slurmctld
- HPC Charm Team
Channel | Revision | Published | Runs on |
---|---|---|---|
latest/stable | 21 | 14 Jan 2022 | |
latest/candidate | 47 | 17 Oct 2022 | |
latest/edge | 84 | 20 Dec 2024 | |
latest/edge | 79 | 27 Nov 2024 | |
latest/edge | 59 | 02 Oct 2023 | |
latest/edge | 58 | 24 Aug 2023 |
juju deploy slurmctld
Deploy universal operators easily with Juju, the Universal Operator Lifecycle Manager.
Platform:
-
acct-gather-custom | string
User supplied
acct_gather.conf
configuration. This value supplements the charm suppliedacct_gather.conf
file that is used for configuring the acct_gather plugins. -
acct-gather-frequency | string
Default: task=30
Accounting and profiling sampling intervals for the acct_gather plugins. Note: a value of
0
disables the periodic sampling. In this case, the accounting information is collected when the job terminates. Example usage: $ juju config slurmcltd acct-gather-frequency="task=30,network=30" -
cgroup-config | string
Default: CgroupAutomount=yes ConstrainCores=yes
Configuration content for
cgroup.conf
. -
cluster-name | string
Default: osd-cluster
Name to be recorded in database for jobs from this cluster. This is important if a single database is used to record information from multiple Slurm-managed clusters.
-
custom-config | string
User supplied Slurm configuration. This value supplements the charm supplied
slurm.conf
that is used for Slurm Controller and Compute nodes. Example usage: $ juju config slurmcltd custom-config="FirstJobId=1234" -
custom-slurm-repo | string
Use a custom repository for Slurm installation. This can be set to the Organization's local mirror/cache of packages and supersedes the Omnivector repositories. Alternatively, it can be used to track a
testing
Slurm version, e.g. by setting toppa:omnivector/osd-testing
(on Ubuntu), orhttps://omnivector-solutions.github.io/repo/centos7/stable/$basearch
(on CentOS). Note: The configurationcustom-slurm-repo
must be set before deploying the units. Changing this value after deploying the units will not reinstall Slurm. -
default-partition | string
Default Slurm partition. This is only used if defined, and must match an existing partition.
-
health-check-interval | int
Default: 600
Interval in seconds between executions of the Health Check.
-
health-check-state | string
Default: ANY,CYCLE
Only run the Health Check on nodes in this state.
-
proctrack-type | string
Default: proctrack/cgroup
Identifies the plugin to be used for process tracking on a job step basis.