svn commit: r297039 - head/sys/x86/x86
Poul-Henning Kamp
phk at phk.freebsd.dk
Sun Mar 27 14:21:21 UTC 2016
--------
In message <20160327130706.GA1741 at kib.kiev.ua>, Konstantin Belousov writes:
>> I haven't seen a single (hardware) system since I started measuring
>> this 15-20 yeas ago on which the i8524 is not fed from the same clock
>> as the TSC.
A very important and relevant detail here is that the *only*
clock/counter which has a standardized frequency *is* the i8254
counter.
>RTC needs its own dedicated crystal.
The RTC *crystal* may not even exist, only the RTC itself which may
be driven by gremlins on a threadmill for all we care.
Besides, getting hold of *precise* timing from the RTC is a nightmare,
it's not meant to be used for that.
>I was not able to find any specifications for allowed jitter in PCH PLLs,
>but I would expect that above IDT chips have much better stability than
>something in overheating PCH.
Jitter requirements are pretty tight for anything you're going to
PLL into the GHz range, but any quartz crystal is going to have much
better phase-noise spec than anything we can measure in the digital
noise of a modern computer.
(Often the PLL chips modulate the quartz to spread out EMI spurs,
look for "spread-spectrum" settings.)
>> > some hypervisors start offering modes where old ISA peripherals
>> > are not emulated,
How do they expect people to run MS Flight Simulator then ? :-)
>I think we have no choice but do something for ISA/LPC-less configurations.
>We could even trust CPU report about its frequency as the last resort.
Usually the errors will be magnificient, so a trivial sanity-check will
catch them. Don't leave home without it.
--
Poul-Henning Kamp | UNIX since Zilog Zeus 3.20
phk at FreeBSD.ORG | TCP/IP since RFC 956
FreeBSD committer | BSD since 4.3-tahoe
Never attribute to malice what can adequately be explained by incompetence.
More information about the svn-src-all
mailing list