Messages in this thread | | | Date | Thu, 29 Nov 2007 21:12:40 +0100 | From | Stefano Brivio <> | Subject | Re: [BUG] jiffies counter leaps in 2.6.24-rc3 |
| |
On Thu, 29 Nov 2007 20:36:24 +0100 Ingo Molnar <mingo@elte.hu> wrote:
> just to make sure there is no tsc impact, does booting with "notsc" > change anything?
No, it doesn't.
> if not, does booting with idle=halt or idle=poll help? [your power usage > will go up so it's not very useful - but it could help exclude a few > sources of trouble.]
With idle=poll nothing changes, except that - as soon as I switch the CPU frequency - I get this in the logs:
[ 297.562722] Marking TSC unstable due to: cpufreq changes. [ 297.566677] Time: acpi_pm clocksource has been installed.
With idle=halt, changing frequency just freezes the system. I can't even use the magic Sys Rq keys then.
I observed another thing. When I don't use any of the parameters you suggested for debugging, I get this at boot:
[ 6.530752] Marking TSC unstable due to: possible TSC halt in C2. [ 6.530761] Time: acpi_pm clocksource has been installed. [ 6.620700] Clocksource tsc unstable (delta = -456217276 ns)
-- Ciao Stefano - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |