[openib-general] Re: Re: Re: Userspace testing results (many kernels, many svn trees)

[Michael S. Tsirkin]

Quoting Roland Dreier <rdreier at cisco.com>:
> However, this is not quite enough to make things work on
> all powerpc systems, because the timebase does not necessarily run at
> the same speed as the CPU.  For example, on an IBM JS20 blade,
> clock_test prints
> 
> 	1 sec = 6536.8 usec
> 	1 sec = 6537.05 usec
> 
> (both as a 32-bit and 64-bit executable) because, as /proc/cpuinfo shows:
> 
> 	processor	: 0
> 	cpu		: PPC970FX, altivec supported
> 	clock		: 2194.624509MHz
> 	revision	: 3.0
> 	
> 	processor	: 1
> 	cpu		: PPC970FX, altivec supported
> 	clock		: 2194.624509MHz
> 	revision	: 3.0
> 	
> 	timebase	: 14318000
> 	machine		: CHRP IBM,8842-P2C
> 
> the timebase runs at about 14.3 MHz, or approx 153 times slower than
> the CPU clock.

Right, the PPC book clearly says
"Since the update frequency of the Time Base is implementation-
dependent, the algorithm for converting the
current value in the Time Base to time of day is also
implementation-dependent."

But I was hoping this would be 1:1 for most systems.

> I'm not sure how you want to fix this in perftest.

I plan on implementing a small program that will use msleep to measure
the timebase rate. (Something like linear regression should do it).
Tests will get a new option to pass in the timebase rate
rather than guessing it from /proc/cpuinfo.

-- 
MST