Coordinated Resource Recovery in VM/ESA

Abstract

A system service for coordinated recovery of resources Is a critical function needed for distributed processing environments because applications need to provide for data integrity while the location of the data and processes are transparent to the application. VM Is the first IBM operating system to provide Coordinated Resource Recovery as a system service rather than as a service provided by unique environments running on the operating system, and the VM Common Programming InterfaceCommunications and Shared File System are the first subsystems to utilize the service. This paper is an overview of why and how VM provided Coordinated Resource Recovery (CRR). CRR is the implementation of the Systems Application Architecture™ (SAA™) resource recovery interface within Virtual Machine/Enterprise Systems Architecture™ (VM/ESA™). This coordinated sync point system service allows one or more applications or subsystems to update multiple resources and to request that all updates be committed or backed out together. The applications and their respective resources can be local or distributed. CRR either coordinates the request to commit or backout immediately, or supports automatic resource resynchronization in case a system or subsystem fails. When restart is not possible, CRR allows for intervention by a system operator or administrator.S upport has long been provided within IBM for the resource recovery requirements of database and data communication objects (e.g., relational tables, files, conversations) controlled by the subsystems IMS/vS, CICS, SQLlDS, and DB2™ in the transaction environments of the MVSIESA™ and VSE operating systems. 1 The main benefit of resource recovery has been integrity for the sup-72 MASLAK, SHOWALTER, AND SZCZYGIELSKI

Two-phase commit optimizations in a commercial distributed environment

“…The PN design effort was done independently from the 2PC effort [34]. PN was designed and developed for the commercial environment and, so far, IBM has implemented it in CICS/MVS 4 [6], and VM/ESA [20].…”

“…For the failure cases (hopefully, rare) where the protocol outcome is blocked, certain participants might choose not to wait for recovery processing to discover the outcome because of valuable locks being held [23,20]. Rather than waiting, these participants unilaterally commit or abort the transaction.…”

VM/ESA support for coordinated recovery of files

“…Copying in printed form for private use is permitted without payment of royalty provided that (I) each reproduction is done without alteration and (2) the Journal reference and IBM copyright notice are included on the first page. For recoverable resources, all processing of the resource in the context of one CMS work unit is treated as an ©Copyright 1991 by International Business Machines Corporation.…”

A method for the recovery of data after a computer system failure: the development of Constant Random Access Memory (CRAM) Recovery System

“…Computer reliability, the causes and solution to hardware and software failures and, data loss and procedures to restore data are all current research topics (Levy & Silberschatz, 1991). Industry is making demands on developers to develop fail-safe systems by introducing recovery systems, such as a resource recovery system (Bacon, 1991;Klopp, 1990;Maslak, Showalter & Szczygielski, 1991;Tam & Hsu, 1990) and…”