[PATCH] Fix save/restore failure cleanup

[PATCH] Fix save/restore failure cleanup

[john.levon]

# HG changeset patch
# User john.levon@sun.com
# Date 1201883258 28800
# Node ID 904da511efb367ef015fc71ac551eda9d73c83da
# Parent  db45491fd981542e1197aa6cf78a8d2215336cc5
Fix save/restore failure cleanup

The save failure cleanup introduced in 13543:207523704fb1 is incorrect:
if we didn't get as far as actually suspending the domain, then the
guest domain will not be expecting the devices to be removed (seen on
both Linux and Solaris, which don't expect a 'Closing' state when they
hold the device open). Only re-jig devices if we definitely shut the
domain down.

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

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
@@ -67,6 +67,8 @@ def save(fd, dominfo, network, live, dst
     # thing is useful for debugging.
     dominfo.setName('migrating-' + domain_name)
 
+    done_suspend = 0
+
     try:
         dominfo.migrateDevices(network, dst, DEV_MIGRATE_STEP1, domain_name)
 
@@ -94,6 +96,7 @@ def save(fd, dominfo, network, live, dst
                 log.debug("Suspending %d ...", dominfo.getDomid())
                 dominfo.shutdown('suspend')
                 dominfo.waitForShutdown()
+                done_suspend = 1
                 dominfo.migrateDevices(network, dst, DEV_MIGRATE_STEP2,
                                        domain_name)
                 log.info("Domain %d suspended.", dominfo.getDomid())
@@ -140,9 +143,14 @@ def save(fd, dominfo, network, live, dst
         log.exception("Save failed on domain %s (%s).", domain_name,
                       dominfo.getDomid())
         
-        dominfo.resumeDomain()
-        log.debug("XendCheckpoint.save: resumeDomain")
-
+        # If we didn't get as far as suspending the domain (for
+        # example, we couldn't balloon enough memory for the new
+        # domain), then we don't want to re-plumb the devices, as the
+        # domU will not be expecting it.
+        if done_suspend:
+            log.debug("XendCheckpoint.save: resumeDomain")
+            dominfo.resumeDomain()
+ 
         try:
             dominfo.setName(domain_name)
         except: