Date: Mon, 7 Oct 2013 12:09:55 +0400 From: Gleb Smirnoff <glebius@FreeBSD.org> To: "Alexander V. Chernikov" <melifaro@FreeBSD.org> Cc: svn-src-head@freebsd.org, Bryan Venteicher <bryanv@FreeBSD.org>, svn-src-all@freebsd.org, src-committers@freebsd.org Subject: Re: svn commit: r256066 - head/sys/dev/virtio/network Message-ID: <20131007080955.GI8860@FreeBSD.org> In-Reply-To: <525080A6.6020505@FreeBSD.org> References: <201310051807.r95I7P0M048589@svn.freebsd.org> <525080A6.6020505@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sun, Oct 06, 2013 at 01:12:06AM +0400, Alexander V. Chernikov wrote: A> On 05.10.2013 22:07, Bryan Venteicher wrote: A> > Author: bryanv A> > Date: Sat Oct 5 18:07:24 2013 A> > New Revision: 256066 A> > URL: http://svnweb.freebsd.org/changeset/base/256066 A> > A> > Log: A> > Do not hold the vtnet Rx queue lock when calling up into the stack A> Do you measure performance penalty for this? A> > A> > This matches other similar drivers and avoids various LOR warnings. A> We're currently trying to eliminate such things in other drivers like A> ixgbe, maybe there can be some other way to eliminate possible LORs? True, but we don't have time to do that before 10.0-RELEASE. So, from upcoming release perspective, Bryan change is correct fix. -- Totus tuus, Glebius.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20131007080955.GI8860>