feat!: overhaul slurmctld charm API

.github/workflows/ci.yaml

@@ -23,7 +23,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Run tests
         uses: get-woke/woke-action@v0
         with:
@@ -34,7 +34,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Install dependencies
         run: python3 -m pip install tox
       - name: Run linters
@@ -45,12 +45,23 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Install dependencies
         run: python3 -m pip install tox
       - name: Run tests
         run: tox -e unit
 
+  type-check:
+    name: Static type checking
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Install dependencies
+        run: python3 -m pip install tox
+      - name: Run tests
+        run: tox -e type
+
   integration-test:
     strategy:
       fail-fast: true
@@ -63,9 +74,10 @@ jobs:
       - inclusive-naming-check
       - lint
       - unit-test
+      - type-check
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Setup operator environment
         uses: charmed-kubernetes/actions-operator@main
         with:

.gitignore

@@ -8,3 +8,4 @@ __pycache__/
 .idea
 .vscode/
 version
+.ruff_cache

README.md

@@ -24,13 +24,7 @@ This operator should be used with Juju 3.x or greater.
 ```shell
 $ juju deploy slurmctld --channel edge
 $ juju deploy slurmd --channel edge
-$ juju deploy slurmdbd --channel edge
-$ juju deploy mysql --channel 8.0/edge
-$ juju deploy mysql-router slurmdbd-mysql-router --channel dpe/edge
-$ juju integrate slurmctld:slurmd slurmd:slurmd
-$ juju integrate slurmdbd-mysql-router:backend-database mysql:database
-$ juju integrate slurmdbd:database slurmdbd-mysql-router:database
-$ juju integrate slurmctld:slurmdbd slurmdbd:slurmdbd
+$ juju integrate slurmctld:slurmd slurmd:slurmctld
 ```
 
 ## Project & Community

charmcraft.yaml

@@ -22,28 +22,15 @@ links:
   source:
   - https://github.com/charmed-hpc/slurmctld-operator
 
-peers:
-  slurmctld-peer:
-    interface: slurmctld-peer
 requires:
   slurmd:
     interface: slurmd
   slurmdbd:
     interface: slurmdbd
   slurmrestd:
     interface: slurmrestd
-  influxdb-api:
-    interface: influxdb-api
-  elasticsearch:
-    interface: elasticsearch
   fluentbit:
     interface: fluentbit
-provides:
-  prolog-epilog:
-    interface: prolog-epilog
-  grafana-source:
-    interface: grafana-source
-    scope: global
 
 assumes:
   - juju
@@ -58,163 +45,102 @@ bases:
         channel: "22.04"
         architectures: [amd64]
 
-parts:
-  charm:
-    build-packages: [git]
-    charm-python-packages: [setuptools]
-
-  # Create a version file and pack it into the charm. This is dynamically generated
-  # as part of the build process for a charm to ensure that the git revision of the
-  # charm is always recorded in this version file.
-  version-file:
-    plugin: nil
-    build-packages:
-      - git
-    override-build: |
-      VERSION=$(git -C $CRAFT_PART_SRC/../../charm/src describe --dirty --always)
-      echo "Setting version to $VERSION"
-      echo $VERSION > $CRAFT_PART_INSTALL/version
-    stage:
-      - version
 
 config:
   options:
-    custom-slurm-repo:
-      type: string
-      default: ""
-      description: >
-        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 to
-        `ppa:omnivector/osd-testing`.
-
-        Note: The configuration `custom-slurm-repo` must be set *before*
-        deploying the units. Changing this value after deploying the units will
-        not reinstall Slurm.
     cluster-name:
       type: string
       default: osd-cluster
-      description: >
+      description: |
         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.
+
     default-partition:
       type: string
       default: ""
-      description: >
+      description: |
         Default Slurm partition. This is only used if defined, and must match an
         existing partition.
-    custom-config:
+
+    slurm-conf-parameters:
       type: string
       default: ""
-      description: >
-        User supplied Slurm configuration.
-
-        This value supplements the charm supplied `slurm.conf` that is used for
-        Slurm Controller and Compute nodes.
+      description: |
+        User supplied Slurm configuration as a multiline string.
 
         Example usage:
-        $ juju config slurmcltd custom-config="FirstJobId=1234"
-    proctrack-type:
-      type: string
-      default: proctrack/cgroup
-      description: >
-        Identifies the plugin to be used for process tracking on a job step
-        basis.
-    cgroup-config:
+        $ juju config slurmcltd slurm-conf-parameters="$(cat additional.conf)"
+
+    cgroup-parameters:
       type: string
       default: |
         CgroupAutomount=yes
         ConstrainCores=yes
-      description: >
-        Configuration content for `cgroup.conf`.
+      description: |
+        User supplied configuration for `cgroup.conf`.
 
     health-check-params:
       default: ""
       type: string
-      description: >
+      description: |
         Extra parameters for NHC command.
 
         This option can be used to customize how NHC is called, e.g. to send an
-        e-mail to an admin when NHC detects an error set this value to
+        e-mail to an admin when NHC detects an error set this value to.
         `-M [email protected]`.
+
     health-check-interval:
       default: 600
       type: int
       description: Interval in seconds between executions of the Health Check.
+
     health-check-state:
       default: "ANY,CYCLE"
       type: string
       description: Only run the Health Check on nodes in this state.
-
-    acct-gather-frequency:
-      type: string
-      default: "task=30"
-      description: >
-        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"
-    acct-gather-custom:
-      type: string
-      default: ""
-      description: >
-        User supplied `acct_gather.conf` configuration.
-
-        This value supplements the charm supplied `acct_gather.conf` file that is
-        used for configuring the acct_gather plugins.
 
 actions:
   show-current-config:
-    description: >
+    description: |
       Display the currently used `slurm.conf`.
 
-      Note: This file only exists in `slurmctld` charm and is automatically
-      distributed to all compute nodes by Slurm.
-
       Example usage:
-      $ juju run-action slurmctld/leader --format=json --wait | jq .[].results.slurm.conf | xargs -I % -0 python3 -c 'print(%)'
+
+      ```bash
+      juju run slurmctld/leader show-current-config \
+          --quiet --format=json  | jq .[].results.slurm.conf | xargs -I % -0 python3 -c 'print(%)'
+      ```
+
   drain:
-    description: >
+    description: |
       Drain specified nodes.
 
       Example usage:
-      $ juju run-action slurmctld/leader drain nodename=node-[1,2] reason="Updating kernel"
+      $ juju run slurmctld/leader drain nodename="node-[1,2]" reason="Updating kernel"
     params:
       nodename:
         type: string
-        description: The nodes to drain, using the Slurm format, e.g. `node-[1,2]`.
+        description: The nodes to drain, using the Slurm format, e.g. `"node-[1,2]"`.
       reason:
         type: string
         description: Reason to drain the nodes.
     required:
       - nodename
       - reason
   resume:
-    description: >
+    description: |
       Resume specified nodes.
 
       Note: Newly added nodes will remain in the `down` state until configured,
       with the `node-configured` action.
 
-      Example usage: $ juju run-action slurmctld/leader resume nodename=node-[1,2]
+      Example usage: $ juju run slurmctld/leader resume nodename="node-[1,2]"
     params:
       nodename:
         type: string
-        description: >
-          The nodes to resume, using the Slurm format, e.g. `node-[1,2]`.
+        description: |
+          The nodes to resume, using the Slurm format, e.g. `"node-[1,2]"`.
     required:
       - nodename
-
-  influxdb-info:
-    description: >
-      Get InfluxDB info.
-
-      This action returns the host, port, username, password, database, and
-      retention policy regarding to InfluxDB.

requirements.txt

@@ -1,5 +1,3 @@
-ops==2.*
-influxdb==5.3.1
-jinja2==3.1.3
-distro
-pycryptodome
+ops==2.14.0
+distro==1.9.0
+pycryptodome==3.20.0