[slurm-dev] task_affinity bug in 2.5.1 and after..

[Magnus Jonsson]

Hi!

We are in the process of upgrading into slurm 2.5.2 but I just found a bug in the task_affinity plugin in combination with cgroups. The commit https://github.com/SchedMD/slurm/commit/791322349856e14a3d50aadc4869d40b034a2f37 which solves some Power7 specific problems breaks task affinity together with cgroups on x86_64.

This code seams to be introduced into slurm from 2.5.1.

From our slurm.conf:

TaskPlugin=task/cgroup,task/affinity

from slurmd.log:


[2013-02-01T13:39:12+01:00] [57] sched_getaffinity(12516) = 0xffffff000000





Best regards,
Magnus

--
Magnus Jonsson, Developer, HPC2N, Umeå Universitet

[2013-02-01T13:39:12+01:00] [57] sched_setaffinity(12516,128,0x0) failed: Invalid argument With cgroups activated we get input cpusets: 0xffffff000000 which translates into 0x0 in the reset_cpuset function. If this is a specific problem for Power7 a #ifdef around it might be good for solving this problem for other platforms.

smime.p7s
Description: S/MIME Cryptographic Signature