Tim wrote:
> I have to ask - do we REALLY need cpusets? I meant, even SGI dropped
> PSET at some point, because (if I recall) NO ONE USED IT.
SGI makes heavy and critical use of the cpuset facilities on both Irix
and Linux that have been developed since pset. These facilities handle
both cpu and memory placment, and provide the essential kernel support
(names and permissions and operations to query, modify and attach) for a
system wide administrative interface for managing the resulting sets of
CPUs and Memory Nodes.
In 2.4 Linux kernels, we ran with our own cpuset patches (called
cpumemsets), which have no prospect of making it into Marcelo's tree.
I wrote those patches, they work, but I still had much to learn about
writing patches that were reasonable to accept into the mainline kernel.
Yes, as I recall, your pset work was rejected by Linus and Alan, years
ago. Times have changed -- Linux has scaled up to much larger systems
since then. And SGI's and others understanding of what we needed for
cpusets has grown as well. If you study what I've described of cpusets
these last two days, I believe you will find it is not the same as your
pset patch.
Things like this don't go away. They get chewed on, over the years,
until they arrive at a state of being sufficiently needed, 'right now',
and sufficiently robust, that they gain wider acceptance.
Thanks for your contributions along the way ...
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.650.933.1373
-------------------------------------------------------
This SF.net email is sponsored by: IT Product Guide on ITManagersJournal
Use IT products in your business? Tell us what you think of them. Give us
Your Opinions, Get Free ThinkGeek Gift Certificates! Click to find out more
http://productguide.itmanagersjournal.com/guidepromo.tmpl
_______________________________________________
ckrm-tech mailing list
https://lists.sourceforge.net/lists/listinfo/ckrm-tech
