Speaker
Description
CloudVeneto is an OpenStack-based scientific cloud with resources spread across two different sites: INFN Padova Unit and the INFN Legnaro National Laboratories. Funded throughout the years by these two INFN local units and ten University of Padova departments, this infrastructure nowadays supports a broad range of scientific and engineering disciplines involving about 330 users distributed in 80 projects. Its hardware resources provide around 3000 computational cores, 20 GPGPU cards, 12 TB of RAM and 700 TB of storage.
CloudVeneto basically implements a IaaS (Infrastructure as a Service) service model, allowing users to create instances sized, customized and configured for their specific use cases. However users are also provided with some higher level services, such as scalable batch systems and kubernetes clusters, eventually enriched with a set of services for big data analytics.
During 2020 the CloudVeneto team put a significant effort to integrate part of their resources with the INFN-Cloud federated infrastructure, which was opened to INFN users in March 2021. This integration has several advantages: ability to provide CloudVeneto users with the high level services of the INFN-Cloud marketplace; to demonstrate that CloudVeneto can provide resource capacity to different INFN user communities in “cloud mode”, as Tier-2s do since decades in “grid mode”; to stay aligned with best practice management of large infrastructures; possibility to participate to national and european projects as INFN-Cloud compliant resource provider.
The presentation will describe the technical steps carried out to implement such integration.