SCHED_ULE should not be the default

Daniel Kalchev daniel at digsys.bg
Thu Dec 15 17:59:16 UTC 2011


On Dec 15, 2011, at 6:26 PM, Attilio Rao wrote:

> 2011/12/13 Daniel Kalchev <daniel at digsys.bg>:
>> 
>> 
>> On 13.12.11 09:36, Jeremy Chadwick wrote:
>>> 
>>> I personally would find it interesting if someone with a higher-end system
>>> (e.g. 2 physical CPUs, with 6 or 8 cores per CPU) was to do the same test
>>> (changing -jX to -j{numofcores} of course).
>> 
>> 
>> Is 4 way 8 core Opteron ok? That is 32 cores, 64GB RAM.
>> 
>> Testing with buildworld in my opinion is not adequate, as it involves way
>> too much I/O. Any advice on proper testing methodology?
> 
> I'm sure that I/O and pmap subsystem contention (because of
> buildworld) and TLB shootdown overhead (because of 32 CPUs) will be so
> overwhelming that you are not really going to benchmark the scheduler
> activity at all.

Can't pmap / TLB be tuned for 32 CPUs and 64GB of RAM?

> 
> However I still don't get what you want to verify exactly?

The obvious: is SCHED_ULE better or worse than SCHED_4BSD on such platform. 

Problem is how to test "interactivity" -- that is a blade server and doesn't really have a display and keyboard, nor does it have X etc.

I have spare pair of those, that might be put to crunch tests to see how things compare for different scenarios - but I need ideas what to test, really.

Daniel


More information about the freebsd-stable mailing list