Restart without reboot; retrievable logs incl. mpv exit reasons
Two related gaps on the headless kiosk: no way to restart the wall short of a full reboot, and no way to see why a stream keeps flapping (the daemon's stderr goes to sway on tty1, and mpv's stderr was discarded). Restart in place: - `rtsp-streamer restart` sends a control-socket command; the daemon tears down its mpv children and syscall.Exec's the on-disk binary. Same PID, same parent (sway), same env — keeps WAYLAND_DISPLAY/ SWAYSOCK and comes back up on the new binary, no reboot. Handles the os.Executable() "(deleted)" sentinel from make install's rename. - sway config now launches the daemon in a relaunch loop, so a crash (or the restart) auto-recovers instead of leaving a black screen. - `make deploy` now does `install` + `restart` instead of restarting getty@tty1 (which left stale duplicate sessions and forced reboots). Retrievable logs: - New internal/logbuf ring; the daemon tees slog output into it and serves the tail over the socket via `rtsp-streamer logs [-n N]` — readable over SSH, no file wrangling, no reboot. - Capture the tail of each mpv's stderr and log its last line when the process exits, so "mpv exited, will restart" now carries the reason (connection refused, unsupported codec, 401, ...). This is the diagnostic for a single tile going unhealthy repeatedly. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -13,11 +13,13 @@ import (
|
||||
"os"
|
||||
"os/exec"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"sync"
|
||||
"syscall"
|
||||
"time"
|
||||
|
||||
"github.com/lwoodard/rtsp-streamer/internal/config"
|
||||
"github.com/lwoodard/rtsp-streamer/internal/logbuf"
|
||||
)
|
||||
|
||||
// Player supervises a single mpv instance bound to one grid slot.
|
||||
@@ -38,6 +40,7 @@ type Player struct {
|
||||
mu sync.Mutex
|
||||
cmd *exec.Cmd
|
||||
started time.Time
|
||||
stderr *logbuf.Writer // tail of the current process's stderr
|
||||
}
|
||||
|
||||
// New creates a player. runDir is where the mpv IPC socket lives.
|
||||
@@ -143,15 +146,19 @@ func (p *Player) start(ctx context.Context) error {
|
||||
cmd.WaitDelay = 2 * time.Second
|
||||
// Inherit the caller's environment (WAYLAND_DISPLAY etc. must be set).
|
||||
cmd.Env = os.Environ()
|
||||
// Discard mpv's chatty stdout/stderr; errors surface via exit code.
|
||||
// Keep the tail of mpv's stderr so a crash's reason (bad codec, dropped
|
||||
// connection, auth failure) is logged when the process exits, instead of
|
||||
// vanishing. Cheap: a small ring, not the whole firehose.
|
||||
stderr := logbuf.New(30)
|
||||
cmd.Stdout = nil
|
||||
cmd.Stderr = nil
|
||||
cmd.Stderr = stderr
|
||||
if err := cmd.Start(); err != nil {
|
||||
return fmt.Errorf("starting mpv: %w", err)
|
||||
}
|
||||
p.mu.Lock()
|
||||
p.cmd = cmd
|
||||
p.started = time.Now()
|
||||
p.stderr = stderr
|
||||
p.mu.Unlock()
|
||||
p.log.Info("mpv started", "pid", cmd.Process.Pid)
|
||||
return nil
|
||||
@@ -177,6 +184,7 @@ func (p *Player) Supervise(ctx context.Context) {
|
||||
}
|
||||
p.mu.Lock()
|
||||
cmd := p.cmd
|
||||
stderr := p.stderr
|
||||
p.mu.Unlock()
|
||||
err := cmd.Wait()
|
||||
|
||||
@@ -187,7 +195,10 @@ func (p *Player) Supervise(ctx context.Context) {
|
||||
if ctx.Err() != nil {
|
||||
return
|
||||
}
|
||||
p.log.Warn("mpv exited, will restart", "err", err, "after", backoff)
|
||||
// Surface the last line(s) mpv printed — that's where the failure
|
||||
// reason lives (connection refused, unsupported codec, 401, ...).
|
||||
reason := lastLine(stderr)
|
||||
p.log.Warn("mpv exited, will restart", "err", err, "after", backoff, "reason", reason)
|
||||
if !sleep(ctx, backoff) {
|
||||
return
|
||||
}
|
||||
@@ -271,6 +282,22 @@ func (p *Player) Healthy() bool {
|
||||
return reply["error"] == "success"
|
||||
}
|
||||
|
||||
// lastLine returns the most recent non-empty stderr line mpv emitted, trimmed,
|
||||
// or "" if there was none. mpv prints its fatal error last, so the tail is the
|
||||
// useful part.
|
||||
func lastLine(w *logbuf.Writer) string {
|
||||
if w == nil {
|
||||
return ""
|
||||
}
|
||||
lines := w.Lines(0)
|
||||
for i := len(lines) - 1; i >= 0; i-- {
|
||||
if s := strings.TrimSpace(lines[i]); s != "" {
|
||||
return s
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
func sleep(ctx context.Context, d time.Duration) bool {
|
||||
t := time.NewTimer(d)
|
||||
defer t.Stop()
|
||||
|
||||
Reference in New Issue
Block a user