From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: Kernel crash after using new Intel NIC (igb) Date: Wed, 27 Apr 2011 14:04:18 +0200 Message-ID: <1303905858.3166.41.camel@edumazet-laptop> References: <201104250033.03401.maxi@daemonizer.de> <201104271346.34431.maxi@daemonizer.de> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: "Wyborny, Carolyn" , "linux-kernel@vger.kernel.org" , "netdev@vger.kernel.org" , StuStaNet Vorstand , "e1000-devel@lists.sourceforge.net" To: Maximilian Engelhardt Return-path: In-Reply-To: <201104271346.34431.maxi@daemonizer.de> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Le mercredi 27 avril 2011 =C3=A0 13:46 +0200, Maximilian Engelhardt a =C3= =A9crit : > Hello Carolyn, >=20 > Thanks for your response. >=20 > I have opened a issue at > https://sourceforge.net/tracker/?func=3Ddetail&aid=3D3293703&group_id= =3D42302&atid=3D447449 > and also posted all information there. >=20 >=20 > Please not that yesterday I updated the kernel, so I'm now running 2.= 6.38.4. > Eric Dumazet mentioned on the LKML that this might be a memory corrup= tion that=20 > my be solved with kernel 2.6.38. >=20 Hmm, I suggested to use slub_nomerge to make sure inetpeer kmemcache is not shared with another (possibly mem corruptor) layer. Please note we were not able to track the bug in 2.6.37 kernels. > I'll report if the crash happens again, but it might take some times = as in the=20 > past it happened within the interval of weeks to month. >=20 Thanks