关于openstack M版+ceph10.20集成整合热迁移测试失败的错误

之前K版本+ceph0.94ceph10.14整合是能热迁移和快照的，之前一直部署的是vmware ESXI上的虚拟机，用的是单网卡，多集群部署

现用的是真实的物理机设备，多网卡、多集群部署，2张网卡的地址段是相同的，192.168.1.0/24，现发现无法进行快照及其热迁移操作，求助大神协助，创建虚拟机、块、上传镜像是正常的。

日志报错如下，奇怪的是快照和热迁移的报错是一模一样...............醉了

016-05-20 02:40:26.852 2790 INFO nova.compute.manager [req-9014cc8f-690c-4d5d-a5a0-031c13305475 36d5d387b3024721ba67692d4cafe310 df064668c1dc4696b781250a856053e0 - - -] [instance: 42a81231-7

a39-4fb2-8926-96f1097df3bb] Successfully reverted task state from image_snapshot on failure for instance.2016-05-20 02:40:26.856 2790 ERROR oslo_messaging.rpc.dispatcher [req-9014cc8f-690c-4d5d-a5a0-031c13305475 36d5d387b3024721ba67692d4cafe310 df064668c1dc4696b781250a856053e0 - - -] Exception during message handling: internal error: unable to execute QEMU command 'migrate': Migration disabled: failed to allocate shared memory2016-05-20 02:40:26.856 2790 ERROR oslo_messaging.rpc.dispatcher Traceback (most recent call last):

2016-05-20 02:40:26.856 2790 ERROR oslo_messaging.rpc.dispatcher   File "/usr/lib/python2.7/dist-packages/oslo_messaging/rpc/dispatcher.py", line 138, in _dispatch_and_reply

if ret == -1: raise libvirtError ('virDomainManagedSave() failed', dom=self)2016-05-20 02:40:26.856 2790 ERROR oslo_messaging.rpc.dispatcher libvirtError: internal error: unable to execute QEMU command 'migrate': Migration disabled: failed to allocate shared memory