Re: Katrina impact on Internet2 backbone -- analysis
Okay, they changed it on me. Flame away. http://www.boingboing.net/2005/09/04/katrina_impact_on_ab.html - ferg -- Fergie (Paul Ferguson) [EMAIL PROTECTED] wrote: I'd be interested in what the curmudgeons on the list think about this: http://www.boingboing.net/2005/09/04/katrina_impact_on_us.html - ferg -- Fergie, a.k.a. Paul Ferguson Engineering Architecture for the Internet [EMAIL PROTECTED] or [EMAIL PROTECTED] ferg's tech blog: http://fergdawg.blogspot.com/
Re: Internet2
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Hi, comments in-line: Dan Hollis wrote: | On Wed, 27 Apr 2005, Randy Bush wrote: | |to source is still the big gap. imiho, from the ops perspective, |only sally's ecn has made any useful approach. sadly, we may be |able to judge the actual demand for e2e qos by ecn's very slow |deployment. i think this is unfortunate, as ecn is pretty cool. - - yeah ecn make sense to us as well. We are currently looking at piece mealing this deployment at our end. fyi - I think kernel.org has also implemented ecn at their end. | | | The low demand is partially due to IWF[0] who unwittingly block it. Many | OSes deploy with ecn support but default it off due to the IWF problem. - --- True enough. Plus devices (by default) may not honor CE (congestion experienced) bits and hence could become non compliant end node which could result in an unnecessary packet drop in the network. | | And there are so many IWF that applying enough cluebats to clear the path | for ECN is going to take enormous effort. | | We could demonstrate how cool ECN is, if there werent so many IWF making | this impossible. Entities who try to deploy ECN are deluged with hey wtf | I cant reach site XYZ anymore, your shit is broken, fix it you ***! | | I have no idea if microsoft supports ECN yet, but if they dont then I | suspect that a sufficiently embarassing benchmark would prod them into | adding it. | | I wonder how many network operators on nanog block ECN. If you do, why? - In fact I raised similar point at NANOG33 in two separate sessions (How to Use Network Design Principles to Differentiate the Good, the Bad, and the Ugly AND IP Fast-Reroute: An Analysis of Applicability to a Core Network) about vendor experience/feedback in this area. Didn't get much feedback. regards, /vicky | | -Dan | | [0]Idiots With Firewalls. See http://urchin.earth.li/cgi-bin/ecn.pl | | -BEGIN PGP SIGNATURE- Version: GnuPG v1.2.5 (MingW32) Comment: Using GnuPG with Thunderbird - http://enigmail.mozdev.org iD8DBQFCctVxpbZvCIJx1bcRAgwcAKDvvBlpDBZBaXfUJysTJ0GUByLUIACgln1F HFQixDoE4zvsyPmdQy7Aa98= =R64s -END PGP SIGNATURE-
Re: Internet2
Maybe you should checkout some performance measurement numbers/papers from ACM (www.acm.org) which should help answer some of your questions. having been an acm member since '67, i am aware of the volume published. give me a specific cite, please. http://www.slac.stanford.edu/comp/net/wan-mon/netmon.html am well aware of les's work for many years. have always argued with him of the accuracy of his pinger. you might find http://www.nanog.org/mtg-0105/casner.html relevant randy
Re: Internet2
On 4/26/05, Adam McKenna [EMAIL PROTECTED] wrote: On Tue, Apr 26, 2005 at 11:18:08PM +0200, Mikael Abrahamsson wrote: On Tue, 26 Apr 2005, Vicky Rode wrote: Basically I meant to say not congested as the current Internet is. If your ISP has congested links you should complain and switch if not fixed promptly. WTF.. She asked a simple question and five people are slamming her for no apparent reason. Actually, I interpreted it as someone asking a question while obviously imbibing too often from the I2 kool-aid pitcher. My attitude towards I2 is that it is a really, really nice private WAN that I have the joy of funding indirectly through NSF grant awards and such - oh, and it has a really catchy name. That doesn't make it better, less congested or faster than the Internet. As Patrick already pointed out, it is difficult to say anything about the Internet as a whole. On 4/26/05, Vicky Rode [EMAIL PROTECTED] wrote: Then again, I'm not saying that Internet is going to crash and burn, its doomed and that one should switch to I2. All I'm asking is for some insight about potential risk of I2 abuse, that's all. That's good to know, because if the internet were to crash and burn, Abilene would be right behind it. As far as I can see from the outside, there's nothing beind done on I2 that couldn't be done on the Internet with fat enough pipes and quality-of-service. -doug
Re: Internet2
Steve Casner's paper, which you cited, and Sue Moon's paper at http://an.kaist.ac.kr/~sbmoon/paper/infocom2004.pdf, both report very limited variation in delay within the ISP network. Sue's paper goes on to describe points of variation on the order of ten and 100 ms in some detail as well as reporting the general case of low variation in delay. But most people don't live within the PE-PE domain, where these studies were done - they connect to the backbone ISP through an access carrier or through an enterprise network, or connect via some longer path. So responding defensively give me numbers and citing as proof of your case a paper that only looks at the path within the ISP has the effect of shutting down and making an end-to-end discussion appear to be invalid when Casner and Moon in fact only perform a measurement of a part of the path. uh, fred. it was vicky who made the comparison i2 to internet, not i. i2 does not include site links, and some are good and some are bad. it is common wisdom today that the internet backbone is not where congestion occurs, but rather the customer tails. though one should always be suspicious of common wisdom, this particular bit seems pretty well supported, pings from uganda's makerere university notwithstanding. you/ve been pushing qos for a long time, fred. but, in the current situation, where the tails are the issue, signaling back from dest to source is still the big gap. imiho, from the ops perspective, only sally's ecn has made any useful approach. sadly, we may be able to judge the actual demand for e2e qos by ecn's very slow deployment. i think this is unfortunate, as ecn is pretty cool. but, in this community, the question would seem to be how long the current situation will prevail, where it is far simpler and less expensive to throw bandwidth at the backbone, as opposed to spending even more on opex-eating complexety and ever more complex and expensive routers. i suspect it'll be a while before we even see cotton balls being blown, and a very long while before new ducts. i.e., raw bandwidth costs will likely stay low. even the price of lighting it is declining. this has been discussed recently, both here and in simon lam's 2004 sigcomm award paper (recent ccr). so, i think we should o encorage i2 as the usg's way of subsidizing higher ed [0] and providing a playpen where big spikes and other traffic anomalies are not discouraged o encourage qos research o keep the real internet as simple as possible, after all, it is fools such as i who have to run it randy --- [0] - and i mean it. the lack of govt support for education in the us is a horrifying tragedy ever in the making
Re: Internet2
On Wed, 27 Apr 2005, Randy Bush wrote: to source is still the big gap. imiho, from the ops perspective, only sally's ecn has made any useful approach. sadly, we may be able to judge the actual demand for e2e qos by ecn's very slow deployment. i think this is unfortunate, as ecn is pretty cool. The low demand is partially due to IWF[0] who unwittingly block it. Many OSes deploy with ecn support but default it off due to the IWF problem. And there are so many IWF that applying enough cluebats to clear the path for ECN is going to take enormous effort. We could demonstrate how cool ECN is, if there werent so many IWF making this impossible. Entities who try to deploy ECN are deluged with hey wtf I cant reach site XYZ anymore, your shit is broken, fix it you ***! I have no idea if microsoft supports ECN yet, but if they dont then I suspect that a sufficiently embarassing benchmark would prod them into adding it. I wonder how many network operators on nanog block ECN. If you do, why? -Dan [0]Idiots With Firewalls. See http://urchin.earth.li/cgi-bin/ecn.pl
Re: Internet2
* Dan Hollis: And there are so many IWF that applying enough cluebats to clear the path for ECN is going to take enormous effort. ECN favors non-conformant endpoints. Therefore, it won't help you in the long run if the congestion is on a path which is shared by multiple customers. Popular file sharing software will just set the proper flags to decrease the discard probability, just like Netscape opened multiple HTTP connections to the same server.
Internet2
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Hi there, Just wondering how's internet2 community/partners protecting themselves from lawsuits of illegal use of music/movie downloads. In general, how are they protecting themselves from malicious code infection spreading at internet2 speed? How are the devices coping up with filters in place, if any? Like to hear what nanog community and the people who are involved w/ internet2 connectivity think. Any insight and /or pointers to any papers will be appreciated. regards, /vicky -BEGIN PGP SIGNATURE- Version: GnuPG v1.2.5 (MingW32) Comment: Using GnuPG with Thunderbird - http://enigmail.mozdev.org iD8DBQFCbp19pbZvCIJx1bcRApbRAKCNWtZP/f+5TPwzB0gkU7tLmgpq9gCgiR+H bsR8d1Ai9zWFnUQeXPPB7fs= =ebza -END PGP SIGNATURE-
Re: Internet2
On Tue, 26 Apr 2005, Vicky Rode wrote: In general, how are they protecting themselves from malicious code infection spreading at internet2 speed? How are the devices coping up with filters in place, if any? What is internet2 speed? As far as I can see Internet2 is a 10G based national network. What is so special about that in this day and age? -- Mikael Abrahamssonemail: [EMAIL PROTECTED]
Re: Internet2
On Tue, 26 Apr 2005, Mikael Abrahamsson wrote: What is internet2 speed? As far as I can see Internet2 is a 10G based national network. What is so special about that in this day and age? I think the difference is the average connection speeds of the end users of the network. It's not at all uncommon today for a provider with a 10G+ backbone to have 100Mbs or less average connection speed, whereas I2 end users are often on campus networks at gig-E or faster. So the speeds mentioned are the realized speeds in p2p and malware spreading applications, or at least that is my assumption based on the original poster's question.
Re: Internet2
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 I made that up :-) Basically I meant to say not congested as the current Internet is. regards, /vicky Mikael Abrahamsson wrote: | On Tue, 26 Apr 2005, Vicky Rode wrote: | | |In general, how are they protecting themselves from malicious code |infection spreading at internet2 speed? How are the devices coping up |with filters in place, if any? | | | What is internet2 speed? As far as I can see Internet2 is a 10G based | national network. What is so special about that in this day and age? | -BEGIN PGP SIGNATURE- Version: GnuPG v1.2.5 (MingW32) Comment: Using GnuPG with Thunderbird - http://enigmail.mozdev.org iD8DBQFCbq2DpbZvCIJx1bcRAgOjAKCuprmc0AVDET7d7qokD+3IlrScngCg22Pj vV0ZVZS8egBkpmIprN3h9f4= =9zJe -END PGP SIGNATURE-
Re: Internet2
On Tue, Apr 26, 2005 at 02:07:15PM -0700, Vicky Rode wrote: Basically I meant to say not congested as the current Internet is. It is? Regards, Daniel -- CLUE-RIPE -- Jabber: [EMAIL PROTECTED] -- [EMAIL PROTECTED] -- PGP: 0xA85C8AA0
Re: Internet2
Basically I meant to say not congested as the current Internet is. cool. and your measurements of internet congestion are? cites, please. randy
Re: Internet2
On Tue, 26 Apr 2005, Vicky Rode wrote: Basically I meant to say not congested as the current Internet is. If your ISP has congested links you should complain and switch if not fixed promptly. -- Mikael Abrahamssonemail: [EMAIL PROTECTED]
Re: Internet2
On Apr 26, 2005, at 5:17 PM, Daniel Roesen wrote: On Tue, Apr 26, 2005 at 02:07:15PM -0700, Vicky Rode wrote: Basically I meant to say not congested as the current Internet is. It is? Parts. Other parts have better connectivity than I2 nodes. You can't really say anything about the _entire_ Internet. -- TTFN, patrick
Re: Internet2
On Tue, Apr 26, 2005 at 11:18:08PM +0200, Mikael Abrahamsson wrote: On Tue, 26 Apr 2005, Vicky Rode wrote: Basically I meant to say not congested as the current Internet is. If your ISP has congested links you should complain and switch if not fixed promptly. WTF.. She asked a simple question and five people are slamming her for no apparent reason. --Adam
Re: Internet2
On Tue, 26 Apr 2005, Vicky Rode wrote: Just wondering how's internet2 community/partners protecting themselves from lawsuits of illegal use of music/movie downloads. In general, how are they protecting themselves from malicious code infection spreading at internet2 speed? How are the devices coping up with filters in place, if any? Like to hear what nanog community and the people who are involved w/ internet2 connectivity think. I don't differentiate between my Internet2 connectivity my other connectivity regarding network abuse issues. Each is a conduit for good bad stuff, each has a NOC when I need it. Jay Ford, Network Engineering Group, Information Technology Services University of Iowa, Iowa City, IA 52242 email: [EMAIL PROTECTED], phone: 319-335-, fax: 319-335-2951
Re: Internet2
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 since you deviated from my original post... http://www.icir.org/floyd/ccmeasure.html regards, /vicky Daniel Roesen wrote: | On Tue, Apr 26, 2005 at 02:07:15PM -0700, Vicky Rode wrote: | |Basically I meant to say not congested as the current Internet is. | | | It is? | | | Regards, | Daniel | -BEGIN PGP SIGNATURE- Version: GnuPG v1.2.5 (MingW32) Comment: Using GnuPG with Thunderbird - http://enigmail.mozdev.org iD8DBQFCbtTopbZvCIJx1bcRAhoYAKDbWlRfn24TrCf1qiL4onXZDZSoSwCgqkEN NxQzrae8KtOS60CQDPyJKEA= =g+6Y -END PGP SIGNATURE-
