Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains, for a time interval, a set of performance metrics for one or more monitored systems. Next, the system aggregates the performance metrics by a processing factor associated with execution of the monitored system(s). The system then uses the aggregated performance metrics to calculate a performance score associated with the processing factor. Finally, the system outputs the performance score with other performance scores for other performance factors associated with execution of the one or more monitored systems for use in assessing the performance of the monitored system(s).

Abstract: A system, method, and apparatus are provided for locally enforcing quotas on resources within a computing environment (e.g., a data center, a computing cluster) that includes multiple brokers, gateway servers, or other entities that control access to the resource(s). Instead of using global access statistics provided by all gateways, each server individually allows or denies requested access to a resource based on whether the requesting client has already exceeded its quota (or would exceed its quota if the request is approved). A client associated with a given call to a resource may be identified using a tuple formed from identifiers of multiple services in the call stack, such as a first service (e.g., a front-end or user-facing service) and an immediate service (e.g., a final service in the stack prior to receipt of the call at a gateway, broker, or other entity that manages access to the controlled resources).

Abstract: A system and method are provided for sticky routing of a user's service requests and connections to a distributed service hosted by multiple data centers. Sticky routing data are generated when a user first connects, to include member ID, preferred data center, a user bucket associated with one data center, a generation of the bucket, a generation of the user's sticky routing data, and timing information identifying a time of issue and/or a time of expiration of the routing data. A user bucket is either online (accepts new users; their requests are routed to the associated data center), offline (not accepting new users; existing users are expelled and must join a different bucket), or closed (not accepting new users; existing users' requests continue to be routed to the associated data center). All of a user's requests, from all devices, are thus routed to one data center, based on member ID.

Abstract: In a computer communication network, affinity between a client and server is established dynamically. The client desiring affinity sends a request to establish affinity to an available server. The server can then respond by sending the client a redirect to an elected server, with which the client already has affinity. If there is no such elected server, the server establishes affinity between itself and the client.

Abstract: A system and method are provided for sticky routing of a user's service requests and connections to a distributed service hosted by multiple data centers. Sticky routing data are generated when a user first connects, to include member ID, preferred data center, a user bucket associated with one data center, a generation of the bucket, a generation of the user's sticky routing data, and timing information identifying a time of issue and/or a time of expiration of the routing data. A user bucket is either online (accepts new users; their requests are routed to the associated data center), offline (not accepting new users; existing users are expelled and must join a different bucket), or closed (not accepting new users; existing users' requests continue to be routed to the associated data center). All of a user's requests, from all devices, are thus routed to one data center, based on member ID.

Abstract: In one embodiment, a method and apparatus for collaborative data redundancy for configuration management database is disclosed. The method includes requesting, by a server of a configuration tracking system, an agent of the configuration tracking system to retrieve asset data when a copy of the asset data located in the server becomes corrupted, retrieving by the agent the requested asset data from one or more assets, and transferring by the agent the asset data to the server without utilizing data redundancy services performed outside of the configuration tracking system. Other embodiments are also disclosed.

Abstract: In one embodiment, an apparatus for directory-based web service distribution is disclosed. The apparatus includes a directory and a request client to initiate a request for a web service, the request client including an application middleware having invocation framework with embedded distribution logic to distribute the request to a destination pod, the destination pod to compute a subset of a state associated with the web service, wherein the distribution logic to distribute the request based on a lookup value extracted from the request and submitted to the directory to determine the destination pod. Other embodiments are also disclosed.

Abstract: A method involving enqueuing, according to a policy associated with an offering, a document in a queue for delivery to a first document endpoint; transmitting the document to the first document endpoint; retaining a copy of the document and marking the copy to indicate transmission of the document; and upon receipt of an indication, unmarking the copy of the document using the processor; and transmitting the copy to a second document endpoint.

Abstract: A quality of service policy for one or more documents for transmission from the local storage to one or more end points for said documents through a communication system is retrieved from a remote registry associated with an offering, and said documents are enqueued according to said quality of service policy. In some cases, the registry may be co-hosted with at least one of the document end points. The quality of service policy may be derived from a transport policy for said one or more documents, and may even be such as to not specify a quality of service for delivery of some or all of the documents. In some cases, XML documents may be used to set forth the quality of service policies.

Abstract: Methods and systems for effecting cleanup and other policies for queues and similar data stores, which policies account for preferences of consumers of the data so stored. Queuing policies for local storage of one or more documents for transmission from the local storage to one or more end points for said documents are retrieved from a remote registry. Upon such retrieval, the documents are enqueued according to the queuing policies, unless, prior to such enqueuing the queues into which the documents are to be placed require creation or clean-up, for example according to one or more queue quota policies. In some cases, the documents are queued according to associated qualities of service to be accorded to delivery of said documents. Such qualities of service may be specified in the queuing policy.

Abstract: A self-reconfiguring name service that distributes workload among the available servers in a system. A Service Monitor for each host system of a site periodically broadcasts information about available servers. The broadcast message also indicates the workload of the host. Each name service (DNS) has an associated process called a Name Binder Modifier that receives the broadcast messages from the Service Monitors. Periodically, each Name Binder Modifier reviews the information it has received from various Service Monitors and updates zones that are used by the DNS to perform load balancing. The Service Monitor and the Name Binding Modifier have associated configuration files.

Abstract: A preferred embodiment of the present invention includes a method and apparatus for allocating and using IP addresses in a network of client systems. More specifically, the present invention includes a router which monitors the assignments of IP addresses by a DHCP server. As each IP address is assigned, the router associates the assigned IP address with an trusted identifier which identifies the client system. Subsequently, if the router received a packet directed at the assigned IP address, the router forwards the packet to the client system having an trusted identifier associated with the destination address of the IP packet. Additionally, if the router receives a packet from a client system, it uses the trusted identifier of the client system to find IP addresses associated with the client system. If the source address of the IP packet is not included in the IP addresses associated with the client system, the packet is discarded.

Abstract: A method and apparatus for performing client-sensitive DNS translations includes the steps of receiving a translation request by a DNS server. The DNS server examines the translation request to determine if a record exists within the DNS server that associates the symbolic name included in the translation request with an IP record. If such a record exists, the IP address is returned as the translation. If not, the DNS server determines whether reflective client-sensitive translation is required. In the affirmative case, the request is reflected to back to the client where client-sensitive translation is performed and returned to the DNS server. If client-sensitive translation is not required, the DNS server determines whether non-reflective client-sensitive translation is required. If so, the requested translation is forwarded to a special DNS server, along with information that identifies the client system requesting translation.

Abstract: A preferred embodiment of the present invention includes a method and apparatus for routing an IP packets in a network of client systems. The router forwards IP packets between the client systems and the server systems. More specifically, the router can be pre-configured to include one or more "routes." Each route is a mapping between an IP address and a client system. The router may also learn route from other routers and by analysis of IP packets. Preferably, the routes known by the router are included in a route table. The router also monitors DHCP assignment of IP addresses to client systems within the network. When the DHCP assignment of an IP address is detected, the router creates a new route that associates the newly assigned IP address and the corresponding client system. The new route is marked so that it may only be overwritten by a subsequent DHCP assignment.

Abstract: A preferred embodiment of the present invention includes a method and apparatus for allocating and using IP addresses in a network of client systems. More specifically, the present invention includes a DHCP server that leases IP addresses to the client systems. The DHCP server works in combination with a secure DHCP relay agent and a secure IP relay agent. Broadcast DHCPREQUEST messages are forwarded to the DHCP server by the secure DHCP relay agent. Before forwarding, the secure DHCP relay agent embeds in each DHCPREQUEST message. The trusted identifier is an unforgeable object specifically associated with the client system sending the DHCPREQUEST message. When the DHCP server receives a DHCPREQUEST message, the DHCP server extracts the trusted identifier. The trusted identifier is then used by the DHCP server to prevent client systems from accessing the IP address leases of other client systems. The DHCP server also counts the number of IP addresses leases assigned to each trusted identifier.