On Sat, Apr 14, 2007 at 10:08:34AM +0200, Willy Tarreau wrote: > On Sat, Apr 14, 2007 at 08:43:34AM +0200, Ingo Molnar wrote: > > > > * Ingo Molnar <[EMAIL PROTECTED]> wrote: > > > > > Nick noticed that upon fork we change parent->wait_runtime but we do > > > not requeue it within the rbtree. > > > > this fix is not complete - because the child runqueue is locked here, > > not the parent's. I've fixed this properly in my tree and have uploaded > > a new sched-modular+cfs.patch. (the effects of the original bug are > > mostly harmless, the rbtree position gets corrected the first time the > > parent reschedules. The fix might improve heavy forker handling.) > > It looks like it did not reach your public dir yet. > > BTW, I've given it a try. It seems pretty usable. I have also tried > the usual meaningless "glxgears" test with 12 of them at the same time, > and they rotate very smoothly, there is absolutely no pause in any of > them. But they don't all run at same speed, and top reports their CPU > load varying from 3.4 to 10.8%, with what looks like more CPU is > assigned to the first processes, and less CPU for the last ones. But > this is just a rough observation on a stupid test, I would not call > that one scientific in any way (and X has its share in the test too).
Follow-up: I think this is mostly X-related. I've started 100 scheddos, and all get the same CPU percentage. Interestingly, mpg123 in parallel does never skip at all because it needs quite less than 1% CPU and gets its fair share at a load of 112. Xterms are slow to respond to typing with the 12 gears and 100 scheddos, and expectedly it was X which was starving. renicing it to -5 restores normal feeling with very slow but smooth gear rotations. Leaving X niced at 0 and killing the gears also restores normal behaviour. All in all, it seems logical that processes which serve many others become a bottleneck for them. Forking becomes very slow above a load of 100 it seems. Sometimes, the shell takes 2 or 3 seconds to return to prompt after I run "scheddos &" Those are very promising results, I nearly observe the same responsiveness as I had on a solaris 10 with 10k running processes on a bigger machine. I would be curious what a mysql test result would look like now. Regards, Willy - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
