[devel] [PATCH 0/3] optimize rpmsetcmp()

[Dmitry V. Levin]

On Tue, Nov 30, 2010 at 03:35:42AM +0300, Dmitry V. Levin wrote:
> On Fri, Nov 26, 2010 at 10:35:37AM +0200, Kirill A. Shutemov wrote:
> > On Fri, Nov 26, 2010 at 12:04:23AM +0200, Kirill A. Shutsemov wrote:
> > > 
> > > Tested on Intel Core2 Duo P9500, 3GiB RAM. i586.
> > 
> > apt-shell < /dev/null
> [...]
> > Around 41% of speed up.
> 
> On AMD Opteron Processor 275:
> without patches:
> 2.98user 0.19system 0:03.18elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (0major+10142minor)pagefaults 0swaps
> with patches:
> 2.20user 0.21system 0:02.42elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (0major+9978minor)pagefaults 0swaps
> speedup is around 24%
> 
> On AMD Opteron Processor 2216:
> without patches:
> 2.42user 0.02system 0:02.44elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (0major+9784minor)pagefaults 0swaps
> with patches:
> 1.86user 0.02system 0:01.88elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (0major+9601minor)pagefaults 0swaps
> speedup is around 23%
> 
> On Intel Xeon 5110
> without patches:
> 2.98user 0.04system 0:03.02elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (0major+9789minor)pagefaults 0swaps
> with patches:
> 2.54user 0.01system 0:02.55elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (0major+9608minor)pagefaults 0swaps
> speedup is around 16%
> 
> On Intel Xeon E5520
> without patches:
> 2.02user 0.00system 0:02.02elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (0major+9730minor)pagefaults 0swaps
> with patches:
> 1.77user 0.00system 0:01.77elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (0major+9565minor)pagefaults 0swaps
> speedup is around 12%
> 
> Not so amazing as on your test platform, but awesome anyway.
> I'm going to apply these patches.
> If anybody has objections, please speak up now.

These patches were made on top of your cleanup patches.  Looks like
I'll have to override unreasoned NAK from Alexey Tourbin and apply
these cleanups as well.


-- 
ldv
----------- следующая часть -----------
Было удалено вложение не в текстовом формате...
Имя     : отсутствует
Тип     : application/pgp-signature
Размер  : 198 байтов
Описание: отсутствует
Url     : <http://lists.altlinux.org/pipermail/devel/attachments/20101203/533eab1c/attachment.bin>