Date: Fri, 17 Aug 2012 07:23:46 -0700 (PDT) From: Barney Cordoba <barney_cordoba@yahoo.com> To: Jason Wolfe <nitroboost@gmail.com> Cc: Konstantin Belousov <kostikbel@gmail.com>, jfv@freebsd.org, Jack Vogel <jfvogel@gmail.com>, John Baldwin <jhb@freebsd.org>, net@freebsd.org Subject: Re: 82574L hangs (with r233708 e1000 driver). Message-ID: <1345213426.53058.YahooMailClassic@web121603.mail.ne1.yahoo.com> In-Reply-To: <CAAAm0r0TZEHKzXpam0Whg6ThMQ8TjAz=2NdDXOSiGmhhdnqxzw@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
=0A=0A--- On Thu, 8/9/12, Jason Wolfe <nitroboost@gmail.com> wrote:=0A=0A> = From: Jason Wolfe <nitroboost@gmail.com>=0A> Subject: Re: 82574L hangs (wit= h r233708 e1000 driver).=0A> To: "Barney Cordoba" <barney_cordoba@yahoo.com= >=0A> Cc: "Konstantin Belousov" <kostikbel@gmail.com>, jfv@freebsd.org, "Ja= ck Vogel" <jfvogel@gmail.com>, "John Baldwin" <jhb@freebsd.org>, net@freebs= d.org=0A> Date: Thursday, August 9, 2012, 7:31 PM=0A> On Thu, Aug 9, 2012 a= t 8:25 AM,=0A> Barney Cordoba <barney_cordoba@yahoo.com>=0A> wrote:=0A> >> = --- On Fri, 5/11/12, Barney Cordoba <barney_cordoba@yahoo.com>=0A> wrote:= =0A> >>=0A> >> FWIW, I've got an X7SPE-HF-D525 MB with 82574L=0A> running o= n a=0A> >> 7.0 driver=0A> >> that seems to work pretty well. It panics once= in a=0A> blue=0A> >> moon when we=0A> >> overload it (like 200Mb/s of traf= fic) but it=0A> generally works=0A> >> ok.=0A> >>=0A> >> BC=0A> >=0A> > Has= anything been done or patched regarding this=0A> problem?=0A> >=0A> > BC= =0A> =0A> Ever since r235553 the 82574L has been stable for me,=0A> collect= ively=0A> passing ~1.2Tb/s for the past 4 months without issue.=A0=0A> We d= id have=0A> some issues with switches not liking the fallout of what=0A> r2= 36162 fixed=0A> that we updated to, but the cards themselves were=0A> fine.= =A0 If you pull=0A> the current e1000 from 8-STABLE you'll get up to r23616= 2.=0A> =0A> Jason=0A=0ADo you get occasional watchdog reset messages? I'm t= rying to see if=0Athe buffer jumping problem has been fixed or if they just= put a condition=0Awatch in to keep it from remaining hung.=0A=0AIs Jack co= nfident that something substantive has been corrected? If so,=0Awhat was th= e culprit? I have to patch it into a 7.x driver.=0A=0ABarney
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1345213426.53058.YahooMailClassic>