Date: Wed, 15 Apr 2015 18:02:06 +0200 From: Andre Albsmeier <Andre.Albsmeier@siemens.com> To: Mike Tancsa <mike@sentex.net> Cc: Andre Albsmeier <Andre.Albsmeier@siemens.com>, freebsd-net@freebsd.org Subject: Re: Intel em (82574L and 82573L) problems: stopping on high network and cpu load (Watchdog timeout) Message-ID: <20150415160206.GA11834@bali> In-Reply-To: <552E7324.90000@sentex.net> References: <20150413101626.GA47411@bali> <552BBF48.4090808@sentex.net> <20150414055445.GA54779@bali> <552D1DAC.9040104@sentex.net> <20150415054244.GA66168@bali> <552E7324.90000@sentex.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 15-Apr-2015 at 10:18:12 -0400, Mike Tancsa wrote: > On 4/15/2015 1:42 AM, Andre Albsmeier wrote: > > On Tue, 14-Apr-2015 at 10:01:16 -0400, Mike Tancsa wrote: > >> On 4/14/2015 1:54 AM, Andre Albsmeier wrote: > >>> > >>> Is this an em specific issue or should one avoid TSO generally > >>> at the moment? That is, should I disable it on machines with > >>> msk (and maybe other) interfaces as well? > >> > >> em specific I think. This thread has some info on what might be going on > >> > >> https://lists.freebsd.org/pipermail/freebsd-stable/2014-September/080081.html > > > > Very interesting, thanks. Until now (and without TSO), the problem > > did not re-occur but I didn't hit the NFS heavily yet. > > Hi, > Just to be clear, the network hang has returned ? Or its still problem > free ? Since I started to use -tso the problem did not come back (until now, hope it stays like this). So it seems to be the correct workaround. -Andre
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20150415160206.GA11834>