[CyberDildonics]

This can delay the execution of an atomic read or write

You can play "what if" all you want if you don't know what else running, but this was always about lock free interprocess communication, which is not broken by a page fault or process suspension.

An atomic instruction by design will do everything it needs to when the instruction runs.

Saying the OS can ultimately control the execution of a process is a nonsense cop out to try to skew away from the original point.

all you ever wanted is anonymous memory

This is local to a process tree and does not work for interprocess communication.

[jstimpfle]

Dude, the example I gave you with shm_open() is creating anonymous memory. That's just what non-file-backed mappings are called, no matter how long you want to keep obsessing about any "file paths".

[CyberDildonics]

This doesn't even seem like a reply to what I said.

If you map memory anonymously you aren't doing interprocess communication.

If you don't, you have a file path that the other program can use to map the same memory.

That's it, there is nothing wrong with this. I don't know why this is so upsetting. Mapping memory anonymously is local to the process tree and doesn't work for two different programs communicating.

[jstimpfle]

Ok, I'm extremely embarassed but it looks like I got the terminology wrong with regards to "Anonymous memory". And sorry for being so upset, at least I finally got something out of it.

It's also a fact that if I'm using disk swap space on a Unix, the same performance and stability issues apply as for disk backed file mappings. In that sense, there really is no difference.