removed slurm errors

BiBiServ · Feb 8, 2024 · 880b6d0 · 880b6d0
1 parent a8f8e44
commit 880b6d0
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 13 deletions.
diff --git a/resources/playbook/roles/bibigrid/tasks/042-slurm.yml b/resources/playbook/roles/bibigrid/tasks/042-slurm.yml
@@ -12,17 +12,17 @@
 - name: Install Slurm package (and dependencies)
   apt:
     name:
-      - slurm-full
+      # - slurm-full
       - munge
 
-# - name: Download Slurm (TEMPORARY)
-#   get_url:
-#     url: "https://docs.cebitec.uni-bielefeld.de/s/FjCP3xQPPnBwSy9/download?path=%2F&files=slurm-full_23.11.0-0_amd64.deb"  # Replace with your package link
-#     dest: "/tmp/package.deb"  # Destination where the package will be saved
-# - name: Install Slurm package
-#   apt:
-#     deb: "/tmp/package.deb"
-#     state: present  # Install the package if not already installed
+- name: Download Slurm (TEMPORARY)
+  get_url:
+    url: "https://docs.cebitec.uni-bielefeld.de/s/FjCP3xQPPnBwSy9/download?path=%2F&files=slurm-full_23.11.0-0_amd64.deb"  # Replace with your package link
+    dest: "/tmp/package.deb"  # Destination where the package will be saved
+- name: Install Slurm package
+  apt:
+    deb: "/tmp/package.deb"
+    state: present  # Install the package if not already installed
 
 - name: Create new secret (Munge)
   copy:

diff --git a/resources/playbook/roles/bibigrid/templates/slurm/slurm.conf b/resources/playbook/roles/bibigrid/templates/slurm/slurm.conf
@@ -9,7 +9,7 @@ AuthAltParameters=jwt_key=/etc/slurm/jwt-secret.key
 ClusterName=bibigrid
 
 MpiDefault=none
-ProctrackType=proctrack/linuxproc
+ProctrackType=proctrack/cgroup # linuxproc
 ReturnToService=2
 SwitchType=switch/none
 TaskPlugin=task/none
@@ -61,7 +61,7 @@ AccountingStorageHost={{ hostvars[groups.master.0].name | lower }}
 AccountingStorageUser={{ slurm_conf.db_user }}
 
 # LOGGING
-SlurmctldDebug=info
+SlurmctldDebug=debug # info
 SlurmctldLogFile=/var/log/slurm/slurmctld.log
 SlurmdDebug=info
 SlurmdLogFile=/var/log/slurm/slurmd.log
@@ -102,7 +102,7 @@ SuspendExcNodes={{ hostvars[groups.master.0].name }}
 # Maximum number of nodes
 TreeWidth= {{ slurm_conf.elastic_scheduling.TreeWidth }}
 # Do not cache dns names
-CommunicationParameters=NoAddrCache
+# REMOVED CommunicationParameters=NoAddrCache
 # Mark node status idle on suspend so DOWN is removed
 SlurmctldParameters=idle_on_node_suspend
 # Show slurm nodes all the time
@@ -113,4 +113,4 @@ ResumeFailProgram=/opt/slurm/fail.sh
 # job container
 # TO BE TESTED
 JobContainerType=job_container/tmpfs
-PrologFlags=Contain
+PrologFlags=Contain