Hi Yakov, | - The above assumes that DRAM will continue to be used to |implement control | plane memory. As had been discussed before on this list, |DRAM is not the | only option - another alternative is RLDRAM.
I think that Robin did an excellent job of expanding on the tradeoffs involved in this, and I agree with his conclusion. I'll also point out that that's at best a one time benefit and that the subsequent speed increases would seem likely to parallel the DRAM speed curve. This is likely since RLDRAM is still using the same basic DRAM cell technology and improving on the electrical interface. Thus, RLDRAM would give us a one-time bump up the speed curve, but it would do nothing to change the shape or slope of the curve. Again, the most important thing here is the slope (or more generally the shape) of the curve. As long as the slope of the prefix curve exceeds the slope of the technology curve, you will eventually and necessarily run into a problem. | - Even if one assumes that the growth rate of prefixes exceeds the | rate of speed improvements in the underlying DRAM that is used to | implement control plane, and that, in turn, would result in cost | increases, let's not forget that deploying new routing architecture | may have its own cost, thus resulting in cost increases. Moreover, | these increases may be higher relative to what would result from | the growth rate of prefixes exceeding the rate of speed improvements | in the underlying DRAM. True, but deploying a new architecture will have a one-time cost impact. Paid for, over and done. It will be spread out over each system that needs to be upgraded, but it is a fixed and finite cost. Paying for a more expensive control plane is likely to be an ongoing, ever increasing cost. | Would the industry be willing to buy into the *promise* of | "a paradise" in the *long* term at the price of fairly certain | cost increases in the *short/medium* term ? | | All of the above means that a "promise" of cost reduction in the | *long* term may not be sufficient - the new routing architecture | needs to deliver in the *short/medium* term sufficient *tangible* | benefits to justify its *short/medium* term cost. One might look it at it instead as avoiding the guarantee of long term higher costs. In any case, there are numerous problems that we do feel we need to overcome with the new architecture. Whether the deployment costs are sufficiently justified will in part depend on what we produce, and we will not know that until we have consensus on a workable architecture. | - One may argue that the real problem is not in the cost increases, | but in the way how these increases are absorbed by the system. | Namely, the real problem is that those who do not benefit | are still required to pay for covering the cost imposed by those | who do benefit. That applies both to the current system, as well | as to any proposal for a new routing architecture. Agreed. The fundamental problem is that the architecture is a ready-made tragedy of the commons. Tony _______________________________________________ rrg mailing list [email protected] https://www.irtf.org/mailman/listinfo/rrg
