From 257676d4f20ecac73eedc857377dd0c0a36b9946f11c4ca2d4054afd20e58650 Mon Sep 17 00:00:00 2001 From: Christian Goll Date: Fri, 12 Jul 2019 18:09:50 +0000 Subject: [PATCH] Accepting request 714908 from home:mslacken:branches:network:cluster - added cray depend libraries to seperate package, as they are now built, since json is enabled - Updated to 18.0.7 for fixing CVE-2019-12838 and (bsc#1140709) * Update "xauth list" to use the same 10000ms timeout as the other xauth commands. * Fix issue in gres code to handle a gres cnt of 0. * Don't purge jobs if backfill is running. * Verify job is pending add/removing accrual time. * Don't abort when the job doesn't have an association that was removed before the job was able to make it to the database. * Set state_reason if select_nodes() fails job for QOS or Account. * Avoid seg_fault on referencing association without a valid_qos bitmap. * If Association/QOS is removed on a pending job set that job as ineligible. * When changing a jobs account/qos always make sure you remove the old limits. * Don't reset a FAIL_QOS or FAIL_ACCOUNT job reason until the qos or account changed. * Restore "sreport -T ALL" functionality. * Correctly typecast signals being sent through the api. * Properly initialize structures throughout Slurm. * Sync "numtask" squeue format option for jobs and steps to "numtasks". * Fix sacct -PD to avoid CA before start jobs. * Fix potential deadlock with backup slurmctld. * Fixed issue with jobs not appearing in sacct after dependency satisfied. * Fix showing non-eligible jobs when asking with -j and not -s. * Fix issue with backfill scheduler scheduling tasks of an array when not the head job. * accounting_storage/mysql - fix SIGABRT in the archive load logic. * accounting_storage/mysql - fix memory leak in the archive load logic. * Limit records per single SQL statement when loading archived data. OBS-URL: https://build.opensuse.org/request/show/714908 OBS-URL: https://build.opensuse.org/package/show/network:cluster/slurm?expand=0&rev=100 --- slurm-18.08.7.tar.bz2 | 3 -- slurm-18.08.8.tar.bz2 | 3 ++ slurm.changes | 85 +++++++++++++++++++++++++++++++++++++++++++ slurm.spec | 47 +++++++++++++++++++----- 4 files changed, 126 insertions(+), 12 deletions(-) delete mode 100644 slurm-18.08.7.tar.bz2 create mode 100644 slurm-18.08.8.tar.bz2 diff --git a/slurm-18.08.7.tar.bz2 b/slurm-18.08.7.tar.bz2 deleted file mode 100644 index 3af2a57..0000000 --- a/slurm-18.08.7.tar.bz2 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:854f922e4147af1ba861988455dbbb53ab5325f1ca138dce0ad553792b888743 -size 6186006 diff --git a/slurm-18.08.8.tar.bz2 b/slurm-18.08.8.tar.bz2 new file mode 100644 index 0000000..c858bb3 --- /dev/null +++ b/slurm-18.08.8.tar.bz2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043a048ac8a6fb6f6bf7c66434b05ed8b5b871e5e86e407c063d0c8cb4cb6e0d +size 6208426 diff --git a/slurm.changes b/slurm.changes index 755247f..4c7c8b6 100644 --- a/slurm.changes +++ b/slurm.changes @@ -1,3 +1,88 @@ +------------------------------------------------------------------- +Fri Jul 12 09:04:55 UTC 2019 - Christian Goll + +- added cray depend libraries to seperate package, as they are now + built, since json is enabled + +------------------------------------------------------------------- +Thu Jul 11 10:57:52 UTC 2019 - Christian Goll + +- Updated to 18.0.7 for fixing CVE-2019-12838 and (bsc#1140709) + * Update "xauth list" to use the same 10000ms timeout as the other xauth + commands. + * Fix issue in gres code to handle a gres cnt of 0. + * Don't purge jobs if backfill is running. + * Verify job is pending add/removing accrual time. + * Don't abort when the job doesn't have an association that was removed + before the job was able to make it to the database. + * Set state_reason if select_nodes() fails job for QOS or Account. + * Avoid seg_fault on referencing association without a valid_qos bitmap. + * If Association/QOS is removed on a pending job set that job as ineligible. + * When changing a jobs account/qos always make sure you remove the old limits. + * Don't reset a FAIL_QOS or FAIL_ACCOUNT job reason until the qos or + account changed. + * Restore "sreport -T ALL" functionality. + * Correctly typecast signals being sent through the api. + * Properly initialize structures throughout Slurm. + * Sync "numtask" squeue format option for jobs and steps to "numtasks". + * Fix sacct -PD to avoid CA before start jobs. + * Fix potential deadlock with backup slurmctld. + * Fixed issue with jobs not appearing in sacct after dependency satisfied. + * Fix showing non-eligible jobs when asking with -j and not -s. + * Fix issue with backfill scheduler scheduling tasks of an array + when not the head job. + * accounting_storage/mysql - fix SIGABRT in the archive load logic. + * accounting_storage/mysql - fix memory leak in the archive load logic. + * Limit records per single SQL statement when loading archived data. + * Fix unnecessary reloading of job submit plugins. + * Allow job submit plugins to be turned on/off with a reconfigure. + * Fix segfault when loading/unloading Lua job submit plugin multiple times. + * Fix printing duplicate error messages of jobs rejected by job submit plugin. + * Fix printing of job submit plugin messages of het jobs without pack id. + * Fix memory leak in group_cache.c + * Fix jobs stuck from FedJobLock when requeueing in a federation + * Fix requeueing job in a federation of clusters with differing associations + * sacctmgr - free memory before exiting in 'sacctmgr show runaway'. + * Fix seff showing memory overflow when steps tres mem usage is 0. + * Upon archive file name collision, create new archive file instead of + overwriting the old one to prevent lost records. + * Limit archive files to 50000 records per file so that archiving large + databases will succeed. + * Remove stray newlines in SPANK plugin error messages. + * Fix archive loading events. + * In select/cons_res: Only allocate 1 CPU per node with the --overcommit and + --nodelist options. + * Fix main scheduler from potentially not running through whole queue. + * cons_res/job_test - prevent a job from overallocating a node memory. + * cons_res/job_test - fix to consider a node's current allocated memory when + testing a job's memory request. + * Fix issue where multi-node job steps on cloud nodes wouldn't finish cleaning + up until the end of the job (rather than the end of the step). + * Fix issue with a 17.11 sbcast call to a 18.08 daemon. + * Add new job bit_flags of JOB_DEPENDENT. + * Make it so dependent jobs reset the AccrueTime and do not count against any + AccrueTime limits. + * Fix sacctmgr --parsable2 output for reservations and tres. + * Prevent slurmctld from potential segfault after job_start_data() called + for completing job. + * Fix jobs getting on nodes with "scontrol reboot asap". + * Record node reboot events to database. + * Fix node reboot failure message getting to event table. + * Don't write "(null)" to event table when no event reason exists. + * Fix minor memory leak when clearing runaway jobs. + * Avoid flooding slurmctld and logging when prolog complete RPC errors occur. + * Fix GCC 9 compiler warnings. + * Fix seff human readable memory string for values below a megabyte. + * Fix dump/load of rejected heterogeneous jobs. + * For heterogeneous jobs, do not count the each component against the QOS or + association job limit multiple times. + * slurmdbd - avoid reservation flag column corruption with the use of newer + flags, instead preserve the older flag fields that we can still fit in the + smallint field, and discard the rest. + * Fix security issue in accounting_storage/mysql plugin on archive file loads + by always escaping strings within the slurmdbd. CVE-2019-12838. + + ------------------------------------------------------------------- Mon Jul 8 08:19:23 UTC 2019 - Egbert Eich diff --git a/slurm.spec b/slurm.spec index 4dd7b99..5203a4b 100644 --- a/slurm.spec +++ b/slurm.spec @@ -18,7 +18,7 @@ # Check file META in sources: update so_version to (API_CURRENT - API_AGE) %define so_version 33 -%define ver 18.08.7 +%define ver 18.08.8 %define _ver _18_08 %define dl_ver %{ver} # so-version is 0 and seems to be stable @@ -442,6 +442,15 @@ Plugin to store accounting in the hdf5 file format. This plugin has to be activated in the slurm configuration. Includes also utility the program sh5utils to merge this hdf5 files or extract data from them. +%package cray +Summary: Cray specific plugins +Group: Productivity/Clustering/Computing + +%description cray +Plugins for specific cray hardware, includes power and knl node management. +Contains also cray specific documentation. + + %prep %setup -q -n %{pname}-%{dl_ver} %patch0 -p1 @@ -460,6 +469,7 @@ sh5utils to merge this hdf5 files or extract data from them. %patch12 -p1 %build +%define _lto_cflags %{nil} %configure --enable-shared \ --disable-static \ --without-rpath \ @@ -468,7 +478,7 @@ sh5utils to merge this hdf5 files or extract data from them. --sysconfdir=%{_sysconfdir}/%{pname} \ %{!?have_hdf5:--without-hdf5} \ %{!?have_lz4:--without-lz4} \ -%{!?have_jasonc:--without-json} +%{!?have_json_c:--without-json} make %{?_smp_mflags} @@ -915,7 +925,6 @@ exit 0 %{_libdir}/slurm/accounting_storage_filetxt.so %{_libdir}/slurm/accounting_storage_none.so %{_libdir}/slurm/accounting_storage_slurmdbd.so -%{_libdir}/slurm/acct_gather_energy_cray.so %{_libdir}/slurm/acct_gather_energy_ibmaem.so %{_libdir}/slurm/acct_gather_energy_none.so %{_libdir}/slurm/acct_gather_energy_rapl.so @@ -926,7 +935,6 @@ exit 0 %{_libdir}/slurm/burst_buffer_generic.so %{_libdir}/slurm/checkpoint_none.so %{_libdir}/slurm/checkpoint_ompi.so -%{_libdir}/slurm/core_spec_cray.so %{_libdir}/slurm/core_spec_none.so %{_libdir}/slurm/crypto_openssl.so %{_libdir}/slurm/ext_sensors_none.so @@ -942,7 +950,6 @@ exit 0 %{_libdir}/slurm/job_container_cncu.so %{_libdir}/slurm/job_container_none.so %{_libdir}/slurm/job_submit_all_partitions.so -%{_libdir}/slurm/job_submit_cray.so %{_libdir}/slurm/job_submit_defaults.so %{_libdir}/slurm/job_submit_logging.so %{_libdir}/slurm/job_submit_partition.so @@ -975,16 +982,13 @@ exit 0 %{_libdir}/slurm/sched_hold.so %{_libdir}/slurm/select_alps.so %{_libdir}/slurm/select_cons_res.so -%{_libdir}/slurm/select_cray.so %{_libdir}/slurm/select_linear.so %{_libdir}/slurm/select_serial.so %{_libdir}/slurm/slurmctld_nonstop.so -%{_libdir}/slurm/switch_cray.so %{_libdir}/slurm/switch_generic.so %{_libdir}/slurm/switch_none.so %{_libdir}/slurm/task_affinity.so %{_libdir}/slurm/task_cgroup.so -%{_libdir}/slurm/task_cray.so %{_libdir}/slurm/task_none.so %{_libdir}/slurm/topology_3d_torus.so %{_libdir}/slurm/topology_hypercube.so @@ -1004,6 +1008,14 @@ exit 0 %{_libdir}/slurm/acct_gather_profile_influxdb.so %{_libdir}/slurm/ext_sensors_rrd.so %{_libdir}/slurm/jobcomp_elasticsearch.so +%if !0%{?is_opensuse} +%{_libdir}/slurm/acct_gather_energy_cray.so +%{_libdir}/slurm/core_spec_cray.so +%{_libdir}/slurm/job_submit_cray.so +%{_libdir}/slurm/select_cray.so +%{_libdir}/slurm/switch_cray.so +%{_libdir}/slurm/task_cray.so +%endif %files lua %{?comp_at} @@ -1071,11 +1083,13 @@ exit 0 %{_mandir}/man5/ext_sensors.conf.* %{_mandir}/man5/slurm.* %{_mandir}/man5/cgroup.* -%{_mandir}/man5/cray.* %{_mandir}/man5/gres.* %{_mandir}/man5/nonstop.conf.5.* %{_mandir}/man5/topology.* %{_mandir}/man5/knl.conf.5.* +%if !0%{?is_opensuse} +%{_mandir}/man5/cray.* +%endif %if 0%{?have_hdf5} %files hdf5 @@ -1084,4 +1098,19 @@ exit 0 %{_mandir}/man1/sh5util.1.gz %endif +%files cray +# do not remove cray sepcific packages from SLES update +%if 0%{?is_opensuse} +%{_libdir}/slurm/acct_gather_energy_cray.so +%{_libdir}/slurm/core_spec_cray.so +%{_libdir}/slurm/job_submit_cray.so +%{_libdir}/slurm/select_cray.so +%{_libdir}/slurm/switch_cray.so +%{_libdir}/slurm/task_cray.so +%{_mandir}/man5/cray.* +%endif +%{_libdir}/slurm/burst_buffer_cray.so +%{_libdir}/slurm/node_features_knl_cray.so +%{_libdir}/slurm/power_cray.so + %changelog