Skip to main content

User account menu

  • Log in
DBS-Logo

Database Group Leipzig

within the department of computer science

ScaDS-Logo Logo of the University of Leipzig

Main navigation

  • Home
  • Study
    • Exams
      • Hinweise zu Klausuren
    • Courses
      • Current
    • Modules
    • LOTS-Training
    • Abschlussarbeiten
    • Masterstudiengang Data Science
    • Oberseminare
    • Problemseminare
    • Top-Studierende
  • Research
    • Projects
      • Benchmark datasets for entity resolution
      • FAMER
      • HyGraph
      • Privacy-Preserving Record Linkage
      • GRADOOP
    • Publications
    • Prototypes
    • Annual reports
    • Cooperations
    • Graduations
    • Colloquia
    • Conferences
  • Team
    • Erhard Rahm
    • Member
    • Former employees
    • Associated members
    • Gallery

Use of Global Extended Memory for Distributed Transaction Processing,

Breadcrumb

  • Home
  • Research
  • Publications
  • Use of Global Extended Memory for Distributed Transaction Processing,

Rahm, E.

Use of Global Extended Memory for Distributed Transaction Processing,

Proc. 4th Int. Workshop on High Performance Transaction Systems, Asilomar (CA), USA, Sep. 1991

1991

Paper

Futher information: https://dbs.uni-leipzig.de/sd,pdbs

Abstract

In current mainframe architectures, extended memory is used as a pageaddressable main memory extension to improve I/O performance. If made non-volatile, extended memory can significantly increase transaction processing performance. In this paper, we study how locally distributed transaction systems may use shared extended memory to support high transaction rates and short response times. We outline how a specific store called GEM (Global Extended Memory) can be utilized to improve I/O performance
and inter-system communication and cooperation. It turns out that
distributed transaction systems of the “shared disk” type (data sharing systems) can benefit most from such a shared store. We describe simple yet efficient schemes using GEM for global concurrency control and constructing a global log file for such systems.

Recent publications

  • 2025 / 8: Slice it up: Unmasking User Identities in Smartwatch Health Data
  • 2025 / 6: SecUREmatch: Integrating Clerical Review in Privacy-Preserving Record Linkage
  • 2025 / 5: Federated Learning With Individualized Privacy Through Client Sampling
  • 2025 / 3: Assessing the Impact of Image Dataset Features on Privacy-Preserving Machine Learning
  • 2025 / 3: Automated Configuration of Schema Matching Tools: A Reinforcement Learning Approach

Footer menu

  • Directions
  • Contact
  • Impressum