CPU stalls in Vmware ESXI 5.1

[Guest]

[TheEricHarris]

I have a 2.5.2 server running on a ESXi 5.1 server.  I'm seeing this in the messages once or twice a day:

Sep 19 09:40:43 gateway1 kernel: [263513.511939] INFO: RCU detected CPU stalls: 0 (detected by 2, t=11010 jiffies)
Sep 19 09:40:43 gateway1 kernel: [263513.512026] sending NMI to all CPUs:
Sep 19 09:40:43 gateway1 kernel: [263514.401239] NMI backtrace for cpu 1
Sep 19 09:40:43 gateway1 kernel: [263514.401249]
Sep 19 09:40:43 gateway1 kernel: [263515.382517] Pid: 3142, comm: flush-252:3 Tainted: P           (2.6.32.43-57.e48.i586 #1) VMware Virt
ual Platform
Sep 19 09:40:43 gateway1 kernel: [263515.382526] EIP: 0060:[<c0425971>] EFLAGS: 00010082 CPU: 1
Sep 19 09:40:43 gateway1 kernel: [263516.133664] EIP is at account_system_time+0x21/0x122
Sep 19 09:40:43 gateway1 kernel: [263516.133671] EAX: 024ba000 EBX: f60c29e0 ECX: 00000001 EDX: 00000001
Sep 19 09:40:43 gateway1 kernel: [263516.133674] ESI: f60c29e0 EDI: 00000001 EBP: c0849980 ESP: f588fd10
Sep 19 09:40:43 gateway1 kernel: [263516.133677]  DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
Sep 19 09:40:43 gateway1 kernel: [263516.133680] CR0: 8005003b CR2: b760e000 CR3: 34b5a000 CR4: 000006d0
Sep 19 09:40:43 gateway1 kernel: [263516.133693] DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000
Sep 19 09:40:43 gateway1 kernel: [263516.133697] DR6: ffff0ff0 DR7: 00000400


The box loses network connectivity for about 5 seconds when this happens.

Any ideas?  Not sure why I stick around with Endian, but I have 15 of these boxes around the country and it's been great to me.  Just wish it had better support from the community.

[mmiat]

I've had a similar problem, in my case server hangs and I can only reboot. I tried Endian 2.5.2 and XenServer 6.2.0 with Endian, same thing. It was a ML110. When I changed bios feature about power management it was more stable but sometimes hangs again. So I've buyed new hardware.