Accepting request 845437 from network:cluster

OBS-URL: https://build.opensuse.org/request/show/845437
OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/slurm?expand=0&rev=48

pam_slurm-Initialize-arrays-and-pass-sizes.patch

@@ -12,14 +12,11 @@ PAM is security critical:
 
 Signed-off-by: Egbert Eich <eich@suse.com>
 ---
- contribs/pam/pam_slurm.c | 20 +++++++++++---------
- 1 file changed, 11 insertions(+), 9 deletions(-)
 
-diff --git a/contribs/pam/pam_slurm.c b/contribs/pam/pam_slurm.c
+diff -Nrua a/contribs/pam/pam_slurm.c b/contribs/pam/pam_slurm.c
-index 0968a9c..ee179d5 100644
 --- a/contribs/pam/pam_slurm.c
 +++ b/contribs/pam/pam_slurm.c
-@@ -266,9 +266,9 @@ static int
+@@ -266,9 +266,9 @@
  _gethostname_short (char *name, size_t len)
  {
  	int error_code, name_len;
@@ -31,7 +28,7 @@ index 0968a9c..ee179d5 100644
  	if (error_code)
  		return error_code;
  
-@@ -296,11 +296,11 @@ static int
+@@ -296,13 +296,13 @@
  _slurm_match_allocation(uid_t uid)
  {
  	int authorized = 0, i;
@@ -40,12 +37,14 @@ index 0968a9c..ee179d5 100644
  	char *nodename = NULL;
  	job_info_msg_t * msg;
  
+ 	slurm_conf_init(NULL);
+ 
 -	if (_gethostname_short(hostname, sizeof(hostname)) < 0) {
 +	if (_gethostname_short(hostname, sizeof(hostname) - 1) < 0) {
  		_log_msg(LOG_ERR, "gethostname: %m");
  		return 0;
  	}
-@@ -409,7 +409,7 @@ _send_denial_msg(pam_handle_t *pamh, struct _options *opts,
+@@ -425,7 +425,7 @@
   */
  extern void libpam_slurm_init (void)
  {
@@ -54,7 +53,7 @@ index 0968a9c..ee179d5 100644
  
  	if (slurm_h)
  		return;
-@@ -417,10 +417,10 @@ extern void libpam_slurm_init (void)
+@@ -433,10 +433,10 @@
  	/* First try to use the same libslurm version ("libslurm.so.24.0.0"),
  	 * Second try to match the major version number ("libslurm.so.24"),
  	 * Otherwise use "libslurm.so" */
@@ -67,7 +66,7 @@ index 0968a9c..ee179d5 100644
  		_log_msg (LOG_ERR, "Unable to write libslurmname\n");
  	} else if ((slurm_h = dlopen(libslurmname, RTLD_NOW|RTLD_GLOBAL))) {
  		return;
-@@ -429,8 +429,10 @@ extern void libpam_slurm_init (void)
+@@ -445,8 +445,10 @@
  			libslurmname, dlerror ());
  	}
  

slurm-20.02.3.tar.bz2

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b73ea8ce63dd73a0744c444f2fbe56fc98e79c9a1ea34e9c82e09534b55c44a3
-size 6330257

slurm-20.02.5.tar.bz2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32a7a32010a526bb8a303df1df081c79dbe15423576543a73c65bdd33301723
+size 6325393

slurm.changes

@@ -1,3 +1,121 @@
+-------------------------------------------------------------------
+Thu Oct 29 12:35:18 UTC 2020 - Ana Guerrero Lopez <aguerrero@suse.com>
+
+- Updated to 20.02.5, changes:
+ * Fix leak of TRESRunMins when job time is changed with --time-min
+ * pam_slurm - explicitly initialize slurm config to support configless mode.
+ * scontrol - Fix exit code when creating/updating reservations with wrong
+   Flags.
+ * When a GRES has a no_consume flag, report 0 for allocated.
+ * Fix cgroup cleanup by jobacct_gather/cgroup.
+ * When creating reservations/jobs don't allow counts on a feature unless
+   using an XOR.
+ * Improve number of boards discovery
+ * Fix updating a reservation NodeCnt on a zero-count reservation.
+ * slurmrestd - provide an explicit error messages when PSK auth fails.
+ * cons_tres - fix job requesting single gres per-node getting two or more
+   nodes with less CPUs than requested per-task.
+ * cons_tres - fix calculation of cores when using gres and cpus-per-task.
+ * cons_tres - fix job not getting access to socket without GPU or with less
+   than --gpus-per-socket when not enough cpus available on required socket
+   and not using --gres-flags=enforce binding.
+ * Fix HDF5 type version build error.
+ * Fix creation of CoreCnt only reservations when the first node isn't
+   available.
+ * Fix wrong DBD Agent queue size in sdiag when using accounting_storage/none.
+ * Improve job constraints XOR option logic.
+ * Fix preemption of hetjobs when needed nodes not in leader component.
+ * Fix wrong bit_or() messing potential preemptor jobs node bitmap, causing
+   bad node deallocations and even allocation of nodes from other partitions.
+ * Fix double-deallocation of preempted non-leader hetjob components.
+ * slurmdbd - prevent truncation of the step nodelists over 4095.
+ * Fix nodes remaining in drain state state after rebooting with ASAP option.
+
+ - changes from 20.02.4:
+ * srun - suppress job step creation warning message when waiting on
+   PrologSlurmctld.
+ * slurmrestd - fix incorrect return values in data_list_for_each() functions.
+ * mpi/pmix - fix issue where HetJobs could fail to launch.
+ * slurmrestd - set content-type header in responses.
+ * Fix cons_res GRES overallocation for --gres-flags=disable-binding.
+ * Fix cons_res incorrectly filtering cores with respect to GRES locality for
+   --gres-flags=disable-binding requests.
+ * Fix regression where a dependency on multiple jobs in a single array using
+   underscores would only add the first job.
+ * slurmrestd - fix corrupted output due to incorrect use of memcpy().
+ * slurmrestd - address a number of minor Coverity warnings.
+ * Handle retry failure when slurmstepd is communicating with srun correctly.
+ * Fix jobacct_gather possibly duplicate stats when _is_a_lwp error shows up.
+ * Fix tasks binding to GRES which are closest to the allocated CPUs.
+ * Fix AMD GPU ROCM 3.5 support.
+ * Fix handling of job arrays in sacct when querying specific steps.
+ * slurmrestd - avoid fallback to local socket authentication if JWT
+   authentication is ill-formed.
+ * slurmrestd - restrict ability of requests to use different authentication
+   plugins.
+ * slurmrestd - unlink named unix sockets before closing.
+ * slurmrestd - fix invalid formatting in openapi.json.
+ * Fix batch jobs stuck in CF state on FrontEnd mode.
+ * Add a separate explicit error message when rejecting changes to active node
+   features.
+ * cons_common/job_test - fix slurmctld SIGABRT due to double-free.
+ * Fix updating reservations to set the duration correctly if updating the
+   start time.
+ * Fix update reservation to promiscuous mode.
+ * Fix override of job tasks count to max when ntasks-per-node present.
+ * Fix min CPUs per node not being at least CPUs per task requested.
+ * Fix CPUs allocated to match CPUs requested when requesting GRES and
+   threads per core equal to one.
+ * Fix NodeName config parsing with Boards and without CPUs.
+ * Ensure SLURM_JOB_USER and SLURM_JOB_UID are set in SrunProlog/Epilog.
+ * Fix error messages for certain invalid salloc/sbatch/srun options.
+ * pmi2 - clean up sockets at step termination.
+ * Fix 'scontrol hold' to work with 'JobName'.
+ * sbatch - handle --uid/--gid in #SBATCH directives properly.
+ * Fix race condition in job termination on slurmd.
+ * Print specific error messages if trying to run use certain
+   priority/multifactor factors that cannot work without SlurmDBD.
+ * Avoid partial GRES allocation when --gpus-per-job is not satisfied.
+ * Cray - Avoid referencing a variable outside of it's correct scope when
+   dealing with creating steps within a het job.
+ * slurmrestd - correctly handle larger addresses from accept().
+ * Avoid freeing wrong pointer with SlurmctldParameters=max_dbd_msg_action
+   with another option after that.
+ * Restore MCS label when suspended job is resumed.
+ * Fix insufficient lock levels.
+ * slurmrestd - use errno from job submission.
+ * Fix "user" filter for sacctmgr show transactions.
+ * Fix preemption logic.
+ * Fix no_consume GRES for exclusive (whole node) requests.
+ * Fix regression in 20.02 that caused an infinite loop in slurmctld when
+   requesting --distribution=plane for the job.
+ * Fix parsing of the --distribution option.
+ * Add CONF READ_LOCK to _handle_fed_send_job_sync.
+ * prep/script - always call slurmctld PrEp callback in _run_script().
+ * Fix node estimation for jobs that use GPUs or --cpus-per-task.
+ * Fix jobcomp, job_submit and cli_filter Lua implementation plugins causing
+   slurmctld and/or job submission CLI tools segfaults due to bad return
+   handling when the respective Lua script failed to load.
+ * Fix propagation of gpu options through hetjob components.
+ * Add SLURM_CLUSTERS environment variable to scancel.
+ * Fix packing/unpacking of "unlinked" jobs.
+ * Connect slurmstepd's stderr to srun for steps launched with --pty.
+ * Handle MPS correctly when doing exclusive allocations.
+ * slurmrestd - fix compiling against libhttpparser in a non-default path.
+ * slurmrestd - avoid compilation issues with libhttpparser < 2.6.
+ * Fix compile issues when compiling slurmrestd without --enable-debug.
+ * Reset idle time on a reservation that is getting purged.
+ * Fix reoccurring reservations that have Purge_comp= to keep correct
+   duration if they are purged.
+ * scontrol - changed the "PROMISCUOUS" flag to "MAGNETIC"
+ * Early return from epilog_set_env in case of no_consume.
+ * Fix cons_common/job_test start time discovery logic to prevent skewed
+   results between "will run test" executions.
+ * Ensure TRESRunMins limits are maintained during "scontrol reconfigure".
+ * Improve error message when host lookup fails.
+
+- Refresh patch: pam_slurm-Initialize-arrays-and-pass-sizes.patch
+
 -------------------------------------------------------------------
 Tue Jul  7 09:05:40 UTC 2020 - Egbert Eich <eich@suse.com>
 

slurm.spec

@@ -18,7 +18,7 @@
 
 # Check file META in sources: update so_version to (API_CURRENT - API_AGE)
 %define so_version 35
-%define ver 20.02.3
+%define ver 20.02.5
 %define _ver _20_02
 %define dl_ver %{ver}
 # so-version is 0 and seems to be stable