Hi!
> > > but perhaps somehow we miss this fact and fail to turn off the lapic
> > > clockevents drivers?
> >
> > Ok, I guess I'm lost. If I offline second CPU, I immediately get
> > 1000Hz timer tick... is that expected?
>
> Hmm. No. I have no idea why this is happening.
>
> 34196 total
Hi!
but perhaps somehow we miss this fact and fail to turn off the lapic
clockevents drivers?
Ok, I guess I'm lost. If I offline second CPU, I immediately get
1000Hz timer tick... is that expected?
Hmm. No. I have no idea why this is happening.
34196 total events, 55.083
On Sun, 25 Nov 2007, Rafael J. Wysocki wrote:
> > Digging into process_32|64.c...
> >
> > 64:
> > while (1) {
> > while (!need_resched()) {
> > void (*idle)(void);
> >
> > if (__get_cpu_var(cpu_idle_state))
> >
On Sun, 25 Nov 2007, Pavel Machek wrote:
> Hi!
>
> Okay, so the problem seems to be we are using unreliable lapic
> timer... which is stopped in C3 (and in C2 on broken machines).
>
> I do not see any mechanism to disable lapic; there seems to be some
> mechanism to work around stopped lapic
Hi!
Okay, so the problem seems to be we are using unreliable lapic
timer... which is stopped in C3 (and in C2 on broken machines).
I do not see any mechanism to disable lapic; there seems to be some
mechanism to work around stopped lapic timer is used (in
acpi/processor_idle.c) but it does not
Hi!
Okay, so the problem seems to be we are using unreliable lapic
timer... which is stopped in C3 (and in C2 on broken machines).
I do not see any mechanism to disable lapic; there seems to be some
mechanism to work around stopped lapic timer is used (in
acpi/processor_idle.c) but it does not
On Sun, 25 Nov 2007, Pavel Machek wrote:
Hi!
Okay, so the problem seems to be we are using unreliable lapic
timer... which is stopped in C3 (and in C2 on broken machines).
I do not see any mechanism to disable lapic; there seems to be some
mechanism to work around stopped lapic timer is
On Sun, 25 Nov 2007, Rafael J. Wysocki wrote:
Digging into process_32|64.c...
64:
while (1) {
while (!need_resched()) {
void (*idle)(void);
if (__get_cpu_var(cpu_idle_state))
On Sunday, 25 of November 2007, Rafael J. Wysocki wrote:
> On Saturday, 24 of November 2007, Pavel Machek wrote:
> > Hi!
> >
> > > > > but perhaps somehow we miss this fact and fail to turn off the lapic
> > > > > clockevents drivers?
> > > >
> > > > Ok, I guess I'm lost. If I offline second
On Saturday, 24 of November 2007, Pavel Machek wrote:
> Hi!
>
> > > > but perhaps somehow we miss this fact and fail to turn off the lapic
> > > > clockevents drivers?
> > >
> > > Ok, I guess I'm lost. If I offline second CPU, I immediately get
> > > 1000Hz timer tick... is that expected?
> >
Hi!
> > > but perhaps somehow we miss this fact and fail to turn off the lapic
> > > clockevents drivers?
> >
> > Ok, I guess I'm lost. If I offline second CPU, I immediately get
> > 1000Hz timer tick... is that expected?
>
> Hmm. No. I have no idea why this is happening.
>
> 34196 total
On Thu 2007-11-22 21:29:51, Thomas Gleixner wrote:
> On Thu, 22 Nov 2007, Pavel Machek wrote:
> > > but perhaps somehow we miss this fact and fail to turn off the lapic
> > > clockevents drivers?
> >
> > Ok, I guess I'm lost. If I offline second CPU, I immediately get
> > 1000Hz timer tick... is
On Thu 2007-11-22 21:29:51, Thomas Gleixner wrote:
On Thu, 22 Nov 2007, Pavel Machek wrote:
but perhaps somehow we miss this fact and fail to turn off the lapic
clockevents drivers?
Ok, I guess I'm lost. If I offline second CPU, I immediately get
1000Hz timer tick... is that
Hi!
but perhaps somehow we miss this fact and fail to turn off the lapic
clockevents drivers?
Ok, I guess I'm lost. If I offline second CPU, I immediately get
1000Hz timer tick... is that expected?
Hmm. No. I have no idea why this is happening.
34196 total events, 55.083
On Saturday, 24 of November 2007, Pavel Machek wrote:
Hi!
but perhaps somehow we miss this fact and fail to turn off the lapic
clockevents drivers?
Ok, I guess I'm lost. If I offline second CPU, I immediately get
1000Hz timer tick... is that expected?
Hmm. No. I have no
On Sunday, 25 of November 2007, Rafael J. Wysocki wrote:
On Saturday, 24 of November 2007, Pavel Machek wrote:
Hi!
but perhaps somehow we miss this fact and fail to turn off the lapic
clockevents drivers?
Ok, I guess I'm lost. If I offline second CPU, I immediately get
Hi!
> > > but perhaps somehow we miss this fact and fail to turn off the lapic
> > > clockevents drivers?
> >
> > Ok, I guess I'm lost. If I offline second CPU, I immediately get
> > 1000Hz timer tick... is that expected?
>
> Hmm. No. I have no idea why this is happening.
>
> 34196 total
Hi!
but perhaps somehow we miss this fact and fail to turn off the lapic
clockevents drivers?
Ok, I guess I'm lost. If I offline second CPU, I immediately get
1000Hz timer tick... is that expected?
Hmm. No. I have no idea why this is happening.
34196 total events, 55.083
On Thu, 22 Nov 2007, Pavel Machek wrote:
> > but perhaps somehow we miss this fact and fail to turn off the lapic
> > clockevents drivers?
>
> Ok, I guess I'm lost. If I offline second CPU, I immediately get
> 1000Hz timer tick... is that expected?
Hmm. No. I have no idea why this is happening.
Hi!
> > > to me this has the feeling of lapic breakage in C2 mode. Does it get any
> > > better if you boot with 'nolapic'? (but that might in turn turn off
> > > high-res timers and nohz in essence) Thomas, any ideas?
> >
> > Hmm, lapic is considered unstable in c2 by default. You have to
Hi!
> > > Clock Event Device: hpet
> > > set_next_event: hpet_legacy_next_event
> > > set_mode: hpet_legacy_set_mode
> > > event_handler: tick_handle_oneshot_broadcast
> > >
> > > Clock Event Device: lapic
> > > set_next_event: lapic_next_event
> > > set_mode: lapic_timer_setup
Hi!
> > > > > and send us the output? (Enabling CONFIG_TIMER_STATS,
> > > > > CONFIG_SCHED_DEBUG and CONFIG_SCHEDSTATS would maximize the amount
> > > > > of information.)
> > > >
> > > > This was w/o hpet=disable . Do you want me to test with hpet=disable?
> > >
> > > no, this is fine.
Hi!
and send us the output? (Enabling CONFIG_TIMER_STATS,
CONFIG_SCHED_DEBUG and CONFIG_SCHEDSTATS would maximize the amount
of information.)
This was w/o hpet=disable . Do you want me to test with hpet=disable?
no, this is fine. You've got a hpet clockevents
Hi!
to me this has the feeling of lapic breakage in C2 mode. Does it get any
better if you boot with 'nolapic'? (but that might in turn turn off
high-res timers and nohz in essence) Thomas, any ideas?
Hmm, lapic is considered unstable in c2 by default. You have to tell
the
Hi!
Clock Event Device: hpet
set_next_event: hpet_legacy_next_event
set_mode: hpet_legacy_set_mode
event_handler: tick_handle_oneshot_broadcast
Clock Event Device: lapic
set_next_event: lapic_next_event
set_mode: lapic_timer_setup
event_handler:
On Thu, 22 Nov 2007, Pavel Machek wrote:
but perhaps somehow we miss this fact and fail to turn off the lapic
clockevents drivers?
Ok, I guess I'm lost. If I offline second CPU, I immediately get
1000Hz timer tick... is that expected?
Hmm. No. I have no idea why this is happening.
34196
* Thomas Gleixner <[EMAIL PROTECTED]> wrote:
> On Tue, 20 Nov 2007, Ingo Molnar wrote:
> >
> > * Pavel Machek <[EMAIL PROTECTED]> wrote:
> >
> > > > and send us the output? (Enabling CONFIG_TIMER_STATS,
> > > > CONFIG_SCHED_DEBUG and CONFIG_SCHEDSTATS would maximize the amount
> > > > of
On Tue, 20 Nov 2007, Ingo Molnar wrote:
>
> * Pavel Machek <[EMAIL PROTECTED]> wrote:
>
> > > and send us the output? (Enabling CONFIG_TIMER_STATS,
> > > CONFIG_SCHED_DEBUG and CONFIG_SCHEDSTATS would maximize the amount
> > > of information.)
> >
> > This was w/o hpet=disable . Do you want
* Pavel Machek <[EMAIL PROTECTED]> wrote:
> > and send us the output? (Enabling CONFIG_TIMER_STATS,
> > CONFIG_SCHED_DEBUG and CONFIG_SCHEDSTATS would maximize the amount
> > of information.)
>
> This was w/o hpet=disable . Do you want me to test with hpet=disable?
no, this is fine. You've
On Mon, 19 Nov 2007, Pavel Machek wrote:
> On unloaded x60 system, 2.6.24-rc3 (tainted-pavel-so if someone can
> reproduce it, it would be helpful):
Can you please provide your .config ?
tglx
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message
* Ingo Molnar <[EMAIL PROTECTED]> wrote:
> > hpet-disable helps.. a bit. 200msec latencies are gone. (What is
> > used for wakeups in this case?)
> >
> > [EMAIL PROTECTED]:~$ while true; do time sleep 0.01; done
> > 0.00user 0.00system 0.01 (0m0.013s) elapsed 22.96%CPU
> > 0.00user 0.00system
* Pavel Machek <[EMAIL PROTECTED]> wrote:
> > > 0.00user 0.00system 0.08 (0m0.081s) elapsed 3.71%CPU
> > > 0.00user 0.00system 0.01 (0m0.013s) elapsed 23.33%CPU
> > > 0.00user 0.00system 0.01 (0m0.019s) elapsed 15.92%CPU
> > >
> > > nohz=off helps a lot. while true; do time sleep 0.0; done does
* Ingo Molnar [EMAIL PROTECTED] wrote:
hpet-disable helps.. a bit. 200msec latencies are gone. (What is
used for wakeups in this case?)
[EMAIL PROTECTED]:~$ while true; do time sleep 0.01; done
0.00user 0.00system 0.01 (0m0.013s) elapsed 22.96%CPU
0.00user 0.00system 0.01
On Mon, 19 Nov 2007, Pavel Machek wrote:
On unloaded x60 system, 2.6.24-rc3 (tainted-pavel-so if someone can
reproduce it, it would be helpful):
Can you please provide your .config ?
tglx
-
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to
* Pavel Machek [EMAIL PROTECTED] wrote:
0.00user 0.00system 0.08 (0m0.081s) elapsed 3.71%CPU
0.00user 0.00system 0.01 (0m0.013s) elapsed 23.33%CPU
0.00user 0.00system 0.01 (0m0.019s) elapsed 15.92%CPU
nohz=off helps a lot. while true; do time sleep 0.0; done does not
have
* Pavel Machek [EMAIL PROTECTED] wrote:
and send us the output? (Enabling CONFIG_TIMER_STATS,
CONFIG_SCHED_DEBUG and CONFIG_SCHEDSTATS would maximize the amount
of information.)
This was w/o hpet=disable . Do you want me to test with hpet=disable?
no, this is fine. You've got a hpet
On Tue, 20 Nov 2007, Ingo Molnar wrote:
* Pavel Machek [EMAIL PROTECTED] wrote:
and send us the output? (Enabling CONFIG_TIMER_STATS,
CONFIG_SCHED_DEBUG and CONFIG_SCHEDSTATS would maximize the amount
of information.)
This was w/o hpet=disable . Do you want me to test with
* Thomas Gleixner [EMAIL PROTECTED] wrote:
On Tue, 20 Nov 2007, Ingo Molnar wrote:
* Pavel Machek [EMAIL PROTECTED] wrote:
and send us the output? (Enabling CONFIG_TIMER_STATS,
CONFIG_SCHED_DEBUG and CONFIG_SCHEDSTATS would maximize the amount
of information.)
This
Hi!
> > On unloaded x60 system, 2.6.24-rc3 (tainted-pavel-so if someone can
> > reproduce it, it would be helpful):
> >
> > [EMAIL PROTECTED]:~$ while true; do time sleep 0.01; done
> > 0.00user 0.00system 0.01 (0m0.013s) elapsed 30.71%CPU
> > 0.00user 0.00system 0.02 (0m0.024s) elapsed 8.36%CPU
* Pavel Machek <[EMAIL PROTECTED]> wrote:
> Hi!
>
> On unloaded x60 system, 2.6.24-rc3 (tainted-pavel-so if someone can
> reproduce it, it would be helpful):
>
> [EMAIL PROTECTED]:~$ while true; do time sleep 0.01; done
> 0.00user 0.00system 0.01 (0m0.013s) elapsed 30.71%CPU
> 0.00user
Hi!
On unloaded x60 system, 2.6.24-rc3 (tainted-pavel-so if someone can
reproduce it, it would be helpful):
[EMAIL PROTECTED]:~$ while true; do time sleep 0.01; done
0.00user 0.00system 0.01 (0m0.013s) elapsed 30.71%CPU
0.00user 0.00system 0.02 (0m0.024s) elapsed 8.36%CPU
0.00user 0.00system
Hi!
On unloaded x60 system, 2.6.24-rc3 (tainted-pavel-so if someone can
reproduce it, it would be helpful):
[EMAIL PROTECTED]:~$ while true; do time sleep 0.01; done
0.00user 0.00system 0.01 (0m0.013s) elapsed 30.71%CPU
0.00user 0.00system 0.02 (0m0.024s) elapsed 8.36%CPU
0.00user 0.00system
* Pavel Machek [EMAIL PROTECTED] wrote:
Hi!
On unloaded x60 system, 2.6.24-rc3 (tainted-pavel-so if someone can
reproduce it, it would be helpful):
[EMAIL PROTECTED]:~$ while true; do time sleep 0.01; done
0.00user 0.00system 0.01 (0m0.013s) elapsed 30.71%CPU
0.00user 0.00system 0.02
Hi!
On unloaded x60 system, 2.6.24-rc3 (tainted-pavel-so if someone can
reproduce it, it would be helpful):
[EMAIL PROTECTED]:~$ while true; do time sleep 0.01; done
0.00user 0.00system 0.01 (0m0.013s) elapsed 30.71%CPU
0.00user 0.00system 0.02 (0m0.024s) elapsed 8.36%CPU
0.00user
44 matches
Mail list logo