From owner-freebsd-questions Thu Mar 25 15:39:54 1999 Delivered-To: freebsd-questions@freebsd.org Received: from leaf.lumiere.net (leaf.lumiere.net [207.218.152.15]) by hub.freebsd.org (Postfix) with ESMTP id E343215123 for ; Thu, 25 Mar 1999 15:39:52 -0800 (PST) (envelope-from j@leaf.lumiere.net) Received: (from j@localhost) by leaf.lumiere.net (8.9.2/8.9.1) id PAA02259; Thu, 25 Mar 1999 15:39:33 -0800 (PST) Date: Thu, 25 Mar 1999 15:39:33 -0800 (PST) From: Jesse To: freebsd-questions@FreeBSD.ORG Subject: Re: 3.1-STABLE dies on 40+ connects (resolved) In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Thanks to the folsk in freebsd-hackers and -net, I was able to solve this fairly quickly. icecast was enlarging the send buffer. This would cause the mbuf usage to grow exponentially and crash the machine (it really shouldn't crash.. grr). I contacted the developers and it was an easy modification (#undef SOCKET_OPERATIONS) to leave the send buffers at the default 16k. Everything is kosher now and I can accept 121+ connections easily. Oh yeah. Raising NMBCLUSTERS to 4096 helped a lot. --- Jesse http://www.lumiere.net/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message