Liana Liyow Fong - Irvington NY Ajei Sarat Gopal - Fort Lee NJ Nayeem Islam - Thornwood NY Andreas Leonidas Prodromidis - New York NY Mark Steven Squillante - Pound Ridge NY
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06F 946
US Classification:
709102, 709104
Abstract:
A system and method whereby a gang scheduling entity assembles a schedule of application tasks to be run on a plurality of distributed parallel processors for pre-set time intervals. The scheduling information, including an ordered set of applications and the length of the time interval, are provided to each of the node level schedulers for the relevant processors, and the node level schedulers assure that the tasks of the applications are executed, with context switching between tasks being controlled at the node level. Tasks from multiple applications can be scheduled simultaneously, with time sharing and space sharing being utilized in the schedule. The inventive system is dynamically scalable, with the gang scheduling entity restructuring the matrix schedule should dynamic re-partitioning result in addition or deletion of processors.
Flexible Dynamic Partitioning Of Resources In A Cluster Computing Environment
Liana Liyow Fong - Irvington NY Ajei Sarat Gopal - Fort Lee NJ Nayeem Islam - Thornwood NY Andreas Leonidas Prodromidis - New York NY Mark Steven Squillante - Pound Ridge NY
Assignee:
IBM Corporation - NY
International Classification:
G06F 900
US Classification:
709104
Abstract:
The invention provides the mechanism, hereinafter referred to as Flexible Dynamic Partitioning (FDP), to allocate and reallocate resources among scheduling schemes of many types for multicomputing environments. Resources can include, but are not limited to, processors, disks and communications connections. Partitioning of resources can be initiated by both application and system triggers. Once dynamic partitioning is triggered, FDP allows a partition to invoke a set of resource allocation functions associated with its partition. The reallocation function performs a set of resource matchings and determine the necessary resource movement among partitions.
Optimizing Method For Digital Content Delivery In A Multicast Network
Charu C. Aggarwal - Ossining NY Jayachandran Sethuraman - Cambridge MA Mark S. Squillante - Pound Ridge NY Joel L. Wolf - Katonah NY Philip S. Yu - Chappaqua NY
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
H04J 116
US Classification:
370468, 370473, 370474, 370242
Abstract:
A method for scheduling delivery of digital objects over a network, in accordance with the invention, includes the steps of providing a user interface for selecting objects to be transmitted thereto, selecting at least one object to be transmitted to the user interface, identifying and receiving in-progress object transmissions corresponding to the at least one selected object, identifying portions of the at least one object not yet received to request transmission of the portions of the at least one object not yet received and receiving remaining portions of the at least one object during additional in-progress transmissions. A system is also included.
Apparatus And Methods For Co-Location And Offloading Of Web Site Traffic Based On Traffic Pattern Recognition
Daniel Manuel Dias - Mohegan Lake NY, US Richard Pervin King - Scarsdale NY, US Zhen Liu - Tarrytown NY, US Mark Steven Squillante - Pound Ridge NY, US Honghui Xia - Croton on Hudson NY, US Shun-Zheng Yu - Guangdong, CN Li Zhang - Yorktown Heights NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06F 15/173
US Classification:
709224
Abstract:
Apparatus and methods for identifying traffic patterns to web sites based on templates that characterize the arrival of traffic to the web sites are provided. Based on these templates, determinations are made as to which web sites should be co-located so as to optimize resource allocation. Specifically, web sites whose templates are complimentary, i. e. a first web site having a peak in arrival traffic at time t and a second web site that has a trough in arrival traffic at time t, are designated as being candidates for co-location. In addition, the present invention uses the templates identified for the traffic patterns of web sites to determine thresholds for offloading traffic to other servers. These thresholds include a first threshold at which offloading should be performed, a second threshold that takes into consideration the lead time needed to begin offloading, and a third threshold that takes into consideration a lag time needed to stop all offloading of traffic to the other servers.
Method And Apparatus For Web Crawler Data Collection
Mark Steven Squillante - Pound Ridge NY, US Joel Leonard Wolf - Katonah NY, US Philip Shi-Lung Yu - Chappaqua NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06F 17/30
US Classification:
707 3, 707 2, 707 5
Abstract:
A Web crawler data collection method is provided for collecting information associated with a plurality of queries, which is used to calculate estimates of return probabilities, clicking probabilities and incorrect response probabilities. The estimated return probabilities relate to a probability that a search engine will return a particular Web page in a particular position of a particular query result page. The estimated clicking probabilities relate to a frequency with which a client selects a returned Web page in a particular position of a particular query result. The estimated incorrect response probabilities relate to the probability that a query to a stale version of a particular Web page yields an incorrect or vacuous response. Further, information may be collected regarding the characteristics and update time distributions of a plurality of Web pages.
Method And System For Embedding Correlated Performance Measurements For Distributed Application Performance Decomposition
Joseph L. Hellerstein - Ossining NY, US Srirama Mandyam Krishnakumar - White Plains NY, US Mark S. Squillante - Pound Ridge NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06F 15/173
US Classification:
709224, 709246
Abstract:
Techniques for use in accordance with application performance decomposition are provided which take advantage of the communications protocol used to carry a transaction between application components in a distributed computing network. Specifically, the invention extends the communications protocol by embedding data, such as timestamp and duration measurement data, in the protocol itself, rather than extending or altering the application or transaction data carried by the protocol as in existing approaches. Thus, the invention provides natural correlation of interactions of distributed application components on such transactions without modification to the application or transaction data. Because the correlation is performed in-line with the application component interactions, minimal data management overhead is required, and correlated performance decomposition is made possible in real-time for the transaction. Furthermore, subsequent processing stages of the distributed application can interpret the communications protocol to glean processing durations of previous stages in order to make decisions regarding treatment of the transaction.
Apparatus And Methods For Classification Of Web Sites
Nagui Halim - Yorktown Heights NY, US Zhen Liu - Tarrytown NY, US Mark Steven Squillante - Pound Ridge NY, US Honghui Xia - Croton on Hudson NY, US Shun-Zheng Yu - Guangdong, CN Li Zhang - Yorktown Heights NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06F 15/173
US Classification:
709224, 709223
Abstract:
Apparatus and methods for classifying web sites are provided. With the apparatus and methods, traffic data is obtained for a plurality of web sites. This patterns, or templates, for each web site are generated based on this traffic data and the patterns are clustered into classes of web sites using a clustering algorithm. The clusters, or classes, are then profiled to generate a template for each class. The template for each class is generated by first shifting the patterns for each web site that is part of the class to compensate for effects like time zone differences, if any, and then identifying a pattern that is most similar to all of the patterns in the class. Once the template for each class is generated, this template is then used with traffic data from a new web site to classify the new web site into one of the existing classes. In other words, when traffic data for a new web site is received, a pattern for the traffic data of the new web site is generated and compared to the templates for the various classes. If a matching class template is identified, the new web site is classified into the corresponding class.
Method And Apparatus For Information Boosting In Related But Disconnected Databases
Jianying Hu - Bronx NY, US Aleksandra Mojsilovic - New York NY, US Ana Radovanovic - New York NY, US Mark S. Squillante - Pound Ridge NY, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06Q 10/00
US Classification:
705 717, 705 711, 705 712, 705 713
Abstract:
Method and apparatus for information boosting in related but disconnected databases, in one aspect, may comprise identifying disconnected data sources comprising data that are related or dependent on one another, determining one or more relationships and dependencies among the disconnected data, and refining the data sources based on one or more relationships and dependencies.