i0t/RTSP-Streamer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Harden health probe against false restarts

Browse Source 
Probe mpv-version (always present) instead of time-pos, which live
streams with caching off can report unavailable while playing fine —
that produced false unhealthy verdicts. Also require 3 consecutive
misses (~60s) before force-restarting a hung stream.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Levi Woodard
2026-07-01 19:41:48 -05:00
parent 0fb731a71e
commit eb05c48db8
2 changed files with 11 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
internal/daemon/daemon.go
View File

@@ -232,8 +232,10 @@ func (d *Daemon) healthLoop(ctx context.Context) {
continue continue
} }
stalls[p.Slot]++ stalls[p.Slot]++
if stalls[p.Slot] >= 2 { // Require three consecutive unresponsive probes (~60s) before
d.log.Warn("stream stalled, forcing restart", "slot", p.Slot, "camera", p.Name) // forcing a restart, so a brief IPC hiccup never bounces a stream.
if stalls[p.Slot] >= 3 {
d.log.Warn("stream hung, forcing restart", "slot", p.Slot, "camera", p.Name, "misses", stalls[p.Slot])
p.Stop() // Supervise relaunches p.Stop() // Supervise relaunches
stalls[p.Slot] = 0 stalls[p.Slot] = 0
} }

11
internal/player/player.go
View File

@@ -212,14 +212,17 @@ func (p *Player) Command(args ...any) (map[string]any, error) {
return nil, fmt.Errorf("no reply from mpv ipc") return nil, fmt.Errorf("no reply from mpv ipc")
} }
// Healthy probes mpv over IPC and reports whether it is actively playing (has // Healthy probes mpv over IPC and reports whether it is responsive. It queries
// a finite time position advancing). A false result signals the daemon to // a property that always exists (mpv-version) rather than time-pos, because a
// consider restarting the slot even if the process is still alive (frozen). // live stream with caching disabled can legitimately report time-pos as
// unavailable while playing fine — using it here caused false "unhealthy"
// verdicts and needless restarts. A false result now means mpv's IPC didn't
// answer at all, i.e. the process is genuinely hung.
func (p *Player) Healthy() bool { func (p *Player) Healthy() bool {
if !p.Running() { if !p.Running() {
return false return false
} }
reply, err := p.Command("get_property", "time-pos") reply, err := p.Command("get_property", "mpv-version")
if err != nil { if err != nil {
return false return false
} }