Date: Thu, 25 Nov 1999 17:46:57 -0500 From: Greg Lehey <grog@mojave.sitaranetworks.com> To: "Niels Chr. Bank-Pedersen" <ncbp@bank-pedersen.dk>, freebsd-questions@FreeBSD.ORG Subject: Re: ping response times over ppp Message-ID: <19991125174657.13723@mojave.sitaranetworks.com> In-Reply-To: <19991125234125.A23366@bank-pedersen.dk>; from Niels Chr. Bank-Pedersen on Thu, Nov 25, 1999 at 11:41:25PM %2B0100 References: <19991125230609.A23253@bank-pedersen.dk> <19991125173107.16398@mojave.sitaranetworks.com> <19991125234125.A23366@bank-pedersen.dk>
next in thread | previous in thread | raw e-mail | index | archive | help
[Format recovered--see http://www.lemis.com/email/email-format.html] On Thursday, 25 November 1999 at 23:41:25 +0100, Niels Chr. Bank-Pedersen wrote: > On Thu, Nov 25, 1999 at 05:31:07PM -0500, Greg Lehey wrote: >> On Thursday, 25 November 1999 at 23:06:09 +0100, Niels Chr. Bank-Pedersen wrote: >>> Hi, >>> >>> We are doing some testing of some new network equipment, and I've >>> stumbled across the following: >>> >>> 64 bytes from 192.168.10.10: icmp_seq=22 ttl=253 time=210.361 ms >>> 64 bytes from 192.168.10.10: icmp_seq=23 ttl=253 time=210.392 ms >>> >>> All responsetimes equals n*10 + epsilon [ms]. I'm pretty sure we don't have >>> any queuing involved that could influence the results, so my question is >>> whether this is caused by timeresolution problems within either ping or >>> ppp; or I'm just plain lucky to hit n*10 every time? :) >> >> Sounds like it could be the other end. What's there? I seem to >> remember that System V STREAMS can sometimes do things like this. > > It's a FreeBSD-STABLE as well: > > FreeBSD freeze.wheel.dk 3.3-STABLE FreeBSD 3.3-STABLE #6: Fri Nov 19 > 22:03:19 CET 1999 root@freeze.wheel.dk:/usr/src/sys/compile/FREEZE > i386 > > - and it's just a few ethernets away - plus of course the ppp-link (see > below). > >> BTW, for normal ping packets and 33.6 or 56 kb/s, these are *very* >> slow times. > > Actually its ISDN, just not the B-channel :-) Ah, now you tell me. That changes everything, of course. D channel data goes through several transformations before being sent. I would strongly suspect that this is telling you something about the way your local switch works. So is D channel usage allowed in Denmark? Greg -- When replying to this message, please take care not to mutilate the original text. For more information, see http://www.lemis.com/email.html Finger grog@lemis.com for PGP public key See complete headers for address and phone numbers To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19991125174657.13723>