Abstract: A distributed storage system includes multiple resource nodes each having associated storage media. The resource nodes are configured to operate a first protocol between the resource nodes that exchanges availability and performance information for storage elements in the associated storage media. The resource nodes also operate a second protocol that dynamically distributes and redistributes data between the different resource nodes based on the availability and performance information for the storage elements. Relative distances may be identified between the different resource nodes and the second protocol may weight the availability and performance information based on the relative distances. The second protocol also may identify types of unshared use, shared use, and concurrent use for different portions of the data and distribute the portions of the data to other resource nodes based on the identified types of use.

Abstract: A docking scheme enables storage systems to adapt different storage configurations to different clients. Dock configurations identify reconfigurable sets of storage extensions for executing storage operations in a resource node. The resource node receives storage requests from clients and identifies the dock configurations associated with the clients. The resource node then generates a set of storage operations that implement the storage extensions for the identified dock configuration and uses the storage operations to execute the storage requests. Different clients may thus access the same stored data through different docks resulting on different operations within the resource node with the aim of optimizing performance for all clients.

Abstract: A distributed storage system includes multiple resource nodes each having associated storage media. The resource nodes are configured to operate a first protocol between the resource nodes that exchanges availability and performance information for storage elements in the associated storage media. The resource nodes also operate a second protocol that dynamically distributes and redistributes data between the different resource nodes based on the availability and performance information for the storage elements. Relative distances may be identified between the different resource nodes and the second protocol may weight the availability and performance information based on the relative distances. The second protocol also may identify types of unshared use, shared use, and concurrent use for different portions of the data and distribute the portions of the data to other resource nodes based on the identified types of use.

Abstract: A docking scheme enables storage systems to adapt different storage configurations to different clients. Dock configurations identify reconfigurable sets of storage extensions for executing storage operations in a resource node. The resource node receives storage requests from clients and identifies the dock configurations associated with the clients. The resource node then generates a set of storage operations that implement the storage extensions for the identified dock configuration and uses the storage operations to execute the storage requests. Different clients may thus access the same stored data through different docks resulting on different operations within the resource node with the aim of optimizing performance for all clients.