Hi Dave
How exactly are these patches being applied?
ie is it via jumpstart ot just normal patchadd on the cli

We did notice an issue almost identical to yours ( missing /dev/zfs )during zones upgrade testing, but it was localised to one lab and only occurs during upgrade,  I began to suspect it might be related to doing a reboot in a finish script, but your customer problem appears quite different in that the patch appears to have been applied post machine being installed.

I am really interested in getting to the bottom of this as it seems to be difficult to reproduce, and hence not easy to figure out.

Any further info on the exact steps to reproduce ( including any reboots etc )
ie what patches were applied and in what order ( perhaps a ls -ltr of /var/sadm/patch, ) plus any further relevant info.
ie was the zone halted at the time of patching, had the zone being booted previously and so on.

Enda


Dave Bevans wrote:
Hi,

I  have a customer with the following problem.

He has a V440 running Solaris 10 1/06 with zones. In the case notes he says that he installed a couple Sol 10 patches and now he has problems booting his zones. After doing  some checking he found that it appears to be related to a couple of ZFS patches (122650 and 122640).  I found a bug (6271309 / lack of zvol breaks all ZFS commands), but not sure if it applies to this situation. Any ideas on this.

Here is the customers problem description...

Hardware Platform: Sun Fire V440
Component Affected: OS Base
OS and Kernel Version: SunOS snb-fton-bck2 5.10 Generic_118833-18 sun4u sparc SUNW,Sun-Fire-V440

Describe the problem: Patch 122650-02 combined with patch 122640-05 seems to have broken no global zones at boot time. I'm just guessing at the exact patches since they were both added recently, and involve the files /usr/sbin/zfs and /lib/svc/method/fs-local which combined, cause the issue.
 
This section of code in /lib/svc/method/fs-local:
 
if [ -x /usr/sbin/zfs ]; then
        /usr/sbin/zfs mount -a >/dev/msglog 2>&1
        rc=$?
        if [ $rc -ne 0 ]; then
                msg="WARNING: /usr/sbin/zfs mount -a failed: exit status $rc"
                echo $msg
                echo "$SMF_FMRI:" $msg >/dev/msglog
                result=$SMF_EXIT_ERR_FATAL
        fi
fi
 
causes the local file system service to exit with an error, and stop the boot process. The reason why is that the non global zone does not have access to /dev/zfs so the "/usr/sbin/zfs mount -a" command exits with an error code.
This system is SRS Net Connect enabled: No
I will be sending an Explorer file: No
List steps to reproduce the problem(if applicable): Global zone:
 
bash-3.00# /usr/sbin/zfs mount -a
bash-3.00# echo $?
0
 
 
CVS Zone:
 
bash-3.00# zlogin cvs
[Connected to zone 'cvs' pts/2]
Last login: Tue Aug  1 11:51:58 on pts/2
Sun Microsystems Inc.   SunOS 5.10      Generic January 2005
# /usr/sbin/zfs mount -a
internal error: unable to open ZFS device
 
# echo $?
1
 
 
=========
It Looks like /dev/zfs is not created in the non-global zone, but is required for
the startup script change included in patch 122650-02:
 
 
Global Zone:
 
bash-3.00# truss -fald -t open /usr/sbin/zfs mount -a
Base time stamp:  1154444288.9594  [ Tue Aug  1 11:58:08 ADT 2006 ]
16159/1:         0.0000 execve("/sbin/zfs", 0xFFBFFD8C, 0xFFBFFD9C)  argc = 3
16159/1:         argv: /usr/sbin/zfs mount -a
...
16159/1:         0.0192 open("/etc/mnttab", O_RDONLY)                   = 3
16159/1:         0.0203 open("/dev/zfs", O_RDWR)                        = 4
 
 
CVS Zone:
# truss -fald -t open /usr/sbin/zfs mount -a
Base time stamp:  1154444344.9469  [ Tue Aug  1 11:59:04 ADT 2006 ]
16198/1:         0.0000 execve("/sbin/zfs", 0xFFBFFECC, 0xFFBFFEDC)  argc = 3
16198/1:         argv: /usr/sbin/zfs mount -a
...
16198/1:         0.0181 open("/etc/mnttab", O_RDONLY)                   = 3
16198/1:         0.0191 open("/dev/zfs", O_RDWR)                        Err#2 ENOENT
internal error: unable to open ZFS device
 
# ls -l "/dev/zfs"
/dev/zfs: No such file or directory
 
======
bash-3.00# zonecfg -z cvs info
zonepath: /oracle/zones/cvs
autoboot: true
pool:
inherit-pkg-dir:
        dir: /lib
inherit-pkg-dir:
        dir: /platform
inherit-pkg-dir:
        dir: /sbin
inherit-pkg-dir:
        dir: /usr
fs:
        dir: /data
        special: /data
        raw not specified
        type: lofs
        options: []
net:
        address: 142.139.95.4
        physical: ce0

When was the problem first noticed: August 1.
The problem is: staying the same
Any changes recently?: New Patch Applied
What software is having the problem?: bash-3.00# uname -a SunOS snb-fton-bck2 5.10 Generic_118833-18 sun4u sparc SUNW,Sun-Fire-V440 bash-3.00# cat /etc/release                        Solaris 10 1/06 s10s_u1wos_19a SPARC            Copyright 2005 Sun Microsystems, Inc.  All Rights Reserved.                         Use is subject to license terms.                            Assembled 07 December 2005 

--
Regards,
Dave
--
Signature


Sun Microsystems
Mailstop ubur04-206
1 Network Drive
Burlington, MA  01803
Dave Bevans - Technical Support Engineer
Phone: 800-872-4786
(opt-1), (opt-1), (case #)
Email:   david.bevans@Sun.com
Operating Systems Team
Submit, Check & Update Cases at the Online Support Center

_______________________________________________ zones-discuss mailing list zones-discuss@opensolaris.org



_______________________________________________
zones-discuss mailing list
zones-discuss@opensolaris.org
  • [zones-discus... Dave Bevans
    • Re: [zon... Enda o'Connor - Sun Microsystems Ireland - Software Engineer

Reply via email to