From: Jens Axboe <axboe@kernel.dk>
To: Meelis Roos <mroos@linux.ee>, Christoph Hellwig <hch@infradead.org>
Cc: linux-scsi@vger.kernel.org, sparclinux@vger.kernel.org,
David Miller <davem@davemloft.net>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: Re: Another (ESP?) scsi blk-mq problem on sparc64
Date: Fri, 14 Nov 2014 12:42:40 -0700 [thread overview]
Message-ID: <54665B30.4070708@kernel.dk> (raw)
In-Reply-To: <alpine.LRH.2.11.1411142114200.26813@adalberg.ut.ee>
On 11/14/2014 12:35 PM, Meelis Roos wrote:
>> Paul, what's the best way to figure out these CPU stalls?
>>
>> The second oops is in blk_mq_map_queue() which is a trivial
>> two level cpu lookup. I wonder if there's something odd about
>> cpu numbers on these big old sparc systems?
>
> CPU numbers are sparse - they are determined by hardware slot number and
> some models only fill every other mainboard slot, and first slots can be
> free. I have first board offline and currently have CPUs numbered
> 10,11,14,15 online.
>
> Here is debug with Jens's patch:
> [ 133.971050] CPU 11: synchronized TICK with master CPU (last diff -1 cycles, maxerr 516 cycles)
> [ 133.975491] CPU 14: synchronized TICK with master CPU (last diff -3 cycles, maxerr 531 cycles)
> [ 133.979943] CPU 15: synchronized TICK with master CPU (last diff -3 cycles, maxerr 531 cycles)
> [ 133.980146] Brought up 4 CPUs
So this looks like this might be the issue. On a scsi-mq disabled boot,
you have 4 CPUs, but how are they numbered?
We might need Christophs debug patch on top this to fully know...
--
Jens Axboe
WARNING: multiple messages have this Message-ID (diff)
From: Jens Axboe <axboe@kernel.dk>
To: Meelis Roos <mroos@linux.ee>, Christoph Hellwig <hch@infradead.org>
Cc: linux-scsi@vger.kernel.org, sparclinux@vger.kernel.org,
David Miller <davem@davemloft.net>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: Re: Another (ESP?) scsi blk-mq problem on sparc64
Date: Fri, 14 Nov 2014 19:42:40 +0000 [thread overview]
Message-ID: <54665B30.4070708@kernel.dk> (raw)
In-Reply-To: <alpine.LRH.2.11.1411142114200.26813@adalberg.ut.ee>
On 11/14/2014 12:35 PM, Meelis Roos wrote:
>> Paul, what's the best way to figure out these CPU stalls?
>>
>> The second oops is in blk_mq_map_queue() which is a trivial
>> two level cpu lookup. I wonder if there's something odd about
>> cpu numbers on these big old sparc systems?
>
> CPU numbers are sparse - they are determined by hardware slot number and
> some models only fill every other mainboard slot, and first slots can be
> free. I have first board offline and currently have CPUs numbered
> 10,11,14,15 online.
>
> Here is debug with Jens's patch:
> [ 133.971050] CPU 11: synchronized TICK with master CPU (last diff -1 cycles, maxerr 516 cycles)
> [ 133.975491] CPU 14: synchronized TICK with master CPU (last diff -3 cycles, maxerr 531 cycles)
> [ 133.979943] CPU 15: synchronized TICK with master CPU (last diff -3 cycles, maxerr 531 cycles)
> [ 133.980146] Brought up 4 CPUs
So this looks like this might be the issue. On a scsi-mq disabled boot,
you have 4 CPUs, but how are they numbered?
We might need Christophs debug patch on top this to fully know...
--
Jens Axboe
next prev parent reply other threads:[~2014-11-14 19:42 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-11-14 11:32 Another (ESP?) scsi blk-mq problem on sparc64 Meelis Roos
2014-11-14 11:32 ` Meelis Roos
2014-11-14 16:58 ` Christoph Hellwig
2014-11-14 16:58 ` Christoph Hellwig
2014-11-14 17:01 ` Jens Axboe
2014-11-14 17:01 ` Jens Axboe
2014-11-14 19:35 ` Meelis Roos
2014-11-14 19:35 ` Meelis Roos
2014-11-14 19:42 ` Jens Axboe [this message]
2014-11-14 19:42 ` Jens Axboe
2014-11-14 22:59 ` Meelis Roos
2014-11-14 22:59 ` Meelis Roos
2014-11-14 23:29 ` Jens Axboe
2014-11-14 23:29 ` Jens Axboe
2014-11-15 6:48 ` Meelis Roos
2014-11-15 6:48 ` Meelis Roos
2014-11-15 15:31 ` Jens Axboe
2014-11-15 15:31 ` Jens Axboe
2014-11-20 6:01 ` Christoph Hellwig
2014-11-20 6:01 ` Christoph Hellwig
2014-11-21 19:56 ` David Miller
2014-11-21 19:56 ` David Miller
2014-11-24 8:21 ` Christoph Hellwig
2014-11-24 8:21 ` Christoph Hellwig
2014-11-24 15:35 ` Jens Axboe
2014-11-24 15:35 ` Jens Axboe
2014-11-24 16:22 ` Paul E. McKenney
2014-11-24 16:22 ` Paul E. McKenney
2014-11-24 17:16 ` Jens Axboe
2014-11-24 17:16 ` Jens Axboe
2014-11-24 17:31 ` Paul E. McKenney
2014-11-24 17:31 ` Paul E. McKenney
2014-11-24 17:33 ` Jens Axboe
2014-11-24 17:33 ` Jens Axboe
2014-11-24 17:44 ` Paul E. McKenney
2014-11-24 17:44 ` Paul E. McKenney
2014-11-24 21:56 ` David Miller
2014-11-24 21:56 ` David Miller
2014-11-24 22:01 ` Jens Axboe
2014-11-24 22:01 ` Jens Axboe
2014-11-24 22:09 ` David Miller
2014-11-24 22:09 ` David Miller
2014-11-24 22:20 ` Jens Axboe
2014-11-24 22:20 ` Jens Axboe
2014-11-24 22:23 ` mroos
2014-11-24 22:23 ` mroos
2014-11-24 22:28 ` David Miller
2014-11-24 22:28 ` David Miller
2015-01-29 7:53 ` Meelis Roos
2015-01-29 7:53 ` Meelis Roos
2015-01-29 16:37 ` Jens Axboe
2015-01-29 16:37 ` Jens Axboe
2015-09-04 8:33 ` Meelis Roos
2015-09-04 8:33 ` Meelis Roos
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=54665B30.4070708@kernel.dk \
--to=axboe@kernel.dk \
--cc=davem@davemloft.net \
--cc=hch@infradead.org \
--cc=linux-scsi@vger.kernel.org \
--cc=mroos@linux.ee \
--cc=paulmck@linux.vnet.ibm.com \
--cc=sparclinux@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.