xen/xenpaging.autostart_delay.patch

Subject: xenpaging: add dynamic startup delay for xenpaging

This is a debug helper. Since the xenpaging support is still fragile, run
xenpaging at different stages in the bootprocess. Different delays will trigger
more bugs. This implementation starts without delay for 5 reboots, then
increments the delay by 0.1 seconds It uses xenstore for presistant storage of
delay values

TODO: find the correct place to remove the xenstore directory when the guest is shutdown or crashed

Signed-off-by: Olaf Hering <olaf@aepfle.de>

---
 tools/python/xen/xend/image.py |   33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

--- xen-4.0.1-testing.orig/tools/python/xen/xend/image.py
+++ xen-4.0.1-testing/tools/python/xen/xend/image.py
@@ -123,6 +123,19 @@ class ImageHandler:
 
         self.device_model = vmConfig['platform'].get('device_model')
         self.xenpaging = vmConfig['platform'].get('xenpaging')
+        if self.xenpaging:
+            self.xenpaging_delay = xstransact.Read("/local/domain/0/xenpaging/%s/xenpaging_delay" % self.vm.info['name_label'])
+            if self.xenpaging_delay == None:
+                log.warn("XXX creating /local/domain/0/xenpaging/%s" % self.vm.info['name_label'])
+                xstransact.Mkdir("/local/domain/0/xenpaging/%s" % self.vm.info['name_label'])
+                xstransact.Store("/local/domain/0/xenpaging/%s" % self.vm.info['name_label'], ('xenpaging_delay', '0.0'))
+                xstransact.Store("/local/domain/0/xenpaging/%s" % self.vm.info['name_label'], ('xenpaging_delay_inc', '0.1'))
+                xstransact.Store("/local/domain/0/xenpaging/%s" % self.vm.info['name_label'], ('xenpaging_delay_use', '5'))
+                xstransact.Store("/local/domain/0/xenpaging/%s" % self.vm.info['name_label'], ('xenpaging_delay_used', '0'))
+            self.xenpaging_delay = float(xstransact.Read("/local/domain/0/xenpaging/%s/xenpaging_delay" % self.vm.info['name_label']))
+            self.xenpaging_delay_inc = float(xstransact.Read("/local/domain/0/xenpaging/%s/xenpaging_delay_inc" % self.vm.info['name_label']))
+            self.xenpaging_delay_use = int(xstransact.Read("/local/domain/0/xenpaging/%s/xenpaging_delay_use" % self.vm.info['name_label']))
+            self.xenpaging_delay_used = int(xstransact.Read("/local/domain/0/xenpaging/%s/xenpaging_delay_used" % self.vm.info['name_label']))
 
         self.display = vmConfig['platform'].get('display')
         self.xauthority = vmConfig['platform'].get('xauthority')
@@ -401,6 +414,17 @@ class ImageHandler:
             return
         if self.xenpaging_pid:
             return
+        if self.xenpaging_delay_used < self.xenpaging_delay_use:
+            self.xenpaging_delay_used += 1
+        else:
+            self.xenpaging_delay_used = 0
+            self.xenpaging_delay += self.xenpaging_delay_inc
+        log.info("delay_used %s" % self.xenpaging_delay_used)
+        log.info("delay_use %s" % self.xenpaging_delay_use)
+        log.info("delay %s" % self.xenpaging_delay)
+        log.info("delay_inc %s" % self.xenpaging_delay_inc)
+        xstransact.Store("/local/domain/0/xenpaging/%s" % self.vm.info['name_label'], ('xenpaging_delay', self.xenpaging_delay))
+        xstransact.Store("/local/domain/0/xenpaging/%s" % self.vm.info['name_label'], ('xenpaging_delay_used', self.xenpaging_delay_used))
         xenpaging_bin = auxbin.pathTo("xenpaging")
         args = [xenpaging_bin]
         args = args + ([ "%d" % self.vm.getDomid()])
@@ -434,6 +458,9 @@ class ImageHandler:
                 except:
                     log.warn("chdir %s failed" % xenpaging_dir)
                 try:
+                    if self.xenpaging_delay != 0.0:
+                        log.info("delaying xenpaging startup %s seconds ..." % self.xenpaging_delay)
+                        time.sleep(self.xenpaging_delay)
                     log.info("starting %s" % args)
                     os.execve(xenpaging_bin, args, env)
                 except Exception, e:
@@ -449,10 +476,16 @@ class ImageHandler:
             self.xenpaging_pid = xenpaging_pid
             os.close(null)
             os.close(logfd)
+            if self.xenpaging_delay == 0.0:
+                log.warn("waiting for xenpaging ...")
+                time.sleep(22)
+                log.warn("waiting for xenpaging done.")
 
     def destroyXenPaging(self):
         if self.xenpaging is None:
             return
+        # FIXME find correct place for guest shutdown or crash
+        #xstransact.Remove("/local/domain/0/xenpaging/%s" % self.vm.info['name_label'])
         if self.xenpaging_pid:
             try:
                 os.kill(self.xenpaging_pid, signal.SIGHUP)