Date: Mon, 27 Jan 1997 08:26:48 +0900 (JST) From: Michael Hancock <michaelh@cet.co.jp> To: David Greenman <dg@root.com> Cc: proff@suburbia.net, hackers@FreeBSD.ORG Subject: Re: SLAB stuff, and applications to current net code (fwd) Message-ID: <Pine.SV4.3.95.970127081447.25160A-100000@parkplace.cet.co.jp> In-Reply-To: <199701261235.EAA06772@root.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sun, 26 Jan 1997, David Greenman wrote: > >On Sun, 26 Jan 1997 proff@suburbia.net wrote: > > > >> Can anyone inform me what a SLAB allocator is, and if so, would freebsd > >> benefit from one? > >> > > > >It's a chunk of memory that you put multiple kernel objects of the same > >type into. We have a modified mach zone allocator. They're both type > >stable memory allocators. > > The memory allocator in BSD is *not* type-stable. For SMP it might more make sense to create typed global pools to allocate objects per zone, than putting effort into a SLAB allocator. > The allocator in BSD is designed to be as fast as possible and trades > space efficiency for performance. I'm very skeptical that a SLAB allocator > would be any faster than the current allocation algorithm, although it > would likely be more space efficient. It did seem easier to color the cache with the SLAB implementation. I don't remember the results of John's page coloring work to distribute hits in the cache. > -DG > > David Greenman > Core-team/Principal Architect, The FreeBSD Project >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.SV4.3.95.970127081447.25160A-100000>