From: Petr Tesarik <ptesarik@suse.cz>
To: "Luck, Tony" <tony.luck@intel.com>
Cc: "linux-ia64@vger.kernel.org" <linux-ia64@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Hedi Berriche <hedi@sgi.com>
Subject: Re: Serious problem with ticket spinlocks on ia64
Date: Fri, 27 Aug 2010 22:13:18 +0000 [thread overview]
Message-ID: <201008280013.19941.ptesarik@suse.cz> (raw)
In-Reply-To: <987664A83D2D224EAE907B061CE93D53015D91D45F@orsmsx505.amr.corp.intel.com>
On Friday 27 of August 2010 23:11:55 Luck, Tony wrote:
> > One more idea. The wrap-around case is the only one when the high word is
> > modified. This is in fact the only case when the fetchadd.acq competes
> > with the st2.rel about the actual contents of that location. I don't know
> > if it matters...
>
> I pondered that for a while - but I have difficulty believing that
> fetchadd looks at which bits changed and only writes back the bytes
> that did.
OTOH the counter is only 15-bit, so it also wraps around at 0xfffe7fff, but
I have never seen it fail there. It always fails after the wrap-around from
0xfffeffff.
Petr Tesarik
WARNING: multiple messages have this Message-ID (diff)
From: Petr Tesarik <ptesarik@suse.cz>
To: "Luck, Tony" <tony.luck@intel.com>
Cc: "linux-ia64@vger.kernel.org" <linux-ia64@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Hedi Berriche <hedi@sgi.com>
Subject: Re: Serious problem with ticket spinlocks on ia64
Date: Sat, 28 Aug 2010 00:13:18 +0200 [thread overview]
Message-ID: <201008280013.19941.ptesarik@suse.cz> (raw)
In-Reply-To: <987664A83D2D224EAE907B061CE93D53015D91D45F@orsmsx505.amr.corp.intel.com>
On Friday 27 of August 2010 23:11:55 Luck, Tony wrote:
> > One more idea. The wrap-around case is the only one when the high word is
> > modified. This is in fact the only case when the fetchadd.acq competes
> > with the st2.rel about the actual contents of that location. I don't know
> > if it matters...
>
> I pondered that for a while - but I have difficulty believing that
> fetchadd looks at which bits changed and only writes back the bytes
> that did.
OTOH the counter is only 15-bit, so it also wraps around at 0xfffe7fff, but
I have never seen it fail there. It always fails after the wrap-around from
0xfffeffff.
Petr Tesarik
next prev parent reply other threads:[~2010-08-27 22:13 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-08-27 13:37 Serious problem with ticket spinlocks on ia64 Petr Tesarik
2010-08-27 13:37 ` Petr Tesarik
2010-08-27 13:48 ` Hedi Berriche
2010-08-27 13:48 ` Hedi Berriche
2010-08-27 14:09 ` Petr Tesarik
2010-08-27 14:09 ` Petr Tesarik
2010-08-27 14:31 ` Hedi Berriche
2010-08-27 14:31 ` Hedi Berriche
2010-08-27 14:40 ` Petr Tesarik
2010-08-27 14:40 ` Petr Tesarik
2010-08-27 14:52 ` Hedi Berriche
2010-08-27 14:52 ` Hedi Berriche
2010-08-27 16:37 ` Petr Tesarik
2010-08-27 16:37 ` Petr Tesarik
2010-08-27 16:08 ` Luck, Tony
2010-08-27 16:08 ` Luck, Tony
2010-08-27 17:16 ` Petr Tesarik
2010-08-27 17:16 ` Petr Tesarik
2010-08-27 18:20 ` Hedi Berriche
2010-08-27 18:20 ` Hedi Berriche
2010-08-27 19:40 ` Petr Tesarik
2010-08-27 19:40 ` Petr Tesarik
2010-08-27 20:29 ` Luck, Tony
2010-08-27 20:29 ` Luck, Tony
2010-08-27 20:41 ` Petr Tesarik
2010-08-27 20:41 ` Petr Tesarik
2010-08-27 21:03 ` Petr Tesarik
2010-08-27 21:03 ` Petr Tesarik
2010-08-27 21:11 ` Luck, Tony
2010-08-27 21:11 ` Luck, Tony
2010-08-27 22:13 ` Petr Tesarik [this message]
2010-08-27 22:13 ` Petr Tesarik
2010-08-27 23:26 ` Luck, Tony
2010-08-27 23:26 ` Luck, Tony
2010-08-27 23:55 ` Luck, Tony
2010-08-27 23:55 ` Luck, Tony
2010-08-28 0:28 ` Hedi Berriche
2010-08-28 0:28 ` Hedi Berriche
2010-08-28 5:01 ` Luck, Tony
2010-08-28 5:01 ` Luck, Tony
2010-08-30 18:17 ` Luck, Tony
2010-08-30 18:17 ` Luck, Tony
2010-08-30 21:41 ` Petr Tesarik
2010-08-30 21:41 ` Petr Tesarik
2010-08-30 22:43 ` Tony Luck
2010-08-30 22:43 ` Tony Luck
2010-08-31 22:17 ` Tony Luck
2010-08-31 22:17 ` Tony Luck
2010-09-01 23:09 ` Tony Luck
2010-09-01 23:09 ` Tony Luck
2010-09-02 0:26 ` Hedi Berriche
2010-09-02 0:26 ` Hedi Berriche
2010-09-03 0:06 ` Tony Luck
2010-09-03 0:06 ` Tony Luck
2010-09-03 9:04 ` Petr Tesarik
2010-09-03 9:04 ` Petr Tesarik
2010-09-03 14:35 ` Petr Tesarik
2010-09-03 14:35 ` Petr Tesarik
2010-09-03 14:52 ` Petr Tesarik
2010-09-03 14:52 ` Petr Tesarik
2010-09-03 15:50 ` Tony Luck
2010-09-03 15:50 ` Tony Luck
2010-09-06 14:47 ` Petr Tesarik
2010-09-06 14:47 ` Petr Tesarik
2010-09-07 13:17 ` Petr Tesarik
2010-09-07 13:17 ` Petr Tesarik
2010-09-07 17:35 ` Tony Luck
2010-09-07 17:35 ` Tony Luck
2010-09-08 15:55 ` Tony Luck
2010-09-08 15:55 ` Tony Luck
2010-09-10 2:55 ` Dave Jones
2010-09-10 2:55 ` Dave Jones
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=201008280013.19941.ptesarik@suse.cz \
--to=ptesarik@suse.cz \
--cc=hedi@sgi.com \
--cc=linux-ia64@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tony.luck@intel.com \
/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.