North American Network Operators Group
Date Prev | Date Next | Date Index | Thread Index | Author Index | Historical

Re: Extreme congestion (was Re: inter-domain link recovery)

  • From: Fred Baker
  • Date: Thu Aug 16 03:01:10 2007
  • Authentication-results: sj-dkim-1; [email protected]; dkim=pass (si g from cisco.com/sjdkim1004 verified; );
  • Dkim-signature: v=0.5; a=rsa-sha256; q=dns/txt; l=765; t=1187246778; x=1188110778; c=relaxed/simple; s=sjdkim1004; h=Content-Type:From:Subject:Content-Transfer-Encoding:MIME-Version; d=cisco.com; [email protected]; z=From:=20Fred=20Baker=20<[email protected]> |Subject:=20Re=3A=20Extreme=20congestion=20(was=20Re=3A=20inter-domain=20 link=20recovery) |Sender:=20; bh=oPEHSkr/I4zg50bV4GCZE4RYBcuVlfaRXblZ6VFDpc4=; b=HeSluNov1jyFX9hb3GWF440CrvtdRD/RpQfCuYE6aLZB7FA5dlGbBviiScyFLv+0Mqf5imsJ WPFSrdssc/v3NirGnavRlQnTi2UfmN42lJm89SJ/1PXQ7HqkjmqpgprKxr/51nf4jodotBaiP7 htR435bikWmo2sPQHNevyIDlY=;

On Aug 15, 2007, at 10:13 PM, Adrian Chadd wrote:
Well, emprically (on multi-megabit customer-facing links) it takes effect immediately and results in congestion being "avoided" (for values of avoided.) You don't hit a "hm, this is fine" and "hm, this is congested"; you actually notice a much smoother performance degredation right up to 95% constant link use.

yes, theory says the same thing. It's really convenient when theory and practice happen to agree :-)

There is also a pretty good paper by Sue Moon et al in INFOCOMM 2004 that looks at the Sprint network (they had special access) and looks at variation in delay pop-2-pop at a microsecond granularity and finds some fairly interesting behavior long before that.