From: cheuche+lkml@free.fr
To: linux-kernel@vger.kernel.org
Subject: Nforce2, APIC, CPU Disconnect and setup_boot_APIC_clock()
Date: Fri, 13 Feb 2004 16:55:00 +0100 [thread overview]
Message-ID: <20040213155500.GA6378@localnet> (raw)
In-Reply-To: <200402140041.17584.ross@datscreative.com.au>
[-- Attachment #1: Type: text/plain, Size: 1228 bytes --]
Hello all,
I once noticed there was a drift between the 8254 timer and the APIC
timer. With vanilla and -mm kernels, APIC timer is running faster. With
Ross' patches I noticed it was running slower, and the crashes go away.
I dig in that direction and found that with a APIC timer directly
programmed slower than calibrated, adding ~20 more bus cycles to the
counter, hangs disappear, at least during the tests (for a few minutes,
maybe they are made much rarer). I eventually disabled altogether the
APIC timer with the patchlet attached, and did an entire test (dumping
the whole hard drive to /dev/null with very high network and soundcard
activity), and it survived. I will continue to test, just to make
sure...
At least there is a way to get nforce2 + APIC + CPU disconnect and
actually have a cooler idle CPU. Side effects are no more LOC rising
counter in /proc/interrupts, no more nmi_watchdog=2 and if you work
around the bios acpi apic source override to get the timer on pin #0, no
more nmi_watchdog=1. This is of course not the best solution.
Now the experts may look why commenting out setup_boot_APIC_clock() in
APIC_init_uniprocessor() of arch/i386/kernel/apic.c works, and find a
better fix if any.
Mathieu
[-- Attachment #2: no_boot_apic_clock.patch --]
[-- Type: text/plain, Size: 299 bytes --]
--- arch/i386/kernel/apic.c.old 2004-02-13 16:13:39.000000000 +0100
+++ arch/i386/kernel/apic.c 2004-02-13 14:29:29.000000000 +0100
@@ -1198,7 +1198,7 @@
if (!skip_ioapic_setup && nr_ioapics)
setup_IO_APIC();
#endif
- setup_boot_APIC_clock();
+ /*setup_boot_APIC_clock();*/
return 0;
}
next prev parent reply other threads:[~2004-02-13 15:55 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-02-11 15:22 [PATCH] 2.6, 2.4, Nforce2, Experimental idle halt workaround instead of apic ack delay Ross Dickson
2004-02-12 18:17 ` Derek Foreman
2004-02-12 16:11 ` Daniel Drake
2004-02-12 19:30 ` [PATCH] 2.6, 2.4, Nforce2, Experimental idle halt workaroundinstead " Carlos Silva
2004-02-12 19:54 ` [PATCH] 2.6, 2.4, Nforce2, Experimental idle halt workaround instead " Derek Foreman
2004-02-12 21:44 ` Jesse Allen
2004-02-12 21:52 ` Derek Foreman
2004-02-12 22:06 ` Craig Bradney
2004-02-12 23:04 ` Jesse Allen
2004-02-12 23:15 ` Craig Bradney
2004-02-12 23:37 ` Jesse Allen
2004-02-12 23:50 ` Craig Bradney
2004-02-12 23:20 ` Roberto Sanchez
2004-02-13 11:17 ` Prakash K. Cheemplavam
2004-02-13 14:41 ` Ross Dickson
2004-02-13 15:55 ` cheuche+lkml [this message]
2004-02-14 1:24 ` Ross Dickson
2004-02-14 4:46 ` GCC feature request: warn on "if (function_name)" Jamie Lokier
2004-02-14 4:51 ` Andrew Pinski
2004-02-14 11:16 ` [PATCH] 2.6, 2.4, Nforce2, Experimental idle halt workaround instead of apic ack delay Prakash K. Cheemplavam
2004-02-14 16:13 ` Ross Dickson
2004-02-14 21:46 ` Ian Kumlien
2004-02-23 1:33 ` Prakash K. Cheemplavam
2004-02-23 19:50 ` Jesse Allen
2004-02-23 1:37 ` Prakash K. Cheemplavam
2004-02-25 12:38 ` Ross Dickson
2004-02-25 19:49 ` Prakash K. Cheemplavam
2004-02-25 21:44 ` Arjen Verweij
2004-02-26 0:13 ` Ross Dickson
2004-02-26 9:59 ` Mikael Pettersson
2004-03-07 14:46 ` Craig Bradney
2004-03-08 22:42 ` Arjen Verweij
2004-03-08 22:59 ` Craig Bradney
2004-03-08 23:11 ` Arjen Verweij
2004-03-14 12:04 ` Arjen Verweij
2004-03-09 18:38 ` Josh McKinney
2004-03-24 15:59 ` Edd Dumbill
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=20040213155500.GA6378@localnet \
--to=cheuche+lkml@free.fr \
--cc=linux-kernel@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).