RE: [PATCH v3 1/4] Add correlated clocksource deriving system time from an auxiliary clocksource

[Hall, Christopher S]

> -----Original Message-----
> From: Peter Zijlstra [mailto:peterz@xxxxxxxxxxxxx]
> Sent: Friday, September 04, 2015 7:28 AM
> To: Richard Cochran
> Cc: Hall, Christopher S; Thomas Gleixner; Kirsher, Jeffrey T;
> hpa@xxxxxxxxx; mingo@xxxxxxxxxx; john.stultz@xxxxxxxxxx; x86@xxxxxxxxxx;
> linux-kernel@xxxxxxxxxxxxxxx; netdev@xxxxxxxxxxxxxxx; intel-wired-
> lan@xxxxxxxxxxxxxxxx
> Subject: Re: [PATCH v3 1/4] Add correlated clocksource deriving system time
> from an auxiliary clocksource
> 
> > > (several milliseconds) and the result will be out of date by some
> fraction of that
> > > amount.
> >
> > Why does it take milliseconds to read one audio time stamp?
> 
> So what I suspect, but please correct me if I'm wrong Chris, is that a
> DSP will buffer and process audio signals, and only later wake up the
> main CPU.
> 
> So by the time the CPU is made aware of the data, it's 'old'.

That's about right.  The DSP runs on a 1 ms cadence.  Any access to registers controlled by the DSP will take 1-2 DSP ticks to access.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/