Benchmarking distributed-interactive HEP analysis workflows on the new Italian National Centre analysis infrastructure

Computationally efficient data processing and the challenges of future colliders are pushing to re-think High Energy Physics (HEP) computing models. The work behind this contribution aims at providing transparent resources for users and experiments, with suitable tools and environment, coupled with flexible and cloud-independent deployment in the framework of the ICSC project (High-Performance Computing, Big Data e Quantum Computing Research Centre). The resources will be experiment-agnostic and applicable across HEP experiments, exploited to benchmark the proposed workflows. Seamless interactive or quasi-interactive analysis are extremely promising: starting from container technology and Kubernetes, analysis tools are provided via Jupyter interface and Dask scheduling system, masking complexity for front end users and rendering cloud resources flexibly. An overview of the technologies involved and the results of two benchmark use cases will be provided, with suitable metrics to evaluate preliminary performance of the workflow.