[bitbake-devel] [PATCH] runqueue: Really fix sigchld handling

[Richard Purdie]

There are several problems. Firstly, a return value of "None" can mean
there is a C signal handler installed so we need to better handle that
case. signal.SIG_DFL is 0 which equates to false so we also need to
handle that by testing explicitly for None.

Finally, the signal handler *must* call waitpid on all child processes
else it will just get called repeatedly, leading to the hanging behaviour
we've been seeing. The solution is to only error for the worker children,
we warn about any other stray children which we'll have to figure out the
sources of in due course.

Hopefully this patch gets things working again properly though.

Signed-off-by: Richard Purdie <richard.purdie at linuxfoundation.org>
---
diff --git a/bitbake/lib/bb/runqueue.py b/bitbake/lib/bb/runqueue.py
index 055db48..3ab5439 100644
--- a/bitbake/lib/bb/runqueue.py
+++ b/bitbake/lib/bb/runqueue.py
@@ -914,32 +914,32 @@ class RunQueue:
         workerpipe.close()
 
     def sigchild_exception(self, *args, **kwargs):
-        for w in [self.worker, self.fakeworker]:
-            if not w:
-                continue
+        pid = -1
+        while pid:
             try:
-                pid, status = os.waitpid(w.pid, os.WNOHANG)
+                pid, status = os.waitpid(-1, os.WNOHANG)
                 if pid != 0 and not self.teardown:
+                    name = None
                     if self.worker and pid == self.worker.pid:
                         name = "Worker"
                     elif self.fakeworker and pid == self.fakeworker.pid:
                         name = "Fakeroot"
                     else:
-                        name = "Unknown"
-                    bb.error("%s process (%s) exited unexpectedly (%s), shutting down..." % (name, pid, str(status)))
-                    self.finish_runqueue(True)
+                        bb.warn("Unknown process (%s) exited unexpectedly (%s), shutting down..." % (pid, str(status)))
+                    if name and not self.teardown:
+                        bb.error("%s process (%s) exited unexpectedly (%s), shutting down..." % (name, pid, str(status)))
+                        self.finish_runqueue(True)
             except OSError:
-                pid = False
-        if callable(self.oldsigchld):
-            self.oldsigchld(*args, **kwargs)
+                return
 
     def start_worker(self):
         if self.worker:
             self.teardown_workers()
         self.teardown = False
-        if not self.oldsigchld:
-            self.oldsigchld = signal.getsignal(signal.SIGCHLD)
-            signal.signal(signal.SIGCHLD, self.sigchild_exception)
+        if self.oldsigchld is None:
+            self.oldsigchld = signal.signal(signal.SIGCHLD, self.sigchild_exception)
+            if self.oldsigchld is None:
+                self.oldsigchld = signal.SIG_DFL
         self.worker, self.workerpipe = self._start_worker()
 
     def start_fakeworker(self, rqexec):
@@ -948,7 +948,7 @@ class RunQueue:
 
     def teardown_workers(self):
         self.teardown = True
-        if self.oldsigchld:
+        if self.oldsigchld is not None:
             signal.signal(signal.SIGCHLD, self.oldsigchld)
             self.oldsigchld = None
         self._teardown_worker(self.worker, self.workerpipe)