From mboxrd@z Thu Jan 1 00:00:00 1970 From: Philippe Gerum In-Reply-To: <5D63919D95F87E4D9D34FF7748CE2C2A01D8F93D@ARVMAIL1.mra.roland-man.biz> References: <5D63919D95F87E4D9D34FF7748CE2C2A01D8F93D@ARVMAIL1.mra.roland-man.biz> Content-Type: text/plain; charset="UTF-8" Date: Wed, 18 Nov 2009 14:37:25 +0100 Message-ID: <1258551445.2348.148.camel@domain.hid> Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Subject: Re: [Xenomai-help] network stall List-Id: Help regarding installation and common use of Xenomai List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: roderik.wildenburg@domain.hid Cc: xenomai@xenomai.org On Tue, 2009-11-17 at 10:42 +0100, roderik.wildenburg@domain.hid wrote: > On one of our platforms (PPC 5200B Kernel 2.4, Xenomai 2.4.8, PCI-bus) = we face rare network stalls (once a day). > In this situation network communication seems to be completly dead, but= obviously only the receive direction is affected as receive-interrupts i= n /proc/interrupts aren=C2=B4t incremented while transmit interrupts are = incremented. > Wireshark-protocoll (taken via port mirroring of the switch) says that = packets are sent to the target, but tcpdump on the target does not show t= hese packets (which is obvious, if receive-interrupt isn=C2=B4t operation= al). > In the send direction only arp-requests are monitored (on the target an= d on the switch). > Unfortunatelly this situation can=C2=B4t be reproduced in an laboratory= environment >=20 > On our other platform, which is very similar (PPC 5200B Kernel 2.4, Xen= omai 2.4.8) but without PCI we don=C2=B4t have this problem. Therefore I = am thinking whether Ipipe (in combination with PCI) could be responsible = for the interrupt lock? >=20 > Does anybody have an idea/suggestion how we can track down the reason f= or interrupt blockade? > Are there some helpful /proc entries (/proc/ipipe wasn=C2=B4t very usef= ul for me)? > Unfortunatelly, as far as I know, Ipipe-tacer is only available for Ker= nel 2.6. Am I right? Yes. >=20 >=20 > I would appreciate any suggestion very much! >=20 Make sure to disable CONFIG_XENO_OPT_ISHIELD. This option was reported to introduce interrupt propagation issues at least once, certainly adds some overhead, and won't buy you anything with your configuration. It has been removed from 2.5. > Roderik >=20 > -------------------------------------------------------- > manroland AG > Vorsitzender des Aufsichtsrates: Hanno C. Fiedler > Vorstand: Gerd Finkbeiner (Vorsitzender), Dr. Ingo Koch, Dr. Markus Ral= l, Paul Steidle =20 > Sitz der Gesellschaft: Offenbach am Main, Registergericht: Amtsgericht = Offenbach HRB-Nr. 42592 > USt-Ident-Nr. DE 250200933 >=20 > _______________________________________________ > Xenomai-help mailing list > Xenomai-help@domain.hid > https://mail.gna.org/listinfo/xenomai-help --=20 Philippe.