On Sun, Jun 19, 2011 at 01:08:53PM +0200, Denys Vlasenko wrote: > On both machines speedup is not so big. Hash seems to help more then getline: > on F15, it reduced run time from 19 to 16 seconds, while getline won > ~0.5 sec only.
For what it's worth, getline should make a much more dramatic difference on libcs where it's not implemented with getc_unlocked but rather memchr - that would be at least glibc and musl. > Don't take me wrong, I'm not saying the patches are not good. > I am saying we need to figure out how much *each* patch speeds up > modprobe, and in what conditions (IOW: why you see big speedup, > and I see small one), so that we can document it in comments > and save some head scratching for future hackers. The discussion here on the ML regarding getline implementations would be a good source for part of the comments. > How much speedup you get if you use getc_unlocked instead of getline > (see attached patch)? I would guess nearly the same speedup on uClibc where getline just calls getc_unlocked, but much less benefit on good getlines. Rich _______________________________________________ busybox mailing list [email protected] http://lists.busybox.net/mailman/listinfo/busybox
