D6.1: First Annual Operations Report of the Tier-1 Service

The main objective of WP6 is the operation of an infrastructure of national HPC Tier-1 systems in Europe, which provides resources to users through PRACE calls for proposals for Tier-1 access (the DECI calls). This Tier-1 infrastructure is the continuation of the infrastructure built by previous DEISA projects and is now tightly integrated with the PRACE Tier-0 infrastructure as a result of the efforts of both the PRACE-1IP and PRACE-2IP projects. The services operated by this work package are based on the services listed in the Service Catalogue, which has been defined by PRACE-1IP-WP6. These services are accepted by all Tier-1 sites.
The second objective of this activity is the integration of new Tier-1 sites. Ten new sites will also provide resources for PRACE calls in the two year period of PRACE-2IP. The integration of these sites is at different stages, because some already provided resources for the first call, which started allocation in November 2011, and some will only provide resources for the last call, starting November 2012, because the system is not available yet. The status of these sites is discussed in section 3.
The management structure of operations is the same as adopted for the Tier-0 infrastructure and the same persons are responsible for particular services on both the Tier-0 and Tier-1 infrastructure. In general there is a close collaboration between operations of the Tier-0 and Tier-1 infrastructure, which is important because of the integration between the two environments. Operational procedures and facilities are also shared. Examples are the change management procedure and the helpdesk facility.
In this project period the DEISA infrastructure is successfully adapted to the PRACE infrastructure. The dedicated 10Gbps network is now operated by PRACE in close collaboration with GÉANT and some of the new sites are already connected too. The data management facilities based on GridFTP are supported by all sites. These facilities enable both high throughput data transfers between PRACE sites as well as between PRACE sites and external sites. For running jobs on the systems users have access to local batch systems and can use UNICORE to submit jobs remotely. A common user administration facility enables the distribution of information needed for the authentication and authorisation for PRACE services and the user needs only one interface for the registration. The helpdesk facility based on the RT facilities is fully migrated to the PRACE facility and the PRACE Common Production Environment (PCPE) is implemented on all sites. The monitoring facilities provided with the Inca tools are successfully migrated to PRACE, with interfaces to the PRACE helpdesk system and the PRACE maintenance information pages. All information for the installation and configuration of services was migrated and adapted in the first months to the PRACE internal wiki pages. The status of services is discussed in detail in section 2.