mavgpud: a yield stops writing a core and reads as a yield (V-491)
llama-server aborts inside its own static teardown on SIGTERM — the handler calls exit(), stream_session_manager's destructor throws, and the process dies "signal: aborted (core dumped)". mavgpud sends that signal on every eviction, so a routine yield wrote a multi-gigabyte core into systemd-coredump and logged the same line a real crash would. LimitCORE=0 in the unit stops the disk cost. A yielding flag, set by stop and cleared by start, makes the log distinguish the two: only an exit we did not ask for is still reported as an exit. Not filed upstream. Searched ggml-org/llama.cpp for "ggml_uncaught_exception" with SIGTERM and for stream_session_manager and found nothing matching, so the issue still wants writing — by someone with an account on that tracker, which is why it is not in this commit.
This commit is contained in:
+17
-3
@@ -24,7 +24,12 @@ type runner struct {
|
||||
mu sync.Mutex
|
||||
cmd *exec.Cmd
|
||||
ready bool
|
||||
http *http.Client
|
||||
// yielding — stop() has sent the signal and the exit that follows is ours.
|
||||
// llama-server aborts on SIGTERM (its static teardown throws, upstream
|
||||
// ggml-org/llama.cpp), so a routine yield and a real crash produce the same
|
||||
// "signal: aborted" and used to log identically (Vikunja #491).
|
||||
yielding bool
|
||||
http *http.Client
|
||||
}
|
||||
|
||||
func newRunner(bin string, args []string, readyURL string) *runner {
|
||||
@@ -70,13 +75,18 @@ func (r *runner) start() error {
|
||||
if err := cmd.Start(); err != nil {
|
||||
return err
|
||||
}
|
||||
r.cmd, r.ready = cmd, false
|
||||
r.cmd, r.ready, r.yielding = cmd, false, false
|
||||
log.Printf("mavgpud: started llama-server pid=%d", cmd.Process.Pid)
|
||||
go func() {
|
||||
err := cmd.Wait()
|
||||
r.mu.Lock()
|
||||
r.cmd, r.ready = nil, false
|
||||
yielded := r.yielding
|
||||
r.cmd, r.ready, r.yielding = nil, false, false
|
||||
r.mu.Unlock()
|
||||
if yielded {
|
||||
log.Printf("mavgpud: llama-server stopped, card yielded (%v)", err)
|
||||
return
|
||||
}
|
||||
log.Printf("mavgpud: llama-server exited: %v", err)
|
||||
}()
|
||||
return nil
|
||||
@@ -90,6 +100,10 @@ func (r *runner) stop(grace time.Duration) {
|
||||
r.mu.Lock()
|
||||
cmd := r.cmd
|
||||
r.ready = false
|
||||
if cmd != nil && cmd.Process != nil {
|
||||
// The exit that follows is ours, not a crash.
|
||||
r.yielding = true
|
||||
}
|
||||
r.mu.Unlock()
|
||||
if cmd == nil || cmd.Process == nil {
|
||||
return
|
||||
|
||||
Reference in New Issue
Block a user