There was some work in Melbourne Uni (or monash) on the energy implications of on-card and off-card routing. If its on-card, it passes through an FPGA path which may be both faster and cheaper energy than the core CPU. if the core cpu wakes up on complex DPI or routing logic it invokes L2 and working-set and so goes into core power and memory bus cost. So, switching-vs-routing and on-card and off-card and in-card fastpath absolutely affect power cost in the device. Is this all L0 or L-1? No. the upper layer routing architecture and use of out of order or un-ordered IPv6 headers affects on-card and in-core routing outcomes. EH means you cost more work to route. -G On Thu, Jul 25, 2019 at 11:52 AM Kent Watsen <kent+ietf@xxxxxxxxxx> wrote: > > > Along these lines, roughly a decade ago I filed a patent for selective routing to data centers for purposes of power control and environmental impact [1]. While I've left Juniper since, if there were interest, they may be willing to assign the IPR to IETF if asked nicely. > > That said, this patent somewhat missed the claim. What's really needed is power-based routing in general (not just to data centers), whereby how green the power is matters. Of course, getting routers to accurately testify the greeness of their power source could be difficult... > > [1] http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=2&f=G&l=50&co1=AND&d=PTXT&s1=8,798,071&OS=8,798,071&RS=8,798,071 > > Kent > > > On Jul 24, 2019, at 2:54 PM, Jari Arkko <jari.arkko@xxxxxxxxx> wrote: > > I think it is an interesting topic and very much on topic for us to think about. And a topic where potential savings could be significant. IT is a huge energy consumer (as well as a producer of short-lived gadgets). IT also has the potential to help optimise many non-IT processes, and therefore directly reduce energy consumption and waste. > > But of course this is also complex topic and not one where only IETF or only standards help. And a topic where continuous improvements in compute and comms are often offset by more high res videos and ever growing software packages (as well as auto-play and zillions of adverts, placed on my screen after way too much ML analysis). > > I’d be eager to work on this, assuming we can come up with proposals that can have an impact. > > Jari > >
