Claude
3265ed80fd
capture-watchdog.sh: long-running script that checks the newest JPEG mtime in each camera's output directory every CAPTURE_STALE_SECS/3 seconds (min 5s). Sends a stall notification via notify.sh if no new frame has arrived within CAPTURE_STALE_SECS. Sends a recovery notification once new frames resume. Only alerts if the camera was previously working (avoids false positives on first start or overnight before the first frame of the day). sky-cam.conf: CAPTURE_STALE_SECS=30 added next to CAPTURE_INTERVAL with a note that it should be at least 2x the interval. install.sh: generates sky-cam-watchdog-<cam>.service for every camera that has a RTSP URL configured. The watchdog service starts after and alongside the capture service, restarts on failure, and is enabled/started with the same loop as the capture service. README.md: note about watchdog and journalctl command for its logs. https://claude.ai/code/session_01C4jbd3waXG3eKZYbGUjLUQ
63 lines
2.3 KiB
Bash
Executable File
63 lines
2.3 KiB
Bash
Executable File
#!/bin/bash
|
|
# capture-watchdog.sh — monitor image output for a camera and send a
|
|
# notification if no new frame arrives within CAPTURE_STALE_SECS seconds.
|
|
# Sends a recovery notification once capture resumes.
|
|
#
|
|
# Runs as a long-running systemd service alongside sky-cam-capture-<cam>.
|
|
# One instance per camera, camera name passed as $1.
|
|
|
|
set -euo pipefail
|
|
|
|
SCRIPT_DIR="$(dirname "$(realpath "$0")")"
|
|
source "$SCRIPT_DIR/sky-cam.conf"
|
|
export TZ="$TIMEZONE"
|
|
|
|
CAM="${1:-$SUNRISE_CAM}"
|
|
STALE_SECS="${CAPTURE_STALE_SECS:-30}"
|
|
CHECK_INTERVAL=$(( STALE_SECS / 3 ))
|
|
[ "$CHECK_INTERVAL" -lt 5 ] && CHECK_INTERVAL=5
|
|
|
|
echo "Watchdog started for ${CAM} — alerting after ${STALE_SECS}s without a new frame"
|
|
|
|
last_good=0 # epoch seconds of the newest frame we have seen
|
|
stale_notified=false
|
|
|
|
while true; do
|
|
sleep "$CHECK_INTERVAL"
|
|
|
|
today=$(date +%Y-%m-%d)
|
|
dir="$BASE_DIR/$CAM/$today"
|
|
now=$(date +%s)
|
|
|
|
# Find newest JPEG in today's directory
|
|
if [ -d "$dir" ]; then
|
|
latest_file=$(ls -t "$dir"/*.jpg 2>/dev/null | head -1 || true)
|
|
if [ -n "$latest_file" ]; then
|
|
latest_mtime=$(stat -c %Y "$latest_file")
|
|
if [ "$latest_mtime" -gt "$last_good" ]; then
|
|
last_good=$latest_mtime
|
|
# Recovery — was stale, now seeing new frames again
|
|
if $stale_notified; then
|
|
stale_for=$(( now - last_good + STALE_SECS ))
|
|
echo "Capture resumed for ${CAM} after ~${stale_for}s stall"
|
|
"$SCRIPT_DIR/notify.sh" "Capture resumed: ${CAM}" \
|
|
"New frames arriving again after ~${stale_for}s without capture" || true
|
|
stale_notified=false
|
|
fi
|
|
fi
|
|
fi
|
|
fi
|
|
|
|
# Only alert if we have seen at least one frame (camera was working)
|
|
# and now there's a gap longer than the threshold
|
|
if [ "$last_good" -gt 0 ]; then
|
|
age=$(( now - last_good ))
|
|
if [ "$age" -gt "$STALE_SECS" ] && ! $stale_notified; then
|
|
echo "Capture stalled for ${CAM} — last frame ${age}s ago"
|
|
"$SCRIPT_DIR/notify.sh" "WARNING: capture stalled — ${CAM}" \
|
|
"No new frames for ${age}s — camera may be offline or stream lost" || true
|
|
stale_notified=true
|
|
fi
|
|
fi
|
|
done
|