From owner-freebsd-hackers Tue Jan 12 16:40:39 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id QAA15546 for freebsd-hackers-outgoing; Tue, 12 Jan 1999 16:40:39 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from alpha.xerox.com (alpha.Xerox.COM [13.1.64.93]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id QAA15527 for ; Tue, 12 Jan 1999 16:40:34 -0800 (PST) (envelope-from fenner@parc.xerox.com) Received: from mango.parc.xerox.com ([13.1.102.232]) by alpha.xerox.com with SMTP id <61513(4)>; Tue, 12 Jan 1999 16:39:44 PST Received: from mango.parc.xerox.com (localhost.parc.xerox.com [127.0.0.1]) by mango.parc.xerox.com (8.8.8/8.8.8) with ESMTP id QAA06354; Tue, 12 Jan 1999 16:39:40 -0800 (PST) (envelope-from fenner@mango.parc.xerox.com) Message-Id: <199901130039.QAA06354@mango.parc.xerox.com> To: Doug White cc: Bill Fenner , hackers@FreeBSD.ORG Subject: Re: using raw sockets In-reply-to: Your message of "Tue, 12 Jan 1999 15:43:47 PST." Date: Tue, 12 Jan 1999 16:39:40 PST From: Bill Fenner Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG In message you write: >I'm assuming the timestamps are generated by tcpdump, >or are they the real packet timestamps? The timestamp that tcpdump prints is the timestamp that bpf attaches (i.e. when the driver calls bpf_[m]tap() ). Can you compare that timestamp against gettimeofday(), to see if it looks like the latency is in the bpf buffer? >From a brief inspection of the bpf code, it looks like bpf won't wake up a selecting process until the buffer is almost full. Have you tried using the BIOCIMMEDIATE ioctl? Bill To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message