Messages in this thread |  | | Date | Sat, 9 Feb 2013 15:50:37 -0800 | Subject | Re: [PATCH -v4 4/5] x86,smp: keep spinlock delay values per hashed spinlock address | From | Michel Lespinasse <> |
| |
On Wed, Feb 6, 2013 at 12:10 PM, Rik van Riel <riel@redhat.com> wrote: > On 01/27/2013 08:04 AM, Michel Lespinasse wrote: >> >> On Fri, Jan 25, 2013 at 11:18 AM, Rik van Riel <riel@redhat.com> wrote: >>> >>> + u32 delay = (ent->hash == hash) ? ent->delay : >>> MIN_SPINLOCK_DELAY; >> >> I still don't like the reseting of delay to MIN_SPINLOCK_DELAY when >> there is a hash collision. > > I've been spending some time looking at this, because I am > not a fan either. > > However, it seems to work and I failed to come up with > anything better. Therefore, I have left it as is in the > -v5 patch series.
Does that mean you know of workloads that would regress if you didn't reset the delay to MIN_SPINLOCK_DELAY when detecting a hash collision ?
I have not seen any public reports of that...
-- Michel "Walken" Lespinasse A program is never fully debugged until the last user dies.
|  |