Abstract: One embodiment of the present invention provides a system for processing a request directed to a secondary storage system. The system operates by receiving the request at an interface of the secondary storage system. This request specifies an operation to be performed on the secondary storage system, a location within the secondary storage system to which the request is directed, and an address of a target buffer located outside of the secondary storage system for holding data involved in the request. Next, the system processes the request by transferring data between the location within the secondary storage system and the target buffer located outside of the secondary storage system. If the target buffer is located within a page cache, processing the request involves communicating with the target buffer located within the page cache.

Abstract: Method for emulating persistent group reservations on non persistent group reservation-compliant devices, apparatus to perform the method, and computer-readable storage medium containing instructions to perform the method. The present invention enables the emulation of persistent group reservations on a non persistent group reservation-compliant device, including a shared disk, to enable the disk's implementation of persistent group reservation-reliant algorithms. This in turn enables the implementation of algorithms based on persistent group reservation features substantially without modification of those algorithms. One such algorithm is a quorum algorithm. One example of persistent group reservations is found in the SCSI-3 standard. The present invention accomplishes persistent group reservation emulation, or PGRE, by storing host- and reservation-specific information on a reserved portion of the disk and using this data to emulate the steps of certain persistent group reservation features.

Abstract: A system for reducing network traffic for remote file system accesses receives requests at a local computer system for access to a file on the remote server. If the request is a read operation, and the operation is directed to an unallocated region of the file on the remote server, the system returns a block of null values to the requestor without receiving the block of null values from the remote server. Otherwise, the system sends a request to the remote server to read from the file. If the request is a write operation, and the operation is directed to an unallocated region of the file on the remote server, the system sends a request to the remote server to allocate storage for the write operation. Next, the system writes the data into a local cache. Later, the system copies the data from the cache to the remote storage.

Abstract: One embodiment of this mechanism provides a system that reduces network traffic and other system overhead for remote file append operations. This system generally operates by keeping track of file append operations on a local computer system when possible instead of always communicating with a remote file server. More specifically, the system operates by receiving a request at the local computer system to append additional data to a file residing in non-volatile storage on the remote file server. If sufficient space has been allocated to accommodate the additional data on the remote file server, the system writes the additional data to the end of a locally cached copy of the file in the local computer system. Next, the system updates a file length value stored in the local computer system to reflect the additional data.

Abstract: One embodiment of the present invention provides a system that reduces network traffic during remote file system operations by using a local path between a client and a storage device to bypass transfers through a server. The system operates by receiving a request at the server to access a file located on the storage device; this request is received across a network from an application on a client. Next, the system determines if a local path exists between the client and the storage device containing the file. Note that a local path is independent from a first path between the server and the storage device. If the local path exists, the system sends a bypass request to the client. This bypass request commands the client to satisfy the request by transferring data between the client and the storage device through the local path. In a variation on the above embodiment, the system additionally receives a completion indicator from the client.

Abstract: A system and method are disclosed that provides transparent, global access to devices on a computer cluster. The present system generates unique device type (dev.sub.-- t) values for all devices and corresponding links between a global file system and the dev.sub.-- t values. The file system is modified to take advantage of this framework so that, when a user requests that a particular device, identified by its logical name, be opened, an operating system kernel queries the file system to determine that device's dev.sub.-- t value and then queries the a device configuration system (DCS) for the location (node) and identification (local address) of a device with that dev.sub.-- t value. Once it has received the device's location and identification, the kernel issues an open request to the host node for the device identified by the DCS.

Abstract: A system and method are disclosed for rendering devices on a cluster globally visible, wherein the cluster includes a plurality of nodes on which the devices are attached. The system establishes for each of the devices in the cluster at least one globally unique identifier enabling global access to the device. The system includes a device registrar that creates the identifiers and a global file system. The identifiers include a globally unique logical name by which users of the cluster identify the device and a globally unique physical name by which the global file system identifies the device. The registrar creates a one-to-one mapping between the logical name and the physical name for each of the devices. The system also includes a device information (dev.sub.-- info) data structure maintained by the device registrar that represents physical associations of the devices within the cluster. Each association corresponds to the physical name of a device file maintained by the global file system.