From 34c5b688ace86c8b863638cb7d617125eae4ddaf Mon Sep 17 00:00:00 2001
From: Mauricio Siu <47042324+Siumauricio@users.noreply.github.com>
Date: Tue, 11 Aug 2026 20:40:24 -0600
Subject: [PATCH] fix: docker cleanup hangs silently on false-positive
 busy-wait match (#5051)

dockerSafeExec's busy-wait matched any process with "docker <letter>"
anywhere in its argv (e.g. Grafana's --packaging=docker cfg:...),
causing the wait loop to spin forever. Anchor the match to the actual
docker binary (argv[0]) instead, and add a MAX_WAIT ceiling so a
genuinely stuck docker process can't hang cleanup indefinitely either.

Also log failures in cleanupAll's catch instead of swallowing them,
since the scheduled cleanup path only goes through this function.

Fixes #5044
---
 packages/server/src/utils/docker/utils.ts | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/packages/server/src/utils/docker/utils.ts b/packages/server/src/utils/docker/utils.ts
index 09fe877cd..42fb252f9 100644
--- a/packages/server/src/utils/docker/utils.ts
+++ b/packages/server/src/utils/docker/utils.ts
@@ -153,19 +153,27 @@ export const getContainerByName = (name: string): Promise<ContainerInfo> => {
  */
 export const dockerSafeExec = (exec: string) => `
 CHECK_INTERVAL=10
+MAX_WAIT=300
+WAITED=0
 
 echo "Preparing for execution..."
 
 while true; do
-    PROCESSES=$(ps aux | grep -E "^.*docker [A-Za-z]" | grep -v grep)
+    PROCESSES=$(ps -eo args | awk '$1 ~ /(^|\\/)docker$/')
 
     if [ -z "$PROCESSES" ]; then
         echo "Docker is idle. Starting execution..."
         break
-    else
-        echo "Docker is busy. Will check again in $CHECK_INTERVAL seconds..."
-        sleep $CHECK_INTERVAL
     fi
+
+    if [ "$WAITED" -ge "$MAX_WAIT" ]; then
+        echo "Docker still busy after \${MAX_WAIT}s, proceeding anyway." >&2
+        break
+    fi
+
+    echo "Docker is busy. Will check again in $CHECK_INTERVAL seconds..."
+    sleep $CHECK_INTERVAL
+    WAITED=$((WAITED + CHECK_INTERVAL))
 done
 
 ${exec}
@@ -323,7 +331,12 @@ export const cleanupAll = async (serverId?: string) => {
 			} else {
 				await execAsync(dockerSafeExec(command));
 			}
-		} catch {}
+		} catch (error) {
+			console.error(
+				`Docker cleanup: "${key}" failed${serverId ? ` on server ${serverId}` : ""}`,
+				error,
+			);
+		}
 	}
 };