Re: [PATCH v8 4/5] locking/qspinlock: Introduce starvation avoidance into CNA

[Peter Zijlstra]

On Fri, Jan 24, 2020 at 11:46:53AM -0500, Waiman Long wrote:
> I also thought about that. As you said, it can be hard to guarantee that
> reliable time value can be retrieved in a timely manner across all the
> archs.

Rememer that this code is limited to 64bit archs that have NUMA, my
quick grep says that is limited to:

  alpha, arm64, ia64, mips, powerpc, s390, sparc, x86

afaict, x86 is the one with the worst clocks between the lot of them
(with exception of ia64, which has been completely buggered for a while
and nobody cares).

> Even if we can do that, we will introduce latency to important
> tasks or contexts. I like the first approach better.

In general, the kernel has no clues what is actually important.