- Test - lists.nanog.org

Re: multi-homing fixes
by smd＠clock.org 30 Aug '01

30 Aug '01

Iljitsch van Beijnum <iljitsch(a)muada.com> writes: | If we remove all non-essential | information from a route, we finally arrive at the single thing that must | always be encoded for each route individually: whether it is reachable or | not. If we assign a bit of memory to every possible route Is this a novel way of doing RIP and solving the split-horizon problem by eliminating the "D" in "DV"? Sorry for being obtuse, but what does this bit-vector really represent? That neighbour A (a MAC address on a LAN, or a p2p interface or a VP/VC/DLCI/blah on an NMBA interface) is an OK next-hop towards prefix X? Variations upon Random Routing will give you better results and significantly reduce your storage requirements! Or is it associated with a next-hop address with a recursive lookup into another database (e.g. your IGP), such that each known next-hop has one of these bit vectors associated with it? Or do you mean something else by "reachability" than I do? | An idea would be to assign /16s to geographic areas. Each ISP that has | customers in that area would announce the /16, just like they would do | now, but with an attached bitmap that indicates for which /24s this | announcement is valid and for which it isn't. So 10 ISPs in one area would | all announce the /16 with a 256 bit bitmap, so just 10 routes end up in | the default-free zone instead of 500. So, a per-prefix "holes" attribute in the form of a flattened Patricia Tree? Where is the savings here? Indeed, how do you avoid unflattening the bit-vector when eventually building your Adj_RIB/Loc_RIB/FIB? (Although admittedly you probably save more space on the line than gzipping the data stream would...) I'm pretty sure I need further explanation to "get it"./ Sean.

2 1

Re: FIBER CUT: Dallas to West Coast
by Sean Donelan 30 Aug '01

30 Aug '01

On Wed, 29 August 2001, Sean Donelan wrote: > Is anyone else seeing a fiber cut between Dallas and San Diego/Los Angeles? There is no mention of it on the UUNET/Worldcom web site, but it appears to be a Worldcom circuit cut somewhere between Dallas and Los Angeles. Some folks are backup now through re-routing. Worldcom has techs on-scene resplicing the cable. No ETR.

4 4

Re: What is the limit? (was RE: multi-homing fixes)
by smd＠clock.org 30 Aug '01

30 Aug '01

| If you had a router that could handle 2^32 prefixes, it will handle | the IPv4 Internet. Forever. The whole growth curve argument is | gone. Sure, just about anybody can build a router which has 2**32 forwarding directives burned into ROM. It gets easier with fewer interfaces, too. But, who wants a static network? In the early 90s we had a network where you could wait a week before the core of the Internet adapted to your topology change, and changed its routing towards a particular prefix. It wasn't really much fun. So, even though I convert (x/2)² into x/2 in what passes for my head, I think that it's pretty clear that the problem isn't the state at any given moment, but rather the rate of change of that state. | The global routing table cannot grow exponentially forever. And neither can the rate of change. The problem only has to be Too Hard to compute affordably, not NP-complete. (I bet others are already explaining this later in my $MAIL, but I seem to be stuck on doing things linearly today...) | For reference, there are approximately 10^80 electrons in the | universe (per several physics sources I found on the net). Oh cool, particle physics. How many degrees of freedom do these electrons have? Interesting point: a prefix in the global routing table CAN have one or more moments of inertia. Maybe something multilevel is even better. Something like following the contributions of constituent quark spin to a hadron or nucleon or would certainly be even more appropriate, since indeed an IGP perturbation can lead to fluctuation at the EGP (i.e. BGP) level, causing announcements to rotate about a set of interfaces. I bet Ahuja & Labowitz have even recorded this happening. Hey maybe there is some deep irony at work in that one can analogize the work of Dyson Sr (QED, QCD) and Jr (ICANN) in this way... | Not to minimze the short term issue, but to hand wave and say | "it's exponential and we'll never get ahead of it" is crap. It | won't be forever, so let's get ahead of it. There's lots of irony in that too. Other than the hand-wave, how do you propose to get (and stay) ahead of it? Sean.

5 4

RE: What is the limit? (was RE: multi-homing fixes)
by Roeland Meyer 30 Aug '01

30 Aug '01

1 0

RE: What is the limit? (was RE: multi-homing fixes)
by Roeland Meyer 30 Aug '01

30 Aug '01

1 0

RE: What is the limit? (was RE: multi-homing fixes)
by Roeland Meyer 30 Aug '01

30 Aug '01

|> From: smd(a)clock.org [mailto:smd@clock.org] |> Sent: Wednesday, August 29, 2001 8:06 AM |> Draw two curves, the first y=x/2, the second y=x^2 |> Move the value of x for y=1 for the first curve left by 2, 5 or 10 |> and it will still be surpassed by the second curve. |> You will even see this for a second curve of y=x*2 or y=x. Prove it. |> The global routing table size HAS grown exponentially |> in the past. Rationalize it any way you want, blame whatever |> you like, but there is no known way to construct a router that |> can handle that kind of growth in anything but a short term, Sorry, Leo is correct. Technologies he outlined are only the tip of the ice-berg of what *isn't* being exploited by the router vendors. Yes, my 2-year old Dell lap-top has more horse-power than your average Cat 3524XL. But, sadly, it doesn't have the I/O capacity. However, one of my tight-fisted dot-com clients (why they're still in business) had me build three 1U 8-port, router/switchs, built from COTS commodity parts. It worked at line-speed. Code was courtesy of the Linux Router Project (open source). At retail prices, the entire parts cost was less than $6KUS each. Specs were, dual PIII-866, 2GB RAM, 1 CDROM boot drive (no HDD), three 4-port PCI 100baseTX PCI cards, 1U rackmount case. 1 week for the build and two for the software. It still cost less than equivalent Cisco purchase. Yes, I tried to sell them Cisco Catalysts instead. To some extent, Cisco deserves what's happening to their stock prices right now. [ side note: one of the biggest benefits of the, non-proprietary, open source Linux movement is that it lets me do *real* computer engineering again]. Yes, the routing vendor's largest advantage is proprietary back-plane design, optimized for I/O. But, with ASIC technology today, and most importantly, modern macro architectures, one works around that easily. I had plenty of capacity to add DNS zone server software and web-based administration with server-side Java. I had seriously considered productizing it, but in the current economic climate, no one is funding such projects, yet. BTW, this was built almost a year ago. They're still online. Note that PCI bus technology is more than 10 years old. We can do better if we want to and if there's money in it. |> and the trend for the components in the router growth curve |> is simply not going to increase to a long term superlinear rate. That trend is set very much by the router vendors. They have deliberately held growth down in order to keep prices inflated. They can do this because there aren't a whole lot of real computer engineers around anymore. Everyone's a specialist these days and very few do engineering at the macro level, they're called Computer Architects. Many of us *don't* do the IETF thing because we'd rather get paid for our work. In the real world, prestige don't pay the rent. The router vendors have done a real good job convincing everyone that they are at the state-of-the-computer-arts. I've got a clue for you, they're far behind it. |> A 10x system performance boost today just moves the x point for |> y=1 of fundamental curve claimed by Moore's Law to the left |> a few notches. Or are you claiming that routing equipment |> will have a fundamentally different, and larger, growth curve |> than other computing systems? (I think there is a basis for |> claiming that there are some reasons which would support a |> _shallower_ growth curve for routing equipment, actually). As said before, we could see a one-time step up, by more than an order of magnitude. That alone should get us to the forseeable end of the IPv4 cycle. Yes, I agree that we need to do something for IPv6...starting NOW! |> In short: are you claiming that the caeteris paribus assumption |> in comparing Moore's Law to global routing table size is |> clearly false? That depends on how you apply *what* technology to the curve. It's only proven by corrolary, no hard evidence is provided. I'm not convinced that the given Moore's law curve is accurate. In the secular world of the router vendor, they may think that they're on it. Simple observation shows that they aren't. Why do you think that warranty terms prohibit pealing open the $10KUS box?

9 15

RE: What is the limit? (was RE: multi-homing fixes)
by Roeland Meyer 30 Aug '01

30 Aug '01

|> From: Vadim Antonov [mailto:avg@exigengroup.com] |> Sent: Wednesday, August 29, 2001 3:45 PM |> |> On Wed, 29 Aug 2001, Roeland Meyer wrote: |> |> > Sorry, Leo is correct. Technologies he outlined are only |> the tip of the |> > ice-berg of what *isn't* being exploited by the router vendors. |> |> Your average PC doesn't have to be NEBS-compliant, doesn't |> have to work |> more than 24 hours w/o crashing, and doesn't have quite |> strict constraints |> on power & heat dissipation. It doesn't have to have |> redundant power, and |> its components are readily available and cheap (those are produced in |> _large_ batches). Excuse me?!?! What universe are you living in? I know a few racks full of 1U, 2U, and 4U PC's, with dual power, have been running 24x7 for over a year, at five 9's, and NONE of them cost more than $5K. Further, they have over 2TB of RAID. It's a componentized cluster architecture. see www.dell.com, www.penguincomputing.com, www.raidzone.com, www.microway.com, www.aspsys.com, www.hp.com, www.ibm.com, www.asacomputers.com, www.ixsystems.net, www.enlightcorp.com, and www.einux.com. Oh yeah, don't forget to look at www.routerrevolution.com. Wake up, the coffee's brewing ... BTW, RAIC = Redundant Array of Inexpensive Computers, usually clustered. |> And don't get me started on heat and airflow issues :) Reason #1 why |> Pluris abandoned the original idea of using commodity CPUs |> was heat, not |> the switching speed. That was how many years ago? BTW, they gave up because what they hired for wizards couldn't solve the problem (made religious vs technical decisions). If it runs hot, either cool it, or get something that runs cooler. Today's answer is a Transmeta chip, a handful of ASICs, a pair of ECC'd PC133 DIMMs, and a couple of Sony memory sticks to replace the HDDs. Oh yeah, enough fans to qualify for an FAA Airworthyness Certificate (only because fans are cool)<g>.

1 0

Re: What is the limit? (was RE: multi-homing fixes)
by Vadim Antonov 30 Aug '01

30 Aug '01

On Wed, 29 Aug 2001, Michael C. Wu wrote: > Companies in Taiwan manufacture the motherboards. They do not need to > reverse engineer them when they A) designed it, or B) have documentation > and beta CPU's for design. Those are high-cost manufacturers who produce business-grade equipment. When it gets to consumer-grade stuff, the margins are so low that those shops which play in that area cannot afford their own designs. And don't forget mainland China, Indonesia, and other places where a lot of "no-brand" stuff is produced. Actually looking inside PCs is often quite enlightening. I'm quite amazed how most of cheapo stuff manages to work at all. Like, missing or leaky capacitors, plain conductors instead of inductance coils, peeling PCBs, missing ground wires, unevenly soldered connections, overclocked CPUs and DRAMs. PCs are very poorly designed, too. If not for Billy's flaky software, that would be quite evident. Anyway, this is drifting off-topic. My point was that CO-grade, non-stop equipment has very different design requirements from PCs. So is military stuff, but somehow nobody complains that MIL-spec equipment is so expensive and so few-generations-behind. --vadim

1 0

Re: What is the limit? (was RE: multi-homing fixes)
by smd＠clock.org 29 Aug '01

29 Aug '01

| I think there is real promise in SMP though. There are many SMP | applications that scale near linearly, and I think properly designed | routing can be one of them. If a linear SMP solution can be found | then there is at least one way to scale the routing infrastructure | to near infinate size simply for $$$'s. So like I have to hop on a plane, but the Russian guy wakes up really soon, and this is very much his field... :-) You won't like the answers though, 'cause they're consistent with mine. Oh well. Sean.

2 1

RE: What is the limit? (was RE: multi-homing fixes)
by Roeland Meyer 29 Aug '01

29 Aug '01

|> From: Leo Bicknell [mailto:bicknell@ufp.org] |> Sent: Wednesday, August 29, 2001 8:35 AM |> |> On Wed, Aug 29, 2001 at 08:05:51AM -0700, Sean M. Doran wrote: |> > The global routing table size HAS grown exponentially |> > in the past. Rationalize it any way you want, blame whatever |> > you like, but there is no known way to construct a router that |> > can handle that kind of growth in anything but a short term, |> > and the trend for the components in the router growth curve |> > is simply not going to increase to a long term superlinear rate. |> |> Ah, but exponential growth can't happen forever, and we can build |> a system to handle the largest possible Internet (with v4, anyway). |> Not to minimze the short term issue, but to hand wave and say |> "it's exponential and we'll never get ahead of it" is crap. It |> won't be forever, so let's get ahead of it. To boost this point, exponential growth, approaching infinity, becomes asymptotic. There is no way that is going to happen and there is no way we can do anything about it if it does. For one thing, there is a finite number of people on the planet. There is also a finite number of nodes we can build in a year. Both factors create upper bounds for the problem under discussion. What *can* happen is a classic "S" curve that has a rather steep cliff at the front of it. But, that is like the six blind dudes and the elephant. The cliff isn't the whole curve. Sooner or later, you run out of atmosphere and you can't climb anymore.

3 2