Abstract: A system and method for distributed locking for networked device management is provided. In one aspect, a lock is granted for a resource attached to a switched fabric, in response to receiving a request to access the resource. If the resource is already locked by another process or device, or otherwise unavailable, the request may be queued or failed.

Abstract: A distributed computer system includes a first subnet including a first group of endnodes, each endnode in the first group of endnodes having a unique destination location identification (DLID) within the first subnet. A second subnet in the distributed computer system includes a second group of endnodes, each endnode in the second group of endnodes having a unique DLID within the second subnet. A communication fabric is physically coupled to the first group of endnodes and the second group of endnodes. A partitioning mechanism associates a first partition key to every DLID in the first subnet for enabling communication between the first group of endnodes over the communication fabric. The partitioning mechanism associates a second partition key to every DLID in the second subnet for enabling communication between the second group of endnodes over the communication fabric.

Abstract: An independent storage node is disclosed that includes a processor and transport hardware in communication with the processor that is capable of communicating data via a transport connection. Executing on the processor is modular storage software that comprises a plurality of software modules and a module interface. The module interface allows dynamic binding of the software modules and is capable of executing on a plurality of processor types by using particular software modules related to a specific processor type.

Abstract: A translation system and method for translating file systems between nodes having heterogeneous file systems are provided. The translation system includes a consumer node having a first file system and a driver for supplementing requests from the first file system to a storage device. Also included in the translation system is an input/output (I/O) node which implements a second file system. The I/O node is connected to the storage device and is in communication with the consumer node over a transport. The I/O node includes a translator layer designed to map the supplemented requests from the first file system to the second file system and back to the first file system.

Abstract: A computer storage method is disclosed for providing data storage independent of an underlying architecture is disclosed. Initially, a file system request is received, where the file system request is configured in a first format based on a first operating system. The file system request is communicated to a file system translator via a communication channel, and the file system configures the file system request into a second format based on a second operating system utilizing the file system translator. The file system request is then performed.

Abstract: A method for partitioning end nodes on a fabric is provided. The method includes configuring a storageless host on the fabric. The storageless host is configured by loading a programming media which has host programming code onto the host. The host programming code is configured to provide the storageless host access to the fabric. The method also includes searching for available end nodes that are connected to the same fabric as the host. After available end nodes are discovered on the fabric, the user selects a desired available end node which is connected to a storage device. The desired available end node is associated with the host on the fabric after the user selects the desired available end node. A management function then installs a partitioning key at the desired available end node and a matching partitioning key at the host. The matching partitioning key installed at the host matches the partitioning key installed at the desired available end node.

Abstract: Methods for booting a computer from logically remote end nodes are provided. In one example, after a computer is powered up, a method validates end nodes that are logically remote from the computer. The method then communicates with a validated end node. The method determines what peripheral devices are attached to the validated end node and ascertains what boot images are available on the peripheral devices. A selection of a boot image from the peripheral device can then be made and the method proceeds to boot the computer. The booting process of the computer does not use a native BIOS/ROM of the computer, thus enabling the booting from any operating system, without regard to the type of hardware associated with the native BIOS/ROM. Further, the described methods enable booting from the storage of any end node on a network fabric.

Abstract: Methods for maintaining consistent data and attributes for files sharable by two or more consumers are provided. One exemplary method includes initially defining a set of consistency bits that are implemented by a file consistency protocol. Once the consistency bits are defined and implemented by a file system managing the shared files, the method receives indication that a change was made to a file associated with the file system. The method then sets a bit of the set of consistency bits on each instance file to reflect the change performed to the file. An update is then messaged to each instance file such that the instance files contain the change made to the file. The messaging can be performed by way of a pulling protocol or a push protocol, which transfers the updates to the instances to maintain the consistency.

Abstract: Methods for N-way mirroring of data to a plurality of distributed storage and systems for carrying out the methods are provided. One method includes initially selecting an initiator storage. The initiator storage is configured to have data that is to be protected. The method also includes selecting a group of storage. Each storage in the group of storage is configured to obtain an initial copy of the data of the initiator storage that is to be protected. A modification in the data that is to be protected in the initiator storage is then detected. The method accordingly proceeds to notify each of the storage of the group of storage regarding the modification. A detection of the notification is configured to cause each of the storage of the group of storage to independently copy the modification so as to maintain data consistency between the initiator storage and each storage of the group of storage.

Abstract: Methods for locking a file managed by a file system are provided. One example, a file consistency protocol is associated with an operating system (O/S). The file consistency protocol is configured to maintain file consistency between instances of the file associated with the file system using a set of file consistency protocol bits. The method includes determining whether any instance of the file is open, and if no instance of the file is open, the method further includes setting an exclusive bit of the file, the exclusive bit being one of the set of file consistency protocol bits. The setting of the exclusive bit is configured to lock the file from being accessed as another instance.

Abstract: Methods for sharing a file while maintaining consistency among instances of the file managed by a file system are disclosed. One exemplary method includes associating a file consistency protocol with an operating system (O/S). The file consistency protocol maintains file consistency between instances of the file associated with the file system using a set of file consistency protocol bits. The method then includes opening an instance of the file in a shared mode by setting a shared bit in the set of file consistency protocol bits associated with the file. A determination is then made as to the existence of another instance of the file. A shared bit the set of file consistency protocol bits associated with the another file is then set. In accordance with the method, a modification is made to the contents (e.g., data or attributes) of the instance of the file. A modified bit is then set in the set of file consistency protocol bits of the instance of the file.

Abstract: A translation system and method for translating file systems between nodes having heterogeneous file systems are provided. The translation system includes a consumer node having a first file system and a driver for supplementing requests from the first file system to a storage device. Also included in the translation system is an input/output (I/O) node which implements a second file system. The I/O node is connected to the storage device and is in communication with the consumer node over a transport. The I/O node includes a translator layer designed to map the supplemented requests from the first file system to the second file system and back to the first file system.

Abstract: Disclosed is a computer implemented system, method and computer readable media for facilitating intelligent input/output (I2O) message communication between a host computer system and a silicon specific target device without implementing an input/output processor. The system is thus configured to make generic storage silicon appear as though it were an I2O capable device, without implementing an I/O processor and associated hardware. The system includes a block storage operating system module (OSM) for receiving a request from an operating system of the host computer system and generating an intelligent input/output message request. Also included is a host-resident intermediate service module driver (e.g., a RAID driver) for translating the intelligent input/output message request into a silicon specific request that is compatible with the silicon specific target device.