nanog mailing list archives
Re: Alternative to BGP-4 for multihoming?
From: Vern Paxson <vern () ee lbl gov>
Date: Mon, 13 Mar 2000 01:07:18 PST
TCP performance is affected by congestion symmetry, since TCP uses the spacing of ACK packets to control the spacing of data packets.
True, but this is a second order effect. The strongest effects are (1) loss rate on the forward path, and (2) bottleneck throughput on the forward path (these two being related). TCP is much more tolerant of lost acks than lost packets - you have to lose an entire flight of acks before it really kills you. So I suspect the match-the-outgoing-hop-with-the-incoming-hop approach is working better for some other reason. Perhaps it's reflecting that Web surfing is in fact bidirectional, and often not all that assymetrically (a small request fetches a small item). In that case, congestion symmetry will help, since both directions are forward paths at some point. Vern
Current thread:
- Re: Alternative to BGP-4 for multihoming?, (continued)
- Re: Alternative to BGP-4 for multihoming? Gary E. Miller (Mar 13)
- Message not available
- Re: Alternative to BGP-4 for multihoming? Randy Bush (Mar 14)
- Re: Alternative to BGP-4 for multihoming? Marc Slemko (Mar 14)
- Re: Alternative to BGP-4 for multihoming? Pete Templin (Mar 14)
- Re: Alternative to BGP-4 for multihoming? Peter A. van Oene (Mar 14)
- Re: Alternative to BGP-4 for multihoming? Adrian Chadd (Mar 14)
- Re: Alternative to BGP-4 for multihoming? Hank Nussbacher (Mar 13)
- Re: Alternative to BGP-4 for multihoming? Scott McGrath (Mar 13)
- Re: Alternative to BGP-4 for multihoming? Randy Bush (Mar 14)
- Re: Alternative to BGP-4 for multihoming? Alex Bligh (Mar 14)
- Re: Alternative to BGP-4 for multihoming? Mr. James W. Laferriere (Mar 15)
- Re: Alternative to BGP-4 for multihoming? k claffy (Mar 15)