Last active
October 27, 2025 03:12
-
-
Save afiqiqmal/274940cee7f37517ab217fc023514752 to your computer and use it in GitHub Desktop.
Monitor Supervisor Zombie Process
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| * * * * * /etc/supervisor/supervisord_watchdog.sh | |
| * 0,3,6 * * * service supervisord restart >> /var/log/supervisord_monitor/monitor.log 2>&1 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/bin/bash | |
| # Variables | |
| LOG_DIR="/var/log/supervisord_monitor" | |
| LOG_FILE="$LOG_DIR/monitor.log" | |
| SUPERVISORD_SERVICE="supervisord" | |
| TIMEOUT_CMD="/usr/bin/timeout" | |
| SUPERVISORCTL_CMD="/usr/local/bin/supervisorctl" | |
| TIMEOUT=5 # seconds | |
| TIMESTAMP=$(date '+%Y-%m-%d %H:%M:%S') | |
| DATE_TAG_FILE="$LOG_DIR/.last_purge_date" | |
| # Ensure log directory exists | |
| mkdir -p "$LOG_DIR" | |
| # --- Daily log purge --- | |
| CURRENT_DATE=$(date +%Y-%m-%d) | |
| if [ ! -f "$DATE_TAG_FILE" ] || [ "$CURRENT_DATE" != "$(cat "$DATE_TAG_FILE")" ]; then | |
| echo "$TIMESTAMP - Rotating monitor log (new day detected: $CURRENT_DATE)" > "$LOG_FILE" | |
| echo "$CURRENT_DATE" > "$DATE_TAG_FILE" | |
| fi | |
| # --- Check supervisord process --- | |
| if ! pgrep -x "$SUPERVISORD_SERVICE" > /dev/null; then | |
| echo "$TIMESTAMP - ERROR: supervisord process not found, attempting restart..." >> "$LOG_FILE" | |
| systemctl restart "$SUPERVISORD_SERVICE" | |
| echo "$TIMESTAMP - supervisord restarted." >> "$LOG_FILE" | |
| exit 1 | |
| fi | |
| # --- Check supervisord responsiveness --- | |
| if ! "$TIMEOUT_CMD" "$TIMEOUT" "$SUPERVISORCTL_CMD" version > /dev/null 2>&1; then | |
| echo "$TIMESTAMP - ERROR: supervisord unresponsive (no version response), attempting restart..." >> "$LOG_FILE" | |
| systemctl restart "$SUPERVISORD_SERVICE" | |
| echo "$TIMESTAMP - supervisord restarted." >> "$LOG_FILE" | |
| exit 1 | |
| fi | |
| # --- Check for zombie process --- | |
| if ps -o stat= -C "$SUPERVISORD_SERVICE" | grep -q 'Z'; then | |
| echo "$TIMESTAMP - ERROR: supervisord is a zombie, attempting restart..." >> "$LOG_FILE" | |
| systemctl restart "$SUPERVISORD_SERVICE" | |
| echo "$TIMESTAMP - supervisord restarted." >> "$LOG_FILE" | |
| exit 1 | |
| fi | |
| # --- Check supervisorctl availability --- | |
| if ! "$TIMEOUT_CMD" "$TIMEOUT" "$SUPERVISORCTL_CMD" version > /dev/null 2>&1; then | |
| echo "$TIMESTAMP - ERROR: supervisord unresponsive (no version response), attempting restart..." >> "$LOG_FILE" | |
| systemctl restart "$SUPERVISORD_SERVICE" | |
| echo "$TIMESTAMP - supervisord restarted." >> "$LOG_FILE" | |
| exit 1 | |
| fi | |
| # --- Check if processes are RUNNING --- | |
| if ! "$TIMEOUT_CMD" "$TIMEOUT" "$SUPERVISORCTL_CMD" status | grep -q RUNNING; then | |
| echo "$TIMESTAMP - ERROR: supervisor config process not running under supervisord." >> "$LOG_FILE" | |
| "$SUPERVISORCTL_CMD" restart all | |
| echo "$TIMESTAMP - supervisorctl process restarted." >> "$LOG_FILE" | |
| exit 1 | |
| fi | |
| # --- Success log --- | |
| echo "$TIMESTAMP - OK: supervisord is running and responsive." >> "$LOG_FILE" | |
| exit 0 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment