Processing

Please wait...

Settings

Settings

Goto Application

1. WO2006020338 - RUNTIME LOAD BALANCING OF WORK ACROSS A CLUSTERED COMPUTING SYSTEM USING CURRENT SERVICE PERFORMANCE LEVELS

Publication Number WO/2006/020338
Publication Date 23.02.2006
International Application No. PCT/US2005/025887
International Filing Date 20.07.2005
Chapter 2 Demand Filed 12.06.2006
IPC
G06F 9/46 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
9Arrangements for program control, e.g. control units
06using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
46Multiprogramming arrangements
CPC
G06F 2209/508
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
2209Indexing scheme relating to G06F9/00
50Indexing scheme relating to G06F9/50
508Monitor
G06F 9/505
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
9Arrangements for program control, e.g. control units
06using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
46Multiprogramming arrangements
50Allocation of resources, e.g. of the central processing unit [CPU]
5005to service a request
5027the resource being a machine, e.g. CPUs, Servers, Terminals
505considering the load
G06F 9/5083
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
9Arrangements for program control, e.g. control units
06using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
46Multiprogramming arrangements
50Allocation of resources, e.g. of the central processing unit [CPU]
5083Techniques for rebalancing the load in a distributed system
Applicants
  • ORACLE INTERNATIONAL CORPORATION [US]/[US] (AllExceptUS)
  • COLRAIN, Carol [AU]/[US] (UsOnly)
  • SIMMONS, Charles [US]/[US] (UsOnly)
  • SEMLER, Daniel [AU]/[US] (UsOnly)
  • POMMERENK, Stefan [DE]/[US] (UsOnly)
  • PRUSCINO, Angelo [IT]/[US] (UsOnly)
Inventors
  • COLRAIN, Carol
  • SIMMONS, Charles
  • SEMLER, Daniel
  • POMMERENK, Stefan
  • PRUSCINO, Angelo
Agents
  • HENKHAUS, John
  • DENDORFER, Claus
Priority Data
10/917,71512.08.2004US
11/168,96727.06.2005US
60/652,36811.02.2005US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) RUNTIME LOAD BALANCING OF WORK ACROSS A CLUSTERED COMPUTING SYSTEM USING CURRENT SERVICE PERFORMANCE LEVELS
(FR) EQUILIBRAGE DE CHARGES D'EXECUTION DU TRAVAIL DANS UN SYSTEME DE CALCUL EN GRAPPES FAISANT APPEL A DES NIVEAUX DE PERFORMANCE DE SERVICE COURANTS
Abstract
(EN) Runtime load balancing of work across a clustered computing system involves servers calculating, and clients utilizing, current service performance grades of each instance in the system. A performance grade for an instance is based on performance metrics for that instance, where the computation used may vary by policy. Examples of possible policies include: (a) using estimated bandwidth as a performance grade, (b) using spare capacity as a performance grade, or (c) using response time as a performance grade. Clients distribute work requests across servers in the system as the requests arrive. Work requests can be distributed according to performance grades, and/or flags associated with the performance grades. Automatically and intelligently directing work requests to the best server instances, based on real-time service performance metrics, minimizes the need to manually relocate work within the clustered system.
(FR) L'invention porte un procédé d'équilibrage de charges d'exécution du travail dans un système de calcul en grappes selon lequel des serveurs calculent, et des clients utilisent, des niveaux de performance de service courants pour chaque instance du système. Un niveau de performance pour une instance est basé sur une métrique de performance pour cette instance, le calcul utilisé pouvant varier selon la politique. Des exemples de politiques possibles comprennent: (a) l'utilisation d'une largeur de bande estimée comme niveau de performance; (b) l'utilisation de la capacité de réserve comme niveau de performance; ou (c) l'utilisation du temps de réponse comme niveau de performance. Les clients distribuent les demandes de travail entre les serveurs du système au fur et à mesure qu'elles arrivent. Les demandes de travail peuvent être distribuées en fonction des niveaux de performance et/ou de fanions associés aux niveaux de performance. En dirigeant automatiquement et intelligemment les demandes de travail vers les meilleurs instances serveur, sur la base d'une métrique de performance de service en temps réel, on parvient à minimiser le besoin de réattribution manuelle du travail au sein du système en grappes.
Related patent documents
Latest bibliographic data on file with the International Bureau