A Crash Recovery Scheme for a Memory-Resident Database System
IEEE Transactions on Computers
The ObjectStore database system
Communications of the ACM
ACM Transactions on Database Systems (TODS)
Crash recovery in client-server EXODUS
SIGMOD '92 Proceedings of the 1992 ACM SIGMOD international conference on Management of data
MLR: a recovery method for multi-level systems
SIGMOD '92 Proceedings of the 1992 ACM SIGMOD international conference on Management of data
ARIES/CSA: a method for database recovery in client-server architectures
SIGMOD '94 Proceedings of the 1994 ACM SIGMOD international conference on Management of data
Fine-grained sharing in a page server OODBMS
SIGMOD '94 Proceedings of the 1994 ACM SIGMOD international conference on Management of data
Shoring up persistent applications
SIGMOD '94 Proceedings of the 1994 ACM SIGMOD international conference on Management of data
PODS '90 Proceedings of the ninth ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems
The Architecture of the Dalí Main-Memory Storage Manager
Multimedia Tools and Applications
Implementation techniques for main memory database systems
SIGMOD '84 Proceedings of the 1984 ACM SIGMOD international conference on Management of data
System M: A Transaction Processing Testbed for Memory Resident Data
IEEE Transactions on Knowledge and Data Engineering
Main Memory Database Systems: An Overview
IEEE Transactions on Knowledge and Data Engineering
An Evaluation of Starburst's Memory Resident Storage Component
IEEE Transactions on Knowledge and Data Engineering
VLDB '91 Proceedings of the 17th International Conference on Very Large Data Bases
Recovering from Main-Memory Lapses
VLDB '93 Proceedings of the 19th International Conference on Very Large Data Bases
Dalí: A High Performance Main Memory Storage Manager
VLDB '94 Proceedings of the 20th International Conference on Very Large Data Bases
Database recovery using incomplete page versions in a multisystem data sharing environment
Information Processing Letters
Recovery in Distributed Extended Long-lived Transaction Models
DASFAA '99 Proceedings of the Sixth International Conference on Database Systems for Advanced Applications
Fault Tolerance in Three-Tier Applications: Focusing on the Database Tier
SRDS '99 Proceedings of the 18th IEEE Symposium on Reliable Distributed Systems
An almost-serial protocol for transaction execution in main-memory database systems
VLDB '02 Proceedings of the 28th international conference on Very Large Data Bases
| Hi-index | 0.00 |
In this paper we present recovery techniques for distributed main-memory databases, specifically forclient-server and shared-disk architectures. We present a recoveryscheme for client-server architectures which is based on shipping logrecords to the server, and two recovery schemes for shared-diskarchitectures—one based on page shipping, and the other based onbroadcasting of the log of updates. The schemes offer differenttradeoffs, based on factors such as update rates.Our techniques are extensions to a distributed-memory setting of acentralized recovery scheme for main-memory databases, which has beenimplemented in the Dalì main-memory database system. Ourcentralized as well as distributed-memory recovery schemes haveseveral attractive features—they support an explicitmulti-level recovery abstraction for high concurrency, reduce diskI/O by writing only redo log records to diskduring normal processing, and use per-transaction redo and undo logsto reduce contention on the system log. Further, the techniques use afuzzy checkpointing scheme that writes only dirty pages to disk, yetminimally interferes with normal processing—all but one of ourrecovery schemes do not require updaters to even acquire a latchbefore updating a page. Our log shipping/broadcasting schemes alsosupport concurrent updates to the same page at different sites.