[jira] [Commented] (IGNITE-9244) Partition eviction may use all threads in sys pool, it leads to hangs send a message via sys pool
[ https://issues.apache.org/jira/browse/IGNITE-9244?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16577994#comment-16577994 ] ASF GitHub Bot commented on IGNITE-9244: Github user DmitriyGovorukhin closed the pull request at: https://github.com/apache/ignite/pull/4513 > Partition eviction may use all threads in sys pool, it leads to hangs send a > message via sys pool > -- > > Key: IGNITE-9244 > URL: https://issues.apache.org/jira/browse/IGNITE-9244 > Project: Ignite > Issue Type: Bug >Reporter: Dmitriy Govorukhin >Assignee: Dmitriy Govorukhin >Priority: Major > Fix For: 2.7 > > > In the current implementation, GridDhtPartitionsEvictor reset partition to > evict one by one. > GridDhtPartitionsEvictor is created for each cache group, if we try to evict > too many groups as sys pool size, group evictors will take all available > threads in sys pool. It leads to hangs send a message via sys pool. As a fix, > I suggest to limit concurrent execution via sys pool or use another pool for > this purpose. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (IGNITE-9244) Partition eviction may use all threads in sys pool, it leads to hangs send a message via sys pool
[ https://issues.apache.org/jira/browse/IGNITE-9244?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16576456#comment-16576456 ] Pavel Kovalenko commented on IGNITE-9244: - [~agoncharuk] Looks good to me also. No other comments. > Partition eviction may use all threads in sys pool, it leads to hangs send a > message via sys pool > -- > > Key: IGNITE-9244 > URL: https://issues.apache.org/jira/browse/IGNITE-9244 > Project: Ignite > Issue Type: Bug >Reporter: Dmitriy Govorukhin >Assignee: Dmitriy Govorukhin >Priority: Major > Fix For: 2.7 > > > In the current implementation, GridDhtPartitionsEvictor reset partition to > evict one by one. > GridDhtPartitionsEvictor is created for each cache group, if we try to evict > too many groups as sys pool size, group evictors will take all available > threads in sys pool. It leads to hangs send a message via sys pool. As a fix, > I suggest to limit concurrent execution via sys pool or use another pool for > this purpose. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (IGNITE-9244) Partition eviction may use all threads in sys pool, it leads to hangs send a message via sys pool
[ https://issues.apache.org/jira/browse/IGNITE-9244?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16576391#comment-16576391 ] Alexey Goncharuk commented on IGNITE-9244: -- Looks good to me now. [~Jokser], do you have any other comments? > Partition eviction may use all threads in sys pool, it leads to hangs send a > message via sys pool > -- > > Key: IGNITE-9244 > URL: https://issues.apache.org/jira/browse/IGNITE-9244 > Project: Ignite > Issue Type: Bug >Reporter: Dmitriy Govorukhin >Assignee: Dmitriy Govorukhin >Priority: Major > Fix For: 2.7 > > > In the current implementation, GridDhtPartitionsEvictor reset partition to > evict one by one. > GridDhtPartitionsEvictor is created for each cache group, if we try to evict > too many groups as sys pool size, group evictors will take all available > threads in sys pool. It leads to hangs send a message via sys pool. As a fix, > I suggest to limit concurrent execution via sys pool or use another pool for > this purpose. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (IGNITE-9244) Partition eviction may use all threads in sys pool, it leads to hangs send a message via sys pool
[ https://issues.apache.org/jira/browse/IGNITE-9244?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16576354#comment-16576354 ] Dmitriy Govorukhin commented on IGNITE-9244: [~agoncharuk] Thanks! All comments fixed. > Partition eviction may use all threads in sys pool, it leads to hangs send a > message via sys pool > -- > > Key: IGNITE-9244 > URL: https://issues.apache.org/jira/browse/IGNITE-9244 > Project: Ignite > Issue Type: Bug >Reporter: Dmitriy Govorukhin >Assignee: Dmitriy Govorukhin >Priority: Major > Fix For: 2.7 > > > In the current implementation, GridDhtPartitionsEvictor reset partition to > evict one by one. > GridDhtPartitionsEvictor is created for each cache group, if we try to evict > too many groups as sys pool size, group evictors will take all available > threads in sys pool. It leads to hangs send a message via sys pool. As a fix, > I suggest to limit concurrent execution via sys pool or use another pool for > this purpose. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
[jira] [Commented] (IGNITE-9244) Partition eviction may use all threads in sys pool, it leads to hangs send a message via sys pool
[
https://issues.apache.org/jira/browse/IGNITE-9244?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16576344#comment-16576344
]
Alexey Goncharuk commented on IGNITE-9244:
--
A few comments:
* Use {{Long.compare}} instead of {{(p1, p2) -> p1.part.fullSize() >
p2.part.fullSize() ? -1 : 1}}
* Method {{calculateBucket(PartitionEvictionTask)}} has an unused argument -
either a bug, or the argument should be removed
* For safety, make sure that {{threads}} does not get {{0}} value after
{{sysPoolSize / 4}}
> Partition eviction may use all threads in sys pool, it leads to hangs send a
> message via sys pool
> --
>
> Key: IGNITE-9244
> URL: https://issues.apache.org/jira/browse/IGNITE-9244
> Project: Ignite
> Issue Type: Bug
>Reporter: Dmitriy Govorukhin
>Assignee: Dmitriy Govorukhin
>Priority: Major
> Fix For: 2.7
>
>
> In the current implementation, GridDhtPartitionsEvictor reset partition to
> evict one by one.
> GridDhtPartitionsEvictor is created for each cache group, if we try to evict
> too many groups as sys pool size, group evictors will take all available
> threads in sys pool. It leads to hangs send a message via sys pool. As a fix,
> I suggest to limit concurrent execution via sys pool or use another pool for
> this purpose.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
[jira] [Commented] (IGNITE-9244) Partition eviction may use all threads in sys pool, it leads to hangs send a message via sys pool
[ https://issues.apache.org/jira/browse/IGNITE-9244?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16576055#comment-16576055 ] ASF GitHub Bot commented on IGNITE-9244: GitHub user DmitriyGovorukhin opened a pull request: https://github.com/apache/ignite/pull/4513 IGNITE-9244 Rework partition eviction. - add evict shared manager - concurrent evict partition from one group - balanced executors by partition size - limitation concurrent evict operation via permits counter You can merge this pull request into a Git repository by running: $ git pull https://github.com/gridgain/apache-ignite ignite-9244 Alternatively you can review and apply these changes as the patch at: https://github.com/apache/ignite/pull/4513.patch To close this pull request, make a commit to your master/trunk branch with (at least) the following in the commit message: This closes #4513 commit ab10ca99d7d7052414ef0927d52f17c81e5d7bde Author: Dmitriy Govorukhin Date: 2018-08-10T10:10:12Z IGNITE-9244 Rework partition eviction. - add evict shared manager - concurrent evict partition from one group - balanced executors by partition size - limitation concurrent evict operation via permits counter Signed-off-by: Dmitriy Govorukhin > Partition eviction may use all threads in sys pool, it leads to hangs send a > message via sys pool > -- > > Key: IGNITE-9244 > URL: https://issues.apache.org/jira/browse/IGNITE-9244 > Project: Ignite > Issue Type: Bug >Reporter: Dmitriy Govorukhin >Assignee: Dmitriy Govorukhin >Priority: Major > Fix For: 2.7 > > > In the current implementation, GridDhtPartitionsEvictor reset partition to > evict one by one. > GridDhtPartitionsEvictor is created for each cache group, if we try to evict > too many groups as sys pool size, group evictors will take all available > threads in sys pool. It leads to hangs send a message via sys pool. As a fix, > I suggest to limit concurrent execution via sys pool or use another pool for > this purpose. -- This message was sent by Atlassian JIRA (v7.6.3#76005)
