We are pleased to announce the availability of Slurm versions 24.11.2
and 24.05.6.
24.11.2 fixes a variety of minor to major bugs. Fixed regressions
include loading non-default QOS on pending jobs from pre-24.11 state,
pending jobs displaying QOS=(null) when not explicitly requesting a QOS,
running jobs that requested multiple partitions potentially having an
incorrect partition when slurmctld is restarted, and burst_buffer.lua
failing if slurm.conf is in a non-standard location. This release also
fixes a few crashes in slurmctld: crashing when a job that can preempt
requests --test-only, crasing when the scheduler evaluates a job on
nodes with suspended jobs, and crashing due to a long-standing bug
causing a job record without job_resrcs.
24.05.6 fixes sattach with auth/slurm, a slurmrestd crash when using
data_parser/v0.0.40, a slurmctld crash when using job suspension, a
performance regression for RPCs with large amounts of data, and some
other moderate severity bugs.
Downloads are available at https://www.schedmd.com/downloads.php .
--
Marshall Garey
Release Management, Support, and Development
SchedMD LLC - Commercial Slurm Development and Support
> * Changes in Slurm 24.11.2
> ==========================
> -- Fix segfault when submitting --test-only jobs that can preempt.
> -- Fix regression introduced in 23.11 that prevented the following
> flags from being added to a reservation on an update:
> DAILY, HOURLY, WEEKLY, WEEKDAY, and WEEKEND.
> -- Fix crash and issues evaluating job's suitability for running in
> nodes with already suspended job(s) there.
> -- Slurmctld will ensure that healthy nodes are not reported as
> UnavailableNodes in job reason codes.
> -- Fix handling of jobs submitted to a current reservation with
> flags OVERLAP,FLEX or OVERLAP,ANY_NODES when it overlaps nodes with a
> future maintenance reservation. When a job submission had a time limit that
> overlapped with the future maintenance reservation, it was rejected. Now
> the job is accepted but stays pending with the reason "ReqNodeNotAvail,
> Reserved for maintenance".
> -- pam_slurm_adopt - avoid errors when explicitly setting
> some arguments to the default value.
> -- Fix qos preemption with PreemptMode=SUSPEND
> -- slurmdbd - When changing a user's name update lineage
> at the same time.
> -- Fix regression in 24.11 in which burst_buffer.lua does not
> inherit the SLURM_CONF environment variable from slurmctld and fails to run
> if slurm.conf is in a non-standard location.
> -- Fix memory leak in slurmctld if select/linear and the
> PreemptParameters=reclaim_licenses options are both set in slurm.conf.
> Regression in 24.11.1.
> -- Fix running jobs, that requested multiple partitions, from
> potentially being set to the wrong partition on restart.
> -- switch/hpe_slingshot - Fix compatibility with newer cxi
> drivers, specifically when specifying disable_rdzv_get.
> -- Add ABORT_ON_FATAL environment variable to capture a backtrace
> from any fatal() message.
> -- Fix printing invalid address in rate limiting log statement.
> -- sched/backfill - Fix node state PLANNED not being cleared from
> fully allocated nodes during a backfill cycle.
> -- select/cons_tres - Fix future planning of jobs with bf_licenses.
> -- Prevent redundant "on_data returned rc: Rate limit exceeded,
> please retry momentarily" error message from being printed in
> slurmctld logs.
> -- Fix loading non-default QOS on pending jobs from pre-24.11 state.
> -- Fix pending jobs displaying QOS=(null) when not explicitly
> requesting a QOS.
> -- Fix segfault issue from job record with no job_resrcs
> -- Fix failing sacctmgr delete/modify/show account operations
> with where clauses.
> -- Fix regression in 24.11 in which Slurm daemons started catching
> several SIGTSTP, SIGTTIN and SIGUSR1 signals and ignored them, while before
> they were not ignoring them. This also caused slurmctld to not being
> able to shutdown after a SIGTSTP because slurmscriptd caught the signal
> and stopped while slurmctld ignored it. Unify and fix these situations and
> get back to the previous behavior for these signals.
> -- Document that SIGQUIT is no longer ignored by slurmctld,
> slurmdbd, and slurmd in 24.11. As of 24.11.0rc1, SIGQUIT is identical to
> SIGINT and SIGTERM for these daemons, but this change was not documented.
> -- Fix not considering nodes marked for reboot without ASAP
> in the scheduler.
> -- Remove the boot^ state on unexpected node reboot after
> return to service.
> -- Do not allow new jobs to start on a node which is being rebooted
> with the flag nextstate=resume.
> -- Prevent lower priority job running after cancelling an ASAP reboot.
> -- Fix srun jobs starting on nextstate=resume rebooting nodes.
>
> * Changes in Slurm 24.05.6
> ==========================
> -- data_parser/v0.0.40 - Prevent a segfault in the slurmrestd when
> dumping data with v0.0.40+complex data parser.
> -- Fix sattach when using auth/slurm.
> -- scrun - Add support '--all' argument for kill subcommand.
> -- Fix performance regression while packing larger RPCs.
> -- Fix crash and issues evaluating job's suitability for running in
> nodes with already suspended job(s) there.
> -- Fixed a job requeuing issue that merged job entries into the
> same SLUID when all nodes in a job failed simultaneously.
> -- switch/hpe_slingshot - Fix compatibility with newer cxi
> drivers, specifically when specifying disable_rdzv_get.
> -- Add ABORT_ON_FATAL environment variable to capture a backtrace
> from any fatal() message.
