"Aneesh Kumar K.V" <aneesh.ku...@linux.vnet.ibm.com> writes:
> Michael Ellerman <m...@ellerman.id.au> writes:
>
....
....
> With patch:
> sys: 0m11.3258
>
> ie, a -0.7% impact
>
> If that impact is high we could possibly put that tracepoint within #ifdef
> CONFIG_DEBUG_VM ?
Since the ebizzy runs results were not stable, I did a micro benchmark
to measure this and I noticed that results observed are within the
run variance of the test. I made sure we don't have context-switches
between the runs. If I try to get large number of page-faults, we end up
with context switches.
for ex: We get without patch
--------------------------------
root@qemu-pr-host trace-fault]# bash run
Performance counter stats for './a.out 3000 300':
643 page-faults # 0.089 M/sec
7.236562 task-clock (msec) # 0.928 CPUs utilized
2,179,213 stalled-cycles-frontend # 0.00% frontend cycles
idle
17,174,367 stalled-cycles-backend # 0.00% backend cycles
idle
0 context-switches # 0.000 K/sec
0.007794658 seconds time elapsed
[root@qemu-pr-host trace-fault]#
And with-patch:
---------------
[root@qemu-pr-host trace-fault]# bash run
Performance counter stats for './a.out 3000 300':
643 page-faults # 0.089 M/sec
7.233746 task-clock (msec) # 0.921 CPUs utilized
0 context-switches # 0.000 K/sec
0.007854876 seconds time elapsed
Performance counter stats for './a.out 3000 300':
643 page-faults # 0.087 M/sec
649 powerpc:hash_fault # 0.087 M/sec
7.430376 task-clock (msec) # 0.938 CPUs utilized
2,347,174 stalled-cycles-frontend # 0.00% frontend cycles
idle
17,524,282 stalled-cycles-backend # 0.00% backend cycles
idle
0 context-switches # 0.000 K/sec
0.007920284 seconds time elapsed
[root@qemu-pr-host trace-fault]#
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
