Messages in this thread | | | Subject | Re: [tip:sched/core] sched: Ensure that a child can't gain time over it's parent after fork() | From | Mike Galbraith <> | Date | Tue, 08 Sep 2009 14:42:13 +0200 |
| |
On Tue, 2009-09-08 at 13:53 +0200, Jens Axboe wrote: > On Tue, Sep 08 2009, Ingo Molnar wrote: > > > > * tip-bot for Mike Galbraith <efault@gmx.de> wrote: > > > > > Commit-ID: b5d9d734a53e0204aab0089079cbde2a1285a38f > > > Gitweb: http://git.kernel.org/tip/b5d9d734a53e0204aab0089079cbde2a1285a38f > > > Author: Mike Galbraith <efault@gmx.de> > > > AuthorDate: Tue, 8 Sep 2009 11:12:28 +0200 > > > Committer: Ingo Molnar <mingo@elte.hu> > > > CommitDate: Tue, 8 Sep 2009 13:15:34 +0200 > > > > > > sched: Ensure that a child can't gain time over it's parent after fork() > > > > > This improves latencies of make -j<n> kernel build workloads. > > > > > > Reported-by: Jens Axboe <jens.axboe@oracle.com> > > > > Jens, mind trying this patch (or latest tip:master) with your make > > -j4 workload, does it improve in any way? > > Already booted it, makes no real difference... I'm trying with NO_HZ > disabled now to see if that changes the picture.
Oh well, BTTODB. Thanks for trying it out.
-Mike
| |