From: Pavel Machek <pavel@suse.cz>
To: Tony Lindgren <tony@atomide.com>
Cc: George Anzinger <george@mvista.com>,
john stultz <johnstul@us.ibm.com>,
Andrea Arcangeli <andrea@suse.de>,
Zwane Mwaikambo <zwane@arm.linux.org.uk>,
Con Kolivas <kernel@kolivas.org>,
Martin Schwidefsky <schwidefsky@de.ibm.com>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH] dynamic tick patch
Date: Wed, 19 Jan 2005 23:06:37 +0100 [thread overview]
Message-ID: <20050119220637.GA7513@elf.ucw.cz> (raw)
In-Reply-To: <20050119171106.GA14545@atomide.com>
Hi!
> > > As this patch is related to the VST/High-Res timers, there
> > > are probably various things that can be merged. I have not
> > > yet looked at what all could be merged.
> > >
> > > I'd appreciate some comments and testing!
> >
> > Good news is that it does seem to reduce number of interrupts. Bad
> > news is that time now runs faster (like "sleep 10" finishes in ~5
> > seconds) and that I could not measure any difference in power
> > consumption.
>
> Thanks for trying it out. I have quite accurate time here on my
> systems, and sleep works as it should. I wonder what's happening on
> your system? If you have a chance, could you please post the results
> from following simple tests?
Unpatched 2.6.11-rc1:
root@amd:~# dmesg | grep -i time; for i in 1 2 3 4 5; do ntpdate -b tak.cesnet.cz && sleep 10; done ; date && sleep 10 && date; while [ 1 ]; do date; done | uniq
PCI: Setting latency timer of device 0000:00:11.5 to 64
19 Jan 22:53:20 ntpdate[7943]: step time server 195.113.144.238 offset 0.013070 sec
19 Jan 22:53:36 ntpdate[8169]: step time server 195.113.144.238 offset -0.005736 sec
19 Jan 22:53:51 ntpdate[8427]: step time server 195.113.144.238 offset -0.010292 sec
19 Jan 22:54:06 ntpdate[8647]: step time server 195.113.144.238 offset -0.045055 sec
19 Jan 22:54:21 ntpdate[8889]: step time server 195.113.144.238 offset 0.054865 sec
Wed Jan 19 22:54:31 CET 2005
Wed Jan 19 22:54:41 CET 2005
Wed Jan 19 22:54:41 CET 2005
Wed Jan 19 22:54:42 CET 2005
Wed Jan 19 22:54:43 CET 2005
Wed Jan 19 22:54:44 CET 2005
Wed Jan 19 22:54:45 CET 2005
Wed Jan 19 22:54:46 CET 2005
Wed Jan 19 22:54:47 CET 2005
Wed Jan 19 22:54:48 CET 2005
Wed Jan 19 22:54:49 CET 2005
Wed Jan 19 22:54:50 CET 2005
Wed Jan 19 22:54:51 CET 2005
Wed Jan 19 22:54:52 CET 2005
Wed Jan 19 22:54:53 CET 2005
Wed Jan 19 22:54:54 CET 2005
Wed Jan 19 22:54:55 CET 2005
Wed Jan 19 22:54:56 CET 2005
On patched 2.6.11-rc1:
[Heh, clock is two times too fast, perhaps that makes ntpdate fail? -- yes.
root@amd:~# dmesg | grep -i time; for i in 1 2 3 4 5; do ntpdate -b tak.cesnet.cz && sleep 10; done ; date && sleep 10 && date; while [ 1 ]; do date; done | uniq
PCI: Setting latency timer of device 0000:00:11.5 to 64
dyn-tick: Enabling dynamic tick timer
dyn-tick: Timer using dynamic tick
19 Jan 22:59:16 ntpdate[1363]: no server suitable for synchronization found
19 Jan 22:59:25 ntpdate[1364]: no server suitable for synchronization found
19 Jan 22:59:34 ntpdate[1365]: no server suitable for synchronization found
19 Jan 22:59:42 ntpdate[1366]: no server suitable for synchronization found
19 Jan 22:59:51 ntpdate[1367]: no server suitable for synchronization found
Wed Jan 19 22:59:51 CET 2005
Wed Jan 19 23:00:01 CET 2005
Wed Jan 19 23:00:01 CET 2005
Wed Jan 19 23:00:02 CET 2005
Wed Jan 19 23:00:03 CET 2005
Wed Jan 19 23:00:04 CET 2005
Wed Jan 19 23:00:05 CET 2005
Wed Jan 19 23:00:06 CET 2005
Wed Jan 19 23:00:07 CET 2005
Wed Jan 19 23:00:08 CET 2005
Wed Jan 19 23:00:09 CET 2005
Wed Jan 19 23:00:10 CET 2005
I used -t 10 to force it to work. Notice that clock is two times too fast.
root@amd:~# dmesg | grep -i time; for i in 1 2 3 4 5; do ntpdate -t 10 tak.cesnet.cz && sleep 10; done ; date && sleep 10 && date; while [ 1 ]; do date; done |
uniq
PCI: Setting latency timer of device 0000:00:11.5 to 64
dyn-tick: Enabling dynamic tick timer
dyn-tick: Timer using dynamic tick
19 Jan 23:03:27 ntpdate[20782]: step time server 195.113.144.238 offset -45.355081 sec
19 Jan 23:03:38 ntpdate[20784]: step time server 195.113.144.238 offset -9.592768 sec
19 Jan 23:03:47 ntpdate[20786]: step time server 195.113.144.238 offset -12.048951 sec
19 Jan 23:04:00 ntpdate[20788]: step time server 195.113.144.238 offset -8.273278 sec
19 Jan 23:04:08 ntpdate[20790]: step time server 195.113.144.238 offset -12.240673 sec
Wed Jan 19 23:04:18 CET 2005
Wed Jan 19 23:04:28 CET 2005
Wed Jan 19 23:04:28 CET 2005
Wed Jan 19 23:04:29 CET 2005
Wed Jan 19 23:04:30 CET 2005
Wed Jan 19 23:04:31 CET 2005
Wed Jan 19 23:04:32 CET 2005
Wed Jan 19 23:04:33 CET 2005
Wed Jan 19 23:04:34 CET 2005
Wed Jan 19 23:04:35 CET 2005
Wed Jan 19 23:04:36 CET 2005
Wed Jan 19 23:04:37 CET 2005
Wed Jan 19 23:04:38 CET 2005
Wed Jan 19 23:04:39 CET 2005
Wed Jan 19 23:04:40 CET 2005
Anything else I should try?
Pavel
--
People were complaining that M$ turns users into beta-testers...
...jr ghea gurz vagb qrirybcref, naq gurl frrz gb yvxr vg gung jnl!
next prev parent reply other threads:[~2005-01-19 22:10 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-01-19 0:05 [PATCH] dynamic tick patch Tony Lindgren
2005-01-19 0:22 ` Lee Revell
2005-01-19 1:04 ` Tony Lindgren
2005-01-19 4:21 ` Benjamin Herrenschmidt
2005-01-19 5:07 ` Tony Lindgren
2005-01-19 5:21 ` Tony Lindgren
2005-01-19 5:44 ` Benjamin Herrenschmidt
2005-01-19 6:26 ` Tony Lindgren
2005-01-19 9:45 ` Pavel Machek
2005-01-19 5:28 ` Benjamin Herrenschmidt
2005-01-19 6:37 ` Tony Lindgren
2005-01-19 7:08 ` Benjamin Herrenschmidt
2005-01-19 7:31 ` Tony Lindgren
2005-01-19 14:11 ` Stephen Frost
2005-01-19 17:17 ` Tony Lindgren
[not found] ` <OFDC470564.D4624EB3-ON41256F8E.00512848-41256F8E.005428CC@de.ibm.com>
2005-01-19 17:37 ` Tony Lindgren
2005-01-19 9:43 ` Pavel Machek
2005-01-19 17:13 ` Tony Lindgren
2005-01-19 17:48 ` Andrea Arcangeli
2005-01-19 18:19 ` Tony Lindgren
2005-01-19 19:12 ` Andrea Arcangeli
2005-01-19 19:17 ` Tony Lindgren
2005-01-19 19:34 ` Tony Lindgren
2005-01-19 22:42 ` Andrea Arcangeli
2005-01-19 22:59 ` George Anzinger
2005-01-19 23:17 ` Tony Lindgren
2005-01-20 0:24 ` George Anzinger
2005-01-20 8:04 ` Tony Lindgren
2005-01-20 23:10 ` George Anzinger
2005-01-21 17:35 ` Tony Lindgren
2005-01-21 20:23 ` George Anzinger
2005-01-19 23:26 ` Thomas Gleixner
2005-01-19 23:45 ` john stultz
2005-01-20 5:56 ` Thomas Gleixner
2005-01-20 0:39 ` George Anzinger
2005-01-20 3:15 ` Valdis.Kletnieks
2005-01-19 11:36 ` Pavel Machek
2005-01-19 17:11 ` Tony Lindgren
2005-01-19 17:30 ` Arjan van de Ven
2005-01-19 17:41 ` Tony Lindgren
2005-01-19 22:06 ` Pavel Machek [this message]
2005-01-19 23:08 ` Tony Lindgren
2005-01-19 23:46 ` Pavel Machek
2005-01-19 23:53 ` Tony Lindgren
2005-01-19 23:59 ` Pavel Machek
2005-01-20 0:07 ` Tony Lindgren
2005-01-20 0:44 ` Pavel Machek
2005-01-20 0:54 ` Pavel Machek
2005-01-20 7:39 ` Tony Lindgren
2005-01-19 22:20 ` Pavel Machek
2005-01-20 4:02 ` Zwane Mwaikambo
2005-01-21 17:48 ` Tony Lindgren
2005-01-21 18:27 ` Zwane Mwaikambo
2005-01-21 18:38 ` Tony Lindgren
2005-01-21 18:54 ` Pavel Machek
2005-01-21 21:23 ` Zwane Mwaikambo
2005-01-21 21:29 ` Pavel Machek
2005-01-21 20:25 ` George Anzinger
2005-01-21 21:38 ` Zwane Mwaikambo
2005-01-22 7:24 ` George Anzinger
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=20050119220637.GA7513@elf.ucw.cz \
--to=pavel@suse.cz \
--cc=andrea@suse.de \
--cc=george@mvista.com \
--cc=johnstul@us.ibm.com \
--cc=kernel@kolivas.org \
--cc=linux-kernel@vger.kernel.org \
--cc=schwidefsky@de.ibm.com \
--cc=tony@atomide.com \
--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