Performance optimization for data sharing across batch...

Details Performance optimization for data sharing across batch... Performance optimization for data sharing across batch...

1999-05-12

2004-05-04

Follansbee, John (Department: 2126)

Electrical computers and digital processing systems: multicomput

Computer-to-computer data routing

Least weight routing

Reexamination Certificate

active

06732137

ABSTRACT:

FIELD OF THE INVENTION
The present invention relates to data sharing in a multiple data processing system arrangement, and more particularly to data sharing across batch sequential processes and on-line transaction processes in a clustered data processing system arrangement.
BACKGROUND OF THE INVENTION
In today's information technology industry, customers desire systems that have better performance and cost improvements over their current systems, while permitting continued use of their existing applications. High availability is also important given today's rising mobile workforce and ability for global connectivity through the Internet. Current processing system designs for information technology applications must provide scalable, granular growth, and continuous application availability. Clustering technology, such as IBM Corporation's S/390 Parallel Sysplex, has been developed to achieve these design needs.
A cluster arrangement links individual data processing systems in a manner that creates a single, powerful system, which can support numerous users simultaneously. A cluster offers high availability and excellent scalability. If one system
ode in the cluster fails, the other systems in the cluster continue to run.
FIG. 1
illustrates a cluster arrangement, e.g., a parallel sysplex system. Multiple systems
10
, e.g., System
1
to System N, are included in the sysplex, where each system
10
has one or more computing processors
12
and memory with local caches
14
. By way of example, the System/390 Parallel Sysplex from IBM Corporation, Armonk, NY, is an example of a set of S/390 systems connected together by a clustering technology. An instance of the operating system, OS/390, runs on each system of the sysplex. Each of the systems access DASD (direct access storage device)
20
that is shared among the systems. The clustered system support enables large business applications to be spread across the multiple systems with dynamic workload balancing, which yields a wide range of application capacity scaling and extremely high application availability across planned and unplanned outage of individual systems. The load-balancing and availability features of parallel sysplex result in an application running on one system at one point in time and then run on another system at another point in time. To help facilitate the activity, the systems
10
are each coupled to an external time reference component
16
and a coupling facility
18
. Connections to DASD subsystems
20
are facilitated through a dynamic switch
22
.
Key elements of the S/390 sysplex technology are hardware and software functions/services that support data sharing. The OS/390 VSAM (virtual storage access method) file management system has been extended to exploit this technology in a product capability called VSAM RLS (record level sharing). VSAM RLS is a generally available function that enables multi-system sharing of VSAM files for CICS (customer information control system) applications. An extension of the file management system of VSAM RLS enables application sharing for batch programs concurrent with transaction programs. While the basic functions to read/write share the data with fill integrity and availability are possible to achieve, significant overhead is incurred for the batch application programs. The overhead includes having to link to the central file management server on each record access and having to lock each record within the batch being processed.
While the basic functions do produce sharing capabilities for batch and on-line/transactional processes, unfortunately, the high performance normally associated with a batch sequential process through extensive read-ahead and deferred writing of data within the application memory space is severely degraded.
Accordingly, a need exists for a technique that achieves concurrent access to file data by batch sequential processes and transaction processes that avoids inefficiency and elongated run-times. The present invention addresses such a need.
SUMMARY OF THE INVENTION
The present invention provides for data sharing across batch sequential processes and on-line transactional processes in a clustered arrangement of multiple data processing systems. In a method aspect, the method includes performing on-line transaction process accesses and batch sequential process accesses on record data. The method further includes utilizing a dual-level locking protocol for the on-line transaction process accesses and batch sequential process accesses to achieve substantially concurrent accessibility to the record data with minimized processing overhead for the batch sequential processes.


REFERENCES:
patent: 5109512 (1992-04-01), Bahr et al.
patent: 5115392 (1992-05-01), Takamoto et al.
patent: 5557792 (1996-09-01), Josten et al.
patent: 5668993 (1997-09-01), Peters et al.
Kataoka, A Multiversion Concurrency Control Algorithm for Concurrent Execution of Partial Updatre and Bulk Retrieval Transactions , 1991, JaPan, p. 130-136.*
IBM Technical Disclosure Bullentin, Lock Management Architecture, Oct. 1988, vol. No.: 5, Pager No. 125-128.*
Kataoka, A Multiversion Concurrency Control Algorithm for Concurrent Execution of Partial Update and Bulk Retrieval Transactions, 1991, JaPan, p. 130-136.*
IBM Technical Disclosure Bullentin, Lock Management Architecture, Oct. 1988, vol. No.:5, p. No. 125-128.

Affiliated with

Also associated with

Rating

Performance optimization for data sharing across batch... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Performance optimization for data sharing across batch..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Performance optimization for data sharing across batch... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3235463