Messages in this thread | | | From | Vincent Guittot <> | Date | Tue, 7 Jan 2014 14:32:07 +0100 | Subject | Re: [PATCH 4/4] sched: bias to target cpu load to reduce task moving |
| |
On 7 January 2014 14:15, Peter Zijlstra <peterz@infradead.org> wrote: > On Tue, Jan 07, 2014 at 01:59:30PM +0100, Peter Zijlstra wrote: >> On Tue, Jan 07, 2014 at 12:55:18PM +0000, Morten Rasmussen wrote: >> > My understanding is that should_we_balance() decides which cpu is >> > eligible for doing the load balancing for a given domain (and the >> > domains above). That is, only one cpu in a group is allowed to load >> > balance between the local group and other groups. That cpu would >> > therefore be reponsible for pulling enough load that the groups are >> > balanced even if it means temporarily overloading itself. The other cpus >> > in the group will take care of load balancing the extra load within the >> > local group later. >> >> Correct. > > On that; one of the things I wanted to (and previously did attempt but > failed) is trying to rotate this cpu. Currently its always the first cpu > (of the group) and that gives a noticeable bias.
Isn't the current policy (it's the 1st idle cpu in priority). a good enough way to rotate the cpus ? Are you need the rotation for loaded use case too ?
> > If we could slowly rotate the cpu that does this that would alleviate > both the load and cost bias. > > One thing I was thinking of is keeping a global counter maybe: > 'x := jiffies >> n' > might be good enough and using the 'x % nr_cpus_in_group'-th cpu > instead. > > Then again, these are micro issue and not a lot of people complain > about this.
| |