[
https://issues.apache.org/jira/browse/IGNITE-20971?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Igor updated IGNITE-20971:
--------------------------
Description:
*Steps to reproduce*
# Start process with `-Xms4096m -Xmx4096m`
# Create tables with 5 columns one by one up to 1000.
*Expected:*
1000 tables are created.
*Actual:*
After ~219 the process was killed by OOM killer due to process took 64GB of
memory of available 65GB.
*Additional information:*
OOM killer output:
{code:java}
[Tue Nov 28 18:35:37 2023]
oom-kill:constraint=CONSTRAINT_NONE,nodemask=(null),cpuset=user.slice,mems_allowed=0,global_oom,task_memcg=/user.slice/user-10002.slice/session-201.scope,task=java,pid=11748,uid=10002
[Tue Nov 28 18:35:37 2023] Out of memory: Killed process 11748 (java)
total-vm:97160836kB, anon-rss:64192728kB, file-rss:0kB, shmem-rss:0kB,
UID:10002 pgtables:127948kB oom_score_adj:0
[Tue Nov 28 18:35:39 2023] oom_reaper: reaped process 11748 (java), now
anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
pubagent:~$ grep MemTotal /proc/meminfo
MemTotal: 65038556 kB
pubagent:~$ free
total used free shared buff/cache available
Mem: 65038556 321848 64557116 900 159592 64174540
Swap: 0 0 0
{code}
GC log
[^gc.20231128_132812_386649.log]
was:
Creating 1000 tables with 5 column each.
*Expected:*
1000 tables are created.
*Actual:*
After some tables (in my case after 75 tables) the Ignite runner process is
silently teared down, no any errors in output. GC log doesn't show any problem.
*Additional information:*
On more performant (in CPU) servers it can create up to 855 tables on 4GB HEAP
and then tearing down with
`java.lang.OutOfMemoryError: Java heap space`
> The Ignite process huge memory overhead for tables creation
> -----------------------------------------------------------
>
> Key: IGNITE-20971
> URL: https://issues.apache.org/jira/browse/IGNITE-20971
> Project: Ignite
> Issue Type: Bug
> Components: general
> Affects Versions: 3.0.0-beta2
> Reporter: Igor
> Assignee: Ivan Bessonov
> Priority: Major
> Labels: ignite-3
> Attachments: gc.20231128_132812_386649.log
>
>
> *Steps to reproduce*
> # Start process with `-Xms4096m -Xmx4096m`
> # Create tables with 5 columns one by one up to 1000.
> *Expected:*
> 1000 tables are created.
>
> *Actual:*
> After ~219 the process was killed by OOM killer due to process took 64GB of
> memory of available 65GB.
>
> *Additional information:*
> OOM killer output:
> {code:java}
> [Tue Nov 28 18:35:37 2023]
> oom-kill:constraint=CONSTRAINT_NONE,nodemask=(null),cpuset=user.slice,mems_allowed=0,global_oom,task_memcg=/user.slice/user-10002.slice/session-201.scope,task=java,pid=11748,uid=10002
> [Tue Nov 28 18:35:37 2023] Out of memory: Killed process 11748 (java)
> total-vm:97160836kB, anon-rss:64192728kB, file-rss:0kB, shmem-rss:0kB,
> UID:10002 pgtables:127948kB oom_score_adj:0
> [Tue Nov 28 18:35:39 2023] oom_reaper: reaped process 11748 (java), now
> anon-rss:0kB, file-rss:0kB, shmem-rss:0kB
> pubagent:~$ grep MemTotal /proc/meminfo
> MemTotal: 65038556 kB
> pubagent:~$ free
> total used free shared buff/cache available
> Mem: 65038556 321848 64557116 900 159592
> 64174540
> Swap: 0 0 0
> {code}
> GC log
> [^gc.20231128_132812_386649.log]
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
