Abstract: Duplicate processing at network operators is avoided by applying once-only processing at operators which are adjacent to either the source or destination host of a data packet. An operator is adjacent to a host if there exists a path between the operator and the host containing no other operators. In one embodiment, an operator determines that it is adjacent to a host if it receives a special broadcast data packet from the host. To ensure that no other operators receive the special broadcast data packet, the adjacent operator drops the packet. In another embodiment, operators determine whether they are adjacent to identified hosts by transmitting special ping packets to the hosts. If an operator receives a ping response from the host, the operator determines that it is adjacent to the host. To ensure that only adjacent operators receive ping responses, intervening operators drop special ping packets received from other operators.

Abstract: Physical connectivity is determined between elements such as switches and routers in a multiple subnet communication network. Each element has one or more interfaces each of which is physically linked with an interface of another network element. Address sets are generated for each interface of the network elements, wherein members of a given address set correspond to network elements that can be reached from the corresponding interface for which the given address set was generated. The members of first address sets generated for corresponding interfaces of a given network element, are compared with the members of second address sets generated for corresponding interfaces of network elements other than the given element. A set of candidate connections between an interface of the given network element and one or more interfaces of other network elements, are determined.

Abstract: A cache management scheme is disclosed for buffering one or more continuous media files being simultaneously accessed from a continuous media server by a plurality of media clients. The continuous media server stores pages of data that will likely be accessed in a cache or buffer. The continuous media server implements a cache management strategy that exploits the sequential page access patterns for continuous media data, in order to determine the buffer pages to be replaced from the cache. The cache management strategy initially identifies unpinned pages as potential victims for replacement. Each unpinned page is evaluated by the continuous media server and assigned a weight. Generally, the assigned weight ensures that a buffer with a larger weight will be accessed by a client later in time than a buffer with a smaller weight. A page associated with a larger weight will be accessed later and hence, is replaced earlier.

Abstract: A request for transfer of data over a network is processed to obtain current values of network parameters such as aggregate network processing overhead and effective network bandwidth. In response to receipt of a data transfer request, the maximum size transport unit which can be sent over the network without packet loss is determined. The full maximum size transport unit is then sent over the network from, for example, a client to a server, in order to provide a measure of full size transport time. Similarly, a half size transport unit is sent over the network to provide a measure of half size transfer time. The fall and half size transfer times are then used to compute current values for the network processing overhead and effective network bandwidth parameters. The current values are processed to determine an internal buffer size to be allocated for use in receiving data transferred over the network in response to the request.

Abstract: Bit error rate in holographic storage/reconstruction is reduced by 2-dimensionally dispersing symbols constituting codewords so that no two codeword-common symbols occupy a single row or column on the SLM display.

Abstract: Bit error rate of an output data stream, reconstructed from a holographic recording, is reduced by reducing the length of same-state pixels on the spatial light modulator.

Abstract: Buffer space and disk bandwidth resources in a continuous media server are continuously re-allocated in order to optimize the number of continuous media requests which may be concurrently serviced at guaranteed transfer rates using on demand paging. Disk scheduling is provided to ensure that whenever an admitted request references a page of data, the page is available in a buffer for transfer to a client. Data for continuous media data files are stored on disk or held in the buffer to eliminate disk bandwidth limitations associated with concurrently servicing any number or combination of requests, provided buffer space is sufficient. Multiple requests for continuous media data files are selectively included in groups for servicing in order to provide that buffer and disk bandwidth requirements are maintained at a minimum and within available resource capabilities.