nanog mailing list archives
Re: Analysing traces for performance bottlenecks
From: Matt Cable <wozz () wookie net>
Date: Tue, 15 Jul 2008 22:08:08 +0000 (UTC)
Kevin Oberman <oberman <at> es.net> writes:
tcptrace is old and pretty basic, but it can provide a LOT if information. Combined with xplot, the graphs often point to the exact nature of a TCP problem, but you need a really good understanding of TCP to figure anything out.
Wireshark also provides tcptrace-like graphs ("Statistics -> TCP Stream Graph -> Time Sequence Graph (tcptrace)"). They're not quite as pretty, but are just as effective at tracking down all sorts of TCP problems, provided, as Kevin said, you have a really good understanding of how TCP behaves.
Current thread:
- Analysing traces for performance bottlenecks Sam Stickland (Jul 15)
- Re: Analysing traces for performance bottlenecks Tim Eberhard (Jul 15)
- Re: Analysing traces for performance bottlenecks Sam Stickland (Jul 15)
- Re: Analysing traces for performance bottlenecks Kevin Oberman (Jul 15)
- Re: Analysing traces for performance bottlenecks Matt Cable (Jul 15)
- Re: Analysing traces for performance bottlenecks Sam Stickland (Jul 17)
- RE: Analysing traces for performance bottlenecks Bulger, Tim (Jul 17)
- RE: Analyzing traces for performance bottlenecks Tim Sanderson (Jul 17)
- Re: Analyzing traces for performance bottlenecks Randy Bush (Jul 17)
- Re: Analysing traces for performance bottlenecks Matt Cable (Jul 15)
- Re: Analysing traces for performance bottlenecks Sean Donelan (Jul 17)
- <Possible follow-ups>
- Re: Analysing traces for performance bottlenecks rcheung (Jul 15)