On Mar 26, 2012, at 2:50 AM, Tomas Vondra wrote:
> Hi all,
>
> today I've noticed this link on HN: http://plasma.cs.umass.edu/emery/hoard
>
> Seems like an interesting option for systems with a lot of CPUs that are
> doing a lot of alloc operations. Right now I don't have a suitable system
> to test it - anyone tried to benchmark it?
It's just another allocator - not a bad one, but it's been around for years. It's
mostly aimed at reducing contention in multi-threaded applications, so
it's not terribly applicable to strictly single-threaded postgresql.
It's licensing is pretty much incompatible with postgresql too.
Cheers,
Steve