Abstract: A storage controller that provides controlled access to storage devices by host computers is disclosed. The storage controller includes a host interface adapter that interfaces the storage controller to the hosts, a device interface adapter that interfaces the storage controller to the storage devices, and a microprocessor that processes requests by the hosts to access the storage devices. An access control table is created in response to user input in a memory accessible by the host interface adapter. When the host interface adapter receives a request, it determines from the access control table whether the requesting host has permission to access the specified storage device. If so, the host interface adapter forwards the request to the microprocessor. Otherwise, the host interface adapter transmits a response to the host denying access in one embodiment, or in another embodiment, provides an indication to the microprocessor that access should be denied.

Abstract: A method for improving performance through selective file caching is disclosed. The caching policy of a client's browser cache is set to cache all files. Web page files that reference a dynamic file include JavaScript code that mangles the dynamic filename, such that a reference by the web page file to the dynamic file is unique each time a browser, processes the web page file. In one embodiment, the filename is mangled by appending to it a known string followed by a 12-digit timestamp. Consequently, the mangled filename misses in the cache, forcing the browser to fetch the dynamic file from the web server. The web server recognizes the filename is in the mangled format, regenerates the original filename, and returns the file to the client. Static filenames are not mangled; hence, they are satisfied from the browser cache. The method also works to selectively defeat network caching.

Abstract: A bus bridge apparatus for performing broadcasted writes to redundant memory subsystems in a network storage controller is disclosed. The bus bridge includes a PCI-X target that receives a write command on a first PCI-X bus on one side of the bridge. The target is coupled to two PCI-X masters coupled to primary and secondary memory subsystems by respective PCI-X buses on the other side of the bridge. A first FIFO buffers the write command data between the target and the first master, and a second FIFO buffers a copy of the data between the target and the second master. The first and second masters concurrently retransmit the write command on their respective PCI-X buses to the primary and secondary memory subsystems. However, the second master only retransmits if broadcasting is enabled and the write command address is in a broadcast address range known by the bus bridge.

Abstract: The methodology of the present invention automatically selects an unused id for a system component in a system where multiple other components with other ids are already present. In this manner, id conflicts are avoided.

Abstract: A network storage controller for transferring data between a host computer and a storage device, such as a redundant array of inexpensive disks (RAID), is disclosed. The network storage controller includes at least one channel interface module which is adapted to be connected to the host computer and storage device. The channel interface module is connected to a passive backplane, and selectively transfers data between the host computer and storage device and the passive backplane. The network storage controller also includes at least one controller management module, attached to the passive backplane. The controller management module communicates with the channel interface module via the passive backplane, and processes and temporarily stores data received from the host computer or storage device. In applications where redundancy is required, at least two controller management modules and at least two channel interface modules may be used.

Abstract: A method for enhancing the performance on non-full stripe writes while closing the RAID5 write hole is disclosed. When a RAID controller receives data to be written to a disk array, the controller stores the data in nonvolatile memory, and opens a write operation. When the current write operation is initiated, the controller reads the old data from the disk array and checks for cached parity that corresponds to the stripe of data that is to be modified. If the parity is cached, the controller reads the cached parity, and if the parity is not cached, the controller reads the old parity from the disk array. New parity is then computed. If the parity was cached, the controller will modify a parity log to show an outstanding data write. If the parity was not cached, the controller will open a parity log to show an outstanding data and parity write. The new parity is then cached in non-volatile memory. The controller then determines whether the following write operation is for the same stripe of data.