DAGwoman: enabling DAGMan-like workflows on non-Condor platforms

Abstract

Scientific analyses have grown more and more complex. Thus, scientific workflows gained much interest and importance to automate and handle complex analyses. Tools abound to ease generation, handling and enactment of scientific workflows on distributed compute resources. Among the different workflow engines DAGMan seems to be widely available and supported by a number of tools. Unfortunately, if Condor is not installed users lack the possibility to use DAGMan. A new workflow engine, DAGwoman, is presented which can be run in user-space and allows to run DAGMan-formatted workflows. Using an artificial and two bioinformatics workflows DAGwoman is compared to GridWay's GWDAG engine and to DAGMan based on Condor-G. Showing good results with respect to workflow engine delay and features richness DAGwoman offers a complementary tool to efficiently run DAGMan-workflows if Condor is not available.