-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
In doing a web search on system clock speeds being too high, I found entries
describing exactly what I am experiencing in the linux-kernel list archives,
but have not yet found a resolution.
I have Mandrake 10.0, kernel-2.6.3-7mdk installed, on an IBM Thinkpad 1412
laptop, celeron 366, 512MB RAM. I am finding that my system clock is ticking
away at a rate of about 3:1 vs reality, ie, I count ~3 seconds on the system
clock for every 1 real second. I am running ntpd but this is unable to keep
up with the rate of system clock passage.
I had to slow my keyboard repeat rate _way_ down in order to be able to type
at all as well. The system is limited, in that I have no way to alter the
actual system clock (in bios at any rate). The CPU is properly identified as
a celeron 366.
Does anyone have any enlightenment, or a fix, to offer? The exact same
software setup on a desktop system, Athlon XP2700+, has no such problems.
praedor
- --
"George W. Bush is a deserter, an election thief, a drunk driver, a WMD
liar and a functional illiterate. And he poops his pants."
- --Barbara Bush, his mother
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (GNU/Linux)
iD8DBQFAZITKSTapoRk9vv8RAkxyAJ45KBKN7ngdNX6qTOwSBIxEs7rfcACgl8e0
0lKo+bfaSHPcNpA+36WGCrE=
=ZdjK
-----END PGP SIGNATURE-----
On Fri, 2004-03-26 at 11:30, Praedor Atrebates wrote:
> In doing a web search on system clock speeds being too high, I found entries
> describing exactly what I am experiencing in the linux-kernel list archives,
> but have not yet found a resolution.
>
> I have Mandrake 10.0, kernel-2.6.3-7mdk installed, on an IBM Thinkpad 1412
> laptop, celeron 366, 512MB RAM. I am finding that my system clock is ticking
> away at a rate of about 3:1 vs reality, ie, I count ~3 seconds on the system
> clock for every 1 real second. I am running ntpd but this is unable to keep
> up with the rate of system clock passage.
>
> I had to slow my keyboard repeat rate _way_ down in order to be able to type
> at all as well. The system is limited, in that I have no way to alter the
> actual system clock (in bios at any rate). The CPU is properly identified as
> a celeron 366.
>
> Does anyone have any enlightenment, or a fix, to offer? The exact same
> software setup on a desktop system, Athlon XP2700+, has no such problems.
Could you please send me dmesg output for this system?
Does booting w/ "clock=pit" help?
thanks
-john
Praedor Atrebates wrote:
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
>
> In doing a web search on system clock speeds being too high, I found entries
> describing exactly what I am experiencing in the linux-kernel list archives,
> but have not yet found a resolution.
>
> I have Mandrake 10.0, kernel-2.6.3-7mdk installed, on an IBM Thinkpad 1412
> laptop, celeron 366, 512MB RAM. I am finding that my system clock is ticking
> away at a rate of about 3:1 vs reality, ie, I count ~3 seconds on the system
> clock for every 1 real second. I am running ntpd but this is unable to keep
> up with the rate of system clock passage.
>
> I had to slow my keyboard repeat rate _way_ down in order to be able to type
> at all as well. The system is limited, in that I have no way to alter the
> actual system clock (in bios at any rate). The CPU is properly identified as
> a celeron 366.
>
> Does anyone have any enlightenment, or a fix, to offer? The exact same
> software setup on a desktop system, Athlon XP2700+, has no such problems.
Try this in the boot command line "clock=pmtmr". If that fails, then try
"clock=pit".
-g
>
> praedor
> - --
> "George W. Bush is a deserter, an election thief, a drunk driver, a WMD
> liar and a functional illiterate. And he poops his pants."
> - --Barbara Bush, his mother
> -----BEGIN PGP SIGNATURE-----
> Version: GnuPG v1.2.4 (GNU/Linux)
>
> iD8DBQFAZITKSTapoRk9vv8RAkxyAJ45KBKN7ngdNX6qTOwSBIxEs7rfcACgl8e0
> 0lKo+bfaSHPcNpA+36WGCrE=
> =ZdjK
> -----END PGP SIGNATURE-----
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
--
George Anzinger [email protected]
High-res-timers: http://sourceforge.net/projects/high-res-timers/
Preemption patch: http://www.kernel.org/pub/linux/kernel/people/rml
On Friday 26 March 2004 04:22 pm, john stultz held forth thus:
> On Fri, 2004-03-26 at 11:30, Praedor Atrebates wrote:
> > In doing a web search on system clock speeds being too high, I found
> > entries describing exactly what I am experiencing in the linux-kernel
> > list archives, but have not yet found a resolution.
[...]
> > Does anyone have any enlightenment, or a fix, to offer? The exact same
> > software setup on a desktop system, Athlon XP2700+, has no such problems.
>
> Could you please send me dmesg output for this system?
>
> Does booting w/ "clock=pit" help?
Thank you, this did fix the problem. Now I have to set the type-matic setting
up because it is so sluggish.
What is clock=pit doing? What is behind this accelerated clock?
praedor
--
"George W. Bush is a deserter, an election thief, a drunk driver, a WMD
liar and a functional illiterate. And he poops his pants."
--Barbara Bush, his mother
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
On Friday 26 March 2004 04:46 pm, George Anzinger held forth thus:
> Praedor Atrebates wrote:
> > In doing a web search on system clock speeds being too high, I found
> > entries describing exactly what I am experiencing in the linux-kernel
> > list archives, but have not yet found a resolution.
> >
> > I have Mandrake 10.0, kernel-2.6.3-7mdk installed, on an IBM Thinkpad
> > 1412 laptop, celeron 366, 512MB RAM. I am finding that my system clock
> > is ticking away at a rate of about 3:1 vs reality, ie, I count ~3 seconds
> > on the system clock for every 1 real second. I am running ntpd but this
> > is unable to keep up with the rate of system clock passage.
[...]
> Try this in the boot command line "clock=pmtmr". If that fails, then try
> "clock=pit".
What is the difference between the two settings? I used the latter and it
worked (didn't try "clock=pmtmr").
praedor
- --
"George W. Bush is a deserter, an election thief, a drunk driver, a WMD
liar and a functional illiterate. And he poops his pants."
- --Barbara Bush, his mother
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (GNU/Linux)
iD8DBQFAZKdCSTapoRk9vv8RAhPDAKDTnTfPABRkJxj0Gy/14d2SsiLL8wCg5r1+
XoUhJcQbDzshPIT++0x/g9o=
=6j96
-----END PGP SIGNATURE-----
On Fri, 2004-03-26 at 15:00, Praedor Atrebates wrote:
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
>
> On Friday 26 March 2004 04:22 pm, john stultz held forth thus:
> > On Fri, 2004-03-26 at 11:30, Praedor Atrebates wrote:
> > > In doing a web search on system clock speeds being too high, I found
> > > entries describing exactly what I am experiencing in the linux-kernel
> > > list archives, but have not yet found a resolution.
> > >
> > > I have Mandrake 10.0, kernel-2.6.3-7mdk installed, on an IBM Thinkpad
> > > 1412 laptop, celeron 366, 512MB RAM. I am finding that my system clock
> > > is ticking away at a rate of about 3:1 vs reality, ie, I count ~3 seconds
> [...]
> > Could you please send me dmesg output for this system?
> >
> > Does booting w/ "clock=pit" help?
>
> Attached is the output of dmesg. As I scanned it I see that I still have APIC
> disabled in Bios. I'll try enabling it and, if that doesn't help, then I
> will try the "clock=pit" switch.
I noticed in the dmesg you sent me that you're using the ACPI PM time
source. There has just recently been a bug opened for a very similar
issue (see http://bugme.osdl.org/show_bug.cgi?id=2375 ).
First of all, scratch trying "clock=pit" and test booting w/
"clock=tsc". If that resolves the issue, disable ACPI PM timesource
support (under the ACPI menu) in your kerel and that should fix you for
the short term.
As for the long term, I'm curious if this is a BIOS/Hardware quirk on
some systems or if there is just something we missed.
Dominik/Len: Any clue on this?
thanks
-john
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
On Friday 26 March 2004 04:57 pm, john stultz held forth thus:
> On Fri, 2004-03-26 at 15:00, Praedor Atrebates wrote:
[...]
> > On Friday 26 March 2004 04:22 pm, john stultz held forth thus:
> > > On Fri, 2004-03-26 at 11:30, Praedor Atrebates wrote:
> > > > In doing a web search on system clock speeds being too high, I found
> > > > entries describing exactly what I am experiencing in the linux-kernel
> > > > list archives, but have not yet found a resolution.
> > > >
> > > > I have Mandrake 10.0, kernel-2.6.3-7mdk installed, on an IBM Thinkpad
> > > > 1412 laptop, celeron 366, 512MB RAM. I am finding that my system
> > > > clock is ticking away at a rate of about 3:1 vs reality, ie, I count
> > > > ~3 seconds
[...]
> > > Does booting w/ "clock=pit" help?
[...]
> I noticed in the dmesg you sent me that you're using the ACPI PM time
> source. There has just recently been a bug opened for a very similar
> issue (see http://bugme.osdl.org/show_bug.cgi?id=2375 ).
>
> First of all, scratch trying "clock=pit" and test booting w/
> "clock=tsc". If that resolves the issue, disable ACPI PM timesource
> support (under the ACPI menu) in your kerel and that should fix you for
> the short term.
Hmpf. I'll try the clock=tsc switch next. I did boot using the clock=pit
switch and the clock was normal...but I had also changed the append statement
acpi=on to acpi=off as well. I'll set it back to "on" and try "clock=tsc" in
combination.
My bios is very limited. This is a rather old laptop and there is just not a
lot I can do. I'll check it one more time as I reboot.
Thanks for the help.
praedor
- --
"George W. Bush is a deserter, an election thief, a drunk driver, a WMD
liar and a functional illiterate. And he poops his pants."
- --Barbara Bush, his mother
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (GNU/Linux)
iD8DBQFAZKlDSTapoRk9vv8RAvmWAJ94jPIPaSwdrtOoNkwKpz4eKokBjwCglolS
ih1YhCpj706DtrVFt7Y42bs=
=oW8n
-----END PGP SIGNATURE-----
On Friday 26 March 2004 04:57 pm, john stultz held forth thus:
[...]
> I noticed in the dmesg you sent me that you're using the ACPI PM time
> source. There has just recently been a bug opened for a very similar
> issue (see http://bugme.osdl.org/show_bug.cgi?id=2375 ).
>
> First of all, scratch trying "clock=pit" and test booting w/
> "clock=tsc". If that resolves the issue, disable ACPI PM timesource
> support (under the ACPI menu) in your kerel and that should fix you for
> the short term.
[...]
OK. Re-enabling ACPI in the append statement and using "clock=tsc" works.
The clock is as it should be.
I took a good look at the bios menus and there just isn't really anything
there I can fiddle with:
ACPI OS Fast Post.........................[enable/disable]
Silent boot.....................................[enable/disable]
PnP OS..........................................[enable/disable]
That's it.
Thanks for the help.
praedor
--
"George W. Bush is a deserter, an election thief, a drunk driver, a WMD
liar and a functional illiterate. And he poops his pants."
--Barbara Bush, his mother
On Fri, 2004-03-26 at 13:54, Praedor Atrebates wrote:
> On Friday 26 March 2004 04:22 pm, john stultz held forth thus:
> > On Fri, 2004-03-26 at 11:30, Praedor Atrebates wrote:
> > > In doing a web search on system clock speeds being too high, I found
> > > entries describing exactly what I am experiencing in the linux-kernel
> > > list archives, but have not yet found a resolution.
> [...]
> > > Does anyone have any enlightenment, or a fix, to offer? The exact same
> > > software setup on a desktop system, Athlon XP2700+, has no such problems.
> >
> > Could you please send me dmesg output for this system?
> >
> > Does booting w/ "clock=pit" help?
>
> Thank you, this did fix the problem. Now I have to set the type-matic setting
> up because it is so sluggish.
>
> What is clock=pit doing? What is behind this accelerated clock?
This is just manually overriding the automatic time source selection.
You're using the PIT (programmable interval timer) over what was being
automatically selected (according the to the dmesg you sent me, the
pmtmr or ACPI PM timer) by your kernel config.
As clock=pit seemed to solve the problem, it looks like its a ACPI PM
issue.
thanks
-john
Praedor Atrebates wrote:
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
>
> On Friday 26 March 2004 04:46 pm, George Anzinger held forth thus:
>
>>Praedor Atrebates wrote:
>>
>>>In doing a web search on system clock speeds being too high, I found
>>>entries describing exactly what I am experiencing in the linux-kernel
>>>list archives, but have not yet found a resolution.
>>>
>>>I have Mandrake 10.0, kernel-2.6.3-7mdk installed, on an IBM Thinkpad
>>>1412 laptop, celeron 366, 512MB RAM. I am finding that my system clock
>>>is ticking away at a rate of about 3:1 vs reality, ie, I count ~3 seconds
>>>on the system clock for every 1 real second. I am running ntpd but this
>>>is unable to keep up with the rate of system clock passage.
>
> [...]
>
>>Try this in the boot command line "clock=pmtmr". If that fails, then try
>>"clock=pit".
>
>
> What is the difference between the two settings? I used the latter and it
> worked (didn't try "clock=pmtmr").
>
There are three clock sources in the x86 kernel, the PIT (programmable interrupt
timer), the TSC, and the pmtimer (power management timer).
The PIT has been in the hardware since, well, day one. It almost always works
and it is clocked by a special Xtal. The down side is it is accessed with 8-bit
I/O instructions and so is dog slow to change or look at.
The TSC (time stamp counter) is a newer thing so is not available on all
hardware although, now, most boxes that don't have TSCs are in land fills :).
It is accessed via a machine register. It is usually the cpu clock and so is a
direct indicator of the cpu speed. The boot report of cpu speed comes from a
comparison of the TSC and the PIT, and, in fact this comparison is used to
calibrate the TSC so it can be used to interpolate between PIT interrupts. So,
even here, the PIT is still the tick generator, while the TSC is used to replace
the reading of the PIT to interpolate between interrupts. The down side is that
prior to the pentium 4, the TSC frequency was exactly the processor clock and
was subject to change to control heat and power usage in the cpu. I.e. the TSC
was slowed down to cool the cpu (and to save power). This makes it an
unreliable time source for those cpus that do this, in particular lap tops that
are very much into saving power.
The pmtimer is part of the ACPI hardware. It is clocked by the same xtal as the
PIT. It does not interrupt, so again, the PIT is the interrupt source for time
ticks. It has a resolution of three times the PIT (same clock, different
divider). It is called the power management timer as it is was designed to
provide a stable time reference for all power states (except off, of course), so
is not subject to the slow downs the TSC is. The down side is that it is
accessed with an I/O instruction and so is slow. I have measured a 3 times
difference in gettimeofday() on an 800MHZ PIII between the TSC and the pmtimer,
for example. (And this was with just one read of the pmtimer per
gettimeofday(), were as the kernel now does three because some hardware gets it
wrong.)
So, you may ask, if the PIT is the interrupt source, why does the pmtimer being
off cause my clock to run fast? It would seem that only the interpolation
between ticks would be fast, not the whole clock. The answer to this is the
"lost tick" detection code. This code uses the pmtimer or the TSC to check for
lost ticks and adjusts the clock based on this.
Questions?
--
George Anzinger [email protected]
High-res-timers: http://sourceforge.net/projects/high-res-timers/
Preemption patch: http://www.kernel.org/pub/linux/kernel/people/rml
On Fri, 2004-03-26 at 15:00, Praedor Atrebates wrote:
> On Friday 26 March 2004 04:22 pm, john stultz held forth thus:
> > On Fri, 2004-03-26 at 11:30, Praedor Atrebates wrote:
> > > In doing a web search on system clock speeds being too high, I found
> > > entries describing exactly what I am experiencing in the linux-kernel
> > > list archives, but have not yet found a resolution.
> > >
> > > I have Mandrake 10.0, kernel-2.6.3-7mdk installed, on an IBM Thinkpad
> > > 1412 laptop, celeron 366, 512MB RAM. I am finding that my system clock
> > > is ticking away at a rate of about 3:1 vs reality, ie, I count ~3 seconds
> [...]
> > Could you please send me dmesg output for this system?
> >
> Attached is the output of dmesg.
You mentioned that your system is an older laptop, and you're setting
"acpi=on" in your boot arguments. What happens when you omit "acpi=on"?
Do you get a message saying something to the effect of your system being
too old for ACPI? Does everything still work as it ought?
I'm still working on this one.
See http://bugme.osdl.org/show_bug.cgi?id=2375 for more details.
thanks
-john
On Tue, Mar 30, 2004 at 07:25:39AM -0800, john stultz wrote:
> On Fri, 2004-03-26 at 15:00, Praedor Atrebates wrote:
> > On Friday 26 March 2004 04:22 pm, john stultz held forth thus:
> > > On Fri, 2004-03-26 at 11:30, Praedor Atrebates wrote:
> > > > In doing a web search on system clock speeds being too high, I found
> > > > entries describing exactly what I am experiencing in the linux-kernel
> > > > list archives, but have not yet found a resolution.
> > > >
> > > > I have Mandrake 10.0, kernel-2.6.3-7mdk installed, on an IBM Thinkpad
> > > > 1412 laptop, celeron 366, 512MB RAM. I am finding that my system clock
> > > > is ticking away at a rate of about 3:1 vs reality, ie, I count ~3 seconds
> > [...]
> > > Could you please send me dmesg output for this system?
> > >
> > Attached is the output of dmesg.
>
> You mentioned that your system is an older laptop, and you're setting
> "acpi=on" in your boot arguments. What happens when you omit "acpi=on"?
> Do you get a message saying something to the effect of your system being
> too old for ACPI? Does everything still work as it ought?
Hm, could you please verify that ACPI throttling and cpufreq is _disabled_
when you do this check? For throttling, please do
echo 1 > /proc/acpi/processor/./throttling
echo 0 > /proc/acpi/processor/./throttling
[just echo'ing 0 is a noop if ACPI thinks it's at T0... and we want to force
T0].
Dominik