← Back to team overview

ac100 team mailing list archive

Re: Stability Under Load


On Sun, Aug 21, 2011 at 02:14:28PM +0100, Gordan Bobic wrote:
> On 08/21/2011 01:57 PM, Julian Andres Klode wrote:
> >975mV might be equal to 1000mV, there is some rounding up involved,
> >and as far as I know, the frequency steps are 50mV.
> Really? I the error I was seeing was specifically mentioning 975mV.
It might be stepping in 25 mV now, I don't know, but there is definitely
a call to a MACRO with ROUND_UP in the name in the DVFS.

> Hmm, it seems my /sys/kernel/debug subtree is empty. I'll have a
> poke through the kernel config and enable it next time I'm
> rebuilding a kernel.
You need to mount a debugfs there.

> Indeed, but there could be some weird interraction going on. Do you
> have vmalloc= in your kernel boot parameters?
Not related. I had booted with vmalloc and with vmalloc=320M, does
not make a difference.

> >You always need to remember that this value is just a maximum for the
> >regulator, it is not fixed. In your case, the regulator scales from
> >725mV to 975mV, in 50(?) mV steps.
> Indeed, but with the performance governor set, it should never drop
> below the max.
Who knows what really happens there.

> >It's most likely not memory related, but a bug in voltage
> >scaling. I currently have DVFS disabled, and the build seems
> >to be running without errors, whereas it would error out after
> >a few minutes with DVFS enabled.
> Is this still relevant with the performance governor enabled,
> though? I was seeing errors with the performance governor, which I
> would expect to cause the voltages to never get changed.
I'm only running with performance and expected the errors there. I
then disabled DVFS via /sys/module/tegra2_dvfs/parameters/ (first
core, then cpu) and started the build again and got no error yet.

Julian Andres Klode  - Debian Developer, Ubuntu Member

See http://wiki.debian.org/JulianAndresKlode and http://jak-linux.org/.

Attachment: pgp08FhM5u1AU.pgp
Description: PGP signature

Follow ups