[Xen-devel] [PATCH] Time-out if guest fails to suspend

[John Levon <john.levon@xxxxxxx>]

# HG changeset patch
# User John Levon <john.levon@xxxxxxx>
# Date 1236822206 25200
# Node ID 7bc32ac888a5088e6c704252675e49468cdf7456
# Parent  0bcb69805b1e11a8b36d92362d74d95653458589
Time-out if guest fails to suspend

If a guest fails to re-write control/shutdown node within a minute,
fail the suspend operation.

Signed-off-by: John Levon <john.levon@xxxxxxx>

diff --git a/tools/python/xen/xend/XendCheckpoint.py 
b/tools/python/xen/xend/XendCheckpoint.py
--- a/tools/python/xen/xend/XendCheckpoint.py
+++ b/tools/python/xen/xend/XendCheckpoint.py
@@ -114,7 +114,7 @@ def save(fd, dominfo, network, live, dst
             if line == "suspend":
                 log.debug("Suspending %d ...", dominfo.getDomid())
                 dominfo.shutdown('suspend')
-                dominfo.waitForShutdown()
+                dominfo.waitForSuspend()
             if line in ('suspend', 'suspended'):
                 dominfo.migrateDevices(network, dst, DEV_MIGRATE_STEP2,
                                        domain_name)
diff --git a/tools/python/xen/xend/XendDomainInfo.py 
b/tools/python/xen/xend/XendDomainInfo.py
--- a/tools/python/xen/xend/XendDomainInfo.py
+++ b/tools/python/xen/xend/XendDomainInfo.py
@@ -2607,6 +2607,31 @@ class XendDomainInfo:
         finally:
             self.state_updated.release()
 
+    def waitForSuspend(self):
+        """Wait for the guest to respond to a suspend request by
+        shutting down.  If the guest hasn't re-written control/shutdown
+        after a certain amount of time, it's obviously not listening and
+        won't suspend, so we give up.  HVM guests with no PV drivers
+        should already be shutdown.
+        """
+        state = "suspend"
+        nr_tries = 60
+
+        self.state_updated.acquire()
+        try:
+            while self._stateGet() in (DOM_STATE_RUNNING,DOM_STATE_PAUSED):
+                self.state_updated.wait(1.0)
+                if state == "suspend":
+                    if nr_tries == 0:
+                        msg = ('Timeout waiting for domain %s to suspend'
+                            % self.domid)
+                        self._writeDom('control/shutdown', '')
+                        raise XendError(msg)
+                    state = self.readDom('control/shutdown')
+                    nr_tries -= 1
+        finally:
+            self.state_updated.release()
+
     #
     # TODO: recategorise - called from XendCheckpoint
     # 

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel