[Devel] nptl perf bench and profiling with pidns patchsets

[Cedric Le Goater]

Pavel Emelianov wrote:
> Cedric Le Goater wrote:
>> Pavel Emelianov wrote:
>>> Cedric Le Goater wrote:
>>>> Pavel and all,
>>> [snip] 
>>>
>>>> findings are : 
>>>>
>>>> * definitely better results for suka's patchset. suka's patchset is 
>>>>   also getting better results with unixbench on a 2.6.22-rc1-mm1 but 
>>>>   the values are really dispersed. can you confirm ?
>>>> * suka's patchset would benefit from some optimization in init_upid() 
>>>>   and dup_struct_pid()  
>>> We have found the reason why Suka's patches showed better performance.
>>> Some time ago I sent a letter saying that proc_flush_task() actually
>>> never worked with his patches - that's the main problem. After removing
>>> this call from my patches the results turned to those similar to my.
>>>
>>> I'd also like to note that broken-out set of patches is not git bisect
>>> safe at all. The very first patch of his own OOPSes the node. Some
>>> subsequent patches contain misprints that break the compilation, etc.
>>>
>>> So I ask you again - let us prepare our patches again and compare the 
>>> performance one more time.
>> OK. that's fine with me. 
>>
>> I'm not exactly in a neutral zone but I have the blades ready for the 
>> next drop of patches. I'll torture them if you don't mind.
> 
> I do not :) I am going to send my view of pid namespaces this evening
> or tomorrow morning (I am in GMT+3 time zone :)). 

I'm in Toulouse, France. GMT+1

> Are you going to fix your patches for comparison?

yes. suka (GMT-8) has a pidns patchset ready for 2.6.22-rc4-mm2 that he 
should send when he wakes up. 

thanks pavel,

C.
_______________________________________________
Containers mailing list
Containers at lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers