James longdev

* Improve the way slurmd sends slurmctld its node-config
* Add an action, `node-config` to get and set unit level  node-configuration
* Add `partition-config` charm configuration that allows an operator to set
partition configuration
* Consolidate the yaml files into `charmcraft.yaml`
* Remove unused code
* Remove slurm-ops-manager
* Replace nhc resource with nhc in build process in charmcraft.yaml
* Remove dependencies on slurmdbd
* rename interface slurmd -> slurmctld

.gitignore

@@ -7,4 +7,6 @@ __pycache__/
 *.py[cod]
 .idea
 .vscode/
-version
+
+# Disable woke checking for nhc.conf.tmpl
+src/templates/nhc.conf.tmpl

README.md

@@ -27,10 +27,29 @@ $ 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
+$ juju integrate slurmctld:slurmdbd slurmdbd:slurmctld
+```
+
+### Operations
+This charm hardens and simplifies operations by codifying common administration operations as charm actions.
+
+#### Node Config
+You can get and set the node configuration using the `node-config` action.
+
+##### Use the `node-config` action to get the node configuration for the unit.
+```bash
+$ juju run --quiet slurmd/0 node-config --format json | jq ".[].results.node.config"
+"NodeName=juju-462521-4 NodeAddr=10.240.222.28 State=UNKNOWN RealMemory=64012 CPUs=12 ThreadsPerCore=2 CoresPerSocket=6 SocketsPerBoard=1"
+```
+
+##### Use the `node-config` action to set a custom weight value for the node.
+```bash
+$ juju run --quiet slurmd/0 node-config node-config="Weight=5000" --format json | jq ".[].results.node.config"
+"NodeName=juju-462521-4 NodeAddr=10.240.222.28 State=UNKNOWN RealMemory=64012 CPUs=12 ThreadsPerCore=2 CoresPerSocket=6 SocketsPerBoard=1 Weight=5000"
 ```
 
 ## Project & Community

charmcraft.yaml

@@ -1,7 +1,29 @@
-# Copyright 2020 Omnivector, LLC
-# See LICENSE file for licensing details.
-
+name: slurmd
 type: charm
+
+summary: |
+  Slurmd, the compute node daemon of Slurm.
+
+description: |
+  This charm provides slurmd, munged, and the bindings to other utilities
+  that make lifecycle operations a breeze.
+  
+  slurmd is the compute node daemon of SLURM. It monitors all tasks running
+  on the compute node, accepts work (tasks), launches tasks, and kills
+  running tasks upon request.
+
+links:
+  contact: https://matrix.to/#/#hpc:ubuntu.com
+
+  issues: 
+  - https://github.com/charmed-hpc/slurmd-operator/issues
+
+  source:
+  - https://github.com/charmed-hpc/slurmd-operator
+
+assumes:
+  - juju
+
 bases:
   - build-on:
       - name: ubuntu
@@ -10,25 +32,75 @@ bases:
       - name: ubuntu
         channel: "22.04"
         architectures: [amd64]
-      - name: centos
-        channel: "7"
-        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
+      - wget
     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
+       wget https://github.com/mej/nhc/releases/download/1.4.3/lbnl-nhc-1.4.3.tar.gz
+       craftctl default
+
+requires:
+  fluentbit:
+    interface: fluentbit
+
+provides:
+  slurmctld:
+    interface: slurmd
+    limit: 1
+
+config:
+  options:
+    partition-config:
+      type: string
+      default: ""
+      description: >
+        Additional partition configuration parameters, specified as a space separated `key=value`
+        in a single line. Find a list of all possible partition configuration parameters
+        [here](https://slurm.schedmd.com/slurm.conf.html#SECTION_PARTITION-CONFIGURATION).
+        
+  
+        Example usage:
+        ```bash
+         $ juju config slurmd partition-config="DefaultTime=45:00 MaxTime=1:00:00"
+        ```
+
+    nhc-conf:
+      default: ""
+      type: string
+      description: >
+        Multiline string.
+        These lines are appended to the `nhc.conf` maintained by the charm.
+
+        Example usage:
+        ```bash
+         $ juju config slurmd nhc-conf="$(cat extra-nhc.conf)"
+        ```
+
+actions:
+  node-configured:
+    description: Remove a node from DownNodes when the reason is `New node`.
+
+  node-config:
+    description: >
+      Set or return node configuration parameters.
+
+      To get the current node configuration for this unit:
+      ``bash
+      $ juju run slurmd/0 node-parameters
+      ```
+
+      To set node level configuration parameters for the unit `slurmd/0`:
+      ``bash
+      $ juju run slurmd/0 node-config parameters="Weight=200 Gres=gpu:tesla:1,gpu:kepler:1,bandwidth:lustre:no_consume:4G"
+      ```
+
+    params:
+       parameters:
+        type: string
+        description: >
+          Node configuration parameter as defined [here](https://slurm.schedmd.com/slurm.conf.html#SECTION_NODE-CONFIGURATION).
+
+  show-nhc-config:
+    description: Display `nhc.conf`.

dispatch

@@ -1,44 +1,11 @@
 #!/bin/bash
-# This hook installs the dependencies needed to run the charm,
-# creates the dispatch executable, regenerates the symlinks for start and
-# upgrade-charm, and kicks off the operator framework.
-
 set -e
 
-# Source the os-release information into the env
-. /etc/os-release
-
 if ! [[ -f '.installed' ]]
 then
-	if [[ $ID == 'centos' ]]
-	then
-		# Install dependencies and build custom python
-		yum -y install epel-release
-		yum -y install wget gcc make tar bzip2-devel zlib-devel xz-devel openssl-devel libffi-devel sqlite-devel ncurses-devel
-
-		export PYTHON_VERSION=3.8.16
-		wget https://www.python.org/ftp/python/${PYTHON_VERSION}/Python-${PYTHON_VERSION}.tar.xz -P /tmp
-		tar xvf /tmp/Python-${PYTHON_VERSION}.tar.xz -C /tmp
-		cd /tmp/Python-${PYTHON_VERSION}
-		./configure --enable-optimizations
-		make -C /tmp/Python-${PYTHON_VERSION} -j $(nproc) altinstall		
-		cd $OLDPWD
-		rm -rf /tmp/Python*
-
-	elif [[ $ID == 'ubuntu' ]]
-	then
-		# Necessary to compile and install NHC
-		apt-get install --assume-yes make
-	fi
-	touch .installed
-fi
-
-# set the correct python bin path
-if [[ $ID == "centos" ]]
-then
-	PYTHON_BIN="/usr/bin/env python3.8"
-else
-	PYTHON_BIN="/usr/bin/env python3"
+    # Necessary to compile and install NHC
+    apt-get install --assume-yes make
+    touch .installed
 fi
 
-JUJU_DISPATCH_PATH="${JUJU_DISPATCH_PATH:-$0}" PYTHONPATH=lib:venv $PYTHON_BIN ./src/charm.py
+JUJU_DISPATCH_PATH="${JUJU_DISPATCH_PATH:-$0}" PYTHONPATH=lib:venv /usr/bin/env python3 ./src/charm.py