Date: Mon, 3 Nov 1997 20:58:15 -0700 (MST) From: Charles Mott <cmott@srv.net> To: freebsd-hackers@freebsd.org Subject: gettimeofday() overhead Message-ID: <Pine.BSF.3.96.971103205304.29009I-100000@darkstar.home>
next in thread | raw e-mail | index | archive | help
In the packet aliasing code used by natd and ppp -alias, gettimeofday() is called for every packet. I think this involves a kernel context switch (correct me if I am wrong) and tests I did a while ago showed something like 60 or 70 microseconds per call on a 386. Since timing measurements don't have to be particularly accurate for libalias, does anyone have an idea how time might be measured entirely in user space? Charles Mott
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.3.96.971103205304.29009I-100000>