Messages in this thread | | | Date | Thu, 17 Apr 2008 12:51:09 +0200 | From | Andi Kleen <> | Subject | Re: [v2.6.26] what's brewing in x86.git for v2.6.26 |
| |
> > The input for the first 'benchmark' was indeed completely unrealistic. > They did show a very convincing speedup, though. This program was > really written to verify the implementation and was later converted > to a benchmark. Many benchmarks are unrealistic. I also wrote a > benchmark for find_first_bit and find_next_bit: > http://heukelum.fastmail.fm/find_first_bit
I think a realistic benchmark would be by running a real kernel and profiling the input values of the bitmap functions and then testing these cases.
I actually started that when I complained last time by writing a systemtap script for this that generates a histogram, but for some reason systemtap couldn't tap all bitmap functions in my kernel and missed some completely and I ran out of time tracking that down.
My gut feeling is the only interesting cases are cpumask/nodemask sized (which can be one word, two words but now upto 8 words on a NR_CPU=4096 x86 kernel) and then 4k sized ext3/reiser/etc. block bitmaps.
> My conclusion would be: the speed of the generic bitmap implementation > is either better than or at least comparable to the current private > implementations in i386/x86_64.
Ok.
The generic version is out-of-line, > while the private implementation of i386 was inlined: this causes a > regression for very small bitmaps. However, if the bitmap size is > a constant and fits a long integer, the updated generic code should > inline an optimized version, like x86_64 currently does it.
Yes it should probably. cpumask walks are relatively common.
I remember profiling mysql some time ago which did bad overscheduling due to dumb locking. Funny was that the mask walking in the scheduler actually stood out. No, i don't claim extreme overscheduling is an interesting case to optimize for, but then there are more realistic workloads which also do a lot of context switching.
BTW if you do generic work on this: one reason the generated code for for_each_cpu etc. is so ugly is that the code has checks for find_next_bit returning >= max size. If you can generize the code enough to make sure no arch does that anymore these checks could be eliminated.
-Andi
| |