[This message was posted by Stefan Basiuk of Rapid Addition Limited <[email protected]> to the "Product Discussion" discussion forum at http://fixprotocol.org/discuss/24. You can reply to it on-line at http://fixprotocol.org/discuss/read/86e822e9 - PLEASE DO NOT REPLY BY MAIL.]
Rapid Addition today announced that it’s FIX engine has processed 70 million messaging with an average time of under 20 µs. The test was a sustained high volume FIX engine message parsing and transmission exercise. In the tests RA processed 99.9% of 70 million messages in under 30 us and had a mean and median message processing time of about 19 µs with a standard deviation of 3.1 µs. The tests were conducted on commodity hardware running .NET3.5 on Windows 2008. Over 70 million New Order Single messages with a size of 197 byte were sent and received across 140 sessions running 2 threads over a 50 minute period An average 12,000 messages were processed per second with 190MB per minute sent and received on the network. Messages were fully validated. Measurements were performed at the application and socket layers. Garbage collection had no discernable impact over the run period. No memory or thread leaks detected Rapid Addition is constantly at the leading edge of high performance low latency technology within the FIX and FAST space producing consistent high quality low latency performance. Toby Corballis, CEO of Rapid Addition said ‘We welcome the recent developments in the low latency space, where we are seeing a number of competitors and the market in general raising their game. At Rapid Addition we have always invested heavily in R & D and working with our partners at Intel and Microsoft , and thus being able to give our clients a truly competitive edge’. Rapid Addition will shortly be publishing the technical performance testing data and would welcome other vendors doing the same. ‘What would also be welcome would be an industry accepted standard in performance measurement. We are seeing a conspicuous need in the market for greater transparency where technical performance testing data is concerned. We intend being at the forefront of the development of an industry initiative for such a standard. This is something that would allow customers to compare FIX engine performance on a proper, like-for-like basis for the benefit of the market and importantly customers. [You can unsubscribe from this discussion group by sending a message to mailto:[email protected]] --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "Financial Information eXchange" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/FIX-Protocol?hl=en -~----------~----~----~----~------~----~------~--~---
