Analyst/Senior Analyst - Storage and Servers

at  ECMWF

ABOUT STORAGE AND SERVERS

ECMWF operates a large-scale very active on-premises data archive, in which all ECMWF users (internal, Member State and external users) can store and retrieve data needed to support both weather forecasting research and operational forecast production. Today this system holds more than 1 exabyte of data, consisting of about 750 petabytes of primary data and about 250 petabytes of the most essential primary data duplicated into the on-site disaster recovery system. More than 500 terabytes of new data are added each day.
The underlying storage hardware is tape, and we have 10 high-capacity tape libraries, hosting more than 450 IBM enterprise tape drives and 64 LTO tape drives, giving access to data held on 55,000 tapes. On top of this tape layer, there are tens of petabytes of high performance and high-capacity disk and solid-state storage to provide cache and buffer space to the ECMWF archive services which are served by many HPE and Dell servers. Cloud and geo-distributed storage are not yet part of the portfolio but is expected to be in the near future.

EDUCATION, EXPERIENCE, KNOWLEDGE AND SKILLS (INCLUDING LANGUAGE)

We encourage you to apply even if you don’t feel you meet precisely all of the these criteria.

EDUCATION

• A university degree (EQF Level 6), preferably in computer science or in a technical or scientific subject, or equivalent professional qualification and experience

EXPERIENCE REQUIRED IN THE FOLLOWING AREAS

• Experience with IBM’s HPSS or similar large scale data archiving product is highly advantageous
• Very good experience in at least one of the following is required:
• Administration of large-scale disk and/or tape system hardware
• Administration of a collection of servers running Linux
• Automated configuration using Ansible
• Infrastructure management using Red Hat Satellite
• Knowledge of a modern scripting language such as Python is required
• Experience of supporting storage area networks and/or network attached storage systems is desirable
• Some experience of configuring and troubleshooting local area network is beneficial

KNOWLEDGE AND SKILLS REQUIRED

• Candidates must be able to work effectively in English and interviews will be conducted in English
• Fluency in Italian would be advantageous as would knowledge of one of the Centre’s other working languages (French or German)

SUMMARY OF THE ROLE

ECMWF are looking for an experienced analyst with a strong background in supporting large scale data storage systems and Linux system administration. The successful candidate will be based in Bologna and work as part of the six-person Storage and Servers team currently working between the offices in Reading and Bologna.
The team is responsible for the day-to-day operation and improvement of the ECMWF data storage systems, comprising tape libraries, disk systems, SAN and NAS attached storage as well as the support and provisioning of servers. This position involves working closely with software analysts responsible for developing and supporting the specialised in-house archiving software.
ECMWF’s data volume and requirements are constantly growing and evolving. This role is expected to be instrumental in defining the strategy of the Centre’s storage services. Part of this process involves the evaluation of future technologies, as well as the selection and introduction of state-of-the-art products.
A key technology used by the team is IBM’s High Performance Storage System (HPSS). HPSS is a complex and specialised software layer designed to support the largest multi-layered storage systems. The candidate is expected to have recent practical experience of HPSS or other large-scale and complex data storage systems. They will need to work on a daily basis to support and configure the system and develop a deep knowledge of the product.
For more details of HPSS, refer to https://hpss-collaboration.org/.

MAIN DUTIES AND KEY RESONSIBILITIES

• Assisting with the overall management of the HPSS & DB2 systems together with their configuration and automation
• Work closely with operation and developer analysts responsible for supporting the specialised in-house archiving services (MARS and ECFS)
• Liaise with Data Centre engineers and vendor technicians to install and configure the flash, disk, SAN and tape systems that underly these archives
• Working closely with development teams of various vendors, evaluate new software, storage devices and media. Being part of the strategic planning and implementation of the storage and cloud infrastructure
• Assisting in the day-to-day maintenance, monitoring and support of the service. This will entail providing periods of 24-hour on-call support as part of a rota within the team
• Creating and maintaining monitoring scripts, tools, documentation and providing operational training for the running of the service, ensuring it is maintained effectively and efficiently
• Assist with the configuration and support of the server farm running RedHat and Rocky Linux together with supporting the data platforms; NetApp ONTAP, TrueNAS, Ceph and Archiware P5