[nycbug-talk] Slab Allocator
sjt.kar at gmail.com
Thu Aug 28 05:33:57 EDT 2008
dragonfly bsd was originally formed to take care NUMA, Core
based architectures form freebsd 4.x. So you would expect this
sort of an comparision.
donot know for sure but the code then was forked to allow per-cpu,
per-core systems to be given an better shot than then GIANT lock.
On 8/28/08, Yarema <yds at coolrat.org> wrote:
> A while ago I read on Matt Dillon's DragonFly diary
> # DragonFly now has slab allocator for the kernel! The allocator is
> about 1/3 the size of FreeBSD-5's slab allocator and features per-cpu
> isolation, mutexless operation, cache sensitivity (locality of
> reference), and optimized zeroing code.
> # The core of the slab allocator is MP safe but at the moment we still
> use the malloc_type structure for statistics reporting which is not yet
> MP safe, and the backing store (KVM routines) are not MP safe. Even, so
> making the whole thing MP safe is not expected to be difficult.
> 1/3 the size of FreeBSD-5's slab allocator?! that's awesome! DragonFly
> rulez! er, WTF is a Slab Allocator?
> it's still over my head, but here's where it all started:
> ... by the creator of ZFS no less. Good story.
> talk mailing list
> talk at lists.nycbug.org
More information about the talk