Hi Roman,
from the provided data I suppose that you a running unpatched Solaris 10
Update 3.
Since fault address is 0xc4 and in zio_create we manipulate mostly with
zio_t structures, then 0xc4 most likely corresponds to io_child member
of zio_t structure. If my assumption about Solaris update is correct,
then corresponding piece of code is:
zio_create+0x133: movl -0x4(%ebp),%edx
zio_create+0x136: movl 0x1f0(%edx),%eax
zio_create+0x13c: movl 0x1f4(%edx),%ecx
zio_create+0x142: addl $0x1,%eax
zio_create+0x145: adcl $0x0,%ecx
zio_create+0x148: movl %eax,0x1f0(%edx)
zio_create+0x14e: movl %ecx,0x1f4(%edx)
zio_create+0x154: movl 0xc4(%edx),%eax
zio_create+0x15a: movl %eax,0xcc(%ebx)
zio_create+0x160: movl $0x0,0xc8(%ebx)
zio_create+0x16a: movl 0xc4(%edx),%eax
zio_create+0x170: testl %eax,%eax
zio_create+0x172: je +0x8 <zio_create+0x17a>
zio_create+0x174: movl %ebx,0xc8(%eax)
zio_create+0x17a: movl -0x4(%ebp),%eax
zio_create+0x17d: movl %ebx,0xc4(%eax)
zio_create+0x183: movl 0x34(%eax),%eax
zio_create+0x186: movl %eax,0x34(%ebx)
zio_create+0x189: pushl %esi
zio_create+0x18a: call +0x555fe07 <mutex_exit>
Failure offset +0x17d corresponds to line 371 of zio.c
http://src.opensolaris.org/source/xref/onnv/onnv-gate/usr/src/uts/common/fs/zfs/zio.c#371
Register %ebx contains address of newly allocates zio_t structure. At
offset +0x17d we are trying to store %ebx into address %eax+0xc4, and
since %eax is 0, we end up with page fault. We load %eax one instruction
earlier from stack, so most probably something have overwritten stack
very recently, since at offset 0x133 we loaded from that stack location
into %edx (it was 0xe83edac0) and successfully dereferenced that
address several times.
Cheers,
Victor
Roman Chervotkin wrote:> Hi.
> My system crashed today. System reboots without a problem and now
everything looks as usual.
> By the way I used ztune.sh to tune parameters several days ago so the
problem may be related to that script
>
> Is that a zfs issue or something different?
>
> Thanks,
> Roman
> ---
> -bash-3.00# more /var/adm/messages
>
> ...
> Apr 15 09:13:53 server3 unix: [ID 836849 kern.notice]
> Apr 15 09:13:53 server3 ^Mpanic[cpu1]/thread=dc28d600:
> Apr 15 09:13:53 server3 genunix: [ID 335743 kern.notice] BAD TRAP: type=e
(#pf Page fault) rp=ecc53b9c addr=c4 occurred in module "zfs" due to a
NULL pointer dereference
> Apr 15 09:13:53 server3 unix: [ID 100000 kern.notice]
> Apr 15 09:13:53 server3 unix: [ID 839527 kern.notice] postgres:
> Apr 15 09:13:53 server3 unix: [ID 753105 kern.notice] #pf Page fault
> Apr 15 09:13:53 server3 unix: [ID 532287 kern.notice] Bad kernel fault at
addr=0xc4
> Apr 15 09:13:53 server3 unix: [ID 243837 kern.notice] pid=16204,
pc=0xf7eda18c, sp=0x0, eflags=0x10282
> Apr 15 09:13:53 server3 unix: [ID 211416 kern.notice] cr0:
80050033<pg,wp,ne,et,mp,pe> cr4: 6d8<xmme,fxsr,pge,mce,pse,de>
> Apr 15 09:13:53 server3 unix: [ID 936844 kern.notice] cr2: c4 cr3: 66e8e000
> Apr 15 09:13:53 server3 unix: [ID 537610 kern.notice] gs: 1b0 fs:
e3390000 es: ecc50160 ds: f7ed0160
> Apr 15 09:13:53 server3 unix: [ID 537610 kern.notice] edi: d esi:
e83edcbc ebp: ecc53bfc esp: ecc53bd4
> Apr 15 09:13:53 server3 unix: [ID 537610 kern.notice] ebx: e3390cc0 edx:
e83edac0 ecx: 0 eax: 0
> Apr 15 09:13:53 server3 unix: [ID 537610 kern.notice] trp: e err:
2 eip: f7eda18c cs: 158
> Apr 15 09:13:53 server3 unix: [ID 717149 kern.notice] efl: 10282 usp:
0 ss: eb6f46d8
> Apr 15 09:13:53 server3 unix: [ID 100000 kern.notice]
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53afc
unix:die+a7 (e, ecc53b9c, c4, 1)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53b88
unix:trap+103f (ecc53b9c, c4, 1)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53b9c
unix:_cmntrap+9a (1b0, e3390000, ecc5)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53bfc
zfs:zio_create+17d (e83edac0, d8969900,)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53c44
zfs:zio_vdev_child_io+67 (e83edac0, e7d27d8c,)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53c98
zfs:vdev_mirror_io_start+14d (e83edac0, ecc53cc8,)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53ca4
zfs:vdev_io_start+15 (e83edac0)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53cc8
zfs:zio_vdev_io_start+13f (e83edac0)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53cd8
zfs:zfsctl_ops_root+2044461b (e83edac0, ecc53d04,)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53ce4
zfs:zio_nowait+b (e83edac0)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53d04
zfs:vdev_mirror_io_start+156 (e840bc80)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53d28
zfs:zio_vdev_io_start+14c (e840bc80)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53d38
zfs:zio_next_stage+76 (e840bc80)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53d50
zfs:zio_ready+37 (e840bc80)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53d60
zfs:zio_next_stage+76 (e840bc80, ecc53d7c,)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53d6c
zfs:zio_gang_pipeline+28 (e840bc80)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53d7c
zfs:zio_next_stage+76 (e840bc80)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53d98
zfs:zio_checksum_generate+6c (e840bc80)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53da8
zfs:zio_next_stage+76 (e840bc80)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53dbc
zfs:zio_wait_for_children+43 (e840bc80, 1, e840be)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53dd0
zfs:zio_wait_children_ready+15 (e840bc80)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53de0
zfs:zfsctl_ops_root+2044461b (e840bc80, ecc53e28,)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53dec
zfs:zio_nowait+b (e840bc80)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53e28
zfs:zil_lwb_write_start+24e (d84fe540, e7d27d88)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53e64
zfs:zil_commit+223 (d84fe540, 2bec75, 0)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53ecc
zfs:zfs_write+74d (ddef0780, ecc53f3c,)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53f04
genunix:fop_write+2a (ddef0780, ecc53f3c,)
> Apr 15 09:13:53 server3 genunix: [ID 353471 kern.notice] ecc53f84
genunix:write+29a (3b, b11cdb20, 6000,)
> Apr 15 09:13:53 server3 unix: [ID 100000 kern.notice]
> Apr 15 09:13:53 server3 genunix: [ID 672855 kern.notice] syncing file
systems...
> Apr 15 09:13:57 server3 genunix: [ID 733762 kern.notice] 333
> Apr 15 09:13:59 server3 genunix: [ID 733762 kern.notice] 55
> Apr 15 09:14:00 server3 genunix: [ID 904073 kern.notice] done
> Apr 15 09:14:01 server3 genunix: [ID 111219 kern.notice] dumping to
/dev/dsk/c0t1d0s1, offset 429391872, content: kernel
> Apr 15 09:14:02 server3 adpu320: [ID 330825 kern.notice] NOTICE: adpu320:
bus reset
> Apr 15 09:14:15 server3 genunix: [ID 409368 kern.notice] ^M100% done:
124333 pages dumped, compression ratio 2.29,
> Apr 15 09:14:15 server3 genunix: [ID 851671 kern.notice] dump succeeded
> Apr 15 09:16:08 server3 genunix: [ID 540533 kern.notice] ^MSunOS Release
5.10 Version Generic_118855-33 32-bit
> Apr 15 09:16:08 server3 genunix: [ID 172907 kern.notice] Copyright
1983-2006 Sun Microsystems, Inc. All rights reserved.
> Apr 15 09:16:08 server3 Use is subject to license terms.
> ...
>
>
> This message posted from opensolaris.org
> _______________________________________________
> zfs-discuss mailing list
> zfs-discuss at opensolaris.org
> http://mail.opensolaris.org/mailman/listinfo/zfs-discuss