Date: Fri, 21 Jan 2000 22:37:19 +0530 From: Greg Lehey <grog@lemis.com> To: Dag-Erling Smorgrav <des@flood.ping.uio.no> Cc: FreeBSD Chat <chat@FreeBSD.ORG> Subject: Re: New speed record? Message-ID: <20000121223719.I918@mojave.worldwide.lemis.com> In-Reply-To: <xzp1z7bmpby.fsf@flood.ping.uio.no>; from des@flood.ping.uio.no on Fri, Jan 21, 2000 at 04:12:01PM %2B0100 References: <20000121172731.B517@mojave.worldwide.lemis.com> <xzp1z7bmpby.fsf@flood.ping.uio.no>
next in thread | previous in thread | raw e-mail | index | archive | help
On Friday, 21 January 2000 at 16:12:01 +0100, Dag-Erling Smorgrav wrote: > Greg Lehey <grog@lemis.com> writes: >> All this has me wondering why. It seems that ftp gets particularly >> bad performance when transferring full frames (1460 bytes payload). >> While this transfer is (not) progressing, I can access the system at >> the other end interactively. It seems that if I could persuade ftpd >> to send smaller frames, I might get better throughput. Does anybody >> have opinions? > > Maybe some routers are configured to give small packets priority over > large ones? I'd guess that this isn't an issue of fragmentation. It *may* be an issue of TOS, but this appears not to be implemented. > Lower the MTU on your interface, see if it helps. No, the PPP interface reassembles the packets. What I'm getting through is 1460 byte packets, which seem to be the default I get from ftpd; the MTU of my PPP interface would only be an issue if that link were the bottleneck. Even a 300 bps link would be adequate in this case :-( Greg -- 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-chat" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20000121223719.I918>