Piql White Paper - Magnetic Tape Technology in a Multi-node Archival Storage System

7

TAPE MEDIA LIFETIME

Tape media for most tape technologies has a simi- lar published theoretical lifetime of around 30 years within the defined constraints of: environment, duty cycle (reads and writes) and cartridge re-packing cy- cles (a regular tape drive mount unpack and pack). It is worth however considering the long-term avail- ability of the drives to read the tape cartridges. The LTO roadmap shows that a new generation of technology is released roughly on a 2 to 3 year cycle. LTO, up to LTO-7 provided read compatibility back 2 generations, so LTO-7 could read LTO-5 cartridges. In order to do a media migration a user will need to have tape drives available (and preferably under sup- port) that can read the oldest media in the archive. Our own experience shows that manufacturers only provide concurrent support for two generations of tape drive; it is their interest to get customers to buy the latest drives and media and hence to mi- grate off of old technology. This paper has examined the current state of the digital tape technology market, suppliers and technologies. It has specifically looked at the use of tape within a multi-node archival storage or digital preservation architecture. It has consid- ered issues of single supply, reliability and media lifetime as factors relevant in making a choice of tape for one or multiple nodes within a storage architecture. Principals and guidelines for building a digital preservation storage system suggest that it should have at least three nodes, in three different loca- tions and employing three different technologies. The use of flash storage for archiving is currently CONCLUSIONS

With two generations of backwards read compati- bility, the maximum period from first availability of media to retirement of the compatible drive tech- nology would be 12 years. However, most users will want to start their migration earlier, so effective life is more realistically 9 years. For LTO-8 with only a single generation backwards read capability this has been reduced to 6 years.

It is also interesting to note that CERN keep their tape cartridges for 6-8 years.

It is prudent in a multi-node archival storage archi- tecture to consider using different tape generations at different nodes. A more robust strategy would be to consider, if available, a non-tape-based strategy for the final or tertiary storage node.

cost prohibitive so the choice appears to be be- tween variations of disk technology and digital tape, both of which suffer from a lack of broad diversity in supply and technology. Both technol- ogies require environmental care, frequent media migration and have inherent reliability risks. Ideally a multi-node digital archive could utilise the advantages of disk and tape-based storage technologies and have access to a ‘third node technology’ that should employ a fundamentally different technology base, have a long life-cycle, be robust and require little maintenance.