Abstract: A method for revocable token identifiers may be employed in a shared storage environment. An access server may generate access tokens and include revocable token identifiers previously obtained from storage devices. When clients present access tokens to storage devices during storage requests, storage devices may check the validity of access tokens by verifying that the revocable token identifiers were previously issued to the access server. An access server may request that the storage device revoke revocable token identifiers. Storage devices may deny any future storage requests including revoked token identifiers. Additionally, an access token may include instructions specifying operations for a storage device to perform in conjunction with a storage request. A trusted server may issue grantor tokens granting permissions for access servers to use when issuing access tokens. An access server may then include such a grantor token in access tokens that it generates and issues to clients.

Abstract: Disclosed is a method implementable by a computer system for maintaining consistency between mirrors of a mirrored data volume. In one embodiment, the method includes the computer system generating first and second write transactions in response to the generation of transaction to write data to a mirrored data volume. The first and second write transactions comprise first and second tags, respectively. The first and second tags relate the first write transaction to the second write transaction. In one embodiment, the first and second tags are identical. After the first and second write transactions are generated, the computer system transmits the first and second write transactions to first and second storage subsystems, respectively. In one embodiment, the first and second storage subsystems store or are configured to store respective mirrors of the data volume.

Abstract: A system using consistent virtual addresses to communicate in cooperative multi-layer virtualization environments includes a volume server, one or more physical storage devices, a front-end layer and a back-end layer of virtualization participants. The volume server may be configured to aggregate storage in the one or more physical storage devices into a logical volume, and to provide configuration information on the logical volume to a front-end virtualization participant and to a back-end virtualization participant. The front-end virtualization participant may be configured to send a storage request including a target virtual address identifying a block of the logical volume to the back-end virtualization participant. The back-end virtualization participant may be configured to use the configuration information to identify a physical data block at a physical storage device corresponding to the target virtual address, and to perform a physical I/O operation on the physical data block.

Abstract: After a first device (e.g., a host node in a shared data clustered system that stores a two-way mirrored volume) in a network creates or modifies a description of a layout for a data volume, the first device transmits separate copies of the data volume layout description to a pair of second devices, respectively, for storage in respective memories thereof. The first device may be a host node, and the pair of second devices may be first and second data storage systems. The first device and the pair of second devices are configured so that I/O transactions are transmitted between the first device and either of the pair of second devices. In other words, the first device is contained in a network layer that is different from the network layer that contains the pair of second devices.

Abstract: A system for write forwarding in a storage environment employing distributed virtualization includes a first and a second storage server providing access to a first and a second physical storage device, respectively, a virtual device server and a virtual device client. The virtual device server may be configured to aggregate storage in the first and second physical storage device into a virtual storage device and make the virtual storage device accessible to the virtual device client for I/O operations. An update requested by the virtual device client may require a first physical write operation at the first physical storage device and a second physical write operation at the second physical device. The virtual device client may be configured to send an update request to the first storage server, rather than to both the first and the second storage servers.