Re: [zfs-discuss] ZPool creation brings down the host

2010-10-15 Thread Anand Bhakthavatsala
Thanks you very much Victor for the update.

Regards,
Anand





From: Victor Latushkin 
To: j...@opensolaris.org
Cc: Anand Bhakthavatsala ; zfs-discuss discuss 

Sent: Fri, 8 October, 2010 1:33:57 PM
Subject: Re: [zfs-discuss] ZPool creation brings down the host


On Oct 8, 2010, at 10:25 AM, James C. McPherson wrote:

> On  8/10/10 03:28 PM, Anand Bhakthavatsala wrote:
> ...
>> --
>> *From:* James C. McPherson 
>> *To:* Ramesh Babu 
>> 
>> On 7/10/10 03:46 PM, Ramesh Babu wrote:
>> > I am trying to create ZPool using single veritas volume. The host is going
>> > down as soon as I issue zpool create command. It looks like the command is
>> > crashing and bringing host down. Please let me know what the issue might
>> > be.Below is the command used, textvol is the veritas volume and testpool
>> > is the name of pool which I am tyring to create.
>> >
>> > zpool create testpool /dev/vx/dsk/dom/textvol
>> >
>> 
>> That's not a configuration that I'd recommend - you're layering
>> one volume management system on top of another. It seems that
>> it's getting rather messy inside the kernel.
>> 
>> 
>> Do you have the panic stack trace we can look at, and/or a
>> crash dump?
> ...
> 
> 
> vxioioctl+0x4c0(1357918, 42a, 0, ff0, 10, 0)
> vdev_disk_open+0x4c4(300036fd9c0, 7c00, 2a100fe3440, 18dbc00, 
>3000cf04900,ctor
> 18c0268)
> vdev_open+0x9c(300036fd9c0, 1, 1274400, 0, 3000e647800, 6)
> vdev_root_open+0x48(30004036080, 2a100fe35b8, 2a100fe35b0, 0, 7c00, 138)
> vdev_open+0x9c(30004036080, 1c, 0, 0, 3000e647800, 6)
> vdev_create+4(30004036080, 4, 0, 130e3c8, 0, 130e000)
> spa_create+0x1a4(0, 30011ffb500, 0, 300124cc040, 0, 3000e647800)
> zfs_ioc_pool_create+0x18c(30008524000, 0, 0, 74, 0, 300124cc040)
> zfsdev_ioctl+0x184(0, 18dbff0, ffbfa728, 0, 0, 1000)
> fop_ioctl+0x20(60015662e40, 5a00, ffbfa728, 13, 3000a4407a0, 127aa58)
> ioctl+0x184(3, 3000cb5fd28, ffbfa728, 0, 0, 5a00)
> syscall_trap32+0xcc(3, 5a00, ffbfa728, 0, 0, ffbfa270)
> 
> 
> Looks like you need to ask Symantec what's going on in their
> vxioioctl function.

This is most likely

6940833 vxio`vxioioctl() panics when zfs passes it a NULL rvalp via ldi_ioctl()

http://bugs.opensolaris.org/bugdatabase/view_bug.do?bug_id=6940833

victor

___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss


Re: [zfs-discuss] ZPool creation brings down the host

2010-10-15 Thread Anand Bhakthavatsala
looks like the attachment missed in the earlier mail

-Anand





From: Anand Bhakthavatsala 
To: j...@opensolaris.org; Ramesh Babu 
Cc: zfs-discuss@opensolaris.org
Sent: Fri, 8 October, 2010 10:56:55 AM
Subject: Re: [zfs-discuss] ZPool creation brings down the host


Thanks James for the response.

Please find attached here with the crash dump that we got from the admin.

Regards,
Anand





From: James C. McPherson 
To: Ramesh Babu 
Cc: zfs-discuss@opensolaris.org; anand_...@yahoo.com
Sent: Thu, 7 October, 2010 11:56:36 AM
Subject: Re: [zfs-discuss] ZPool creation brings down the host

On  7/10/10 03:46 PM, Ramesh Babu wrote:
> I am trying to create ZPool using single veritas volume. The host is going
> down as soon as I issue zpool create command. It looks like the command is
> crashing and bringing host down. Please let me know what the issue might
> be.Below is the command used, textvol is the veritas volume and testpool
> is the name of pool which I am tyring to create.
>
> zpool create testpool /dev/vx/dsk/dom/textvol
>

That's not a configuration that I'd recommend - you're layering
one volume management system on top of another. It seems that
it's getting rather messy inside the kernel.


Do you have the panic stack trace we can look at, and/or a
crash dump?



James C. McPherson
--
Oracle
http://www.jmcp.homeunix.com/blog

[r...@losan048:losan048.lss.emc.com]# cd /var/crash/losan048.lss.emc.com


[r...@losan048:losan048.lss.emc.com]# echo '::status' | mdb -k unix.11 vmcore.11
debugging crash dump vmcore.11 (64-bit) from losan048.lss.emc.com
operating system: 5.10 Generic_142900-10 (sun4us)
panic message:
BAD TRAP: type=31 rp=2a100fe3110 addr=0 mmu_fsr=0 occurred in module "vxio" due
to a NULL pointer dereference
dump content: kernel pages and pages from PID 7440
[r...@losan048:losan048.lss.emc.com]#




[r...@losan048:losan048.lss.emc.com]# echo '::msgbuf' | mdb -k unix.11 vmcore.11
MESSAGE
WARNING: /p...@17,2000/l...@1/f...@0,0/s...@w5972081ad99d,3 (ssd20):
Corrupt label; wrong magic number

...

WARNING: /p...@16,2000/l...@1/f...@0,0/s...@w5972081ad99d,5 (ssd13):
Corrupt label; wrong magic number

NOTICE: mount: not a UFS magic number (0x7c104d79)
NOTICE: mount: not a UFS magic number (0x7c104d79)

panic[cpu0]/thread=3000862f060:
BAD TRAP: type=31 rp=2a100fe3110 addr=0 mmu_fsr=0 occurred in module "vxio" due
to a NULL pointer dereference


zpool:
trap type = 0x31
pid=7440, pc=0x7bb5bdf8, sp=0x2a100fe29b1, tstate=0x4480001602, context=0x6b1
g1-g7: 7ba3da28, 9a8, 7036e6b0, 7036e738, e6, 0, 3000862f060

02a100fe2e30 unix:die+78 (31, 2a100fe3110, 0, 0, 2a100fe2ef0, 109d800)
  %l0-3: 1fff 0031 0100 2000
  %l4-7: 0181be88 0181bc00  004480001602
02a100fe2f10 unix:trap+8f8 (2a100fe3110, 1, 5, e000, 0, 1)
  %l0-3:  03000a4344b0 0031 
  %l4-7:   0005 00010200
02a100fe3060 unix:ktl0+48 (0, 0, 2a100fe3350, 7b800, 2a100fe3290, 30007b9880
0)
  %l0-3: 0003 1400 004480001602 0101cbec
  %l4-7: 0029 0029  02a100fe3110
02a100fe31b0 vxio:vxioioctl+1b0 (1357918, 42a, 0, ff0, 10, 0)
  %l0-3: 02a100fe3290 00070400 70522b28 
  %l4-7: 0001 564f4c00 564f4c04 564f4c00
02a100fe32a0 zfs:vdev_disk_open+4c4 (300036fd9c0, 7c00, 2a100fe3440, 18d
bc00, 3000cf04900, 18c0268)
  %l0-3:  030012598e40  0130e400
  %l4-7: 0600115c5220  0016 0003
02a100fe3390 zfs:vdev_open+9c (300036fd9c0, 1, 1274400, 0, 3000e647800, 6)
  %l0-3: 0001  ea159738076c 1c869fa152f059f8
  %l4-7: cd8ef796b4dc7274 0001 018dbdd8 000a
02a100fe3450 zfs:vdev_root_open+48 (30004036080, 2a100fe35b8, 2a100fe35b0, 0
, 7c00, 138)
  %l0-3: 0300036fd9c0 0006  
  %l4-7:  0300036fd9c0 0300125fcc90 01138c00
02a100fe3500 zfs:vdev_open+9c (30004036080, 1c, 0, 0, 3000e647800, 6)
  %l0-3: 0001 0300036fd9c0 0001 0020
  %l4-7: 01139a68 0007 0007 00d8
02a100fe35c0 zfs:vdev_create+4 (30004036080, 4, 0, 130e3c8, 0, 130e000)
  %l0-3: 018db3c8 030004036080 0001 0001
  %l4-7:   030011cb6718 
02a100fe3670 zfs:spa_create+1a4 (0, 30011ffb500, 0, 300124cc040, 0, 3000e647
800)
  %l0-3:  0

Re: [zfs-discuss] ZPool creation brings down the host

2010-10-15 Thread Anand Bhakthavatsala
Thanks James for the response.

Please find attached here with the crash dump that we got from the admin.

Regards,
Anand





From: James C. McPherson 
To: Ramesh Babu 
Cc: zfs-discuss@opensolaris.org; anand_...@yahoo.com
Sent: Thu, 7 October, 2010 11:56:36 AM
Subject: Re: [zfs-discuss] ZPool creation brings down the host

On  7/10/10 03:46 PM, Ramesh Babu wrote:
> I am trying to create ZPool using single veritas volume. The host is going
> down as soon as I issue zpool create command. It looks like the command is
> crashing and bringing host down. Please let me know what the issue might
> be.Below is the command used, textvol is the veritas volume and testpool
> is the name of pool which I am tyring to create.
>
> zpool create testpool /dev/vx/dsk/dom/textvol
>

That's not a configuration that I'd recommend - you're layering
one volume management system on top of another. It seems that
it's getting rather messy inside the kernel.


Do you have the panic stack trace we can look at, and/or a
crash dump?



James C. McPherson
--
Oracle
http://www.jmcp.homeunix.com/blog


___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss


Re: [zfs-discuss] ZPool creation brings down the host

2010-10-08 Thread Victor Latushkin

On Oct 8, 2010, at 10:25 AM, James C. McPherson wrote:

> On  8/10/10 03:28 PM, Anand Bhakthavatsala wrote:
> ...
>> --
>> *From:* James C. McPherson 
>> *To:* Ramesh Babu 
>> 
>> On 7/10/10 03:46 PM, Ramesh Babu wrote:
>> > I am trying to create ZPool using single veritas volume. The host is going
>> > down as soon as I issue zpool create command. It looks like the command is
>> > crashing and bringing host down. Please let me know what the issue might
>> > be.Below is the command used, textvol is the veritas volume and testpool
>> > is the name of pool which I am tyring to create.
>> >
>> > zpool create testpool /dev/vx/dsk/dom/textvol
>> >
>> 
>> That's not a configuration that I'd recommend - you're layering
>> one volume management system on top of another. It seems that
>> it's getting rather messy inside the kernel.
>> 
>> 
>> Do you have the panic stack trace we can look at, and/or a
>> crash dump?
> ...
> 
> 
> vxioioctl+0x4c0(1357918, 42a, 0, ff0, 10, 0)
> vdev_disk_open+0x4c4(300036fd9c0, 7c00, 2a100fe3440, 18dbc00, 
> 3000cf04900,ctor
> 18c0268)
> vdev_open+0x9c(300036fd9c0, 1, 1274400, 0, 3000e647800, 6)
> vdev_root_open+0x48(30004036080, 2a100fe35b8, 2a100fe35b0, 0, 7c00, 138)
> vdev_open+0x9c(30004036080, 1c, 0, 0, 3000e647800, 6)
> vdev_create+4(30004036080, 4, 0, 130e3c8, 0, 130e000)
> spa_create+0x1a4(0, 30011ffb500, 0, 300124cc040, 0, 3000e647800)
> zfs_ioc_pool_create+0x18c(30008524000, 0, 0, 74, 0, 300124cc040)
> zfsdev_ioctl+0x184(0, 18dbff0, ffbfa728, 0, 0, 1000)
> fop_ioctl+0x20(60015662e40, 5a00, ffbfa728, 13, 3000a4407a0, 127aa58)
> ioctl+0x184(3, 3000cb5fd28, ffbfa728, 0, 0, 5a00)
> syscall_trap32+0xcc(3, 5a00, ffbfa728, 0, 0, ffbfa270)
> 
> 
> Looks like you need to ask Symantec what's going on in their
> vxioioctl function.

This is most likely

6940833 vxio`vxioioctl() panics when zfs passes it a NULL rvalp via ldi_ioctl()

http://bugs.opensolaris.org/bugdatabase/view_bug.do?bug_id=6940833

victor
___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss


Re: [zfs-discuss] ZPool creation brings down the host

2010-10-07 Thread James C. McPherson

On  8/10/10 03:28 PM, Anand Bhakthavatsala wrote:
...

--
*From:* James C. McPherson 
*To:* Ramesh Babu 

On 7/10/10 03:46 PM, Ramesh Babu wrote:
 > I am trying to create ZPool using single veritas volume. The host is going
 > down as soon as I issue zpool create command. It looks like the command is
 > crashing and bringing host down. Please let me know what the issue might
 > be.Below is the command used, textvol is the veritas volume and testpool
 > is the name of pool which I am tyring to create.
 >
 > zpool create testpool /dev/vx/dsk/dom/textvol
 >

That's not a configuration that I'd recommend - you're layering
one volume management system on top of another. It seems that
it's getting rather messy inside the kernel.


Do you have the panic stack trace we can look at, and/or a
crash dump?

...


vxioioctl+0x4c0(1357918, 42a, 0, ff0, 10, 0)
vdev_disk_open+0x4c4(300036fd9c0, 7c00, 2a100fe3440, 18dbc00, 3000cf04900,
18c0268)
vdev_open+0x9c(300036fd9c0, 1, 1274400, 0, 3000e647800, 6)
vdev_root_open+0x48(30004036080, 2a100fe35b8, 2a100fe35b0, 0, 7c00, 138)
vdev_open+0x9c(30004036080, 1c, 0, 0, 3000e647800, 6)
vdev_create+4(30004036080, 4, 0, 130e3c8, 0, 130e000)
spa_create+0x1a4(0, 30011ffb500, 0, 300124cc040, 0, 3000e647800)
zfs_ioc_pool_create+0x18c(30008524000, 0, 0, 74, 0, 300124cc040)
zfsdev_ioctl+0x184(0, 18dbff0, ffbfa728, 0, 0, 1000)
fop_ioctl+0x20(60015662e40, 5a00, ffbfa728, 13, 3000a4407a0, 127aa58)
ioctl+0x184(3, 3000cb5fd28, ffbfa728, 0, 0, 5a00)
syscall_trap32+0xcc(3, 5a00, ffbfa728, 0, 0, ffbfa270)


Looks like you need to ask Symantec what's going on in their
vxioioctl function.



James
--
Oracle
http://www.jmcp.homeunix.com/blog
___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss


Re: [zfs-discuss] ZPool creation brings down the host

2010-10-06 Thread James C. McPherson

On  7/10/10 03:46 PM, Ramesh Babu wrote:

I am trying to create ZPool using single veritas volume. The host is going
down as soon as I issue zpool create command. It looks like the command is
crashing and bringing host down. Please let me know what the issue might
be.Below is the command used, textvol is the veritas volume and testpool
is the name of pool which I am tyring to create.

zpool create testpool /dev/vx/dsk/dom/textvol



That's not a configuration that I'd recommend - you're layering
one volume management system on top of another. It seems that
it's getting rather messy inside the kernel.


Do you have the panic stack trace we can look at, and/or a
crash dump?



James C. McPherson
--
Oracle
http://www.jmcp.homeunix.com/blog
___
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss