From 1e95dd7b2f630f2764cc7b8d917d27e158c18018 Mon Sep 17 00:00:00 2001
From: Kris Lamoureux <kris@lamoureux.io>
Date: Sun, 18 Aug 2024 00:00:08 -0400
Subject: [PATCH] Fix munge key race condition and update docs

- Add sleep to prevent munge.key race condition
- Warn about CPU override conflicts in README
- Update README with CPU config details for minimal setup
- Correct `less` command examples for prime number output
- Force update slurm/cgroups configs in the provision script
---
 README.md    | 11 ++++++++++-
 provision.sh | 11 ++++++-----
 slurm.conf   |  2 +-
 3 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index 89ae680..183c7a8 100644
--- a/README.md
+++ b/README.md
@@ -63,7 +63,7 @@ By default, each node is allocated:
 4. View the resulting prime numbers found, check `ls` for exact filenames
 
        less slurm-1_0.out
-       less slurm-2_1.out
+       less slurm-1_1.out
 
 ### Configuration Tool
 
@@ -96,6 +96,10 @@ ignored by .gitignore. Be cautious when using this command as it will delete
 files that are not tracked by Git. Use the `-n` flag to dry-run first.
 
 ## Global Overrides
+
+**WARNING:** Always update `slurm.conf` to match any CPU overrides to prevent
+resource allocation conflicts.
+
 If you wish to override the default settings on a global level,
 you can do so by creating a `.settings.yml` file based on the provided
 `example-.settings.yml` file:
@@ -125,6 +129,11 @@ file without modifications. This results in a cluster configuration using only
 1 vCPU and 1 GB RAM per node (totaling 4 threads/cores and 4 GB RAM), allowing
 basic operation on modest hardware.
 
+When using this minimal setup with 1 vCPU, you'll need to update the `slurm.conf` file.
+Apply the following change to the default `slurm.conf`:
+
+	sed -i 's/CPUs=2/CPUs=1/g' slurm.conf
+
 ### Slurm Settings Overrides
 - `SLURM_NODES`
   - Default: `4`
diff --git a/provision.sh b/provision.sh
index 2101a90..795f903 100755
--- a/provision.sh
+++ b/provision.sh
@@ -46,12 +46,12 @@ fi
 dpkg -s slurm-client &>/dev/null || apt-get install -y slurm-client
 
 # Create directories for Slurm
-mkdir -p /var/spool/slurm /var/log/slurm /etc/slurm
-chown slurm:slurm /var/spool/slurm /var/log/slurm /etc/slurm
+mkdir -p /var/spool/slurm /etc/slurm
+chown slurm:slurm /var/spool/slurm /etc/slurm
 
 # Copy slurm.conf and cgroup.conf
-cp -u /vagrant/slurm.conf /etc/slurm/slurm.conf
-cp -u /vagrant/cgroup.conf /etc/slurm/cgroup.conf
+cp -f /vagrant/slurm.conf /etc/slurm/slurm.conf
+cp -f /vagrant/cgroup.conf /etc/slurm/cgroup.conf
 chown slurm:slurm /etc/slurm/slurm.conf /etc/slurm/cgroup.conf
 chmod 644 /etc/slurm/slurm.conf /etc/slurm/cgroup.conf
 
@@ -107,7 +107,8 @@ else
     sleep 10
   done
 
-  # Enable/start/test munge service
+  # Enable/start munge service
+  sleep 3
   cp -f /vagrant/munge.key /etc/munge/munge.key
   chown munge:munge /etc/munge/munge.key
   chmod 400 /etc/munge/munge.key
diff --git a/slurm.conf b/slurm.conf
index cbfb6fb..5a48aca 100644
--- a/slurm.conf
+++ b/slurm.conf
@@ -1,4 +1,4 @@
-#slurm.conf file generated by configurator easy.html.
+# slurm.conf file generated by configurator easy.html.
 # Put this file on all nodes of your cluster.
 # See the slurm.conf man page for more information.
 #