advise on future of glibc (mktime issue)

[Jairo Medina]

James Antill wrote:

>"Jairo19@interhosting.us" <jairo19@interhosting.us> writes:
>
>  
>
>>>On Tue, Jun 07, 2005 at 10:35:48AM -0400, Jairo19@interhosting.us wrote:
>>>
>>>      
>>>
>>>>and lastly they suggested to set TZ=/etc/localtime (which makes the
>>>>program run a little faster, but not as fast as RH7.3).
>>>>
>>>>        
>>>>
>>     I ran tests in my DUAL Athlon with RH7.3 installed (compiled in 7.3):
>>linux3 >time ~/temp/test_mktime_7.3
>>
>>real    0m2.263s
>>    
>>
>
>  
>
>>linux3 >LC_ALL=C time ~/temp/test_mktime_7.3
>>Command exited with non-zero status 1
>>2.27user 0.00system 0:02.27elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
>>0inputs+0outputs (139major+13minor)pagefaults 0swaps
>>
>>   Now in the same machine with FC3 (compiled in FC3):
>>linux2 >time ./test_mktime
>>real    0m7.023s
>>    
>>
>[...]
>  
>
>>linux2 >export TZ=/etc/localtime
>>
>>linux2 >export TZ=/etc/localtime
>>
>>linux2 >time ./test_mktime
>>
>>real    0m2.628s
>>
>>linux2 >LC_ALL=C time ./test_mktime
>>Command exited with non-zero status 1
>>2.63user 0.00system 0:02.63elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
>>0inputs+0outputs (0major+232minor)pagefaults 0swaps
>>    
>>
>
> So you've gone from 310% to 116% of the original (and I'll bet that
>16% difference is nothing to do with glibc's mktime()). So I very much
>doubt a real application will differ significantly.
>
>  
>
>>  Regarding my claim,  searching google for +Performance +Fedora will
>>  get you a lot of claims, I don't have a way to quantify it of
>>  course,
>>    
>>
>
> So, that would be a "no".
>
>  
>
>>  I'm just trying to make an educated decision on what to do next
>>  given the fact that my programs run slower in FC3 and RHEL4. I
>>  cannot accept a my runs to go from 1 day to 3 days.
>>    
>>
>
> You do not have runs that take 3x as long, so there is nothing to
>accept.
>
>  
>
    Hola:

    The program I have, takes 1 day to run in a machine with RH7.3, the 
same program (recompiled) in FC3 and RHEL4 takes 3 days. I traced the 
difference in time between them to be caused the calls to mktime (which 
is calling stat64).