From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: possible bug in tcp_probe Date: Tue, 13 Nov 2007 14:28:08 +0100 Message-ID: References: <20071113112615.GA7491@nuim.ie> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: netdev@vger.kernel.org To: Gavin McCullagh Return-path: Received: from cantor.suse.de ([195.135.220.2]:41272 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751637AbXKMN2J (ORCPT ); Tue, 13 Nov 2007 08:28:09 -0500 In-Reply-To: <20071113112615.GA7491@nuim.ie> (Gavin McCullagh's message of "Tue\, 13 Nov 2007 11\:26\:15 +0000") Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Gavin McCullagh writes: > I'm using linux v2.6.22.6 and tcp_probe with a couple of small > modifications[1]. > > Even with moderately large numbers of flows (16 on the one machine) and > increasingly as I monitor more flows than that, I get strange overflow > problems such as this one: You probably just need to increase the buffer (bufsize option to the module or tcp_probe.bufsize if compiled in) In general I think tcp_probe was always more intended a demo of how kprobes could be used than a real production tool (with no offense to sch) -Andi