Thursday, May 24, 2007

OpenSER VS SER, running on a $3,000 Lintel server, both manage 8 billion minutes of VoIP traffic per year.

VoIP IP Telephony @ http://snapvoip.blogspot.com via eMediawire.
Two competing open source projects have now been compared in a side by side test. SIP Express Router, also known as SER (www.iptel.org), is the respected pioneer of open source SIP proxies. SER has been available since November 2003 and has a reputation for high performance and reliability. The upstart, OpenSER (www.openser.org) was created when developers disappointed by SER's slow release schedule, forked a version of SER to create OpenSER in June 2005.
Ever since, SIP proxy users have been faced with the question, which project is best?

TransNexus, an independent developer of VoIP Operations and Billing Support System (OSS/BSS) software decided to answer this question for its customers once and for all. Most product benchmark test plans are designed to yield incredible results for marketing promotion. The TransNexus benchmark plan was different. It was designed to mimic a production network with a lot of failed call attempts and the added overhead of call detail record collection.

As expected, the TransNexus results were not as amazing as some of the other published test results, but they were realistic and still very impressive. Telecom equipment vendors need to beware, both SER and OpenSER are ready to scale for the largest wholesale carrier operations. To summarize the results, TransNexus found that either OpenSER or SER SIP proxies have the performance to manage 720 calls per second on a $3,000 Linux server with dual Intel Xeon CPUs. For a typical wholesale carrier operation, this performance is sufficient to manage over 700 million minutes of traffic each month! While OpenSER and SER are competing against each other, they are rapidly out running the cost/benefit performance offered by commercial telecom equipment vendors.

Here is What Transnexus had to say;

Performance Results for OpenSER and SIP Express Router

We often hear the questions:

  • How fast are OpenSER or SER in a real world environment?

  • How do SER and OpenSER compare?

We decided to answer these questions and created a detailed performance test for OpenSER and SIP Express Router. To simulate a production environment, the SIP proxy under test queries an external OSP server for routing information on each and call and then reports call detail records to an external OSP server. Five destinations are returned to the SIP proxy for each call in random order. Four of the five destinations simulate call failure scenarios so the SIP proxy must retry the call an average of two times before the call is completed. These tests were performed on a single core of an Intel Xeon 5140 2.33 GHz CPU.

Here is a brief summary of what transnexus learned. For all the test details, click here.

  • The performance of OpenSER V1.2 and SER 2.0 are not materially different, however, there are two minor differences.
    • SER V2.0 requires less memory.
    • OpenSER V1.2 has less post dial delay.
  • By all measures, OpenSER V1.2 is significantly better than OpenSER V1.1.

  • For production operation (with call retries and CDR reporting), we suggest the following simple guideline for sizing server hardware to operate at 60% CPU utilization for OpenSER V1.2 and SER V2.0:

One GHz of CPU processing capacity can manage 60 calls per second.

For example, a server with two, dual core, 3.0 GHz CPUs would effectively have (2 CPUs * 2 cores * 3 GHz per CPU) twelve GHz of CPU processing capacity. This server, hosting either OpenSER V1.2 or SER 2.0, would be able to manage 720 calls per second at approximately 60% CPU utilization.

CPU Utilization

The following chart plots CPU utilization as a function of calls per second. The results for OpenSER V1.2 and SER 2.0 are identical. The performance of OpenSER V1.2 is 13% better than OpenSER V1.1.


Memory Usage

Memory is not a major resource requirement, even at high loads. SER 2.0 has the lowest memory requirement.

Post Dial Delay

The data on the following chart is an indirect indication of Post Dial Delay (PDD). The data presented is the percentage of calls in each test that experienced a PDD greater than six seconds.

Call Completion

The following chart presents the percentage of calls which were not completed successfully for each test. When CPU utilization was less 90%, both OpenSER V1.2 and SER 2.0 completed all calls successfully.



0 comments:

Blog Widget by LinkWithin