Software-defined storage: Difference between revisions

Revision as of 16:45, 15 May 2018

Revision as of 23:24, 17 September 2018

Line 28:

* Abstraction of logical storage services and capabilities from the underlying physical storage systems, and in some cases pooling across multiple different implementations. Since data movement is relatively expensive and slow compared to computation and services , pooling approaches sometimes suggest leaving it in place and creating a mapping layer to it that spans arrays. Examples include:

** [[Storage virtualization]], the generalized category of approaches and historic products. External-controller based arrays include storage virtualization to manage usage and access across the drives within their own pools. Other products exist independently to manage across arrays and/or server DAS storage.

** Virtual volumes (vVolsVVols), a proposal from [[VMware]] for a more transparent mapping between large volumes and the VM disk images within them, to allow better performance and data management optimizations. This does not reflect a new capability for virtual infrastructure administrators (who can already use, for example, NFS) but it does offer arrays using [[iSCSI]] or [[Fibre Channel]] a path to higher admin leverage for cross-array management apps written to the virtual infrastructure.

** Parallel [[Network File System|NFS]] (pNFS), a specific implementation which evolved within the NFS community but has expanded to many implementations.

** [[OpenStack]] and its Swift, [[Ceph (software)|Ceph]] and Cinder APIs for storage interaction, which have been applied{{by whom|date=August 2014}} to open-source projects as well as to vendor products.