Hierarchical deablock detection for nested transactions
- 43 Downloads
In this paper, we propose an algorithm for detecting deadlocks in a distributed Nested Transaction. This algorthms does not require that the global wait-for graph be built and maintained nor that the edges of a global wait-for graph be followed in order for deadlocks to be detected. Our algorithm uses the fact that transactions are organized in a tree structure. Each transaction maintains a representative wait-for graph that summarizes the waiting conditions in the subtree below the transaction. Deadlocks can be detected by individually checking these condensed wait-for graph.
Key wordsDistributed databases Distributed transactions Nested transactions Deadlocks
Unable to display preview. Download preview PDF.
- 1.Beeri C, Bernstein P, Goodman N, Lai M, Shasha D: A concurrency control theory for Nested Transactions. Proc 2nd ACM SIGACT SIGOPS Symp on Principles of Distributed Computing (1983)Google Scholar
- 2.Bernsein P, Hadzilacos V, Goodman N: Concurrency control and recovery in database systems. Addison Wesley, USA 1987Google Scholar
- 3.Ceri S, Pelagatti G: Distributed database principles and systems. McGraw-Hill, New York 1984Google Scholar
- 4.Chandy M, Misra J, Haas L: Distributed deadlock detection. ACM Trans Comput Syst 2:144–156 (1983)Google Scholar
- 5.Lynch N, Merritt M: Introduction to the theory of nested transactions. International Conference on Database Theory. Rome, Italy, 1986Google Scholar
- 6.Mueller E, Moore J, Popek G: A Nested Transaction Mechanism for LOCUS. Proc. of Operating Systems Principles. Bretton Woods NH, 1983Google Scholar
- 7.Moss, E: Nested Transactions: an approach to reliable distributed computing. Res Rep Notes Inf Syst Cambridge, Mass. MIT Press, Cambridge, Mass. 1985Google Scholar
- 8.Spector A, Butcher J, Daniels D, Duchamp D, Eppinger J, Fineman C, Heddaya A: Support for distributed transactions in the TABS prototype. IEEE Trans Software Eng SE 11(6):520–530 (1985)Google Scholar