On Mon, Nov 29, 2010 at 9:24 AM, Andres Freund <andres@anarazel.de> wrote:
> On Monday 29 November 2010 17:57:51 Robert Haas wrote:
>> On Sun, Nov 28, 2010 at 11:51 PM, Tom Lane <tgl@sss.pgh.pa.us> wrote:
>> > Robert Haas <robertmhaas@gmail.com> writes:
>> >> Yeah, very true. What's a bit frustrating about the whole thing is
>> >> that we spend a lot of time pulling data into the caches that's
>> >> basically static and never likely to change anywhere, ever.
>> >
>> > True. I wonder if we could do something like the relcache init file
>> > for the catcaches.
>>
>> Maybe. It's hard to know exactly what to pull in, though, nor is it
>> clear to me how much it would really save. You've got to keep the
>> thing up to date somehow, too.
>>
>> I finally got around to doing some testing of
>> page-faults-versus-actually-memory-initialization, using the attached
>> test program, compiled with warnings, but without optimization.
>> Typical results on MacOS X:
>>
>> first run: 297299
>> second run: 99653
>>
>> And on Fedora 12 (2.6.32.23-170.fc12.x86_64):
>>
>> first run: 509309
>> second run: 114721
> Hm. A quick test shows that its quite a bit faster if you allocate memory
> with:
> size_t s = 512*1024*1024;
> char *bss = mmap(0, s, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_POPULATE|
> MAP_ANONYMOUS, -1, 0);
Could you post the program?
Are you sure you haven't just moved the page-fault time to a part of
the code where it still exists, but just isn't being captured and
reported?
Cheers,
Jeff