cache
> 2 tx partitioned caches
> 2 atomic partitioned onheap caches
> 2 atomic replicated onheap caches
> 2 tx partitioned onheap caches
> 2 tx replicated onheap caches
> 3 partitioned atomic indexed caches
> 30 groups with 10 partitioned caches each (atomic and tx, total 300 logical caches)
> 20 groups with 10 replicated caches each (atomic and tx, total 200 logical caches)
> - Preload amount: 10K-30K entries per cache
> - Key range: 20K
> - Persistent store is enabled (long running transactions are reproduced with disabled PDS as well)
> - 32 server nodes (4 nodes per phisical host), 5 client nodes (2 of 5 failed due to benchmark problems)
> Preloading took 50 minutes that is too long for configured preloading amount.
> Warmup took an hour instead of configured 5 minutes (possibly because of long running transaction), and operations are also slowed down.
> Complete configs are attached.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)