What is data-dependency barrier: Linux Kernel

Question

As question says it all I was looking for in depth explanation of data-dependency barrier in SMP especially with respect to Linux Kernel. I have the definition and brief description handy in this link here.

Linux Kernel Memory Barriers Documentation

However I was attempting to get a profound understanding of this concept. Your thoughts and inputs are highly appreciated.

score 2 · Answer 1 · answered Aug 25 '14 at 22:36

2

Actually, at least in terms of C++11, this is more closely related to consume semantics. You can read more about it e.g. here. In short, they provide weaker guarantees than acquire semantics, which makes them more efficient on certain platforms that support data dependency ordering.

answered Aug 25 '14 at 22:36

Ivan Vergiliev

3,771
24
23

Consume is also very natural in term of inherent dependency of f.ex. using a pointer: you need to know it first to dereference. – curiousguy Nov 26 '19 at 22:09

score 1 · Answer 2 · answered Sep 27 '22 at 02:34

1

In C++ terms, it is called memory_order_consume. See this presentation from Paul Mckenney.

answered Sep 27 '22 at 02:34

Patrick Pan

485
2
6
15

Arch D. Robison · Accepted Answer · 2022-09-28T00:42:50.597

-1

Old answer: I believe "acquire semantics" is the more commonly used term for what the document is calling a "data-dependency barrier". See for example this presentation or the C++11 memory_order_acquire.

Update: per comments, the Linux description for Data Dependency Barriers sounds more like C++ "consume semantics".

edited Sep 28 '22 at 00:42

answered Feb 03 '14 at 15:19

Arch D. Robison

3,829
2
16
26

@ Arch D. Robinson Thanks for the link very informative indeed! – Ace Feb 03 '14 at 18:13
Linux uses "acquire" operations but also a lot of "consume" for rarely changed data. – curiousguy Nov 26 '19 at 22:07
Actually it is "consume" semantics, instead of "acquire". – Patrick Pan Sep 27 '22 at 02:37

What is data-dependency barrier: Linux Kernel

3 Answers3