Pageserver: High-Performance SSD-Based Checkpointing of Transactional Distributed Memory

Pageserver: High-Performance SSD-Based Checkpointing of Transactional Distributed Memory

The Rainbow cluster operating system provides fault tolerance by storing incremental checkpoints on a solid state disk (SSD) drive. As the access characteristics of SSD drives differ substantially from those of traditional magnetic hard disk drives (HDDs) new interesting techniques of storing checkp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gerhold, Steffen, Kaemmer, Nico, Weggerle, Alexander, Himpel, Christian, Schulthess, Peter
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Checkpointing
Clustering algorithms
Computer applications
Distributed computing
Drives
Hard disks
Java
Operating systems
Throughput
Time division multiplexing
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The Rainbow cluster operating system provides fault tolerance by storing incremental checkpoints on a solid state disk (SSD) drive. As the access characteristics of SSD drives differ substantially from those of traditional magnetic hard disk drives (HDDs) new interesting techniques of storing checkpoints in an elegant object-oriented fashion can be applied. The usage of transactional distributed memory (TDM) simplifies the distributed checkpointing algorithm as it automatically guarantees consistent checkpoints of the entire Rainbow cluster without additional coordination overhead.
DOI:10.1109/ICCEA.2010.53