Re: [kernel] 247f5d7caa: will-it-scale.per_process_ops 9.6% improvement
From: Jann Horn
Date: Fri Feb 21 2020 - 11:29:40 EST
On Fri, Feb 21, 2020 at 12:56 PM kernel test robot
<rong.a.chen@xxxxxxxxx> wrote:
[...]
> will-it-scale.per_process_ops
>
> 83000 +-------------------------------------------------------------------+
> 82000 |-+ O O O O |
> | O O O O O O O O O O O |
> 81000 |-O O O O O O O O O O O O O |
> 80000 |-+ O |
> | |
> 79000 |-+ |
> 78000 |-+ |
> 77000 |-+ |
> | |
> 76000 |-+ |
> 75000 |-+ |
> |. .+. .+. .+.+.. .+.. |
> 74000 |-+..+.+ +..+.+.+.+..+ +.+..+ +.+.+ +.+.+.+..+.+ |
> 73000 +-------------------------------------------------------------------+
>
>
> will-it-scale.workload
>
> 1.32e+06 +----------------------------------------------------------------+
> | O O O O O O O O |
> 1.3e+06 |-O O O O O O O O O O O O O |
> 1.28e+06 |-+ O O O O |
> | |
> 1.26e+06 |-+ |
> | |
> 1.24e+06 |-+ |
> | |
> 1.22e+06 |-+ |
> 1.2e+06 |-+ |
> | |
> 1.18e+06 |.+.+..+.+.+. .+.+..+.+.+.+.+.+..+.+.+.+.+.+..+.+. .+. .+ |
> | + + + |
> 1.16e+06 +----------------------------------------------------------------+
>
>
> [*] bisect-good sample
> [O] bisect-bad sample
Some comments on the report format:
"O" appears in the graphs, but not "*". Is "+" supposed to be the
"bisect-good sample"? Also, what do "per_process_ops" and "workload"
mean - are higher numbers better or worse? And what does "bisect-good"
and "bisect-bad" even mean in the context of a performance
*improvement* - is the "good" commit the newer one and the "bad" one
the older one?