Modularization of the LHCb software environment and preparation for heterogeneous resources

The LHCb software stack has to be run in very different computing environments: the trigger farm at CERN, on the grid, on shared clusters, on software developer's desktops... The old model assumes the availability of CVMFS and relies on custom scripts (a.k.a LbScripts) to configure the environment to build and run the software. It lacks flexibility and does not allow, for example running in container and be very difficult to configure and run on non standard environments. This paper describes the steps taken to modularize this environment to allow for easier development and deployment (as standard python packages), but also added integration with container technology to better support non standard environments.