Abstract: A technique is disclosed that enables the run-time behavior of a data-processing system to be analyzed and, in many cases, to be predicted. In particular, the illustrative embodiment of the present invention comprises i) transforming the messages that constitute an unstructured log into a numerical series and ii) applying a time-series analysis on the resultant series for the purpose of pattern detection. Indeed, it is recognized in the illustrative embodiment that the problem really is to detect patterns that depict aspects of system behavior, regardless of the textual content of the individual log messages. In other words, by analyzing the totality of the messages in the log or logs—as opposed to looking for pre-defined patterns of the individual messages—system behavior can be mapped and understood. The mapping helps in characterizing the system for the purposes of predicting failure, determining the time required to reach stability during failure recovery, and so forth.

Abstract: Systems and methods for constructing and maintaining a peer-to-peer overlay graph are disclosed herein. The systems and methods include adding a node to the overlay graph. Adding the node includes choosing an edge that is not connected to the node, breaking the edge and connecting the node to broken edge nodes previously connected to the edge. The process is repeating if additional connections are need and node addition data is stored for the node.

Abstract: Methods that enable the detection and handling of lost messages during load-balancing routing protocols are disclosed. In accordance with the illustrative embodiment, when a candidate intermediate node N receives a routing-protocol message, node N performs: (1) a first procedure that is capable of detecting some lost routing-protocol messages that were previously transmitted by node N, and (2) a second procedure that is capable of detecting some lost routing-protocol messages that were previously transmitted by a neighbor of node N.

Abstract: A method and apparatus provide for persistent caching of methods delivered via a publish-subscribe network. At a first node, a message having data via the network is received. The data is time-marked. The data is cached in a cache memory at the first node. The message is routed to a second node using content-based routing. These steps are repeated at a second node. A router that includes modules for executing this method is provided. A publish-subscribe network that includes nodes that include modules for executing this method is provided. A computer-readable medium that includes instructions for executing this method is provided.

Abstract: An apparatus and methods are disclosed that enable a non-multi-hop wireless terminal (i.e., a wireless terminal that has not been programmed to participate in multi-hop ad-hoc wireless networks) to in fact participate in a multi-hop ad-hoc wireless network, without any changes to the non-multi-hop terminal's software or hardware. In the illustrative embodiment, a wireless terminal T that already belongs to a multi-hop ad-hoc wireless network is assigned to a non-multi-hop wireless terminal W, and a signal is transmitted to terminal W that induces terminal W to use terminal T as a relay for transmitting messages. The assignment of multi-hop-capable terminals in the network to non-multi-hop terminals can be based on a variety of factors, such as signal strengths and the geo-locations of terminals.

Abstract: An apparatus and methods are disclosed that enable load-balancing of routes in ad-hoc wireless networks. In accordance with the illustrative embodiment, when a candidate intermediate node receives a routing-protocol message, the node waits before it transmits a message in response to the received message, where the amount of time that the node waits is based on the value of a load metric at the node and is independent of any other nodes in the network. As a result, a node that has a larger load will wait longer to transmit its routing-protocol message, and consequently, it is less likely that this node will be selected for inclusion in the new route. The techniques of the illustrative embodiment are applicable to both proactive and on-demand routing protocols, and are also applicable to other kinds of networks.

Abstract: A distributed computing system includes a number of computers, workstations or other computing machines interconnected by a network. One or more service managers are introduced that provide a management interface to corresponding middleware services. The service manager monitors the corresponding middleware service, as well as the underlying distributed computer environment on which an application process that utilizes the middleware service is executing, and allows the middleware service to operate more efficiently, in response to run-time environmental conditions. A fault-tolerance service manager is provided as a management interface to a fault-tolerance service. The fault-tolerance service manager monitors the fault-tolerance service, as well as the underlying distributed computer environment, to make globally optimal decisions, based on run-time environmental data, and to provide the resulting information to the fault-tolerance service.

Abstract: Packet routing via payload inspection at routers in a core of a distributed network for use in providing alert services. Packets include subjects and attributes in addition to routing information. The subjects correspond with particular types of content for subscriptions, and the attributes encapsulate the data or content, which can include video clips from cameras at particular locations. The routers store filters corresponding with subscriptions to content. Upon receiving a packet, a router inspects the payload section of the packet containing the attributes in order to retrieve the attributes and apply them to the filters for the subscriptions to content from the cameras. If an attribute satisfies a filter, the packet is routed to the next link. If the attributes do not satisfy the filters, the router discards the packet. These routing decisions are distributed among routers in the network core.

Abstract: Packet routing via payload inspection at routers in a core of a distributed network. Packets include subjects and attributes in addition to routing information. The subjects correspond with particular types of content for subscriptions, and the attributes encapsulate the data or content. The routers store filters corresponding with subscriptions to content. Upon receiving a packet, a router inspects the payload section of the packet containing the attributes in order to retrieve the attributes and apply them to the filters for the subscriptions. If an attribute satisfies a filter, the packet is routed to the next link. If the attributes do not satisfy the filters, the router discards the packet. These routing decisions are distributed among routers in the network core. The router locally caches the data in the network core.

Abstract: Packet routing via payload inspection at routers in a core of a distributed network for use in distributing content according to quality of service guarantees. Packets contain subjects and attributes in addition to routing information. The subjects correspond with particular types of content for subscriptions, and the attributes encapsulate the data or content. The subscriptions are associated with particular quality of service guarantees or levels of service. The routers store filters corresponding with subscriptions to content. Upon receiving a packet, a router inspects the payload section of the packet containing the attributes in order to retrieve the attributes and match them to the filters for the subscriptions. If the attributes satisfies a filter, the packet is routed to the next link in accordance with the quality of service guarantee associated with that filter. If the attributes do not satisfy any of the filters injected to and stored at the router, the router discards the packet.

Abstract: A method and apparatus provide for persistent caching of methods delivered via a publish-subscribe network. At a first node, a message having data via the network is received. The data is time-marked. The data is cached in a cache memory at the first node. The message is routed to a second node using content-based routing. These steps are repeated at a second node. A router that includes modules for executing this method is provided. A publish-subscribe network that includes nodes that include modules for executing this method is provided. A computer-readable medium that includes instructions for executing this method is provided.

Abstract: Channels between routers for use in packet routing via payload inspection. The channels constitute logical connections between routers and include subjects and attributes. Publishers create channels for routing particular types of content as defined by the subjects and attributes. The publishers also create proxies and notifications on the channels. The channel definitions for routers identify packet or message structures so that the routers can locate attributes in the packets for content-based routing. The routers apply the packet attributes to filters encapsulating subscriptions in order to perform the content-based routing in the network core. The routers also locally cache content, providing distributed caching of content throughout the network core.

Abstract: A system for providing coherent access to different versions of a group of documents stored in a file system and retrievable over the Internet from an HTTP server includes a state management server which stores registration data indicating the file paths of the documents in each version of the group and a set of index paths used by clients to reference documents in the group. State information identifying the version of said group previously accessed by a client is stored in a cookie which is associated with the domain of the state management server and the path of the group. A client requests a document from the group by issuing a request to an HTTP server including the index path of the desired document. The request and associated cookie, which is automatically transmitted by the client Internet software, is forwarded to the state management server. The state information stored in the cookie is extracted and used to determine which version of the group of documents should be accessed.

Abstract: An application module (A) running on a host computer in a computer network is failure-protected with one or more backup copies that are operative on other host computers in the network. In order to effect fault protection, the application module registers itself with a ReplicaManager daemon process (112) by sending a registration message, which message, in addition to identifying the registering application module and the host computer on which it is running, includes the particular replication strategy (cold backup, warm backup, or hot backup) and the degree of replication associated with that application module. The backup copies are then maintained in a fail-over state according to the registered replication strategy. A WatchDog daemon (113), running on the same host computer as the registered application periodically monitors the registered application to detect failures.

Abstract: An application module (A) running on a host computer in a computer network is failure-protected with one or more backup copies that are operative on other host computers in the network. In order to effect fault protection, the application module registers itself with a ReplicaManager daemon process (112) by sending a registration message, which message, in addition to identifying the registering application module and the host computer on which it is running, includes the particular replication strategy (cold backup, warm backup, or hot backup) and the degree of replication associated with that application module. The backup copies are then maintained in a fail-over state according to the registered replication strategy. A WatchDog daemon (113), running on the same host computer as the registered application periodically monitors the registered application to detect failures.

Abstract: In a communication arrangement, client terminals request information objects, e.g., hypertext markup language (HTML) documents, which are identified by their uniform resource locators (URLs) from a server system connected to the World Wide Web (WWW). For example, the information objects may represent different chapters of the same book and are thus logically connected. In accordance with the invention, when the logically connected information objects are updated, the updated versions of the information objects are stored in a temporary memory space. For those client terminals requesting the logically connected information objects by their URLs before the update, the server system consistently provides the original versions of the information objects at such URLs to the client terminals.

Abstract: A method and system for adaptively determining an operating point for a transmitter-receiver pair in a wireless communication network. The receiver receives data over an uplink and measures an average observed word error rate avg.sub.-- WER of the received data and transmits the average observed word error rate avg.sub.-- WER over a downlink to the transmitter when the average observed word error rate avg.sub.-- WER is not within an acceptable word error rate range. The transmitter receives the average observed word error rate avg.sub.-- WER over the downlink and determines a power-code pair (P,c) for the transmitter based on the average observed word error rate avg.sub.-- WER. The power code pair (P,c) defines an operating point of the transmitter, where P of the power-code pair is a selected transmit power level of the transmitter and c of the power-code pair is a selected forward error correcting code used for encoding the data. The receiver can also determine a predicted word error rate WER.sub.

Abstract: A server system for processing client requests received over a communication network includes a cluster of N document servers and at least one redirection server. The redirection server receives a client request from the network and redirects it to one of the document servers, based on a set of pre-computed redirection probabilities. Each of the document servers may be an HTTP server that manages a set of documents locally and can service client requests only for the locally-available documents. A set of documents are distributed across the document servers in accordance with a load distribution algorithm which may utilize the access rates of the documents as a metric for distributing the documents across the servers and determining the redirection probabilities. The load distribution algorithm attempts to equalize the sum of the access rates of all the documents stored at a given document server across all of the document servers.

Abstract: A dynamic combined power control and forward error correction control (FEC) technique for mobile radio systems which illustratively decreases the power consumed by wireless transmitters and increases the number of simultaneous connections which may be supported thereby. Individual transmitter-receiver pairs may adaptively determine the minimal power and FEC required to satisfy specified quality-of-service (QOS) constraints. Specifically, in accordance with an illustrative embodiment of the present invention, a first portion of a signal is encoded with a first code to generate a first encoded signal portion. Then, the first encoded signal portion is transmitted with a first power level. Next, parameter data is received, wherein the parameter data is representative of one or more characteristics of a received signal portion having been received by the receiver, the received signal portion having been based on the transmitted first encoded signal portion.