Date: Mon, 28 Jan 2013 21:01:19 +0200 From: Andriy Gapon <avg@FreeBSD.org> To: John Baldwin <jhb@FreeBSD.org> Cc: svn-src-head@FreeBSD.org, svn-src-all@FreeBSD.org, src-committers@FreeBSD.org Subject: Re: svn commit: r245850 - in head/sys/sparc64: include sparc64 Message-ID: <5106CAFF.3050905@FreeBSD.org> In-Reply-To: <201301280954.51558.jhb@freebsd.org> References: <201301232252.r0NMqLxh085107@svn.freebsd.org> <5103ABCC.3010706@FreeBSD.org> <201301280954.51558.jhb@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
on 28/01/2013 16:54 John Baldwin said the following: > On Saturday, January 26, 2013 5:11:24 am Andriy Gapon wrote: >> on 24/01/2013 00:52 Marius Strobl said the following: >>> This is due to >>> the fact that on sparc64, spinlock_enter() only raises the PIL but doesn't >>> disable interrupts completely. >> >> John, >> >> I wonder if you are considering pushing your amd64 TPR patch some day... > > I have it in a p4 branch still that is easy to update. I haven't yet been > able to do any testing/benchmarks that show it as beneficial. > I am thinking about architectural benefits. Like doing inter-processor stuff with less risk of deadlocks. Or "hard CPU stop" without resorting to NMI. Things like that... -- Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?5106CAFF.3050905>