nanog mailing list archives
Re: Practical guide to predicting latency effects?
From: Eric Tykwinski <eric-list () truenet com>
Date: Wed, 8 Apr 2020 22:41:30 -0400
There is still one in XCode tools. It’s a alternate download: https://developer.apple.com/download/more/?q=Additional%20Tools%20for%20Xcode <https://developer.apple.com/download/more/?q=Additional%20Tools%20for%20Xcode> Of course this is limited to OSX, but it’s there. Sincerely, Eric Tykwinski TrueNet, Inc. P: 610-429-8300
On Apr 8, 2020, at 10:33 PM, Lee <ler762 () gmail com> wrote: On 4/7/20, Adam Thompson <athompson () merlin mb ca> wrote:I’m looking for a practical guide – i.e. specifically NOT an academic paper, thanks anyway – to predicting the effect of increased (or decreased) latency on my user’s applications. Specifically, I want to estimate how much improvement there will be in {bandwidth, application XYZ responsiveness, protocol ABC goodput, whatever} if I decrease the RTT between the user and the server by 10msec, or by 20msec, or by 40msec. My googling has come up with lots of research articles discussing theoretical frameworks for figuring this out, but nothing concrete in terms of a calculator or even a rule-of-thumb.There used to be network simulators that claimed to figure that out for you - eg https://opnetmodeler.wordpress.com/ "Predict application performance using real traffic in a simulated mode" I suspect all that died after encryption became the norm, since you have to be able to see and understand what's going on before you can predict what will happen after changing the network. Take a look at https://www.cse.wustl.edu/~jain/cse567-08/ftp/simtools/index.html the date is 2008 and all the references are http://xxx (or maybe I can't search worth beans & missed all the current references) Or maybe simulation just got too expensive? I vaguely recall sitting through a few OPNET sales pitches in the early 2000s & people getting excited about the product until they found out how much it cost :( Regards, LeeUltimately, this goes into MY calculator – we have the usual north-american duopoly on last-mile consumer internet here; I’m connected directly to only one of the two. There’s a cost $X to improve connectivity so I’m peered with both, how do I tell if it will be worthwhile? Anyone got anything at all that might help me? Thanks in advance, -Adam Adam Thompson Consultant, Infrastructure Services [[MERLIN LOGO]]<https://www.merlin.mb.ca/> 100 - 135 Innovation Drive Winnipeg, MB, R3T 6A8 (204) 977-6824 or 1-800-430-6404 (MB only) athompson () merlin mb ca<mailto:athompson () merlin mb ca> www.merlin.mb.ca<http://www.merlin.mb.ca/>
Current thread:
- Practical guide to predicting latency effects? Adam Thompson (Apr 07)
- Re: Practical guide to predicting latency effects? Saku Ytti (Apr 07)
- Re: Practical guide to predicting latency effects? Lee (Apr 08)
- Re: Practical guide to predicting latency effects? Eric Tykwinski (Apr 08)
- <Possible follow-ups>
- RE: Practical guide to predicting latency effects? Jakob Heitz (jheitz) via NANOG (Apr 08)
- Re: Practical guide to predicting latency effects? Eric Tykwinski (Apr 08)