Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 17 Jan 2015 12:11:08 -0700
From:      Jason Wolfe <nitroboost@gmail.com>
To:        Hans Petter Selasky <hps@selasky.org>, John Baldwin <jhb@freebsd.org>
Cc:        Adrian Chadd <adrian@freebsd.org>, FreeBSD Current <freebsd-current@freebsd.org>, "freebsd-arch@freebsd.org" <freebsd-arch@freebsd.org>
Subject:   Re: [RFC] kern/kern_timeout.c rewrite in progress
Message-ID:  <CAAAm0r0S=s8pRHR3-h%2BntEt27cw6tshHCONSezaAr3zBhLhSWA@mail.gmail.com>
In-Reply-To: <54B7DECF.8070209@selasky.org>
References:  <54A1B38C.1000709@selasky.org> <20150101005613.4f788b0c@nonamehost.local> <54A49CA5.2060801@selasky.org> <54A4A002.8010802@selasky.org> <54A53F4F.2000003@selasky.org> <54A92ED1.2070906@selasky.org> <CAJ-Vmo=tc-hqykhyc5bQW8qd_34PZU6yfGY8wziByA0xnR3ANQ@mail.gmail.com> <54A9A71E.70609@selasky.org> <CAAAm0r39Sv3TCvwaCiNQ1Y9iBVtY_nb0A_iNOC41bgxqXmt%2B4w@mail.gmail.com> <54B29A49.3080600@selasky.org> <CAAAm0r2eNYicq%2BKKj5f5EE%2BKLPxdvy15wj1ZWS=zA6sgOtcoGQ@mail.gmail.com> <54B67DA7.3070106@selasky.org> <54B7DECF.8070209@selasky.org>

next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Jan 15, 2015 at 8:37 AM, Hans Petter Selasky <hps@selasky.org> wrote:
> On 01/14/15 15:31, Hans Petter Selasky wrote:
>>
>> On 01/11/15 19:08, Jason Wolfe wrote:
>>>
>>> Hans,
>>>
>>> We've had 50 machines running 10.1-STABLE with this patch for the
>>> better part of a week without issue.  Prior we would have seen a panic
>>> every few days at the least, so things are looking very promising on
>>> our front.
>>>
>>> Jason
>>
>>
>> Hi,
>>
>> I've updated D1438 including the manual page changes needed for
>> timeout.9 aswell in addition to a minor fix for those using timeout()
>> and untimeout() and KTR().
>>
>> https://reviews.freebsd.org/D1438
>>
>> --HPS
>
>
> FYI:
>
> Now in -current:
>
> https://svnweb.freebsd.org/changeset/base/277213
>
> Thanks for all good comments and reviews.
>
> --HPS

HPS,

Just to give a quick status update, this patch has most certainly
resolved our spin lock held too long panics on stable/10.

Thank you to JHB for spending some time digging into the issue and
leading us to td_slpcallout as the culprit, and HPS for your rewrite.
I had heard rumors of other being affected by similar issues, so this
seems like a fine candidate for an MFC if possible.

Jason



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAAAm0r0S=s8pRHR3-h%2BntEt27cw6tshHCONSezaAr3zBhLhSWA>