From: Thomas Gleixner <tglx@linutronix.de>
To: Andrew Morton <akpm@osdl.org>
Cc: Ingo Molnar <mingo@elte.hu>, LKML <linux-kernel@vger.kernel.org>,
John Stultz <johnstul@us.ibm.com>,
Valdis Kletnieks <valdis.kletnieks@vt.edu>,
Arjan van de Ven <arjan@infradead.org>,
Dave Jones <davej@redhat.com>,
David Woodhouse <dwmw2@infradead.org>, Jim Gettys <jg@laptop.org>,
Roman Zippel <zippel@linux-m68k.org>
Subject: Re: [patch 00/22] high resolution timers / dynamic ticks - V3
Date: Thu, 05 Oct 2006 11:48:25 +0200 [thread overview]
Message-ID: <1160041705.9060.35.camel@localhost.localdomain> (raw)
In-Reply-To: <20061005015052.4b4f14e8.akpm@osdl.org>
On Thu, 2006-10-05 at 01:50 -0700, Andrew Morton wrote:
> The stock kernel shows a local-apic interrupt rate of 18Hz (HZ=250). Other
> times I've seen 13Hz.
>
> With this patch series applied, disabling the local apic in config fixes
> things up (using the PIT).
>
> With the stock kernel and SMP, the system is slow, but not _as_ slow.
> Bootup takes maybe twice as long, but not all week. This time the local
> APIC interrupt rate is 8Hz, so something peculiar is happening here -
> nothing is proportional.
The stock SMP kernel increases jiffies in IRQ0, while HIGH_RES=y
emulates the tick via the lapic timer. If you disable lapic, hrtimer
emulates via PIT in the HIGH_RES=y case.
> It'd be nice to fix the local apic rather than working around it. Any idea
> why it's doing this?
Not at all. Can you please apply the patch below and add "apic=verbose"
to the commandline ? This should give use some hint.
Watch out for "calibrating APIC timer ..." in the boot messages.
tglx
Index: linux-2.6.18-mm3/arch/i386/kernel/apic.c
===================================================================
--- linux-2.6.18-mm3.orig/arch/i386/kernel/apic.c 2006-10-04 19:11:08.000000000 +0200
+++ linux-2.6.18-mm3/arch/i386/kernel/apic.c 2006-10-05 11:33:04.000000000 +0200
@@ -1147,7 +1147,7 @@ static int __init calibrate_APIC_clock(v
lapic_clockevent.min_delta_ns =
clockevent_delta2ns(0xF, &lapic_clockevent);
- apic_printk(APIC_VERBOSE, "..... tt1-tt2 %ld\n", tt1 - tt2);
+ apic_printk(APIC_VERBOSE, "..... tt1: %ld tt2: %ld\n", tt1, tt2);
apic_printk(APIC_VERBOSE, "..... mult: %ld\n", lapic_clockevent.mult);
apic_printk(APIC_VERBOSE, "..... calibration result: %ld\n", result);
prev parent reply other threads:[~2006-10-05 9:43 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-10-04 17:31 [patch 00/22] high resolution timers / dynamic ticks - V3 Thomas Gleixner
2006-10-04 17:31 ` [patch 01/22] GTOD: exponential update_wall_time Thomas Gleixner
2006-10-04 17:31 ` [patch 02/22] GTOD: persistent clock support, core Thomas Gleixner
2006-10-04 17:31 ` [patch 03/22] GTOD: persistent clock support, i386 Thomas Gleixner
2006-10-04 17:31 ` [patch 04/22] time: uninline jiffies.h Thomas Gleixner
2006-10-04 17:31 ` [patch 05/22] time: fix msecs_to_jiffies() bug Thomas Gleixner
2006-10-04 17:31 ` [patch 06/22] time: fix timeout overflow Thomas Gleixner
2006-10-04 17:31 ` [patch 07/22] cleanup: uninline irq_enter() and move it into a function Thomas Gleixner
2006-10-04 17:31 ` [patch 08/22] dynticks: extend next_timer_interrupt() to use a reference jiffie Thomas Gleixner
2006-10-04 17:31 ` [patch 09/22] hrtimers: namespace and enum cleanup Thomas Gleixner
2006-10-04 17:31 ` [patch 10/22] hrtimers: clean up locking Thomas Gleixner
2006-10-04 17:31 ` [patch 11/22] hrtimers: state tracking Thomas Gleixner
2006-10-04 17:31 ` [patch 12/22] hrtimers: clean up callback tracking Thomas Gleixner
2006-10-04 17:31 ` [patch 13/22] hrtimers: Move and add documentation Thomas Gleixner
2006-10-04 17:31 ` [patch 14/22] clockevents: core Thomas Gleixner
2006-10-04 17:31 ` [patch 15/22] clockevents: drivers for i386 Thomas Gleixner
2006-10-04 17:31 ` [patch 16/22] high-res timers: core Thomas Gleixner
2006-10-04 17:31 ` [patch 17/22] GTOD: Mark TSC unusable for highres timers Thomas Gleixner
2006-10-04 17:31 ` [patch 18/22] dynticks: core Thomas Gleixner
2006-10-04 17:31 ` [patch 19/22] dyntick: add nohz stats to /proc/stat Thomas Gleixner
2006-10-04 17:31 ` [patch 20/22] dynticks: i386 arch code Thomas Gleixner
2006-10-04 17:31 ` [patch 21/22] high-res timers, dynticks: enable i386 support Thomas Gleixner
2006-10-04 17:31 ` [patch 22/22] debugging feature: timer stats Thomas Gleixner
2006-10-05 8:16 ` [patch 00/22] high resolution timers / dynamic ticks - V3 Andrew Morton
2006-10-05 8:11 ` Ingo Molnar
2006-10-05 8:17 ` Ingo Molnar
2006-10-05 20:57 ` Andi Kleen
2006-10-05 21:11 ` Thomas Gleixner
2006-10-06 7:28 ` Arjan van de Ven
2006-10-16 10:53 ` Andi Kleen
2006-10-05 8:19 ` Andrew Morton
2006-10-05 8:23 ` Ingo Molnar
2006-10-05 8:50 ` Andrew Morton
2006-10-05 9:48 ` Thomas Gleixner [this message]
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=1160041705.9060.35.camel@localhost.localdomain \
--to=tglx@linutronix.de \
--cc=akpm@osdl.org \
--cc=arjan@infradead.org \
--cc=davej@redhat.com \
--cc=dwmw2@infradead.org \
--cc=jg@laptop.org \
--cc=johnstul@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=valdis.kletnieks@vt.edu \
--cc=zippel@linux-m68k.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