Return-Path: X-Original-To: apmail-activemq-users-archive@www.apache.org Delivered-To: apmail-activemq-users-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 85A8EEFB7 for ; Wed, 23 Jan 2013 20:22:44 +0000 (UTC) Received: (qmail 53808 invoked by uid 500); 23 Jan 2013 20:22:44 -0000 Delivered-To: apmail-activemq-users-archive@activemq.apache.org Received: (qmail 53740 invoked by uid 500); 23 Jan 2013 20:22:44 -0000 Mailing-List: contact users-help@activemq.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: users@activemq.apache.org Delivered-To: mailing list users@activemq.apache.org Received: (qmail 53729 invoked by uid 99); 23 Jan 2013 20:22:44 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 23 Jan 2013 20:22:43 +0000 X-ASF-Spam-Status: No, hits=2.0 required=5.0 tests=SPF_NEUTRAL,URI_HEX,WEIRD_PORT X-Spam-Check-By: apache.org Received-SPF: neutral (nike.apache.org: local policy) Received: from [216.139.250.139] (HELO joe.nabble.com) (216.139.250.139) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 23 Jan 2013 20:22:38 +0000 Received: from [192.168.236.139] (helo=joe.nabble.com) by joe.nabble.com with esmtp (Exim 4.72) (envelope-from ) id 1Ty6pq-0000Rk-7g for users@activemq.apache.org; Wed, 23 Jan 2013 12:22:14 -0800 Date: Wed, 23 Jan 2013 12:22:14 -0800 (PST) From: Frank Vanderhallen To: users@activemq.apache.org Message-ID: <1358972534134-4662102.post@n4.nabble.com> Subject: Apollo 1.5 MQTT - impossible to connect from many clients MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Virus-Checked: Checked by ClamAV on apache.org Hello, I've been trying how many MQTT connections I can have open at the same time with Apollo 1.5, and I'm quite disappointed by the result. I find it hard to believe that Apollo cannot do better, so it might be a configuration issue. I'm adding MQTT clients, which publish a small message every 4 minutes, until Apollo stops accepting connections. When the number of connections reaches 50000, it starts to go wrong (both CPU's get to 100% cpu usage, and they don't recover anymore). This is the setup: - Amazon EC2 c1.medium instance - ulimit -a core file size (blocks, -c) 0 data seg size (kbytes, -d) unlimited scheduling priority (-e) 0 file size (blocks, -f) unlimited pending signals (-i) 59480 max locked memory (kbytes, -l) 64 max memory size (kbytes, -m) unlimited open files (-n) 999999 pipe size (512 bytes, -p) 8 POSIX message queues (bytes, -q) 819200 real-time priority (-r) 0 stack size (kbytes, -s) 8192 cpu time (seconds, -t) unlimited max user processes (-u) 59480 virtual memory (kbytes, -v) unlimited file locks (-x) unlimited - apollo.xml testBroker localhost 127.0.0.1 ****************.compute.amazonaws.com I didn't find any documentation about the usage of MQTT in Apollo, so this configuration might make no sense at all. Any advice or pointers to more information? Thanks, Frank -- View this message in context: http://activemq.2283324.n4.nabble.com/Apollo-1-5-MQTT-impossible-to-connect-from-many-clients-tp4662102.html Sent from the ActiveMQ - User mailing list archive at Nabble.com.