From: Tony Lindgren <tony@atomide.com>
To: Pavel Machek <pavel@ucw.cz>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Arjan van de Ven <arjan@infradead.org>,
Martin Schwidefsky <schwidefsky@de.ibm.com>,
Andrea Arcangeli <andrea@suse.de>,
George Anzinger <george@mvista.com>,
Thomas Gleixner <tglx@linutronix.de>,
john stultz <johnstul@us.ibm.com>,
Zwane Mwaikambo <zwane@arm.linux.org.uk>,
Lee Revell <rlrevell@joe-job.com>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH] Dynamic tick, version 050127-1
Date: Sat, 5 Feb 2005 18:33:44 -0800 [thread overview]
Message-ID: <20050206023344.GA15853@atomide.com> (raw)
In-Reply-To: <20050205230017.GA1070@elf.ucw.cz>
* Pavel Machek <pavel@ucw.cz> [050205 15:08]:
> Hi!
>
> > > > > It could also be that the reprogamming of PIT timer does not work on
> > > > > your machine. I chopped off the udelays there... Can you try
> > > > > something like this:
> > > >
> > > > I added the udelays, but behaviour did not change.
> > >
> > > Yeah, and if the first patch was working better, that means the PIT
> > > interrupts work. I'll do another version of the patch where PIT
> > > interrupts work again without local APIC needed, let's see what
> > > happens with that.
> >
> > I think something broke TSC timer after the first patch, but I could
> > not figure out yet what. So the bad combo might be local APIC + TSC.
> > At least I'm seeing similar problems with local APIC + TSC timer.
> >
> > Attached is a slightly improved patch, but the patch does not fix
> > the TSC problem. It just fixes compile without local APIC, and
> > booting SMP kernel on uniprocessor machine.
> >
> > Currently the suggested combo is local APIC + ACPI PM timer...
>
> Ok, works slightly better: time no longer runs 2x too fast. When TSC
> is used, I get same behaviour as before ("sleepy machine"). With
> "notsc", machine seems to work okay, but I still get 1000 timer
> interrupts a second.
Sounds like dyn-tick did not get enabled then, maybe you don't have
CONFIG_X86_PM_TIMER, or don't have ACPI PM timer on your board?
After modifying I8042_POLL_PERIOD and leaving out CONFIG_NETFILTER
I'm getting roughly 6HZ timer rate when idle :)
$ dmesg | grep -i "time\|tick\|apic"
ACPI: PM-Timer IO Port: 0x1008
Kernel command line: root=/dev/nfs ip=dhcp ro console=ttyS0,115200
lapic init=/bin/minit
Local APIC disabled by BIOS -- reenabling.
Found and enabled local APIC!
mapped APIC to ffffd000 (fee00000)
Using pmtmr for high-res timesource
dyn-tick: Registering dynamic tick timer
per-CPU timeslice cutoff: 365.35 usecs.
task migration cache decay timeout: 1 msecs.
Machine check exception polling timer started.
Real Time Clock Driver v1.12
dyn-tick: Maximum ticks to skip limited to 2678
dyn-tick: Timer using dynamic tick
$ cat /proc/interrupts | grep timer && sleep 10 && cat /proc/interrupts | grep timer
0: 10689 XT-PIC timer
0: 10745 XT-PIC timer
> > And if that works, changing the I8042_POLL_PERIOD from HZ/20 in
> > drivers/input/serio/i8042.h to something like HZ increases the
> > sleep interval quite a bit. I think I had lots of polling also in
> > CONFIG_NETFILTER, but I haven't verified that.
>
> Okay, I set POLL_PERIOD to 5*HZ, and disabled USB. Perhaps it will
> sleep better now?
Sounds like your system is not running with the dyn-tick... I'll try
to fix that TSC bug.
Tony
next prev parent reply other threads:[~2005-02-06 2:35 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-01-27 21:29 [PATCH] Dynamic tick, version 050127-1 Tony Lindgren
2005-01-27 21:50 ` Tony Lindgren
2005-02-01 11:00 ` Pavel Machek
2005-02-01 20:40 ` Tony Lindgren
2005-02-01 21:25 ` Pavel Machek
2005-02-01 23:03 ` Tony Lindgren
2005-02-02 13:50 ` Pavel Machek
2005-02-02 13:50 ` Pavel Machek
2005-02-02 13:56 ` Pavel Machek
2005-02-02 14:11 ` Pavel Machek
2005-02-03 3:04 ` Tony Lindgren
2005-02-03 10:56 ` Pavel Machek
2005-02-03 16:43 ` Tony Lindgren
2005-02-04 5:19 ` Tony Lindgren
2005-02-04 6:33 ` Zwane Mwaikambo
2005-02-04 17:18 ` Tony Lindgren
2005-02-04 17:31 ` Zwane Mwaikambo
2005-02-04 17:42 ` Tony Lindgren
2005-02-04 17:54 ` Zwane Mwaikambo
2005-02-04 18:58 ` Tony Lindgren
2005-02-04 19:24 ` Tony Lindgren
2005-02-05 23:00 ` Pavel Machek
2005-02-06 2:33 ` Tony Lindgren [this message]
2005-02-06 3:54 ` Tony Lindgren
2005-02-06 8:41 ` Pavel Machek
2005-02-06 8:50 ` Pavel Machek
2005-02-06 17:07 ` Tony Lindgren
2005-02-06 12:15 ` Pavel Machek
2005-02-06 17:08 ` Tony Lindgren
2005-02-06 8:11 ` Pavel Machek
2005-02-06 8:53 ` Lee Revell
2005-02-06 10:25 ` Pavel Machek
2005-02-07 22:08 ` George Anzinger
2005-02-06 17:10 ` Tony Lindgren
2005-02-06 18:34 ` Pavel Machek
2005-02-01 20:20 ` Lee Revell
2005-02-01 23:42 ` Tony Lindgren
2005-02-02 1:06 ` Eric St-Laurent
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=20050206023344.GA15853@atomide.com \
--to=tony@atomide.com \
--cc=andrea@suse.de \
--cc=arjan@infradead.org \
--cc=benh@kernel.crashing.org \
--cc=george@mvista.com \
--cc=johnstul@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=pavel@ucw.cz \
--cc=rlrevell@joe-job.com \
--cc=schwidefsky@de.ibm.com \
--cc=tglx@linutronix.de \
--cc=zwane@arm.linux.org.uk \
/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