-
公开(公告)号：JP2004078944A
公开(公告)日：2004-03-11
申请号：JP2003285445
申请日：2003-08-01
Applicant: Internatl Business Mach Corp
, インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Maschines Corporation Inventor： BRITTON EDWARD GLEN , DEVINE WESLEY MCMILLAN , HUYNH LAP THIET , RAJARAMAN BALA , STAGG ARTHUR JAMES
CPC classification number: G06F12/126
Abstract: PROBLEM TO BE SOLVED: To provide a caching system and a caching method based on a value.
SOLUTION: This value-based caching method includes classification of a cache into various value-based partitions. A data to be stored in the cache is evaluated, and the evaluated data is cached in the individual value-based partition. A cache entry is discharged thereafter from the value-based partition. The caching and the discharge are controlled according to an evaluation step. A caching step and a discharging step guarantee, in relation thereto, high cache responsiveness with respect to the data having a high value concerned in the other cached data.
COPYRIGHT: (C)2004,JPO-
公开(公告)号：AU2003240078A1
公开(公告)日：2003-12-31
申请号：AU2003240078
申请日：2003-06-09
Applicant: IBM
Inventor： LINDQUIST DAVID , RAJARAMAN BALA , TAN YIH-SHIN , TOPOL BRAD
Abstract: A computing services grid. The grid can include a service desk coupled to one or more computing service instances. Each service instance can conform to an interface which is common to all service instances in the grid. A routing component can be disposed in the grid. Specifically, the routing component can route individual service requests to individual ones of the service instances. An instance selection service is used to satisfy QoS characteristics associated with the requester of the service. The grid further can include a service instance monitoring component. The monitoring component can monitor the performance of individual service instances charged with processing individual service requests. Fail-over logic can be configured to re-route service requests from selected service instances to others of the service instances where the monitoring component detects a fail-over condition in the selected service instances. In that regard, fail-over conditions can include error conditions and a performance deficiency conditions in which the performance of a selected service instance lags behind guaranteed levels of performance.
-
Patent Agency Ranking
公开(公告)号：CA2486434C
公开(公告)日：2011-06-28
申请号：CA2486434
申请日：2003-06-09
Applicant: IBM
Inventor： LINDQUIST DAVID , RAJARAMAN BALA , TAN YIH-SHIN , TOPOL BRAD
Abstract: A computing services grid. The grid can include a service desk coupled to one or more computing service instances. Each service instance can conform to an interface which is common to all service instances in the grid. A routing component can be disposed in the grid. Specifically, the routing component can route individual service requests to individual ones of the service instances. An instance selection service is used to satisfy QoS characteristics associated with the requestor of the service. The grid further can include a service instance monitoring component. The monitoring component can monitor the performance of individual service instances charged with processing individual service requests. Fail-over logic can be configured to re-route service requests from selected service instances to others of the service instances where the monitoring component detects a fail-over condition in the selected service instances. In that regard, fail-over conditions can include error conditions and a performance deficiency conditions in which the performance of a selected service instance lags behind guaranteed levels of performance.
-
公开(公告)号：CA2228334A1
公开(公告)日：1998-08-19
申请号：CA2228334
申请日：1998-01-30
Applicant: IBM
Inventor： OVERBY LINWOOD HUGH , RAJARAMAN BALA , CAMPBELL SCOTT ALLAN , LONG LYNN DOUGLAS
IPC: G06F13/00 , G06F13/42 , H04L12/56 , H04L13/08 , H04L29/06 , H04L29/08 , H04L29/10 , H04L12/20 , H04L12/54
Abstract: Transmission control improves the performance in a communications system relating to transferring large data objects between domains or applications. This reduces or eliminates data movement between domains by transferring ownership of the "container" containing the data as opposed to moving the contents of the container from one domain to another domain resulting in copying the large data object. Thus, transmission control provides for control of the transmission of relatively large data objects between domains in a communications system which otherwise only allows efficient transmission of relatively small data objects between domains in a communications system. Tokens are assigned and associated with buffers containing the data to be shared. The token is not an address, but rather an identifier for the buffer which can be transferred from one domain to a second domain without requiring the copying of the data. The domain which originally requests the buffer is assigned a primary token and secondary tokens are assigned to each subsequent domain which also requests access to the buffer. A storage manager uniquely associates the buffer with the first domain and a primary token with the first buffer to permit the first domain to refer to the buffer. Secondary tokens are associated with the first buffer and subsequent domains also requesting the buffer. Thus, the buffer can be passed from the first domain to subsequent domains without physically moving the data. Once each domain is finished processing the data and the buffer is released by each domain, the buffer is released or reallocated and returned to a pool of available buffers. Alternatively, ownership of the buffer may be returned to the original domain that requested the buffer once processing of the buffer is completed by all domains.
-
公开(公告)号：CA2486434A1
公开(公告)日：2003-12-24
申请号：CA2486434
申请日：2003-06-09
Applicant: IBM
Inventor： LINDQUIST DAVID , TOPOL BRAD , TAN YIH-SHIN , RAJARAMAN BALA
Abstract: A computing services grid. The grid can include a service desk coupled to on e or more computing service instances. Each service instance can conform to an interface which is common to all service instances in the grid. A routing component can be disposed in the grid. Specifically, the routing component c an route individual service requests to individual ones of the service instance s. An instance selection service is used to satisfy QoS characteristics associated with the requestor of the service. The grid further can include a service instance monitoring component. The monitoring component can monitor the performance of individual service instances charged with processing individual service requests. Fail-over logic can be configured to re-route service requests from selected service instances to others of the service instances where the monitoring component detects a fail-over condition in th e selected service instances. In that regard, fail-over conditions can include error conditions and a performance deficiency conditions in which the performance of a selected service instance lags behind guaranteed levels of performance.
-
公开(公告)号：CA2229399A1
公开(公告)日：1998-08-19
申请号：CA2229399
申请日：1998-02-13
Applicant: IBM
Inventor： RAJARAMAN BALA , GUGLIOTTA DALE C , LONG LYNN DOUGLAS , OVERBY LINWOOD HUGH JR , CAMPBELL SCOTT ALLAN , MIYAKE MASASHI E
Abstract: Management of the processing of relatively large data objects in a communications stack having multiple layers improves the performance in a communications system in preparing relatively large data objects for transmission across a communications network. This reduces or eliminates data movement and copying during segmentation of the relatively large data objects into relatively small data objects, and appendage of headers to the relatively small data object segments during processing in the communications stack. A shared storage manager creates and controls multiple tokens representing multiple images of portions of the relatively large data objects to enable separate scheduling of the multiple images from the same storage unit or buffer to be passed from one layer in a communications stack to the next lower layer in the communications stack. The large data object is segmented into a plurality of relatively small data object segments at one or more of the layers in the communications stack. When dictated by the communications stack, header segments are also created for each relatively small data object segment. Each header segment contains specific information for the relatively small data object segment to which the header corresponds. A separate buffer list is generated by the communications stack for each relatively small data object segment and for each corresponding header segment.
-
公开(公告)号：CA2227366A1
公开(公告)日：1998-08-19
申请号：CA2227366
申请日：1998-01-16
Applicant: IBM
Inventor： STAGG ARTHUR JAMES , RAJARAMAN BALA , CAMPBELL SCOTT ALLAN , MIYAKE MASASHI E , GUGLIOTTA DALE C , MENDITTO LOUIS , LONG LYNN DOUGLAS , OVERBY LINWOOD HUGH JR
Abstract: Management of datastream construction prior to transmission of the datastream ac ross a channel of a communications system by providing for data blocking while reducing movement or copying of the data improves the performance in a communications system. Multipl e header segments received from a higher layer in the communications stack are copied int o the datastream header area of a datastream such that the header segments are sequentially store d in the datastream header area. A datastream buffer list having entries referencing the datastream header area is generated. Buffer list entries referencing data segments received from higher la yers in the communications stack are also stored in the datastream buffer list. The data seg ments are not physically moved or copied into the datastream during processing by the communic ations stack. Rather, a "virtual" datastream is generated by the communications stack for tran smission without physically moving or copying the data segment. The datastream is transmitted acr oss the channel by the system input/output interface by first writing the datastream header area re ferenced by the datastream buffer list directly into the channel, and the data segments directly from their original storage location into the channel of the communications system using the datastr eam buffer list entries.
-
-
-
-
-
-
Search Results
7
records
(took 0.017 seconds)
