Re: [PATCH 0/3] lockless sys_times and posix_cpu_clock_get

[Rik van Riel <riel@redhat.com>]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On 08/19/2014 05:21 PM, Andrew Theurer wrote:
> 
>> Thanks to the feedback from Oleg, Peter, Mike, and Frederic, I
>> seem to have a patch series that manages to do times() 
>> locklessly, and apparently correctly.
> 
> 
>> 
>> Oleg points out that the monotonicity alone is not enough of a 
>> guarantee, but that should probably be attacked separately,
>> since that issue is equally present with and without these
>> patches...
>> 
>> The test case below, slightly changed from the one posted by
>> Spencer Candland in 2009, now runs in 11 seconds instead of 5
>> minutes.
>> 
>> Is it worthwhile?  There apparently are some real workloads that
>> call times() a lot, and I believe Sanjay and Andrew have one
>> sitting around.
> 
> Thanks for doing this.  When running a OLTP workload in a KVM VM,
> we saw a 71% increase in performance!  do_sys_times() was a big
> bottleneck for us.

Thanks Andrew, a 71% performance increase seems like it would be
enough to justify merging these patches...


Peter, Ingo, Andrew,

Do any of you have an objection to these patches?

Which tree should I merge them through?

I am happy to resubmit them against any tree, just let
me know where you want the patches to go.

thanks,

Rik
- -- 
All rights reversed
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1

iQEcBAEBAgAGBQJUB2AiAAoJEM553pKExN6DlKsH/RygM0SAcKcqbhk7qbKgQsFI
fe9mzJeDg5X2OVW1LuKKhpdo0wPiJ6arg3s2kWnJ8YuToMlIYjFwh9V+fwk1p7bV
4X8KYEK1DyJux8ZYwOBXlZORL+mE30scwuOF8B0sY+TepiRHeorv0srTIXgJfGyJ
avv95X/hx5JSqjAeRomHPmIX8VzgbHTXPEzWxVj+64qehI63CqyLGXXSlHPvFL4D
uhIRvCC4WxKNldUX20HZFUlQETsJttWoM14SiT1HZbfZNJxDMkD6kjcNl7Uimw9j
gVQeE4qy5OkdY1RSsVN35mg+mGA8kzUoQV0aEkogXwbJYNB+wFQ7OEupA1BKiGw=
=6lUC
-----END PGP SIGNATURE-----