We synthesize idealized ephemeris time via a cohort of atomic clocks. Google's TrueTime tracks this along with the local uncertainty. This allows Spanner to explicitly wait out uncertainty windows, establishing a single externally consistent order to all possible observers, even in the presence of hidden communication channels.

This is the whole point of the system, and what the article covers.

What you're saying about time isn't even exactly true in the general case where we need account for relativity. While observers of clocks in different locations may not agree on clocks alone, they will agree on the total spacetime interval.

In any case, accounting for relativity is only necessary in high precision radio frequency systems operating between ground and orbit like GPS. And even then we can still track the frequency and phase offsets of the oscillators in real time and establish their relationship to idealized ephemeris time.

So yes, the sentences in the article DO make sense.

EDIT: at least the ones concerning time and consistent orders due. The words about effectively CA are ... not great.

They may agree on the spacetime interval but that is of no consequence, since they will still not agree on the ordering. Establishing a single externally consistent order of events for all possible observers is physically impossible, unless the spacetime interval separating them is timelike, a condition that is rarely true of distributed transactions that are happening independently: e.g. Abel puts in money in Spain, Beth removes it in Australia -- do you charge an overdraft fee/interest? (N.B., Abel and Beth may be names of HFT algorithms.)

"Spanner for causal transactions" would be more accurate.

P.S. Not sure what you mean by "hidden communication channels."

> Establishing a single externally consistent order of events for all possible observers is physically impossible

No, it is not. It does however require communication.

Additionally, what's true in an absolute physical sense, is somewhat removed from what's practical engineered product. For example, we cannot literally make a physical part that is perfectly 1 meter in length. This has not stopped us from making everything from microchips to spacecraft.

> Abel puts in money in Spain, Beth removes it in Australia -- do you charge an overdraft fee/interest? (N.B., Abel and Beth may be names of HFT algorithms.)

Spanner handles this by using two phase commit over sets of independent consensus replication groups. By using TrueTime's ability to provide absolute intervals, it can wait out uncertainty windows to enforce the total order.

> P.S. Not sure what you mean by "hidden communication channels."

Schemes such as lamport and vector clocks require all messages exchanged to include clock data. If two clients establish their own communication channel using some other protocol, they may not agree on the same event order, because the system has no way to know it needs to advance the logical clocks based on this hidden communication.

Spanner in combination with TrueTime avoids this limitation. External observers will see the same commit order in real time, regardless of how they communicate.

Please read and understand the papers to get what you're missing.

The paper is not talking about time, in the abstract, or simultaneity / ordering in the abstract (which indeed don't exist), but rather with reference to "timestamps". "Timestamps" are not abstract time, and as such may be ordered, compared, be simultaneous, etc.

Your comment is irrelevant and pointless since the paper is talking about timestamps.

No amount of sophistry will help the matter at hand. Spanner considers a true spacelike interval to be some kind of fuzzy clock measurement error (or "uncertainty"). Call it timestamp all you want, whatever shall you stamp when you should have one node on Earth and another on Mars?

> whatever shall you stamp when you should have one node on Earth and another on Mars?

Again, if you were familiar with the content of the papers, you could answer this yourself.

How it would work is establishing a phase locked loop between the oscillator on earth and the oscillator on mars, and then running a TrueTime style interval protocol. The downside of "Mars Spanner" is the very long round trip time would make the two phase commit protocol unacceptably long latency. However, the basic properties would still hold.

I don't know how else to explain it to you: a communicating distributed system can establish a single, canonical, total order on events. This is not a physical impossibility.

"Can establish a ... total order on events" is somewhat vacuous, the point is how it corresponds to the actual observed ordering. Otherwise you can just label arbitrarily, 1, 2, 3, ... that's also an ordering. I'm saying there is no such correspondence that is globally correct. It doesn't matter what protocol you run. You cannot synchronize two clocks that are apart. You can only synchronize them when they are in the same place.

I perfectly understand that with communication you can establish (read: impose) any arbitrary ordering you want and get nodes to agree to that. That's not really a useful resolution except in a narrow sense of "sometimes we really don't care about strict observed ordering," which may or may not be true.

The larger point is, Spanner doesn't solve any distributed database problem. It simply notices that on the timescale that today's workload appears to operate at, all the nodes can still be approximated as being collocated. There is, after all, a clock inside a computer as well, and this just extends it a little further.

> You cannot synchronize two clocks that are apart. You can only synchronize them when they are in the same place.

You are categorically mistaken. Please read the literature. I won't be replying further.