shuttle flash crowd statistics
Hello, I write this to ask network operators to share your statistics of this flash crowd with NANOG. For example, if possible, could NASA folks let us know the peak and average hit rate to NASA TV (rtsp://198.116.66.254) or the traffic rates on the routers leading into this server? (border.hcn.hq.nasa.gov and realhq.hq.nasa.gov) Similarly, for UUnet folks (as you're the provider) or anyone that has collected statistics that they're willing to share. Graphical (MRTG-esq) would be the best. If folks don't want to hear about this, I'll take any info privately and summarize to anyone that asks me. Thanks, scott
On Sat, 1 Feb 2003, Scott Weeks wrote:
Hello,
I write this to ask network operators to share your statistics of this flash crowd with NANOG.
For example, if possible, could NASA folks let us know the peak and average hit rate to NASA TV (rtsp://198.116.66.254) or the traffic rates on the routers leading into this server? (border.hcn.hq.nasa.gov and realhq.hq.nasa.gov)
This sounds like fabulous data to see.
Similarly, for UUnet folks (as you're the provider) or anyone that has collected statistics that they're willing to share.
Unfortunately UUNET doesn't provide connectivity to this, except for UUNET customers, NASA is not a direct customer...
Graphical (MRTG-esq) would be the best. If folks don't want to hear about this, I'll take any info privately and summarize to anyone that asks me.
Thanks, scott
Thanks for the response Chris. I should not have used the word "provider" when speaking of NASA. All the traceroutes I have done show hand-off from your company though. For example: 9 193.ATM4-0.BR2.SJC1.ALTER.NET (152.63.51.181) [...] 13 border.hcn.hq.nasa.gov (198.116.63.2) 14 realhq.hq.nasa.gov (198.116.66.254) and 10 POS6-0.BR3.DCA6.ALTER.NET [152.63.38.117] [...] 14 border.hcn.hq.nasa.gov [198.116.63.2] 15 realhq.hq.nasa.gov (198.116.66.254) BTW folks are interested, but there is little data coming in to share. As time goes on, I hope folks that show unusual traffic levels (on both sides; eyeball networks and content networks as well as transit networks) will send pointers to me that I can share with others. I am very interested in flash crowd situations and how to mitigate the problems associated with them... scott On Sat, 1 Feb 2003, Christopher L. Morrow wrote: : : : On Sat, 1 Feb 2003, Scott Weeks wrote: : > Hello, : > : > I write this to ask network operators to share your statistics of this : > flash crowd with NANOG. : > : > For example, if possible, could NASA folks let us know the peak and : > average hit rate to NASA TV (rtsp://198.116.66.254) or the traffic rates : > on the routers leading into this server? (border.hcn.hq.nasa.gov and : > realhq.hq.nasa.gov) : : This sounds like fabulous data to see. : : > : > Similarly, for UUnet folks (as you're the provider) or anyone that has : > collected statistics that they're willing to share. : > : : Unfortunately UUNET doesn't provide connectivity to this, except for UUNET : customers, NASA is not a direct customer... : : > Graphical (MRTG-esq) would be the best. If folks don't want to hear about : > this, I'll take any info privately and summarize to anyone that asks me. : > : > Thanks, : > scott : > : :
On Sat, 1 Feb 2003, Scott Weeks wrote:
BTW folks are interested, but there is little data coming in to share. As time goes on, I hope folks that show unusual traffic levels (on both sides; eyeball networks and content networks as well as transit networks) will send pointers to me that I can share with others. I am very interested in flash crowd situations and how to mitigate the problems associated with them...
Historically providers have been reluctant to provide that level of detail concerning traffic levels. A few providers, generally smaller ones, do make MRTG graphs available. Once in a while a provider will announce they had X Peta/Terrabytes of traffic for some time period. But most prefer measurements which can not be correlated with revenue (e.g. packet drops, latency, jitter, availability, etc). I didn't see any noticable change on Abovenet/MFN's public MRTG graphs at MAE-West/MIX-West. Keynote/Matrix public data show no visible changes of the web sites they measure. They may have some private data which shows more details. Of course, NASA is a US federal agency, so you can always try the Freedom of Information Act (FOIA). But they have other things to do today.
There is not a big spike in multicast traffic as there was on 9/11/2001. NASA TV multicast only has reports from 3 viewers at present, which suggest a total viewership of 10 or less. Regards Marshall Eubanks On Saturday, February 1, 2003, at 06:02 PM, Sean Donelan wrote:
On Sat, 1 Feb 2003, Scott Weeks wrote:
BTW folks are interested, but there is little data coming in to share. As time goes on, I hope folks that show unusual traffic levels (on both sides; eyeball networks and content networks as well as transit networks) will send pointers to me that I can share with others. I am very interested in flash crowd situations and how to mitigate the problems associated with them...
Historically providers have been reluctant to provide that level of detail concerning traffic levels. A few providers, generally smaller ones, do make MRTG graphs available. Once in a while a provider will announce they had X Peta/Terrabytes of traffic for some time period. But most prefer measurements which can not be correlated with revenue (e.g. packet drops, latency, jitter, availability, etc).
I didn't see any noticable change on Abovenet/MFN's public MRTG graphs at MAE-West/MIX-West. Keynote/Matrix public data show no visible changes of the web sites they measure. They may have some private data which shows more details.
Of course, NASA is a US federal agency, so you can always try the Freedom of Information Act (FOIA). But they have other things to do today.
T.M. Eubanks Multicast Technologies, Inc. 10301 Democracy Lane, Suite 410 Fairfax, Virginia 22030 Phone : 703-293-9624 Fax : 703-293-9609 e-mail : tme@multicasttech.com http://www.multicasttech.com Test your network for multicast : http://www.multicasttech.com/mt/ Status of Multicast on the Web : http://www.multicasttech.com/status/index.html
From: "Sean Donelan"
Historically providers have been reluctant to provide that level of detail concerning traffic levels. A few providers, generally smaller ones, do make MRTG graphs available. Once in a while a provider will announce they had X Peta/Terrabytes of traffic for some time period. But most prefer measurements which can not be correlated with revenue (e.g. packet drops, latency, jitter, availability, etc).
You mean a lot like when IE 5 first came out? As a result, I got the priviledge of shutting one of my providers off. :) It's sad when a 3Mb pipe is prefered over a 12Mb pipe; even sadder when it's actually faster. Glad I learned my lessons before I really learned the meaning of bandwidth. :) -Jack
Hi, Whilst our statistics may be important let us also not forget the seven families for whom today has been a nightmare. Steve Dyer
: Whilst our statistics may be important let us also not forget the seven : families for whom today has been a nightmare. No, let's don't forget. Although I use an old unix account in Maui, I now live in Friendswood, Texas. 3 miles from Ellington and 5 or so miles from NASA's JSC. My family members have worked for NASA since the Mercury mission. NASA employees live next door and all around the area. It is a sad day here. Tomorrow the churches will be full... scott ps. My apologies for so many posts, but I felt the need to do one last one.
participants (6)
-
Christopher L. Morrow -
Jack Bates -
Marshall Eubanks -
Scott Weeks -
Sean Donelan -
Steve Dyer