[ewg] [PATCH] ib_srp: Avoid that module removal can trigger a deadlock
Rupert Dance
rsdance at soft-forge.com
Tue Oct 16 20:12:54 PDT 2012
Tziporet,
UNH-IOL completed the testing of the new daily build and here is what we
found.
+++++++++++++++++++++++++++++++++++
SL 6.3 2.6.32-279.el6.x86_64
OFED-3.5-20121016-0341.tgz 16-Oct-2012 03:42 18M
The new build now allows you to load and unload successfully with no system
crashes. We were also able to run the OFA Interop SRP tests successfully.
However the Module took a long time (~1-2 minutes) to unload 2. Message
saying something to the effect of 'stale connection...retrying' was observed
The attached file is a capture from the dmesg output.
++++++++++++++++++++++++++++++++++++
This is bug 2374.
Thanks
Rupert
-----Original Message-----
From: Rupert Dance [mailto:rsdance at soft-forge.com]
Sent: Tuesday, October 16, 2012 6:59 AM
To: 'Tziporet Koren'
Cc: 'Vladimir Sokolovsky'
Subject: RE: [PATCH] ib_srp: Avoid that module removal can trigger a
deadlock
Tziporet,
I have asked them to get this done today. I will let you know as soon as I
can confirm.
Thanks
Rupert
-----Original Message-----
From: Tziporet Koren [mailto:tziporet at mellanox.com]
Sent: Tuesday, October 16, 2012 6:36 AM
To: Vladimir Sokolovsky; Rupert Dance
Cc: 'Bart Van Assche'; 'ewg'
Subject: RE: [PATCH] ib_srp: Avoid that module removal can trigger a
deadlock
Rupert
I must get your input for SRP stability to know when we can build a new RC
Thanks
Tziporet
-----Original Message-----
From: Vladimir Sokolovsky [mailto:vlad at dev.mellanox.co.il]
Sent: Tuesday, October 16, 2012 12:34 PM
To: Rupert Dance
Cc: 'Bart Van Assche'; 'ewg'; Tziporet Koren
Subject: Re: [PATCH] ib_srp: Avoid that module removal can trigger a
deadlock
On 10/15/2012 04:46 PM, Rupert Dance wrote:
> Vlad,
>
> Thanks for getting this done. Is this in today's daily build or if not
> when will I have access?
>
> Thanks
>
> Rupert
Hi Rupert,
Yes, today's daily build includes this fix.
Regards,
Vladimir
>
> -----Original Message-----
> From: Vladimir Sokolovsky [mailto:vlad at dev.mellanox.co.il]
> Sent: Monday, October 15, 2012 9:28 AM
> To: Bart Van Assche
> Cc: Rupert Dance; ewg; Tziporet Koren
> Subject: Re: [PATCH] ib_srp: Avoid that module removal can trigger a
> deadlock
>
> On 10/12/2012 02:03 PM, Bart Van Assche wrote:
>> Avoid that scsi_remove_host() is invoked from the context of a work
>> queue thread on which work has been queued that scsi_remove_host()
>> might be waiting for. That avoids that module removal of ib_srp
>> triggers a deadlock on a pre-2.6.36 kernel. This patch has been
>> tested on RHEL 6.1, RHEL 6.2, RHEL 6.3 and SLES 11 SP2.
>>
>> Reported-by: Rupert Dance <rsdance at soft-forge.com>
>> Signed-off-by: Bart Van Assche <bvanassche at acm.org>
>> ---
>
> Applied,
>
> Regards,
> Vladimir
>
>
>
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: srp_dmesg_after_unload_patch.txt
URL: <http://lists.openfabrics.org/pipermail/ewg/attachments/20121016/c93bbc70/attachment.txt>
More information about the ewg
mailing list