[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] xen-3.4 BUG: spinlock lockup on CPU# and network stall


  • To: xen-devel@xxxxxxxxxxxxxxxxxxx
  • From: Teck Choon Giam <giamteckchoon@xxxxxxxxx>
  • Date: Tue, 23 Jun 2009 20:43:24 +0800
  • Delivery-date: Tue, 23 Jun 2009 05:43:47 -0700
  • Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:date:message-id:subject:from:to:content-type :content-transfer-encoding; b=bk85/XCUOu+030x8GyAN2hrRHRXXPBEds50SKHH0dAfzjE6T50uIeeU03ybaLqrA0x WTm+dD+8FIYrgeS3YnqrKfxM0Hec6/jCiUotAKakzypvoMdHnjXaHmNURrIRNG8GUz3B 57mWFIimo8RI3TS/YV7FtuKojpYoWkBBkyKaI=
  • List-id: Xen developer discussion <xen-devel.lists.xensource.com>

Hi,

Just report the following which caused few of my domUs in different
servers to crash....

domU console showing:
BUG: spinlock lockup on CPU#1, swapper/0, c1520a80
 [<c01f05d0>] _raw_spin_lock+0x110/0x140
 [<c035d3b5>] schedule+0xf5/0x8c0
 [<c0108572>] raw_safe_halt+0xa2/0x120
 [<c0103261>] cpu_idle+0x71/0x80

Another domU console showing:
BUG: spinlock lockup on CPU#1, perl/14953, c03c99a8
 [<c01f05d0>] _raw_spin_lock+0x110/0x140
 [<c035f874>] _spin_lock_irqsave+0x24/0x30
 [<c0113c9b>] pgd_free+0x6b/0x170
 [<c011e122>] __mmdrop+0x12/0x30
 [<c01236e7>] do_exit+0x107/0x8d0
 [<c016f741>] vfs_write+0x101/0x170
 [<c017c630>] pipe_write+0x0/0x30
 [<c0123ee3>] do_group_exit+0x33/0x90
 [<c0105457>] syscall_call+0x7/0xb

Another domU showing:
BUG: spinlock lockup on CPU#3, sh/9934, c12a7300
 [<c01f05b0>] _raw_spin_lock+0x110/0x140
 [<c0119991>] task_rq_lock+0x51/0x90
 [<c011a60f>] try_to_wake_up+0x1f/0x350
 [<c014a8e2>] find_get_page+0x42/0x60
 [<c014f1d0>] free_pages_bulk+0x30/0x2d0
 [<c013491b>] autoremove_wake_function+0x1b/0x50
 [<c0119399>] __wake_up_common+0x39/0x60
 [<c01198e8>] __wake_up+0x38/0x50
 [<c017bf98>] pipe_release+0x68/0xc0
 [<c0170228>] __fput+0xb8/0x1a0
 [<c016d327>] filp_close+0x47/0x80
 [<c012254c>] put_files_struct+0x9c/0xc0
 [<c0123725>] do_exit+0x145/0x8d0
 [<c01ef87e>] copy_to_user+0x3e/0x80
 [<c0123ee3>] do_group_exit+0x33/0x90
 [<c0105457>] syscall_call+0x7/0xb
BUG: spinlock lockup on CPU#2, swapper/0, c12a7300
 [<c01f05b0>] _raw_spin_lock+0x110/0x140
 [<c035d2c5>] schedule+0xf5/0x8c0
 [<c0108572>] raw_safe_halt+0xa2/0x120
 [<c0103261>] cpu_idle+0x71/0x80

I noticed once I used xen-3.4.0, at least *three* servers I
experienced network stall in a regular basis... yes, no network at all
for eth0 and eth1 both are using tg3 drivers (Dell PE860). brctl and
ifconfig are showing normal but I can't ping gateway or make any
connection to outside via eth0 or eth1 at all.  The only way to
resolve this is to stop all domUs, stop xendomains, stop xend then
restart network-bridge, start xend and lastly start back domUs.  The
following changesets happened to my servers:

xen-3.4-testing.hg changeset 19645 and 19658
linux-2.6.18-xen.hg changeset 897 and 908

I am running xen kernel for dom0/domU and not xen0 and xenU.  Any
suggestions for me to track down the problems?

Thanks in advance.

Kindest regards,
Giam Teck Choon

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.