Frankly, who cares. If you think that the engine inside your car affects your ability to get to the shop to buy beer, you really don’t understand the problem.

What really scared me into an awakening is seeing the investment levels ‘pure play’ networking silicon companies like Broadcom, Fulcrum, Marvell, Dune, etc are putting into their chipsets. They are using very cutting edge processes, 45nm etc, and doing so with 100′s and sometimes 1000′s of engineers working on the chipsets. This level of investment results in extremely capable silicon that is designed with quite flexible packet processing engines that can be re-purposed for many different networking applications. It’s not a one-size fits all, but with the maturation of the market there are pretty capable silicon systems available that are quite programmable and solve a good chunk of the networking use-cases.

dg

Many things have come full-circle, although its also good to see some innovation also being delivered by vendors to customers in networking – whether requiring silicon innovation, or software, or protocol. One area I am personally very interested in is improving the operational/administrative experience of networking products — I like adding things there that make life easier and simplify complex workflows. Think there is still a lot of room to improve there.

dg

You knew this would eventually come back to bite you, it always does in networking architectures Jump in the way-back machine and see Welfleet distributed processing vs. Cisco 7000s with a single RP…and then Cisco moved to VIPs and distributed processing (GSR, etc.). Kalpana originally did cut-through switching, until networks melted because of bad CRCs, so we went back to fast bridging (aka Store-Forward Switching) and now I hear that people want to go back to cut-through again for latency. Somewhere I’m sure there are people at Cisco that are upset about the original Granite K1 chip that was considered impossible to manufacture, and Andy has probably taken those lessons along to Arista.

It’s all cyclical. What you bash today will be what you’re pitching in 24 months. Just remember Gracely’s Theorem of Technology – “There are no great new ideas, just reapplication of old ideas on newer CPUs and bigger bandwidth”.

I wonder what other old post of yours I can find???