I think it's a libpcap bug, actually, and I think I sent Craig Metz'
diff that fixed it to Marcus some months ago. But he's a busy guy, so
it's possible he didn't see it.
Anyway, if libpcap stops doing stupid things (reading more data than it
needs to, not using the in-kernel packet filters, etc.), the performance
will improve. I don't know what version of libpcap NFR is working with
these days, but it might be worthwhile for someone to find out and tweak
it to do the right thing.
Mike
-- 772074.63 609785.36- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/