[Xen-devel] [PATCH] Do not destroy domains that timeout when shutting down

[john.levon@xxxxxxx]

# HG changeset patch
# User john.levon@xxxxxxx
# Date 1180046767 25200
# Node ID bfd2245773b4772671a5aa7772ff88554292de34
# Parent  c7dee061ade1ac0c4ef417ecadd98f048ddece96
Do not destroy domains that timeout when shutting down

Instead of violently destroying a domain that is not responding to a shutdown
request, rename the domain to indicate the problem and leave it alone; this
allows the admin to make corrective actions (which may or may not include
destroying the domain).

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

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
@@ -351,6 +351,7 @@ class XendDomainInfo:
         self.vmWatch = None
         self.shutdownWatch = None
         self.shutdownStartTime = None
+        self.unresponsive = False
         self._resume = resume
 
         self.state = DOM_STATE_HALTED
@@ -998,21 +999,25 @@ class XendDomainInfo:
                 # failed.  Ignore this domain.
                 pass
             else:
-                # Domain is alive.  If we are shutting it down, then check
-                # the timeout on that, and destroy it if necessary.
+                # Domain is alive.
                 if xeninfo['paused']:
                     self._stateSet(DOM_STATE_PAUSED)
                 else:
                     self._stateSet(DOM_STATE_RUNNING)
                     
-                if self.shutdownStartTime:
+                if self.shutdownStartTime and not self.unresponsive:
                     timeout = (SHUTDOWN_TIMEOUT - time.time() +
                                self.shutdownStartTime)
                     if timeout < 0:
+                        # The domain is not responding to shutdown requests.
+                        # Log a message, and rename the domain to indicate the
+                        # state; we keep the domain running, however, to
+                        # allow corrective action.
                         log.info(
                             "Domain shutdown timeout expired: name=%s id=%s",
                             self.info['name_label'], self.domid)
-                        self.destroy()
+                        self.setName('unresponsive-' + self.getName())
+                        self.unresponsive = True
         finally:
             self.refresh_shutdown_lock.release()
 
@@ -1299,6 +1304,7 @@ class XendDomainInfo:
         log.debug('XendDomainInfo.constructDomain')
 
         self.shutdownStartTime = None
+        self.unresponsive = False
 
         image_cfg = self.info.get('image', {})
         hvm = image_cfg.has_key('hvm')

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