- 17 May, 2019 7 commits
-
-
Nate Rini authored
Bug 7050.
-
Morris Jette authored
Previous logic only checked the first gpu record found, which is not going to reliably work if the first gpu type is on one socket and the next gpu type is on a different socket or itself spans sockets.
-
Morris Jette authored
The wrong variable was clearly being used resulting in a node's "gres" string not containing the proper socket identification for GRES bound to sockets.
-
Morris Jette authored
This change adds a job name to all tests spawned by the test. It also explicitly sets the MPI type to none. This is required by some of the tests if using OpenMPI in multi-slurmd mode. See note in test1.88 for full description of OpenMPI limitations in this Slurm mode.
-
Tim Wickberg authored
-
Tim Wickberg authored
This is select/cons_res, not select/cons_tres.
-
Morris Jette authored
Previous select/cons_res logic would allocate one CPU per task on the node Bug 6981
-
- 16 May, 2019 18 commits
-
-
Dominik Bartkiewicz authored
Bug 6221
-
Morris Jette authored
Previous select/cons_tres logic would allocate one CPU per task on the node Bug 6981
-
Morris Jette authored
Modify task layout with --overcommit option plus a heterogeneous job allocation so that a cyclic task distribution can start happening before all CPUs on all nodes are fully allocated. The number of tasks per node will be unchanged from the previous algorithm, but tasks will be distributed in a cyclic fashion first and then extra tasks placed on nodes with more CPUs. Previously all CPUs would be fully allocated in a cyclic fashion, then excess tasks distributed evenly across all allocated nodes. Bug 6981
-
Morris Jette authored
OpenMPI can only run in multi-slurmd mode if no more than one node has more than one task. Individual nodes with more than one task use shared memory for communications and if more than one node is doing that, their shared memory use collides. That means these MPI tests will work if five nodes or more are available, otherwise some tests will fail. See test1.117 for a variation of this test that will work with OpenMPI and multi-slurmd mode.
-
Dominik Bartkiewicz authored
Bug 6969.
-
Dominik Bartkiewicz authored
Bug 6969.
-
Dominik Bartkiewicz authored
Add warning to slurm.h.in that no new reservation flags can be stored in slurmdbd in 19.05. (Although they could still be used by slurmctld without issue.) Note that the underlying RPC still uses uint32_t, but this will be changed before 20.02 on master, and changing the column to uint32_t in 19.05 just to change it again in 20.02 is best avoided. Bug 6969.
-
Morris Jette authored
OpenMPI can only run in multi-slurmd mode if no more than one node has more than one task. Individual nodes with more than one task use shared memory for communications and if more than one node is doing that, their shared memory use collides. That means these MPI tests will work if five nodes or more are available, otherwise some tests will fail. See test1.117 for a variation of this test that will work with OpenMPI and multi-slurmd mode.
-
Morris Jette authored
replace spaces with tabs in test
-
Tim Wickberg authored
-
Morris Jette authored
a job with --gpus=1 --nodes=2 is not currently supported
-
Morris Jette authored
-
Morris Jette authored
proctrack/cray plugin renamed to proctrack/cray_aries
-
Morris Jette authored
Note that configure option --enable-native-cray has been removed
-
Nathan Rini authored
Free format_list, plugin_id_select_list, rpc_version_list in _free_cluster_cond_members(). Bug 7020.
-
Alejandro Sanchez authored
-
Marshall Garey authored
There was a syntax error in the mysql for inserting the event records into the event table caused by commit 3d61b6aa. The syntax error was a semicolon in the middle of the query, for example: insert into "voyager_event_table" (time_start, time_end, node_name, cluster_nodes, reason, reason_uid, state, tres) values ('1538669453', '1539298628', 'v1', '', 'cold-start', '1017', '0', '1=8,2=4000,5=8,1001=4,1002=1');, (<... another record>);, ... Bug 7025.
-
Marshall Garey authored
This commit caused loading usage table archive files to fail. Specifically, wckey and assoc hourly/daily/monthly usage tables and the cluster usage tables archive files would all fail to load. Bug 7025.
-
- 15 May, 2019 5 commits
-
-
Tim Wickberg authored
For a stray socket, this call would cause nss_slurm to deadlock, as any calling path that leads to slurm_conf_lock(), which will call getpwuid(), which will re-enter the nss_slurm code, which will end up back here but with the slurm_conf_lock already held, at which point the process will never continue. For nss_slurm, this means a node rebooting with stale sockets will hang in the middle of the init process, which is a rather unpleasant experience. So - only handle the stray socket cleanup within the slurmd process itself. Bug 7030
-
Alejandro Sanchez authored
-
Alejandro Sanchez authored
It's more suitable for the purpose of checking if a file exists, plus avoids the unnecessary struct stat variable since we don't care about the file information. Continuation of 1e234c3d. Bug 6033.
-
Marshall Garey authored
Replace strncpy with xstrdup and snprintf with xstrfmtcat respectively in _make_archive_name. This also fixes a coverity error CID 198462. Continuation of 1e234c3d. Bug 6033.
-
Morris Jette authored
-
- 14 May, 2019 3 commits
-
-
Danny Auble authored
Continuation of 3beabdb1
-
Danny Auble authored
Continuation of 3beabdb1
-
Morris Jette authored
These test changes are designed to support gres/gpu configurations where only some sockets actually have GPUs. The tests will not work with all possible configurations, but this change will result in the tests working in more cases.
-
- 13 May, 2019 4 commits
-
-
Morris Jette authored
select/cray replaced by select/cray_aries in tests
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Chad Vizino authored
Bug 6902.
-
- 11 May, 2019 3 commits
-
-
Morris Jette authored
If they do not, then explicitly cancel them
-
Morris Jette authored
-
Morris Jette authored
Change to work on CPU-rich / memory-poor nodes.
-