Path: utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!tut.cis.ohio-state.edu!ucbvax!pasteur!helios.ee.lbl.gov!ace.ee.lbl.gov!leres
From: leres@ace.ee.lbl.gov (Craig Leres)
Newsgroups: comp.protocols.tcp-ip
Subject: Re: tcpdump (more info)
Message-ID: <2752@helios.ee.lbl.gov>
Date: 1 Jun 89 18:06:26 GMT
References: <1559@cunixc.cc.columbia.edu>
Sender: usenet@helios.ee.lbl.gov
Reply-To: leres@helios.ee.lbl.gov (Craig Leres)
Organization: Lawrence Berkeley Laboratory, Berkeley
Lines: 13

Micky Liu writes:
> 2) The clock resolution on Sun-3's is pretty lame... 1/50 of a
>    second.  If you have dollars for a nice protocol analyzer,
>    go for it!

The Intersil ICM7170 chip Sun used is actually running at 100Hz. I've
modified our SunOS 3.5 kernels to use it directly thus giving 10ms
resolution. (As it turns out, the code that actually decodes the chip
was so inefficient that rewriting it more than made up for the overhead
of reading it twice as often.) If there's sufficient interest, I'll
prepare some diffs.

		Craig