Abstract: A method for communicating information from a first computing node to at least one of the following: a storage device and a second computing node. The first computing node is monitored to collect at least one estimate of available resources, and based on this estimate, an amount of data collected is modified. Then, the collected data is sent to at least one of the following: the storage device and the second computing node. This invention also provides for the determination of an optimum batch size for aggregating data wherein, for a number of batch sizes, costs are estimated for sending batched information to persistent storage and for losing batched data. Then, the optimum batch size is selected from the number of different batch sizes based on sums of these costs. This invention also provides for selective compression of data, wherein it is determined which of a number of compression algorithms do not incur an overhead that exceeds available resources.

Abstract: Methods for serving data include maintaining an incomplete version of an object at a server and at least one fragment at the server. In response to a request for the object from a client, the incomplete version of the object, an identifier for a fragment comprising a portion of the object, and a position for the fragment within the object are sent to the client. After receiving the incomplete version of the object, the identifier, and the position, the client requests the fragment from the server using the identifier. The object is constructed by including the fragment in the incomplete version of the object in a location specified by the position.

Abstract: Improved load balancing techniques are disclosed. For example, in one illustrative aspect of the invention, a method of satisfying requests in a system comprised of a plurality of servers comprises the following steps. At least one load balancer is provided for routing requests to the plurality of servers. At the at least one load balancer, a request sent from a client is obtained. At the at least one load balancer, the request is examined. Costs of satisfying the request by at least two of the plurality of servers are estimated. The estimation is based on at least one of a number and a cost of at least one remote access for satisfying the request. The request is routed to a server of the plurality of servers with a low estimated cost of satisfying the request.

Abstract: Techniques for efficiently authenticating multiple objects and clustering objects based on access patterns are provided. For example, in an illustrative aspect of the invention, a technique for generating and/or reading authentication information, wherein the authentication information provides evidence that a plurality of objects were one of generated and sent by an entity, comprises using one or more object access patterns indicative of whether at least two of the plurality of objects are accessed within a similar time period to group objects together to reduce an overhead for at least one of generating and reading the authentication information.

Abstract: Techniques for efficiently clustering objects based on access patterns are provided. For example, in an illustrative aspect of the invention, a technique for clustering a plurality of objects based on access patterns comprises the following steps/operations. A first group of sets is created in which at least one set includes a plurality of objects read in close temporal proximity to each other. A second group of sets is created in which at least one set contains a plurality of objects written in close temporal locality to each other. A third group of sets is created in which at least one set s1 is constructed by identifying at least two objects o1 and o2 in a same set of the first group. At least one object is added to set s1 which is included in a set including object o1 of the second group. At least one object is added to set s1 which is included in a set including object o2 of said second group.

Abstract: A solid oxide fuel cell generator (10) is made which contains a plurality of bundles (14) of solid oxide fuel cells (36), the fuel cells, capable of generating electrical current, a bus bar unit (128) in adjacent contact with the plurality of fuel cell bundles at the sides of the generator, where the bus bar unit (128) can pass electrical current from the adjacent fuel cell bundles, the bus bar unit (128) containing inner flat plate/screen sections (130) near the fuel cell bundles, outer solid nickel bar (134) and with wide, solid, flexible, corrugated nickel strap electric current take-off connections (136) between the screens and bar; a power lead (140) electrically connected to the outer solid nickel bar, and also electrically through the bus bar unit to the fuel cell bundles through the take-off connections and inner screen sections; where the inner screen sections (130) and take-off connections (136) pass electrical current generated in the fuel cell bundles through the bus bar units (128) to an electric

Abstract: Techniques are provided for dynamically scheduling requests in data processing systems in accordance with differentiated service levels. In a first aspect of the invention, a technique for processing a request to at least one server comprises the following steps. A request is received. Then, submission of the request to the at least one server is scheduled based on: (i) a quality-of-service (QoS) class assigned to a client from which the request originated; (ii) a response target associated with the QoS class; and (iii) an estimated response time associated with the at least one server. The technique may further comprise the step of withholding the request from submission to the at least one server when the request originated from a client assigned to a first QoS class to allow a request that originated from a client assigned to a second QoS class to meet a response target associated therewith.

Abstract: In a client-server environment having a server group including one or more participating servers and one or more controller servers, where each participating server can communicate with at least one controller server, a method for coordinating actions among the servers in the server group comprising the steps of: (1) communicating between a client and at least one of the servers in the server group using a protocol that has limited or no defined procedures for passing state information between the client and the servers; (2) transmitting a request for an action from the client to one of the servers; and (3) communicating among a plurality of servers with at least one controller server coordinating actions of at least some of the servers in response to the request.

Abstract: A system and method for maintaining consistency in a system where multiple copies of an object may exist is provided for maintaining consistent copies. Consistency is maintained using a plurality of consistency policies in which at least one consistency policy results in different performance than a second consistency policy. A consistency policy is selected from the plurality consistency policies for each object to improve system performance.

Abstract: A system and method for maintaining objects in storage elements includes maintaining information regarding which storage elements are storing particular objects and responding to a request to update an object by using maintained information to determine which of the storage elements store a copy of the object. Each storage element is instructed to invalidate the copy of the object, and an update of the object is performed after each storage element that includes the copy of the object indicates that the storage element has invalidated the copy of the object or the storage element is determined to be unresponsive.

Abstract: In a system having a plurality of caches, a method for maintaining cached objects includes storing an object in a plurality of caches. In response to a request to update the object, a future invalidation time is determined when the object should be invalidated in caches currently storing the object. Updating of the object is delayed until the invalidation time has passed.

Abstract: Techniques for serving data to a plurality of clients in a client-server environment are provided. In one aspect of the invention, the technique provides a plurality of versions of data in which different versions have different overheads associated therewith. Individual clients are assigned to one of a plurality of quality-of-service classes. Requests are satisfied so that a client belonging to a high quality-of-service class is given preferential access to data versions which require higher overheads to serve.

Abstract: Techniques for improved cache management including cache replacement are provided. In one aspect, a distributed caching technique of the invention comprises the use of a central cache and one or more local caches. The central cache communicates with the one or more local caches and coordinates updates to the local caches, including cache replacement. The invention also provides techniques for adaptively determining holding times associated with data storage applications such as those involving caches.

Abstract: A method for managing computer memory, in accordance with the present invention, includes maintaining multiple sets of free blocks of memory wherein a free block is added to a set based on its size. In response to a request for a block of a request size, a set of blocks is searched for a free block which is at least as large as the request size but smaller than the request size plus a threshold. If such a block is found, the block is allocated in its entirety.

Abstract: A method for constructing a plurality of objects, in accordance with the present invention includes the steps of providing a plurality of fragments, providing at least one fragment, determining an order for constructing objects based on at least one inclusion relationship between an object and the at least one fragment and constructing the plurality of objects based on the at least one inclusion relationship and the determined order for constructing the objects. A program storage device is also described. A system for constructing a plurality of objects, in accordance with the present invention, includes a content authoring system for generating fragments and providing include relationships between the fragments. A dependency parser is included for receiving the fragments and parsing the include relationships. A dependency analyzer is provided for determining an efficient order for constructing the plurality of objects from the fragments based on the include relationships.

Abstract: Techniques for managing storage of objects of sizes smaller than a storage transfer unit in a computer system. A plurality of storage transfer units are maintained in a first storage medium (e.g., disk storage) organized by a quantity of free space in a storage transfer unit. A cache is maintained in a second storage medium (e.g., main memory), the cache including a copy of at least one of the plurality of storage transfer units. In response to a request to store an object of a size less than a storage transfer unit, the technique searches for a cached storage transfer unit with sufficient free space to store the object. If no such cached storage transfer unit can be found, the technique identifies an uncached storage transfer unit with sufficient free space to store the object and stores a copy of the identified storage transfer unit in the cache.

Abstract: Methods for serving data include maintaining an incomplete version of an object at a server and at least one fragment at the server. In response to a request for the object from a client, the incomplete version of the object, an identifier for a fragment comprising a portion of the object, and a position for the fragment within the object are sent to the client. After receiving the incomplete version of the object, the identifier, and the position, the client requests the fragment from the server using the identifier. The object is constructed by including the fragment in the incomplete version of the object in a location specified by the position.