Messages in this thread | | | Subject | Re: sched: Avoid SMT siblings in select_idle_sibling() if possible | From | Peter Zijlstra <> | Date | Mon, 26 Mar 2012 10:29:43 +0200 |
| |
On Thu, 2012-03-22 at 21:02 +0530, Srivatsa Vaddagiri wrote: > Anyway, there are degradations as well, considering which I see > several > possibilities: > > 1. Do balance-on-wake for vcpu threads only.
Hell no ;-) we're not going to special case some threads over others.
> 2. Document tuning possibility to improve performance in virtualized > environment: > - Either via sched_domain flags (disable SD_WAKE_AFFINE > at all levels and enable SD_BALANCE_WAKE at SMT/MC levels)
But domain flags are not exported -- except under SCHED_DEBUG and that sysctl mess.. also SD_flags are not stable.
> - Or via a new sched_feat(BALANCE_WAKE) tunable
sched_feat() is not a stable ABI and shouldn't ever be used for anything but debugging (hence it lives in debugfs and goes away if you disable SCHED_DEBUG).
I would very much like more information on why things are a loss. Is it really related to what cpu you pick, or is it the cost of doing the balance thing?
| |