In 2006 iVEC formed the view that Western Australian researchers could benefit greatly from a Large Scale Data Storage system. As this idea developed, it was clear that there was a significant need within the scientific research community which had not yet been addressed. iVEC, working with CSIRO, formalised this idea and prepared a tender in the first quarter of 2007; the tender went out and was quickly short listed. With a 1 million dollar budget cap for hardware and software, iVEC was looking for a company with a local presence that was willing to develop a close working relationship; Sun Microsystems (pre Oracle) won the tender and the equipment was delivered in 2007.

The Petabyte Data Store is a scalable storage solution based on Sun’s SAM-QFS (Storage and Archive Manager File System & Quick File System) software, and consists of a 70TB of disk cache and a second 100TB file system, all backed by a 6500 slot automated tape library with 8 LTO4 Tape Drives. The SAM-QFS software automates the migration and retrieval of files across multiple tiers of storage, from the online disk cache, to near-line tape storage, to offline tape archival. This system allows the user to see their complete directory hierarchy and have seamless access to their files within a single file system. Each file that is placed on the system has a copy written to two separate tapes.

The system is managed via archival policies based on “file size” and “file last access time”. The dual write policy ensures data is highly protected and available, and the archival policies allow for exclusion lists for “on disk only” or “always on disk”, with high and low watermarks defined to ensure disk space is never completely filled. SAM-QFS uses tar archives when copying data to tape (many files are bundled), providing an easy mechanism for “bare-metal” recovery from tape to any Unix compatible system, with or without SAM-QFS.

SAM-QFS is capable of supporting an almost infinite capacity. By increasing the number of available tape slots in the library and/or by using higher capacity tape media and scaling the disk cache appropriately, SAM-QFS can continue to grow.

Currently there is 70TB of online disk storage (cache) and a second 100TB file system, backed by LTO4 tape technology which features a native capacity of 800GB, (up to 1600GB compressed) and a native throughput of up to 120MB/sec. The Tape Library is a StorageTek SL8500 with 6,500 available media slots, The SAM-QFS software is currently licensed for 2PB (Petabyte) under managment, which provides 1PB of usable space because we make two copies of all data.

Currently we are not in a position to create a tertiary offsite copy of all data; in the event of a catastrophic failure destroying both onsite copies, we will be unable to recover the data. A tertiary copy can be created for smaller amounts of non-recreatable data upon request; this would be at an alternate facility or to an alternate tape for offsite storage but this service will be evaluated on a case by case basis and may have a cost associated with it.

Please contact help@ivec.org if you have a requirement.