Messages in this thread | | | Subject | Re: [PATCH] x86,sched: Fix sched_smt_power_savings totally broken | From | Suresh Siddha <> | Date | Tue, 10 Jan 2012 11:01:13 -0800 |
| |
On Tue, 2012-01-10 at 22:21 +0530, Vaidyanathan Srinivasan wrote: > * Youquan Song <youquan.song@intel.com> [2012-01-10 11:54:26]: > > > > > > Youquan, As far as I know both the > > > sched_smt_power_savings/sched_mc_power_savings are broken for atleast an > > > year. > > > > > > Have you checked the state of 'sched_mc_power_savings' to see if it is > > > working or gets addressed with your proposed patches? > > Thanks Suresh! > > > > We have verified that sched_mc_power_savings works well in mainline and > > -tip tree, only sched_smt_power_savings broken. > > Hi Suresh, > > My testing also shows that sched_mc works find and only sched_smt > suffers from the group capacity problem at the core level. >
No. I just checked and it doesn't work as intended.
On a 2 socket 8-core SMT system, I ran 8 cpu hoggers and just toggled 'sched_mc_power_savings' between 0 and 1 multiple times. Irrespective of the value, those 8 hoggers are distributed evenly between two sockets - 4 each and doesn't change their positions.
So I can bet it doesn't work.
thanks, suresh
| |