From owner-freebsd-questions@FreeBSD.ORG Sun Sep 14 18:34:03 2003 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A17AF16A4BF for ; Sun, 14 Sep 2003 18:34:03 -0700 (PDT) Received: from southgate.ph.inter.net (lanceb.ph.inter.net [202.61.82.144]) by mx1.FreeBSD.org (Postfix) with ESMTP id A519B43FDD for ; Sun, 14 Sep 2003 18:34:02 -0700 (PDT) (envelope-from chael@southgate.ph.inter.net) Received: from JMICH (jmich [192.168.1.254]) by southgate.ph.inter.net (Postfix) with SMTP id 8336E20BE for ; Mon, 15 Sep 2003 09:34:00 +0800 (PHT) Message-ID: <012901c37b29$7186c880$fe01a8c0@JMICH> From: To: References: <001601c37838$e9a963c0$fe01a8c0@JMICH><000701c37980$ef9881f0$420ea8cb@mrj><44isnwod9e.fsf@be-well.ilk.org> <001801c37a29$77c6a220$440ea8cb@mrj> Date: Mon, 15 Sep 2003 09:34:02 +0800 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1158 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1165 Subject: OK w/ 4.8R: sendto: buffer space not available X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 15 Sep 2003 01:34:03 -0000 IMO, I think this area of dev should be revisited before 4.9-RELEASE. Because when I brought it down to 4.8-RELEASE via cvsup, it has not failed yet. It usually fails around 12 hrs from boot. And it has been 14+ hours now running very fine. One thing I noticed though... it seems that over time, the peak values on netstat -m grows. Although it is still far from the max value I set in kern.ipc.nmbclusters. Last value before networking stalls is around 9000 to 10000+ on my mbuf clusters. Now with 4.8-RELEASE, the netstat -m shows a steady peak value of just 5226. Thanks. > > Yes, exact kernel configurations too. To be specific, I just copy/pasted the > extra options plus the pseudo-device gre. And, yes. The same, on a 256MB > machine. > > I have also tried the advice of Colin to set the sysctl : > > net.inet.raw.recvspace=131072 > net.inet.raw.maxdgram=8192 > net.inet.tcp.sendspace=131072 > net.inet.tcp.recvspace=131072 > net.inet.udp.maxdgram=8192 > net.inet.udp.recvspace=131072 > > kern.ipc.nmbclusters=16384 at /boot/loader.conf > (nmbufs automatically sets itself to x4 of nmbclusters) > > But that didn't work either. > > netstat -m peaks just over 9000 for mbuf clusters. > > I should try bring it back to 4.8-RELEASE now. > > Thanks. > > > > writes: > > > > > This is serious. I have just cvsuped stable-supfile again and did all > > > necessary steps re kernel/world. It is still having this problem. > Anybody > > > stumbled accross the same? Should I just reinstall back to 4.8-RELEASE? > > > Because I got another identical hardware/machine working without this > error > > > on 4.8-RELEASE. > > > > Same kernel configuration? > > > > > options MAXDSIZ="(256*1024*1024)" > > > options MAXSSIZ="(256*1024*1024)" > > > options DFLDSIZ="(256*1024*1024)" > > > options NMBCLUSTERS=131072 > > > > On a 256MB machine? > > > > > > _______________________________________________ > freebsd-questions@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-questions > To unsubscribe, send any mail to "freebsd-questions-unsubscribe@freebsd.org" >