From f8421345a3f1ff0c1625931fea394265a4e32390 Mon Sep 17 00:00:00 2001
From: "justin.kruse" <justin.kruse@doosan.com>
Date: Tue, 27 Feb 2024 18:57:15 -0600
Subject: [PATCH] feat: add retry logic for dnf operations

---
 modules/runners/templates/user-data.sh | 39 +++++++++++++++++++++++---
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/modules/runners/templates/user-data.sh b/modules/runners/templates/user-data.sh
index 3de7f41273..68edb79b0a 100644
--- a/modules/runners/templates/user-data.sh
+++ b/modules/runners/templates/user-data.sh
@@ -1,5 +1,22 @@
 #!/bin/bash -e
 
+install_with_retry() {
+  max_attempts=5
+  attempt_count=0
+  success=false
+  while [ $success = false ] && [ $attempt_count -le $max_attempts ]; do
+    echo "Attempting $attempt_count/$max_attempts: Installing $*"
+    dnf install -y $*
+  if [ $? -eq 0 ]; then
+      success=true
+    else
+      echo "Failed to install $1 - retrying"
+      attempt_count=$(( attempt_count + 1 ))
+      sleep 5
+    fi
+  done
+}
+
 exec > >(tee /var/log/user-data.log | logger -t user-data -s 2>/dev/console) 2>&1
 
 # AWS suggest to create a log for debug purpose based on https://aws.amazon.com/premiumsupport/knowledge-center/ec2-linux-log-user-data/
@@ -15,15 +32,29 @@ set -x
 
 ${pre_install}
 
-dnf upgrade-minimal -y
+max_attempts=5
+attempt_count=0
+success=false
+while [ $success = false ] && [ $attempt_count -le $max_attempts ]; do
+  echo "Attempting $attempt_count/$max_attempts: upgrade-minimal"
+  dnf upgrade-minimal -y
+if [ $? -eq 0 ]; then
+    success=true
+  else
+    echo "Failed to run `dnf upgrad-minimal -y` - retrying"
+    attempt_count=$(( attempt_count + 1 ))
+    sleep 5
+  fi
+done
 
 # Install docker
-dnf install -y docker
+install_with_retry docker
+
 service docker start
 usermod -a -G docker ec2-user
 
-dnf install -y amazon-cloudwatch-agent jq git
-dnf install -y --allowerasing curl
+install_with_retry amazon-cloudwatch-agent jq git
+install_with_retry --allowerasing curl
 
 user_name=ec2-user