From 056f122d528b8627d004e64d6e98e3be4a2855d2 Mon Sep 17 00:00:00 2001 From: Keir Fraser Date: Mon, 26 May 2008 08:53:25 +0100 Subject: [PATCH] xend: take care of dead qemu-dm process This patch fix xend as when fatal error happened (e.g. qemu-dm process was killed) log error message then mark that domain as crashed, do what specified on crashed in the domain config file. Added some code in xend to check those crashed hvm DM status each 30 seconds. Signed-off-by: Xiaowei Hu --- tools/python/xen/xend/server/SrvServer.py | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/tools/python/xen/xend/server/SrvServer.py b/tools/python/xen/xend/server/SrvServer.py index 95be674da8..5b4a6b0349 100644 --- a/tools/python/xen/xend/server/SrvServer.py +++ b/tools/python/xen/xend/server/SrvServer.py @@ -44,6 +44,7 @@ import fcntl import re import time import signal +import os from threading import Thread from xen.web.httpserver import HttpServer, UnixHttpServer @@ -148,14 +149,27 @@ class XendServers: # Reaching this point means we can auto start domains try: - xenddomain().autostart_domains() + dom = xenddomain() + dom.autostart_domains() except Exception, e: log.exception("Failed while autostarting domains") # loop to keep main thread alive until it receives a SIGTERM self.running = True while self.running: - time.sleep(100000000) + # loop to destroy those hvm domain that whoes DM has dead unexpectedly. + for item in dom.domains.values(): + if item.info.is_hvm(): + device_model_pid = item.gatherDom(('image/device-model-pid', str)) + dm_stat_cmd = "ps -o stat --no-headers -p"+device_model_pid + dm_stat = os.popen(dm_stat_cmd).readline().rstrip() + if dm_stat == 'Z': + log.warn("Devices Model for domain " + str(item.domid) + "was killed unexpectedly") + item.info['crashed'] = 1 + item.refreshShutdown(item.info) + else: + continue + time.sleep(30) if self.reloadingConfig: log.info("Restarting all XML-RPC and Xen-API servers...") -- 2.30.2