You can clone with
Cannot retrieve contributors at this time
NanoMQ======NanoMQ is a ultra low latency messaging kernel. It enables messagingbetween processes in much the same way as POSIX message queues but atsub-microsecond latencies. NanoMQ uses efficient wait-free ringbuffers arranged in a complete graph. Each node can send messages toany other node, receiving nodes needs to exclusively own a CPU core orHyperThread. The ultra low latency can thus be achieved by avoidingcontext switches.Building--------Just run make. Requires recent GCC. Tests require Google Test.Performance-----------On my Intel(R) Core(TM)2 Duo CPU T7500 @ 2.20GHz I get an average RTTof 250 ns and a throughput of 13M msg/s for a two node setup with 100byte messages. It will be interesting to see measurements on multi CPUsystems and the latency depending on which cache the cores share.Use case--------In high frequency trading (HFT) systems you want to separate feedhandlers and order management systems (OMS) from strategy code inorder to increase fault tolerancy and support live deployment of bugfixes or new strategies. NanoMQ allows you to separate these parts ofa trading system into separate processes while keeping communicationlatencies to a fraction of a microsecond.Resources---------Git repository: http://github.com/rigtorp/nanomqCopying-------Free use of this software is granted under the terms of the GNUGeneral Public License (GPL). For details see the file `COPYING`included with the NanoMQ distribution.