OpenVZ Forum


Home » Mailing lists » Devel » Re: New pid namespaces patches testing
Re: New pid namespaces patches testing [message #19018] Tue, 19 June 2007 19:06
ebiederm is currently offline  ebiederm
Messages: 1354
Registered: February 2006
Senior Member
Pavel Emelianov <xemul@openvz.org> writes:

> OK. We have measured the nptl perf test for init namespace.
> Summary - flat model is very light, Suka's patches break the 
> kernel performance event when CONFIG_PID_NS is off.
>
>                  |    perf, s   | perf loss  |
> -----------------+--------------+------------+
> 2.6.22-rc4-mm2   | 13.79 ± 0.13 |    ---     |
>                  |              |            |
> suka  + PID_NS=n | 14.07 ± 0.13 |    2.0%    |
> suka  + PID_NS=y | 14.06 ± 0.08 |    2.0%    |
>                  |              |            |
> pavel + PID_NS=n | 13.80 ± 0.07 |    0.0%    |
> pavel + FLAT     | 13.80 ± 0.07 |    0.0%    |
> pavel + MULTI    | 14.28 ± 0.08 |    3.5%    |
> -----------------+--------------+------------+
>
> I do believe that Suka's hierarchical model is better than mine,
> but my point is: let's support the flat model as well.

If performance is to be the deciding factor between implementations,
then we need to do the research and see what specifically makes the
difference in performance.

My hunch is the real difference in Sukas patches is the extra memory
allocation, or some other stupid silly thing that we can optimize out
and make things simpler, faster, and more maintainable.

Eric

_______________________________________________
Containers mailing list
Containers@lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers
 
Read Message
Previous Topic: Re: [PATCH] create_new_namespaces: fix improper return of NULL
Next Topic: dev_change_netns on a tunnel device
Goto Forum:
  


Current Time: Mon Jul 14 19:54:47 GMT 2025

Total time taken to generate the page: 0.01827 seconds