Re: [Quickfix-developers] Performance tests for various QuickFix flavors

[Steve B. <st...@te...>]

> My question for the group: Is there an architectural reason why QuickFix
> outperforms QuickFix/J?  Or is this a case of C++ being faster than Java
> in this problem domain (network programming and byte manipulation)?

There's currently a lot of String manipulation in QFJ. Some of this could
be optimized away. However, even in the best case the message fields are
usually String fields. Converting to Java Unicode Strings from a byte
array results in some extra processing compared to C/C++ strings.

Is the C++ version using asynchronous I/O? In Java, asynchronous I/O is
good for scaling to numerous simultaneous connections but can perform
slightly worse than synchronous I/O in some situations.

There are other places, like support for ordered fields, where
microseconds could be shaved.

Steve