Re: "REPORT: sd-0.46 vs cfs-v6 vs mainline 2.6.21-rc7 Beryl + Video + Audio"

[Ingo Molnar <mingo@elte.hu>]

* hechacker1 <hechacker1@gmail.com> wrote:

> "REPORT: sd-0.46 vs cfs-v6 vs mainline 2.6.21-rc7 Beryl + Video + Audio"

thanks for testing it out.

one immediate observation i have is that you used a 2msec granularity 
setting on CFS, but even that did not cause context-switching as high as 
SD's rr_interval==2 setting:

> cfs-v6:
> 700m kernel # cat sched_granularity_ns
> 2000000
> r  b   swpd   free   buff  cache    si   so    bi    bo   in   cs us sy id
> 1  0      0 100412     44 1519364    0    0     0     0 7426 7634 62  4 34  
> 4  0      0 100288     44 1519364    0    0     0     0 7039 7442 60  6 34  

> sd-0.46:
> 700m kernel # cat rr_interval
> 2
> r  b   swpd   free   buff  cache   si   so    bi    bo   in    cs us sy id
> 5  0      0 918052    536 832840    0    0   411     0 2387 15242 89 11  0  
> 4  1      0 915600    536 834908    0    0   388     0 2283 15428 90 10  0  

so SD context-switched twice as much and saturated the CPU fully, while 
under cfs-v6 there was 34% idle time left. That double context-switch 
rate and higher CPU utilization could easily result in you experiencing 
a 'smoother' desktop (and smoother video playback) on SD.

could you try to maximize the preemption ratio on CFS by using a 
sched_granularity_ns of 0? Does that result in a higher context-switch 
rate and in better CPU utilization? Thanks,

	Ingo