Storage is an integral part to any HPC Solution. OCF has vast experience in the most common HPC file systems, such as BeeGFS, IBM Spectrum Scale and Lustre, all available on a number of hardware platforms, OCF is able to offer solutions for whatever your capacity or performance requirement
HPC is not all about compute - what’s the point of having a million cores if they are all sitting waiting for the storage to catch up. At OCF, we believe building a balanced HPC cluster is crucial and high performance scratch storage is a critical piece of that puzzle.
OCF has vast experience in delivering high performance scratch storage systems having in-house capability to deliver and support storage solutions at virtually any scale.
With expertise in all major parallel file systems used in HPC, such as IBM Spectrum Scale, Lustre, BeeGFS, together with storage hardware from our partners Lenovo, Dell, DDN, NetApp and IBM, OCF has the expertise and technology to meet your scratch storage requirement whatever it may be.
Since its introduction in 1998, IBM Spectrum Scale (formerly known as general parallel file system or GPFS) has been field-proven on some of the world’s most powerful supercomputers, providing highly reliable and efficient use of infrastructure bandwidth.
Spectrum Scale is a distributed cluster file system whereby many nodes can safely access many files concurrently. Simultaneously, since metadata management is delegated to the Spectrum Scale, clients accessing each file with multiple nodes can access a single file without this being a burden on the Spectrum Scale storage servers. Efficient byte-range locking is used to allow this extremely high level of concurrency.
Spectrum Scale splits files into blocks and distributes these blocks across many storage drives. This allows the performance of many drives to be yielded in parallel, potentially even for a single file to a single client.
Spectrum Scale has commercial support, enterprise features and a very strong user community.
Lustre is a well-established open-source, parallel file system used in HPC applications across the world, including a large percentage of World Top 500 installations.
OCF's partner DataDirect Networks (DDN) acquired Intel’s Lustre File System business in 2018 and offers commercially supported ExaScaler Lustre Appliances and standalone Lustre support through Whamcloud.
BeeGFS (formerly known as FhGFS) is an open source, parallel file system gaining popularity in HPC due to its high performance and a distributed architecture which allows for file systems to be built from relatively inexpensive hardware.
BeeGFS also has a number of advanced features including BeeOND which is designed to integrate with HPC schedulers to create temporary parallel file system instances out of local SSD's and NVMe drives on compute nodes.
BeeGFS is supported by the open source community or, optionally, commercially supported through OCF partner ThinkParQ.