The 40 CPUs were almost evenly used, with the exception of the first core that was handling all the network interruptions.
With proper tuning, we managed to handle the traffic with a memory footprint of 28KB per online user. We managed to surpass the target and we support more than 2 million concurrent users on a single ejabberd.įor XMPP servers, the main limitation to handle a massive number of online users is usually memory consumption. The connections were not using TLS to make sure we were focusing on testing ejabberd itself and not openSSL performance.Ĭode snippets and comments regarding the Tsung scenario are available for download: tsung_snippets.md Overall Benchmark Results This is the standard open source version that is widely available and widely used across the world.
#EJABBERD STIRED USERS SOFTWARE#
Regarding ejabberd software itself, the test was made with ejabberd Community Server version 16.01. ejabberd was running on a single node of instance type m4.10xlarge (40 vCPU, 160 GiB). We used a single large instance to generate the load.īoth ejabberd and the test platform were running on Amazon EC2 instances. In that situation, the scenario produced 550 connections/second and thus 550 logins per second.ĭatabase for authentication and roster storage was MySQL, running on the same node as ejabberd.įor the benchmark itself, we used Tsung, a tool dedicated to generating large loads to test servers performance. It means that presence packets were broadcast for those users, so there was some traffic as an addition to packets handling users connections and managing sessions. The scenario involves 2.2M registered users, so almost all contacts are online at the peak load. Here is our benchmark scenario: Target was to reach 2,000,000 concurrent users, each with 18 contacts on the roster and a session lasting around 1h. Looking for experts to deploy an enterprise-grade ejabberd cluster? It turns out you can get very far with ejabberd. That’s how we ended up with the challenge of fitting a very large number of concurrent users on a single ejabberd node. However, we wanted to provide benchmark results and hard figures to demonstrate our outstanding performance level and give a baseline about what to expect in simple cases. From our experience, we all get the idea that ejabberd has massive scalability.
0 kommentar(er)
