Date: Tue, 19 Oct 2010 09:55:30 +0300 From: Andriy Gapon <avg@freebsd.org> To: Giovanni Trematerra <gianni@freebsd.org> Cc: alc@freebsd.org, freebsd-current@freebsd.org Subject: Re: panic in uma_startup for many-core amd64 system Message-ID: <4CBD40E2.7030507@freebsd.org> In-Reply-To: <AANLkTim-z-rNvPa%2BFDGAb7oroKB2DWxZSECti=ioH8GD@mail.gmail.com> References: <4C9B9B9C.6000807@freebsd.org> <4CBBEBDF.3060905@freebsd.org> <AANLkTi=O4GtAKDqEr%2BR27E5Xe%2BdGBZc0d2_=KpobtuSW@mail.gmail.com> <4CBC5719.1020807@freebsd.org> <AANLkTim-z-rNvPa%2BFDGAb7oroKB2DWxZSECti=ioH8GD@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
on 19/10/2010 00:01 Giovanni Trematerra said the following: > On Mon, Oct 18, 2010 at 4:18 PM, Andriy Gapon <avg@freebsd.org> wrote: >> Again, not sure if I follow you, I don't see relation between per-cpu caches and >> dynamic slab size. > > Your patch seems just a work around about initial slab size where the > keg is backed. Well, setting aside my confusion with the terminology - yes, the patch is just that, and precisely because I only tried to solve that particular problem. > Having dynamic slab sizes would allow to have the keg backed on a larger slab > without going OFFPAGE. I agree in principle. But without seeing code that implements that I can't guess if it would really be more efficient or more maintainable, i.e. more useful in general. Still a very good idea. -- Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4CBD40E2.7030507>