fix message monitor (#104)

* fix message monitor

* Restart When Stale set to default-TRUE

* Restart When Stale is default `true`

README.md

@@ -278,7 +278,7 @@ You should now be feeding ADSB-ES & UAT to the "new" aggregators, FlightAware, a
 | `LAT`    | Latitude of your receiver. Only required if you want range statistics for InfluxDB, Prometheus, or tar1090/ultrafeeder graphs. | Unset   |
 | `LON`    | Longitude of your receiver. Only required if you want range statistics for InfluxDB, Prometheus, or tar1090/ultrafeeder graphs. | Unset   |
 | `DUMP978_MSG_MONITOR_INTERVAL` | Interval between runs of the Message Monitor that checks if new messages are received. Format of value is anything that is accepted by the Linux `sleep` command | Unset (30 minutes) |
-| `DUMP978_MSG_MONITOR_RESTART_WHEN_STALE` | If set to `true`/`on`/`yes`/`1`, the receiver process is restarted when no messages are received during the monitoring interval | Unset (`false`) |
+| `DUMP978_MSG_MONITOR_RESTART_WHEN_STALE` | If set to `true`/`on`/`yes`/`1`, the receiver process is restarted when no messages are received during the monitoring interval | `true` |
 
 ### `dump978-fa` General Options
 

rootfs/etc/s6-overlay/scripts/message-monitor

@@ -4,8 +4,13 @@
 source /scripts/common
 mkdir -p /run/stats
 s6wrap=(s6wrap --quiet --prepend="$(basename "$0")" --timestamps --args)
+
+# Adjustment Timeframe is the same as used for AutoGain, with a default of 0800-1800 "container time" if omitted
 READSB_AUTOGAIN_ADJUSTMENT_TIMEFRAME="${DUMP978_AUTOGAIN_ADJUSTMENT_TIMEFRAME:-${READSB_AUTOGAIN_ADJUSTMENT_TIMEFRAME:-0800-1800}}"
 
+# Restart When Stale is default-TRUE. This is acceptable - worst case, we'd restart the dump978 s6 service once every 30 minutes
+DUMP978_MSG_MONITOR_RESTART_WHEN_STALE="${DUMP978_MSG_MONITOR_RESTART_WHEN_STALE:-true}"
+
 while :
 do
     # Make sure we're receiving messages from the SDR
@@ -35,14 +40,16 @@ do
         "${s6wrap[@]}" echo "[STARTING] Receiver starting: No messages have been received as the container is still starting"
         new_msg_count=0
     elif (( new_msg_count == old_msg_count )); then
-        # only print and restart if we're within the adjustment timeframe
-        if (( $(date +%s) < $(date -d "${READSB_AUTOGAIN_ADJUSTMENT_TIMEFRAME%%-*} today" +%s) )); then
-            "${s6wrap[@]}" echo "[WARNING] Receiver appears stale: No messages received since last run of the Messages Monitor ($secs_since_last_check secs ago)"
-
+        "${s6wrap[@]}" echo "[WARNING] Receiver appears stale: No messages received since last run of the Messages Monitor ($secs_since_last_check secs ago)"
+        # only restart if we're within the adjustment timeframe
+        if (( $(date +%s) >= $(date -d "${READSB_AUTOGAIN_ADJUSTMENT_TIMEFRAME%%-*} today" +%s) )) \
+        && (( $(date +%s) <= $(date -d "${READSB_AUTOGAIN_ADJUSTMENT_TIMEFRAME##*-} today" +%s) )); then
             if chk_enabled "$DUMP978_MSG_MONITOR_RESTART_WHEN_STALE"; then
                 "${s6wrap[@]}" echo "[WARNING]                         Restarting the dump978 service..."
                 s6-svc -r /run/service/dump978 2>/dev/null || true
             fi
+        else
+            "${s6wrap[@]}" echo "                                  No action is taken since we're outside the Adjustment Timeframe of ${READSB_AUTOGAIN_ADJUSTMENT_TIMEFRAME}"
         fi
     elif (( new_msg_count > old_msg_count )); then
         "${s6wrap[@]}" echo "[INFO] Receiver is OK: $(( new_msg_count - old_msg_count )) messages received since last run of the Messages Monitor ($secs_since_last_check secs ago)"