On Mon, Jan 16, 2006 at 01:42:43PM -0800, john stultz wrote:
> On Mon, 2006-01-16 at 21:40 +0100, Mattia Dongili wrote:
[...]
> > # date
> > Mon Jan 16 21:29:26 CET 2006
> > now count with me 1..2..3..4..5
> > # date
> > Mon Jan 16 21:29:27 CET 2006
> >
> > I'd say the time is far from being accurate.
>
> Ok, as I thought. Although 5:1 seems a bit large for cpufreq scaling. It
> does appear that the TSC is halting.
it's far worse than 5:1 actually I wasn't only counting to 5 :)
[...]
> > I'll be happy to test new patches if necessary (I'm running -mm4)
>
> Below is a patch that should provide a bit more debug info. If you
> could, boot up w/ it (be sure to enable CONFIG_PARANOID_GENERIC_TIME)
> and send me your dmesg.
done, I did put it here[1] and added some comments at the end of the
file to better show what was going on.
[1]: http://oioio.altervista.org/linux/tsc_debug.html
and also included at the end of this mail as plain text w/o
comments
Will test the other patch now.
Oh, by the way, after I caught the above dmesg I got this:
[ 556.512000] TSC: Marked unstable
[ 556.512000] [<c0103bb3>] show_trace+0x13/0x20
[ 556.512000] [<c0103bde>] dump_stack+0x1e/0x20
[ 556.512000] [<c0108b77>] mark_tsc_unstable+0x27/0x40
[ 556.512000] [<c01090fb>] time_cpufreq_notifier+0x19b/0x1b0
[ 556.512000] [<c0127e3d>] notifier_call_chain+0x2d/0x50
[ 556.512000] [<c029b551>] cpufreq_notify_transition+0xb1/0x170
[ 556.512000] [<d120f39d>] speedstep_target+0xad/0xe0 [speedstep_ich]
[ 556.512000] [<c029b1d7>] __cpufreq_driver_target+0x77/0x80
[ 556.512000] [<d11de66e>] do_dbs_timer+0x1be/0x200 [cpufreq_ondemand]
[ 556.512000] [<c012b1da>] run_workqueue+0x9a/0x140
[ 556.512000] [<c012b477>] worker_thread+0x107/0x140
[ 556.512000] [<c012eaa9>] kthread+0xd9/0xe0
[ 556.512000] [<c0101005>] kernel_thread_helper+0x5/0x10
[ 556.532000] check_periodic_interval: Long interval! 135987395 ns.
[ 556.532000] Something may be blocking interrupts.
[ 563.016000] TSC: Marked unstable
[ 563.016000] [<c0103bb3>] show_trace+0x13/0x20
[ 563.016000] [<c0103bde>] dump_stack+0x1e/0x20
[ 563.016000] [<c0108b77>] mark_tsc_unstable+0x27/0x40
[ 563.016000] [<c01090fb>] time_cpufreq_notifier+0x19b/0x1b0
[ 563.016000] [<c0127e3d>] notifier_call_chain+0x2d/0x50
[ 563.016000] [<c029b5dc>] cpufreq_notify_transition+0x13c/0x170
[ 563.016000] [<d120f3c0>] speedstep_target+0xd0/0xe0 [speedstep_ich]
[ 563.016000] [<c029b1d7>] __cpufreq_driver_target+0x77/0x80
[ 563.016000] [<d11de5ee>] do_dbs_timer+0x13e/0x200 [cpufreq_ondemand]
[ 563.016000] [<c012b1da>] run_workqueue+0x9a/0x140
[ 563.016000] [<c012b477>] worker_thread+0x107/0x140
[ 563.016000] [<c012eaa9>] kthread+0xd9/0xe0
[ 563.016000] [<c0101005>] kernel_thread_helper+0x5/0x10
[ 563.032000] check_periodic_interval: Long interval! 140156640 ns.
[ 563.032000] Something may be blocking interrupts.
[ 576.756000] Time: jiffies clocksource has been installed.
--
mattia
:wq!
-
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/
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]
