Date: Thu, 23 Jun 2005 18:28:25 -0400 From: John Baldwin <jhb@FreeBSD.org> To: freebsd-current@freebsd.org Cc: Emanuel Strobl <Emanuel.strobl@gmx.net>, Bruce M Simpson <bms@spc.org>, Robert Watson <rwatson@freebsd.org>, Dag-Erling =?iso-8859-1?q?Sm=F8rgrav?= <des@des.no> Subject: Re: lapic@2k interrukts eating CPU cycles Message-ID: <200506231828.27226.jhb@FreeBSD.org> In-Reply-To: <20050622150842.GF791@empiric.icir.org> References: <200506091423.39940@harrymail> <20050622154538.H26664@fledge.watson.org> <20050622150842.GF791@empiric.icir.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wednesday 22 June 2005 11:08 am, Bruce M Simpson wrote: > On Wed, Jun 22, 2005 at 03:50:24PM +0100, Robert Watson wrote: > > I have a feature request in to John to add statistics gathering on IPIs, > > since he's currently reworking the interrupt paths. > > I like this LAPIC change a lot. Actually I like APICs a lot. They may not > give you 'real' vectored hardware interrupts a la SPARC and PowerPC, but > at least it comes a bit closer. > > It would be nice to be doing APIC on uniprocessor systems a bit further > down the line, but that's for the wishlist -- the 8259s are not going away > just yet. I think all new systems going forward are going to have APICs though. HTT and multi core require APIC just like SMP does. -- John Baldwin <jhb@FreeBSD.org> <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve" = http://www.FreeBSD.org
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200506231828.27226.jhb>