Ticket 2885

Summary:	slurmctld crash on startup
Product:	Slurm	Reporter:	Paul Edmon <pedmon>
Component:	slurmctld	Assignee:	Dominik Bartkiewicz <dbartkiewicz>
Status:	RESOLVED FIXED	QA Contact:
Severity:	2 - High Impact
Priority:	---	CC:	dbartkiewicz
Version:	16.05.2
Hardware:	Linux
OS:	Linux
Site:	Harvard University	Slinky Site:	---
Alineos Sites:	---	Atos/Eviden Sites:	---
Confidential Site:	---	Coreweave sites:	---
Cray Sites:	---	DS9 clusters:	---
Google sites:	---	HPCnow Sites:	---
HPE Sites:	---	IBM Sites:	---
NOAA SIte:	---	NoveTech Sites:	---
Nvidia HWinf-CS Sites:	---	OCF Sites:	---
Recursion Pharma Sites:	---	SFW Sites:	---
SNIC sites:	---	Tzag Elita Sites:	---
Linux Distro:	---	Machine Name:
CLE Version:		Version Fixed:	16.05.3
Target Release:	---	DevPrio:	---
Emory-Cloud Sites:	---
Attachments:	crash log slurmctld backtrace

Description Paul Edmon 2016-07-11 05:46:45 MDT

This is on our test cluster so while it is a high serverity bug in that it causes a crash, it is not on our production servers so its not currently causing us problems.  When restarting slurmctld in 16.05.2 the ctld crashes on start.  This may be due to a specific job that is faulty, but slurm shouldn't crash on that.  I've included the log and I have a core dump.  The ctld is running CentOS 7.

Let me know what other info you need from the core dump.  Thanks.

-Paul Edmon-

Comment 1 Paul Edmon 2016-07-11 05:47:17 MDT

Created attachment 3292 [details]
crash log

Comment 2 Dominik Bartkiewicz 2016-07-11 05:56:58 MDT

Can you get full backtrace from all thread?

thread apply all bt full

Dominik

Comment 3 Paul Edmon 2016-07-11 06:00:11 MDT

Created attachment 3293 [details]
slurmctld backtrace

Comment 6 Dominik Bartkiewicz 2016-07-11 07:54:42 MDT

This bug was fixed in commit 65b4f283ef2  (https://github.com/SchedMD/slurm/commit/65b4f283ef2a908b6e3e8921acf62dad73528f00.patch).
This patch will be included also in 16.05.3 release.

Dominik

Comment 7 Paul Edmon 2016-07-11 07:58:15 MDT

Thanks!

-Paul Edmon-

On 07/11/2016 09:54 AM, bugs@schedmd.com wrote:
>
> *Comment # 6 <https://bugs.schedmd.com/show_bug.cgi?id=2885#c6> on bug 
> 2885 <https://bugs.schedmd.com/show_bug.cgi?id=2885> from Dominik 
> Bartkiewicz <mailto:bart@schedmd.com> *
> This bug was fixed in commit 65b4f283ef2
> (https://github.com/SchedMD/slurm/commit/65b4f283ef2a908b6e3e8921acf62dad73528f00.patch).
> This patch will be included also in 16.05.3 release.
>
> Dominik
> ------------------------------------------------------------------------
> You are receiving this mail because:
>
>   * You reported the bug.
>

Comment 9 Dominik Bartkiewicz 2016-07-13 09:00:54 MDT

Please reopen if the problem still exists after this commit.

Dominik