Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1
daniel at digsys.bg
Fri Dec 23 11:38:32 UTC 2011
On 23.12.11 12:48, O. Hartmann wrote:
> Look at Steve Kargls problem. He investigated a SCHED_ULE problem in a
> way that is far beyond enough! He gave tests, insights of his setup,
> bad performance compared to SCHED_4BSD and what happend? We are still
> stuck with this problem and more and more people realise, that FreeBSD
> does have somewhere a problem and this seems to be a nasty problem not
> easy to find or investigate.
This has made me to realize, that I was having a problem with SCHED_ULE
that I was not aware of until now. WOW! :)
Every scheduler has some problem, some fail here some fail there. I am
confident, that the case that Steve Kargls has reported will be resolved.
> Another problem is this very elite-feeling closed club. Once you
> managed it getting into the club of committers or core team members,
> you'll probably fight for your seat ... I dont propose for that
> socialists crap Linux people tend to be like,
You never heard of the "People's Republic of Berkeley"? :)
As for commiter access, this sort of comments trigger the system
administrator in me. I have seen enough people, who for the lack of
other excuses always use "but I don't have enough RIGHTS!". I am evil, I
> But I follow the illusion that if people can see what benchmarks
> reveal, they start thinking and if the facts are starting to give a
> heavy load load on those rejecting the facts, they migght change their
> opinion or get hopefully replaced by more openminded people.
Here is now it works:
If you see an problem and have a solution: go fix it. Many will be grateful.
If you can't fix it, but have an idea how to fix it, share it. May will
If you can't fix it and don't have any idea, just say "there is a
problem" and stop there. There are many, many, many like you who just
hold their breath.
We all learn, every day.
More information about the freebsd-current