sdab

We (co-author here) are using EEVDF already since its in the latest mainline kernels. We havent noticed any major differences using the default settings, but plan to get around to tuning it later.

I don't know what github is doing here, but I've seen this antipattern quite a few times in production at some big name companies...

"That allows a single bit to potentially hold two values at once, or for two bits to hold four values at once. Keep scaling those numbers, and you quickly end up with a device that can process data exponentially faster than today’s computers."

Yet another quote for the misrepresentation of science in articles.

My question was about his claim in regards to the result in the paper. In practice, you are right but a consensus algorithm is still "partially correct" if it never decides on a value. It is only incorrect if different nodes decide on different values. For example, paxos does is not guaranteed to decide on a value. So timeouts are useful guessing tools, but I dont see how there is no consensus possible without them.

You mean the OP's comment or mine? I agree with you if you mean the OP's comment. Though your quote refers to synchronized clocks. I dont think OP is referring to synchronized clocks, though your point that Lynch et al does not rely on timeouts is what Im getting at.

"When used as a failure detector, timeouts are just a guess that something is wrong. (If they could, distributed algorithms would do without clocks entirely, but then consensus becomes impossible [10]."

Having just re-read Lynch's paper, can you explain what you mean here? I didn't see anything explicitly relying on time. It could be there is some implicit usage I didnt see. Additionally, the paper's impossibility result is about "perfectly correct consensus" which applies with and without clocks and then has a positive result for "partially correct consensus" (i.e. not deciding a value is a correct result). Im not sure which you mean when you say "consensus becomes impossible" as it is either already impossible (the perfectly correct protocol) with one faulty process or (to my understanding) not dependent on time (the partially correct protocol).

p.s. great article!

The article refers to 1180 MW of _power_. MW is joules/s and the unit of power is the watt (j/s). Your math talks about MegaWatt-Hours.

These are often confused in articles, do you happen to know if that was the case in this article? Did they mean 1180 MWH or 1180 MW as stated? Otherwise your yearly production calculation is very off. 1180 MW (j/s) would produce 10^7 MHW per hour.

I figured performance came into it also. It would be nice to see some performance numbers though.

If a user realized that the "cost" of viewing the image was free, wouldn't the user disregard the cost on future instances of the experiment?

Did the experiment limit a user's participation to one time? Otherwise, the results might be skewed and the benefits exaggerated.