On multiversion replication control in distributed systems
Computer Systems Science and Engineering
Distributed snapshots: determining global states of distributed systems
ACM Transactions on Computer Systems (TOCS)
Reliability mechanisms for SDD-1: a system for distributed databases
ACM Transactions on Database Systems (TODS)
On the Optimum Checkpoint Interval
Journal of the ACM (JACM)
An optimal algorithm for mutual exclusion in computer networks
Communications of the ACM
Time, clocks, and the ordering of events in a distributed system
Communications of the ACM
The notions of consistency and predicate locks in a database system
Communications of the ACM
SIGMOD '81 Proceedings of the 1981 ACM SIGMOD international conference on Management of data
On totally ordering checkpoints in distributed data bases
SIGMOD '82 Proceedings of the 1982 ACM SIGMOD international conference on Management of data
An Adaptive Checkpointing Scheme for Distributed Databases with Mixed Types of Transactions
Proceedings of the Fourth International Conference on Data Engineering
PODC '83 Proceedings of the second annual ACM symposium on Principles of distributed computing
What have we learnt from using real parallel machines to solve real problems?
C3P Proceedings of the third conference on Hypercube concurrent computers and applications - Volume 2
| Hi-index | 0.00 |
The goal of checkpointing in database management systems is to save database states on a separate secure device so that the database can be recovered when errors and failures occur. This paper presents a non-interfering checkpointing mechanism being developed for ADAMS. Instead of waiting for a consistent state to occur, our checkpointing approach constructs a state that would result by completing the transactions that are in progress when the global checkpoint begins. The checkpointing algorithm is executed concurrently with transaction activity while constructing a transaction-consistent checkpoint on disk, without requiring the database quiesce. This property of non-interference is highly desirable to real-time applications, where restricting transaction activity during the checkpointing operation is in many cases not feasible. Two main properties of this checkpointing algorithm are global consistency and reduced interference, both of which are crucial for achieving high availability.