Re: [PATCH] malloc: Use correct C11 atomics for fastbin

[DJ Delorie <dj@redhat.com>]

Wilco Dijkstra <Wilco.Dijkstra@arm.com> writes:
>>> You can test that with a tunable; the max count per bin is runtime
>>> tunable.
>
> Yes you can use tunables, but how many applications actually use more
> optimized settings? It's the default that is the problem.

If testing shows that a larger default makes sense across a wide range
of applications, then we can change the default.  I'm a bit opposed to
changing anything because "it makes sense".  Back it up with data.

> Yes, that's due the tiny size of tcache (let's call it
> tiny-cache!). Once exhausted, you mostly end up using the fastbins.

tcache is wide but shallow, fastbins are narrow but deep (tcache caches
much larger chunks than fastbins do) Benchmarks show they both provide a
speed boost separately, and more so when combined.

> Modern allocators are not only much faster than GLIBC in their default
> settings

Back this up with data please.  Tcache invalidated most online
benchmarks.

> but also have lower memory usage.

This is a project we've got on our to-do list.