Re: [PATCH -next 0/5] rbtree: optimize frequent tree walks

[Davidlohr Bueso]

On Mon, 10 Feb 2020, Andrew Morton wrote:
> Measurable for microbenchmarks, I think?  But what benefit will a user
> see, running a workload that is cared about?

Well avoiding pointer chasing on large SMP systems has been shown to be
something we care about in the past. And yes my performance data comes
from an adhoc test scenario which only measures iteration latencies but
that doesn't mean there isn't value here.

Thanks,
Davidlohr