Re: sched: context tracking demolishes pipe-test

2013-07-02 Thread Mike Galbraith
CCs net-wizards since staring at profile/annotation isn't helping, and I know all too well how these things laugh perversely at bisection. On Tue, 2013-07-02 at 06:03 +0200, Mike Galbraith wrote: > On Mon, 2013-07-01 at 11:20 +0200, Mike Galbraith wrote: > > On Mon, 2013-07-01 at 11:12 +0200, Mi

Re: sched: context tracking demolishes pipe-test

2013-07-01 Thread Mike Galbraith
On Mon, 2013-07-01 at 11:20 +0200, Mike Galbraith wrote: > On Mon, 2013-07-01 at 11:12 +0200, Mike Galbraith wrote: > > On Mon, 2013-07-01 at 10:06 +0200, Peter Zijlstra wrote: > > > > > So aside from the context tracking stuff, there's still a regression > > > we might want to look at. That's s

Re: sched: context tracking demolishes pipe-test

2013-07-01 Thread Mike Galbraith
On Mon, 2013-07-01 at 11:12 +0200, Mike Galbraith wrote: > On Mon, 2013-07-01 at 10:06 +0200, Peter Zijlstra wrote: > > > So aside from the context tracking stuff, there's still a regression > > we might want to look at. That's still a ~10% drop against 2.6.32 for > > TCP_RR and few percents for

Re: sched: context tracking demolishes pipe-test

2013-07-01 Thread Mike Galbraith
On Mon, 2013-07-01 at 10:06 +0200, Peter Zijlstra wrote: > So aside from the context tracking stuff, there's still a regression > we might want to look at. That's still a ~10% drop against 2.6.32 for > TCP_RR and few percents for tbench. Yeah, known, and some of it's ours. -Mike -- To unsubscr

Re: sched: context tracking demolishes pipe-test

2013-07-01 Thread Peter Zijlstra
On Mon, Jul 01, 2013 at 08:07:55AM +0200, Mike Galbraith wrote: > On Sun, 2013-06-30 at 23:29 +0200, Peter Zijlstra wrote: > > > Yeah, who'd have thought that putting stuff in the syscall path would've > > made syscalls more expensive ;-) > > (careful, you'll injure my innocence, Santa and the To

Re: sched: context tracking demolishes pipe-test

2013-06-30 Thread Mike Galbraith
On Sun, 2013-06-30 at 23:29 +0200, Peter Zijlstra wrote: > Yeah, who'd have thought that putting stuff in the syscall path would've > made syscalls more expensive ;-) (careful, you'll injure my innocence, Santa and the Tooth Fairy exist!) > But yeah, that's a _lot_ more expensive.. I'd not be su

Re: sched: context tracking demolishes pipe-test

2013-06-30 Thread Peter Zijlstra
On Sun, Jun 30, 2013 at 09:57:36AM +0200, Mike Galbraith wrote: > taskset -c 3 pipe-test 1 > > switch-rate > 3.10.0-master 426.4 KHz > 3.10.0-masterx591.8 Khz 1.387 (591=notgood, 426=omfg) > > 3.10.0-master3.10.0-masterx >

sched: context tracking demolishes pipe-test

2013-06-30 Thread Mike Galbraith
taskset -c 3 pipe-test 1 switch-rate 3.10.0-master 426.4 KHz 3.10.0-masterx591.8 Khz 1.387 (591=notgood, 426=omfg) 3.10.0-master3.10.0-masterx 7.13% [k] __schedule9.58% [k] __schedule !6.