Abstract: Each processor in a multi-processor system is periodically interrupted for preempting the current thread for servicing of a watchdog thread during normal operation. Upon failing to service the watchdog thread over a grace period, a system watchdog initiates an orderly shutdown and reboot of the system. In order to prevent spinlocks from causing fake panics, if the current thread is holding one or more spinlocks when the interrupt occurs, then preemption is deferred until the thread releases the spinlocks. For diagnostic purposes, a count is kept of the number of times that preemption is deferred for each processor during each watchdog grace period.

Abstract: A physical address extension feature maps multiple virtual memory spaces to an extended physical memory. Performance is enhanced by mapping chunks of both common and separate physical memory to each of the virtual memory spaces to provide efficient communication of parameters to and results from well-defined or well-contained software modules assigned to the chunks of separate physical memory. For example, the common physical memory stores stack allocation, per-processor data for communication between the virtual address spaces, BIOS, and device drivers. A first virtual memory space is directly mapped to a bottom region of physical memory containing buffer cache and page tables. In a file server, for example, one of the virtual memory spaces contains an inode cache, another contains a domain name lookup cache, and still another contains a block map for snapshot copies.

Abstract: Permitting multiple concurrent read operations upon a file system enhances small file performance. A respective instance of a thread routine stores the data from each file into a series of buffers for the file. Each instance is identified by a Process Identifier (PID) used for streaming the data from the buffers in the order in which the files are opened instead of the order in which the file data are returned by the read operations. In order to conserve buffer memory, read operations upon a file are suspended once a certain amount of data have been read from the file unless data from the file are being streamed from the buffers.

Abstract: A problem of latency during a read of a file is solved by activating multiple concurrent read threads and also by prefetching blocks of file data from storage to a file system cache. Prefetching ensures that by the time that a client or application needs more file data, the file data will already have been read from storage and written to the cache as a background operation. For example, a file server responds to a request to read an extent of file data consisting of eight consecutive file blocks by activating concurrent block read threads for reading the file blocks and by prefetching from the storage to the cache eight more consecutive blocks of data from the file.

Abstract: In a network attached cached disk storage system, data is transmitted over the network in data packets having a data length that is much smaller than the logical block size for reading or writing to disk storage. To avoid copying of data from network port buffers to the cache memory, the cache blocks of the cache memory are organized as linked lists of list elements, which can be used as network port input or output buffers. For TCP data packets, for example, each list element has a data slot for storing up to 1,500 bytes, and a field indicating the number of bytes stored in the data slot.

Abstract: In a network attached cached disk storage system, data is transmitted over the network in data packets having a data length that is much smaller than the logical block size for reading or writing to disk storage. To avoid copying of data from network port buffers to the cache memory, the cache blocks of the cache memory are organized as linked lists of list elements, which can be used as network port input or output buffers. For TCP data packets, for example, each list element has a data slot for storing up to 1,500 bytes, and a field indicating the number of bytes stored in the data slot.

Abstract: Consistent updates are made automatically over a wide-area IP network, concurrently with read-only access to the remote copies. A replication control protocol (RCP) is layered over TCP/IP providing the capability for a remote site to replicate and rebroadcast blocks of the remote copy data to specified groups of destinations, as configured in a routing table. A volume multicast layer over RCP provides for multicasting to specified volume extents of the blocks. The blocks are copied at the logical level, so that it does not matter what physical structure is used for storing the remote copies. Save volumes buffer the remote copy data transmitted between the primary or secondary file system volume and the IP network, in order to ensure independence between the replication process, the IP transport method, and the primary file system being replicated.

Abstract: In a multi-processor system, each processor has a respective hard affinity queue and soft affinity queue. For execution of a thread, a queue loader places an instance of the thread upon the hard or soft affinity queue of a selected processor. The selection may use an affinity attribute, processor attribute, accessor function, or a respective program of code threads for each processor. A thread instance on a processor's hard affinity queue is executed only by that processor. A thread instance on a processor's soft affinity queue is executed by that processor unless another processor has a soft affinity queue empty of thread instances ready for execution. Each processor alternates service priority between its hard and soft affinity queues. When a thread has a soft affinity it is initially bound to the processor it is started from. It will, then, be bound to the last processor it has been run on.

Abstract: A degradable plastic film comprising film forming ethylene copolymers and lignin incorporated in the form of pulverulent powder having a grain diameter of about 1 to 5 microns. The films are homogeneous and possess a thickness of about 15 to 25 microns. The films may be made doubly decomposable by adding photoactive or oxidizing agents.

Abstract: A method for producing a catalytic carbon deposit on a conductive support mprising admixing (i) a suspension of between 200 and 400 grams per liter of catalytic carbon in a liquid medium, with (ii) a solution of between 20 and 50 grams per liter of polyvinyl chloride in a cyclic ketone solvent, to form an emulsion, depositing said emulsion on said support, and evaporating the liquid components of said emulsion from said support to form a layer of catalytic carbon in a polyvinyl chloride binder.