Messages in this thread | | | Date | Sun, 21 Dec 2008 22:19:12 +0100 (CET) | From | Thomas Gleixner <> | Subject | Re: TSC not updating after resume: Bug or Feature? |
| |
Deepak,
On Wed, 17 Dec 2008, Deepak Saxena wrote: > > Hi, > > I am using ftrace to get a detailed timing analysis of the resume process > on the OLPC XO laptop and am seeing that when we start running again, the > system timestamep is not being updated for several (hundreds of) thousands > of cycles (~2000 ftrace entries). From following the ftrace, what is > happening is that the clocksource is not updated until we run the cpu_idle() > thread due to an explicit scheduling operation in the resume path that occurs > via call to msleep from pci_set_power_state(). As I'm still fully groking the > timekeeping code, the question(s) I have is whether this is expected behaviour > and I should not assume valid timestamp data in the initial bits of the suspend path, > whether this is an OLPC-specific bug, or whether I've uncovered a generic bug in > the timekeeping implementation. This is on 2.6.27.7 as I've not gotten 28-rc > up and running on the XO but can move that up in priority if this behaviour > is different in newer kernels.
Can you please upload the full trace somewhere ?
Thanks,
tglx
| |