Samverkan vid UPPMAX

User-funded Offload Storage

Do you need to store a lot of data, but don't know where to put it? UPPMAX offers a solution for any researcher or group who needs a large volume of "cool" storage.

Lutra is a file system that is mounted on Rackham and Snowy, like Crex, but is entirely funded by user fees (at cost). Performance is lower than Crex, making it suitable for data which is not accessed or changed directly by running jobs, which is why we call it "Offload Storage".

Off-site backup is included. Lutra is CIA (KRT)-rated at 221 and does not include any of the increased security features of Bianca.

The price is set at 500 SEK/TB/year, in increments of 50 TB and 4 years. The minimum buy-in, therefore, is 100 000 SEK.

If you are interested, contact, UPPMAX Technical
Coordinator, or UPPMAX Director

Q: How is this storage different from existing storage, e.g. Crex and Castor?
A: The normal UPPMAX storage systems are intended for active project data,
i.e. the data which is needed during the course of a project. You have to
justify your storage needs in your project applications and storage can be
rationed when we run out. The storage itself is paid for through SNIC in
that case. When we run out of space on these resources, we have to be more
aggressive in urging users to limit their storage needs.

This storage solution is provided by us, but paid for by its users. We will
not question your needs to store data up to your quota. However, since it is
not intended for active project data, the performance of the solution is
tuned for large capacity, not a high amount of write operations. If you need
that, you should still apply for project storage.

Q: What kind of data can I put there?
A: The kind of use cases we see are storing various large data sets from old
projects. This can include the primary results from specific experiments.
If you ever need to re-analyze the data, you'll have it readily available
on our clusters. On the resource mounted on Rackham, you are not allowed to
store sensitive data, with the same interpretation of that concept as is
currently used for computation and storage projects allocations. Typical
examples of sensitive data we encounter are personally identifiable data
from population registries, health information systems, and biomolecular
assays (including genomic data).

Q: I don't need 50 TB. Why don't you offer a smaller volume?
A: We have chosen this limit to keep both the technical and financial
administration cost-efficient. Even at this price point, a substantial part
of our costs are staff costs for maintaining the solution and providing user

Q: What will the availability be like? My data is super-critical.
A: We will maintain the same level of availability we do for other UPPMAX
resources, that is a best effort intent to maintain continuous operations,
with monthly service windows. An outage outside of office hours will in
general not start to be addressed until the next working day. If you need to
ensure immediate access to the data under all circumstances, we recommend
that you choose another solution.

Q: What happens if the hardware breaks down?
A: We will have redundancy within the solution, so failure of individual disks
will not affect user data. In addition, data will be backed up on tape at an
off-site location.

Q: How does this relate to other storage offerings and future rules and
solutions for long-term research data storage?
A: We are currently trying to serve a very concrete need for users that have
data that cannot easily be considered active project data, but where the
natural place to access the data, if it is ever needed again, would be
UPPMAX. In those cases, we think it is better to provide a common solution,
rather than individual groups buying and maintaining smaller storage systems.
In addition, our solution will be directly connected to our core network.
Even though it's a high-capacity solution, rather than a high-performance
solution, it will give higher bandwidth to our clusters than any solution
placed outside of our computer room.

The technical and organizational frameworks for true long-term storage of
research data will hopefully be clarified in the coming years, but we
believe there will still be some need for keeping data close to
computational resources, but outside of truly active project storage.
This should not be considered a replacement for permanent archival and
metadata tagging of data.

UPPMAX för företag


UPPMAX har beräknings- och lagringsresurser till förfogande som kan hyras av företag under liknande villkor som akademiska forskare har. Det betyder att företag kan få skriva avtal med UPPMAX om att få använda en viss mängd beräkningstid per månad och lagringskapacitet. Ditt företag får då tillgång till vetenskapliga mjukavarupaket inom genomik, bioinformatik, kemi med mera. Support för systemrelaterade frågor såväl som frågor om tillämpningar ingår.

Hur funkar det?

Du loggar in på ett Linux kluster och använder terminalkommandon. Kurser för nybörjare och avancerade användare finns. Datatiden används genom att skicka beräkningsjobb till ett kösystem där mängden avtalade timmar avgör prioritering. Support sker på liknande sätt genom ett kösystem.

Intresserad? Hör av dig till så kontaktar vi dig.