Distributed systems pose many difficult problems to researchers. Due to their large-scale complexity, their numerous constituents (e.g., computing nodes, network links) tend to fail in unpredictable ways. This particular fragility of experiment execution threatens reproducibility, often considered to be a foundation of experimental science.
XPFlow is a new approach to description and execution of experiments involving large-scale computer installations. The main idea consists in describing the experiment as workflow and using achievements of Business Workflow Management to reliably and efficiently execute it. Moreover, to facilitate the design process, the framework provides abstractions that hide unnecessary complexity from the user.
# gem install xpflow --pre
Create a script with description of your experiment:
# file: basic.rb process :main do log "Hello World" end
And launch it:
$ xpflow helloword.rb
The latest version of XPFlow is 0.1c.
Source code, bug tracker, contact
$ git clone git://scm.gforge.inria.fr/xpflow/xpflow.git
If you have any question, please use the mailing list.
The following publications are related to XPFlow:
- Towards Complete Tracking of Provenance in Experimental Distributed Systems Research - Tomasz Buchert, Lucas Nussbaum, Jens Gustedt, REPPAR 2014, August 2015, Vienna, Austria
- A workflow-inspired, modular and robust approach to experiments in distributed systems - Tomasz Buchert, Lucas Nussbaum, Jens Gustedt, CCGrid 2014, May 2014, Chicago, USA
- Orchestration d'expériences à l'aide de processus métier - Tomasz Buchert, ComPAS 2013 (RenPar), Jan 2013, Grenoble, France
- Using business workflows to improve quality of experiments in distributed systems research - Tomasz Buchert, Lucas Nussbaum, SuperComputing 2012 (poster session), Nov 2012, Salt Lake City, USA
- Leveraging business workflows in distributed systems research for the orchestration of reproducible and scalable experiments - Tomasz Buchert, Lucas Nussbaum, MajecSTIC 2012, Oct 2012, Lille, France