On Fri, 17 Oct 2003, Bruce Evans wrote: > On Fri, 17 Oct 2003, Jeff Roberson wrote: > > > On Fri, 17 Oct 2003, Bruce Evans wrote: > > > > > How would one test if it was an improvement on the 4BSD scheduler? It > > > is not even competitive in my simple tests. > > > ... > > > > At one point ULE was at least as fast as 4BSD and in most cases faster. > > This is a regression. I'll sort it out soon. > > How much faster? > make kernel on UP seems to be within 1% of 4BSD now. I actually had some runs which showed lower system time. I think I can still improve the situation some. Anyway, I found some bugs relating to idle prio tasks, and also ULE had been doing almost twice as many context switches as 4BSD. Now it's doing about 8% more. I'm still tracking this down. Anyhow, it should be much closer now. I still have some plans for SMP that should improve things quite a bit there but UP is looking good. Cheers, JeffReceived on Sun Oct 26 2003 - 22:22:51 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:37:26 UTC