Messages in this thread | | | Date | Sat, 14 Dec 2013 21:27:59 +0800 | From | Alex Shi <> | Subject | Re: [PATCH 0/4] sched: remove cpu_load decay |
| |
On 12/14/2013 04:03 AM, Peter Zijlstra wrote: > > > I had a quick peek at the actual patches. > > afaict we're now using weighted_cpuload() aka runnable_load_avg as the > ->cpu_load. Whatever happened to also using the blocked_avg?
When enabling the sched_avg in load balance, I didn't find any positive testing result for several blocked_avg trying, just few regression. :(
And since this patchset is almost clean up only, no blocked_load_avg trying again...
> > I totally hate patch 4; it seems like a random hack to make up for the > lack of blocked_avg.
Yes, this bias criteria seems a bit arbitrary. :) But, anyway even with blocked_load_avg, we still need to consider to bias to local cpu. like in a scenario, 2 cpus both has nearly zero blocked_load_avg.
BTW,
Paul, do you has new idea on blocked_load_avg using?
-- Thanks Alex
| |