On Thu, Aug 6, 2020 at 11:00 AM Matthew Wilcox <willy@xxxxxxxxxxxxx> wrote:
>
> It wasn't clear to me whether Hugh thought it was an improvement or
> not that trylock was now less likely to jump the queue. There're
> the usual "fair is the opposite of throughput" kind of arguments.
Yeah, it could go either way. But on the whole, if the lock bit is
getting any contention, I think we'd rather have it be fair for
latency reasons.
That said, I'm not convinced about my patch, and I actually threw it
away without even testing it (sometimes I keep patches around in my
private tree for testing, and they can live there for months or even
years when I wonder if they are worth it, but this time I didn't
bother to go to the trouble).
If somebody is interested in pursuing this, I think that patch might
be a good starting point (and it _might_ even work), but it seemed to
be too subtle to really worry about unless somebody finds an actual
acute reason for it.
I think the existing patch narrowing the window is good, and it
clearly didn't hurt throughput (although that was almost certainly for
other reasons).
Linus
