From 5ae0da50a1475885d9f3f60b47d7e7c990f5bfe3 Mon Sep 17 00:00:00 2001
From: Azreen Zaman <azreenzaman@microsoft.com>
Date: Tue, 19 May 2026 16:01:04 -0400
Subject: [PATCH 1/2] Add retry logic to sacctmgr ping in start-services.sh

---
 azure-slurm-install/start-services.sh | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/azure-slurm-install/start-services.sh b/azure-slurm-install/start-services.sh
index 63b29405..e5bd6ddc 100644
--- a/azure-slurm-install/start-services.sh
+++ b/azure-slurm-install/start-services.sh
@@ -7,13 +7,25 @@ run_slurmdbd_via_systemctl() {
     echo "Starting slurmdbd via systemctl..."
     systemctl start slurmdbd
 
-    # Verify slurmdbd is responding
-    sleep 10
-    if ! sacctmgr ping > /dev/null 2>&1; then
-        echo "ERROR: slurmdbd started but is not responding to sacctmgr ping"
+    # Verify slurmdbd is responding with retry logic
+    attempts=3
+    delay=5
+    set +e
+    for i in $( seq 1 $attempts ); do
+        echo $i/$attempts sleeping $delay seconds before running sacctmgr ping
+        sleep $delay
+        sacctmgr ping > /dev/null 2>&1
+        if [ $? == 0 ]; then
+            echo "slurmdbd is running and responding to ping"
+            set -e
+            return 0
+        fi
+    done
+
+    if [ $i == $attempts ] && [ $? != 0 ]; then
+        echo "ERROR: slurmdbd started but is not responding to sacctmgr ping after $attempts attempts"
         exit 2
     fi
-    echo "slurmdbd is running and responding to ping"
 }
 
 run_slurmdbd() {

From 1adce12dac84033489f7a05a23274c4907974118 Mon Sep 17 00:00:00 2001
From: Azreen  Zaman <azreenzaman@microsoft.com>
Date: Thu, 21 May 2026 14:30:38 -0400
Subject: [PATCH 2/2] Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
---
 azure-slurm-install/start-services.sh | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/azure-slurm-install/start-services.sh b/azure-slurm-install/start-services.sh
index e5bd6ddc..70679565 100644
--- a/azure-slurm-install/start-services.sh
+++ b/azure-slurm-install/start-services.sh
@@ -10,19 +10,21 @@ run_slurmdbd_via_systemctl() {
     # Verify slurmdbd is responding with retry logic
     attempts=3
     delay=5
+    ping_rc=0
     set +e
     for i in $( seq 1 $attempts ); do
         echo $i/$attempts sleeping $delay seconds before running sacctmgr ping
         sleep $delay
         sacctmgr ping > /dev/null 2>&1
-        if [ $? == 0 ]; then
+        ping_rc=$?
+        if [ "$ping_rc" -eq 0 ]; then
             echo "slurmdbd is running and responding to ping"
             set -e
             return 0
         fi
     done
 
-    if [ $i == $attempts ] && [ $? != 0 ]; then
+    if [ "$i" == "$attempts" ] && [ "$ping_rc" -ne 0 ]; then
         echo "ERROR: slurmdbd started but is not responding to sacctmgr ping after $attempts attempts"
         exit 2
     fi