From: Fernando Pablo Lopez-Lezcano <nando@ccrma.Stanford.EDU>
To: Lee Revell <rlrevell@joe-job.com>
Cc: Scott Wood <scott@timesys.com>, Ingo Molnar <mingo@elte.hu>,
manas.saksena@timesys.com,
linux-kernel <linux-kernel@vger.kernel.org>,
Fernando Pablo Lopez-Lezcano <nando@ccrma.Stanford.EDU>
Subject: Re: [patch] PPC/PPC64 port of voluntary preempt patch
Date: 26 Aug 2004 18:18:54 -0700 [thread overview]
Message-ID: <1093569534.22682.222.camel@cmn37.stanford.edu> (raw)
In-Reply-To: <1093490252.5678.56.camel@krustophenia.net>
On Wed, 2004-08-25 at 20:17, Lee Revell wrote:
> On Tue, 2004-08-24 at 15:51, Scott Wood wrote:
> > On Mon, Aug 23, 2004 at 06:18:16PM -0400, Scott Wood wrote:
> > > I have attached a port of the voluntary preempt patch to PPC and
> > > PPC64. The patch is against P7, but it applies against P8 as well.
> > > I've tested it on a dual G5 Mac, both in uniprocessor and SMP.
> > > Some notes on changes to the generic part of the patch/existing
> > > generic code:
> >
> > Another thing that I forgot to mention is that I have some doubts as
> > to the current generic_synchronize_irq() implementation. Given that
> > IRQs are now preemptible, a higher priority RT thread calling
> > synchronize_irq can't just spin waiting for the IRQ to complete, as
> > it never will (and it wouldn't be a great idea for non-RT tasks
> > either). I see that a do_hardirq() call was added, presumably to
> > hurry completion of the interrupt, but is that really safe? It looks
> > like that could end up re-entering handlers, and you'd still have a
> > partially executed handler after synchronize_irq() finishes (causing
> > not only an extra end() call, but possibly code being executed after
> > it's been unloaded, and other synchronization violations).
> >
> > If I'm missing something, please let me know, but I don't see a good
> > way to implement it without blocking for the IRQ thread's completion
> > (such as with the per-IRQ waitqueues in M5).
>
> I think Scott may be on to something. There are several reports that P9
> does not work on SMP machines at all - it either doesn't boot, locks up
> the first time there is heavy IRQ activity (starting KDE), or locks up
> as soon as the first RT process is run. This is exactly the behavior
> that would be expected if Scott is correct. See this thread:
>
> http://ccrma-mail.stanford.edu/pipermail/planetccrma/2004-August/005899.html
>
> Does anyone have P9 working on SMP? Fernando, can you see if M5 works
> on SMP? If this works it would seem that the preemptible IRQs are the
> problem.
Sorry, I could not get SMP 2.6.8.1 + voluntary M5 to boot on my dual
Athlon test system. Again problems with interrupts but worse than P9,
this time acpi=off or pci=noacpi did not help (I can boot single user,
but the machine hang in the network startup - or if I disable that,
later on X startup). I saw two messages, one "irq 9: nobody cared!" and
then "Disabling IRQ # 9" (that's the one for the network card). On a
different boot:
Badness in free_irq at .... irq.c
free_irq
load_balance_new_idle
floppy_release_irq_and_dma
set_dor
motor_off_callback
...
So I could not get to the point where I could test jack and SCHED_FIFO
processes.
-- Fernando
next prev parent reply other threads:[~2004-08-27 1:25 UTC|newest]
Thread overview: 93+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-08-23 22:18 Scott Wood
2004-08-24 6:14 ` [patch] voluntary-preempt-2.6.8.1-P9 Ingo Molnar
2004-08-24 17:43 ` K.R. Foley
2004-08-24 20:32 ` Lee Revell
2004-08-24 20:53 ` Scott Wood
2004-08-24 19:20 ` K.R. Foley
2004-08-24 22:47 ` Lee Revell
2004-08-25 2:00 ` Lee Revell
2004-08-25 3:17 ` K.R. Foley
2004-08-25 3:22 ` Lee Revell
2004-08-25 14:34 ` K.R. Foley
2004-08-25 16:00 ` K.R. Foley
2004-08-25 3:26 ` K.R. Foley
2004-08-25 9:58 ` [patch] voluntary-preempt-2.6.8.1-P9 : oprofile latency at 3.3ms P.O. Gaillard
2004-08-26 21:39 ` [patch] voluntary-preempt-2.6.8.1-P9 Lee Revell
2004-08-27 16:54 ` Lee Revell
2004-08-28 7:37 ` Ingo Molnar
2004-08-28 15:10 ` Lee Revell
2004-08-28 12:14 ` Ingo Molnar
2004-08-30 9:27 ` voluntary-preempt-2.6.8.1-P9 : big latency when logging on console P.O. Gaillard
2004-08-30 9:41 ` Ingo Molnar
2004-08-30 12:25 ` P.O. Gaillard
2004-08-30 9:48 ` [patch] voluntary-preempt-2.6.8.1-P9 : a few submillisecond latencies P.O. Gaillard
2004-08-28 12:03 ` [patch] voluntary-preempt-2.6.9-rc1-bk4-Q0 Ingo Molnar
2004-08-28 16:18 ` Felipe Alfaro Solana
2004-08-28 16:50 ` K.R. Foley
2004-08-28 17:52 ` Lee Revell
2004-08-28 19:44 ` [patch] voluntary-preempt-2.6.9-rc1-bk4-Q2 Ingo Molnar
2004-08-28 20:01 ` Lee Revell
2004-08-28 20:04 ` Ingo Molnar
2004-08-28 20:08 ` Lee Revell
2004-08-28 20:10 ` Daniel Schmitt
2004-08-28 20:31 ` [patch] voluntary-preempt-2.6.9-rc1-bk4-Q3 Ingo Molnar
2004-08-28 21:10 ` Lee Revell
2004-08-28 21:13 ` Ingo Molnar
2004-08-28 21:16 ` Lee Revell
2004-08-28 23:51 ` Lee Revell
2004-08-29 2:35 ` Lee Revell
2004-08-29 5:43 ` [patch] voluntary-preempt-2.6.9-rc1-bk4-Q4 Ingo Molnar
2004-08-29 6:57 ` Lee Revell
2004-08-29 18:01 ` Ingo Molnar
2004-08-29 19:06 ` Ingo Molnar
2004-08-30 0:47 ` K.R. Foley
2004-08-30 3:42 ` K.R. Foley
2004-08-30 13:06 ` Alan Cox
2004-08-30 17:37 ` Ingo Molnar
2004-08-31 16:39 ` K.R. Foley
2004-08-30 9:06 ` [patch] voluntary-preempt-2.6.9-rc1-bk4-Q5 Ingo Molnar
2004-08-30 14:25 ` Thomas Charbonnel
2004-08-30 18:00 ` Ingo Molnar
2004-08-31 19:23 ` Thomas Charbonnel
2004-08-31 19:30 ` Ingo Molnar
2004-08-31 19:45 ` Thomas Charbonnel
2004-08-31 6:40 ` Lee Revell
2004-08-31 6:53 ` Ingo Molnar
2004-08-31 23:03 ` Lee Revell
2004-09-01 15:52 ` Martin Josefsson
2004-09-01 21:15 ` Lee Revell
2004-09-01 21:30 ` Lee Revell
2004-08-31 7:06 ` Ingo Molnar
2004-08-31 19:21 ` Lee Revell
2004-08-31 19:37 ` Ingo Molnar
2004-08-31 19:47 ` Lee Revell
2004-08-31 19:51 ` Ingo Molnar
2004-08-31 20:09 ` Ingo Molnar
2004-08-31 20:10 ` Lee Revell
2004-08-31 20:14 ` Ingo Molnar
2004-08-31 20:20 ` Ingo Molnar
2004-08-31 20:34 ` Lee Revell
2004-08-31 20:39 ` Ingo Molnar
2004-08-31 20:41 ` Lee Revell
2004-08-31 17:40 ` Peter Zijlstra
2004-09-01 1:43 ` Lee Revell
2004-09-01 2:30 ` Lee Revell
2004-09-01 7:27 ` Lee Revell
2004-09-01 8:29 ` [patch] voluntary-preempt-2.6.9-rc1-bk4-Q6 Ingo Molnar
2004-09-01 13:51 ` [patch] voluntary-preempt-2.6.9-rc1-bk4-Q7 Ingo Molnar
2004-09-01 17:09 ` Thomas Charbonnel
2004-09-01 19:03 ` K.R. Foley
2004-09-01 20:11 ` Peter Zijlstra
2004-09-01 20:16 ` Lee Revell
2004-09-01 20:53 ` K.R. Foley
[not found] ` <41367E5D.3040605@cybsft.com>
2004-09-02 5:37 ` Ingo Molnar
2004-09-02 5:40 ` Ingo Molnar
2004-08-30 12:52 ` [patch] voluntary-preempt-2.6.9-rc1-bk4-Q3 Ingo Molnar
2004-08-29 7:40 ` Matt Heler
2004-08-24 19:51 ` [patch] PPC/PPC64 port of voluntary preempt patch Scott Wood
2004-08-26 3:17 ` Lee Revell
2004-08-26 16:38 ` Scott Wood
2004-08-27 1:18 ` Fernando Pablo Lopez-Lezcano [this message]
2004-08-28 12:36 ` Ingo Molnar
2004-08-28 13:01 ` [patch] voluntary-preempt-2.6.9-rc1-bk4-Q1 Ingo Molnar
2004-08-30 1:06 ` Fernando Pablo Lopez-Lezcano
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=1093569534.22682.222.camel@cmn37.stanford.edu \
--to=nando@ccrma.stanford.edu \
--cc=linux-kernel@vger.kernel.org \
--cc=manas.saksena@timesys.com \
--cc=mingo@elte.hu \
--cc=rlrevell@joe-job.com \
--cc=scott@timesys.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®