- 09 May, 2017 2 commits
-
-
Brian Christiansen authored
When running sacct from a federated client, the db returns jobs for each cluster with duplicate jobs removed on each cluster. A federated job could have ran on a different cluster when the before the jobid's rolled. This patch filters out past old federated jobs and leaves the newest ones. Reverted d31965 which was too slow.
-
Brian Christiansen authored
This reverts commit d31965f3.
-
- 08 May, 2017 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
- 06 May, 2017 3 commits
-
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
-
- 05 May, 2017 10 commits
-
-
Danny Auble authored
-
Morris Jette authored
Work is incomplete, but for now we get all jobs in federation and highlight the local nodes associated with each job.
-
Danny Auble authored
select_g_select_nodeinfo_set(). This is a continuation of commit 80443cc1. Bug 3690. Test 1.62 will fail otherwise.
-
Danny Auble authored
we failed. Bug 3690 continuation of commit bf0429d1.
-
Morris Jette authored
Add "cluster_name" field to node_info_t and partition_info_t data structure. It is filled in only when the cluster is part of a federation and SHOW_GLOBAL flag used. Functions slurm_load_node() slurm_load_partitions() modified to show all nodes/partitions in a federation when the SHOW_GLOBAL flag is used.
-
Danny Auble authored
bf0429d1 this is no longer needed to wait as long. Bug 3690 continuation of commit bf0429d1.
-
Danny Auble authored
If this failed the job was 3/4's allocated and not in the database. This would cause a segfault if done where it happened before. Bug 3690 continuation of commit bf0429d1
-
Brian Christiansen authored
The decay thread could signal the cond before the init thread waits for it causing deadlock.
-
Morris Jette authored
-
Morris Jette authored
In order to test with larger systems, modify capmc script to generate output with arbitrary start and end NID values
-
- 04 May, 2017 11 commits
-
-
Tim Wickberg authored
-
Danny Auble authored
Bug 3725
-
Tim Wickberg authored
in general.
-
Brian Christiansen authored
-
Brian Christiansen authored
at shutdown. More likely to happen in the fed_mgr than the dbd since the fed_mgr closes the persistent connections before they are signaled by the persistent connection server.
-
Danny Auble authored
-
Alejandro Sanchez authored
pointer.
-
Alejandro Sanchez authored
selected for a job. Bug 3690
-
Morris Jette authored
Document the node_features_p_node_xlate2() function and update the description of node_features_p_node_xlate(). These changes were made in commit 6690685a bugs 3614, 3679
-
Tim Wickberg authored
-
Tim Wickberg authored
Allows for annotations such as xassert(verify_lock(CONFIG_LOCK, READ_LOCK)); to ensure that the calling thread has the correct locks in place to head off potential race conditions / corruption.
-
- 03 May, 2017 12 commits
-
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
Remove outdated disclaimers, proctrack/cgroup is awesome. (jobacct_gather/cgroup is still not recommended though.) Change it to the default with the configurators as well.
-
Morris Jette authored
-
Morris Jette authored
It seems to be a popular item. It would be nice to eventually re-write the tool to use Slurm's perl API at some time...
-
Dominik Bartkiewicz authored
Do not create a backfill resource reservation for jobs prevented from starting due to QOS limit. bug 3680
-
Brian Christiansen authored
-
Brian Christiansen authored
As found by CLANG
-
Tim Wickberg authored
No functional change, all are in comment blocks.
-
Tim Wickberg authored
-
Tim Wickberg authored
Restructure code slightly to make code path cleaner.
-