Messages in this thread | | | Date | Thu, 14 May 2015 02:36:58 -0400 | Subject | Re: [PATCH] x86: skip delays during SMP initialization similar to Xen | From | Len Brown <> |
| |
> [ 0.404369] x86: Booting SMP configuration: ... > [ 2.737884] x86: Booted up 4 nodes, 120 CPUs > [ 2.743758] smpboot: Total of 120 processors activated (671097.18 BogoMIPS) > > (2.743758-0.404369) = 2.339389 for all 119 processors > /119 = .01965873109243697478 - lets call it 19ms each
For the record, the same (bare metal) box running latest tip boots 10ms/processor quicker than upstream Linux, as expected. So this 120 processor box now boots 1.19 seconds faster, in total.
[ 0.415969] x86: Booting SMP configuration: ... [ 1.553658] x86: Booted up 4 nodes, 120 CPUs [ 1.559173] smpboot: Total of 120 processors activated (671182.14 BogoMIPS)
1.553658-0.415969 = 1.137689 - seconds to bring 119 processors on-line. ./119 = .00956041176470588235 -- 9.5ms per processor, down from 19.
BTW. this time can be reduced by 7% (113 ms) by deleting announce_cpu():
[ 1.445815] x86: Booted up 4 nodes, 120 CPUs
cheers, Len Brown, Intel Open Source Technology Center
| |