Messages in this thread | | | Date | Tue, 04 Jun 2013 12:55:54 +0800 | From | Alex Shi <> | Subject | Re: [DISCUSSION] removing variety rq->cpu_load ? |
| |
>>> >> Forgive me but I'm a little lost on this thread... >>> >> >>> >> So we are planing to rely on instant 'cpu_load[0]' and decayed >>> >> 'runnable_load_avg' only, do we? >> > >> > cpu_load is a kind of time decay for cpu load, but after runnable load introduced, >> > the decay functionality is a kind duplicate with it. >> > So, remove them will make code simple. The idea were mentioned by Paul, Peter and I. > Nice, what about make a patch 9 and clean up all those stuff? > > I suppose we will get more benefit :)
I'd like to.
But since Peter doesn't response this thread for long time, I even don't know what's he opinions of patch 1~8. :(
-- Thanks Alex
| |