Date: Tue, 22 Apr 2014 03:01:10 +0400 From: Solar Designer <solar@...nwall.com> To: john-dev@...ts.openwall.com Subject: Re: mmap(2) in wordlist.c On Mon, Apr 21, 2014 at 11:56:03PM +0200, magnum wrote: > On 2014-04-21 21:22, Solar Designer wrote: > >I think this is worth a try, while also keeping the present approach > >(for Windows, and for systems where it's faster). > > That clashes with a hidden agenda though: A total rewrite of wordlist.c > starting with core 1.8 version, and re-implementing Jumbo features as > cleanly and KISS as possible. Unless real-world performance in some > situations end up a lot worse than today's, I'd like to drop the old > buffering altogether, including the --mem-file-size option which ideally > should not be needed. Right. When I wrote "also keeping the present approach" I didn't mean the present implementation of it in jumbo. And the approach may change somewhat, too. I only meant that we need both a read() and a mmap() version of the code. > >I briefly experimented with read() vs. mmap() while developing popa3d, > >in 1998 or 1999. At the time, read() turned out to be significantly > >faster, on Linux 2.0.x and ext2fs, when the read buffer size is properly > >tuned. I didn't try this experiment in JtR. > > What order of size was that at the time? 64 KB. I think somewhat larger worked OK too, but wasn't necessary. popa3d still has it at 64 KB, I didn't bother re-tuning (and this might still be nearly optimal anyway). Alexander
Powered by blists - more mailing lists
Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.