From owner-freebsd-hackers Wed Mar 26 17:32:01 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id RAA20396 for hackers-outgoing; Wed, 26 Mar 1997 17:32:01 -0800 (PST) Received: from murrow.prognet.com (prognet.com [205.219.198.1]) by freefall.freebsd.org (8.8.5/8.8.5) with SMTP id RAA20367 for ; Wed, 26 Mar 1997 17:31:59 -0800 (PST) Received: from peterh (two89.dev.prognet.com) by murrow.prognet.com with SMTP id AA01397 (5.67b/IDA-1.5 for ); Wed, 26 Mar 1997 17:32:50 -0800 Message-Id: <3.0.1.32.19970326173157.01bd1940@mail.prognet.com> X-Sender: peterh@mail.prognet.com X-Mailer: Windows Eudora Pro Version 3.0.1 (32) Date: Wed, 26 Mar 1997 17:31:57 -0800 To: freebsd-hackers@freebsd.org From: Peter Haight Subject: ENOBUFS on heavy udp sending Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-hackers@freebsd.org X-Loop: FreeBSD.org Precedence: bulk When sending a bunch of udp packets (about 1600 a second) I start to get ENOBUFS on the sendto's near the end of a block of about 200 sends in a fairly tight loop. (There are also about 200 TCP connections established, but with no activity during this.) The kernel is 2.2-BETA and it has NMBCLUSTERS=20480 and MAXMEM=98304. One of the times after this happend I did a 'netstat -a' and there are about 200 alive UDP connections after I killed my program. They all look like this: Proto Recv-Q Send-Q Local Foreign udp 0 0 *.* *.* Any ideas about what is going on and how I can fix it?