Whenever we do a:
service slurm restart
on our master it ends up initiating a massive MySQL query:
2821957 slurm localhost slurm Query 2 Sorting result
select job_db_inx, id_job, id_assoc, id_wckey, time_eligible,
time_start, time_end, time_suspended, cpus_alloc, cpus_req, id_resv from
"odyssey_job_table" where (time_eligible < 1391169600 && (time_end >=
1391166000 || time_end = 0)) order by id_assoc, time_eligible
Which ends up stalling out the slurmctld until it completes. This takes
about 30 minutes on our system. During this time SLURM appears to be
down. This doesn't happen on reconfigures only on restarts.
Is there a way to prevent it from doing this query or at least make this
query nonblocking for slurm? Thanks.
-Paul Edmon-
