I would like to introduce an opensource, Coord, which is built on gSOAP. You can download Coord as follows:
- http://dev.naver.com/frs/download.php/107/coord-lib0.1-20081114- linux-i686_32.tar.gz - http://dev.naver.com/frs/download.php/8/coord-lib0.1-20081114-linux- x86_64.tar.gz For installation & quick start, you can refer to the following wiki. - http://dev.naver.com/wiki/coord/ [introduction] Coord is a large-scale computational space such as a distributed memory. If you've already known javaspaces or gigaspaces, it is easy to understand Coord since Coord is like C++-wise javaspaces/gigaspaces. Using gSOAP, I developed a SOA(service-oriented architecture), and built a SBA(space-based architecture) on the SOA. And then, the SBA scaled out by means of using DHT(distributed hash tables). 1. Coord is a space-based architecture built on distributed hash tables. - SBA(Space-based Architecture) processes communicate with others thru. only spaces - DHT(Distributed Hash Tables) data identified by hash functions are placed on numerically near nodes 2. Coord is a computing platform to project a single address space on distributed memories, as if users worked in a single computing environment. 3. Coord provides inter-process communication, resource share, and synchronization thru. the space. - Coord hides some complicated codes for network programming - The peers don't need to recognize each other since Coord provides time-/location-decoupling 4. Coord supports a variety of distributed programming models with only simple API(write/read/take) - Client-Server - Master-Worker: provide a scalable framework for parallel processing - Scatter-Gather: provide an on-the-fly framework for data exchange - Map-Reduce: provide a simplified framework for massive data processing 5. Coord propers for general-purpose distributed programming as well as data-/computation-intensive distributed programming Feel free to make use of Coord, and any comments can help us.
