Showing papers by "Michael Merritt published in 1990"

Atomic snapshots of shared memory

Abstract: This paper introduces a general formulation of atonuc wzap~hot rnenzory, a shared memory partitioned into words written (apduted) by individual processes, or instantaneously read (scanned) in its entirety. Thk paw’ Presents three wait-free implementations of atomic snapshot A preliminary version of this paper appeared in Proceedings of the 9th Annaa[ ACM SVmpmnwn on Plznctptes of’ Distributed Compafing (Quebec city. Quebec, A%). ACM New York, 199Q pp. 1-14. H. Attiya’s and N. Shavit’s research was partially supported by National Science Foundation grant CCR-86-1 1442, by Office of Naval Research contract NW014-S5-K-0168, and by DARPA cmltracts NOO014-83-K-0125 and NOO014-89-J1988. E. Gafni’s research was partially supported by National Science Foundation Grant DCR 84-51396 and XEROX Co. grant W8S1111. Part of this work was done while N. Shavit was at Hebrew University, Jerusalem, visiting AT&T Bell Laboratories and the Theory of Distributed Systems Group at Massachusetts Institute of Technology, and while H. Attiya was at the LaboratoV for Computer Science at Massachusetts Institute of Technology. Authors’ present addresses: Y. Afek, Computer Science Department. Tel-Aviv University, Ramat-Aviv, Israel 69978; H. Attiya, Department of Computer Science, Technion, Haifa, Israel 3~000:” D Dolev, Department of computer Science, Hebrew University, Jerusalem, Israel 91904: E. Gafni, 3732 Boelter Hall, Computer Science Department, U. C. L.A., Los Angeles. Cahfornia 90024. M. Merritt, 600 Mountain Ave., Murray Hill. NJ 07974; N. Shavit, Laborato~ for Computer Scienee, MIT NE43, 367 Technology Square, Cambridge MA 02139. Permission to copy without fee all or part of this material is granted provided that the copies are not made or distributed for direct commercial advantage, the ACM copyright notice and the title of the publication and its date appear, and notice N gwen that copying is by permission of the Association for Computing Machinery. To copy otherwise, or to republish, requires a fee and/or specific permission. (!2 1993 ACM 0004-541 1/93/0900-0873 $01.50 Joumd of ihe Amocl.]tmn for Computmg Mdchmerv, Vd 40. No 4. Scptemhcr 1993. pp 873-89[1

Limitations of the Kerberos authentication system

Abstract: The Kerberos authentication system, a part of MIT's Project Athena, has been adopted by other organizations. Despite Kerberos's many strengths, it has a number of limitations and some weaknesses. Some are due to specifics of the MIT environment; others represent deficiencies in the protocol design. We discuss a number of such problems, and present solutions to some of them. We also demonstrate how special-purpose cryptographic hardware may be needed in some cases.

Completeness theorems for automata

Abstract: These notes present completeness results for varieties of products, state mappings and auxiliary variable constructions, for a (Mealy) automata-theoretic model of computation that generalizes the I/O automaton model of Lynch and Tuttle [Lyn88, LT87]. Conditions are examined under which these tools suffice to demonstrate that one specification implements another. The major theorem is a restatement of a completeness theorem due to Abadi and Lamport [AL88], translated from their (Moore) state machine model. The multivalued possibilities mappings of Lynch and Tuttle are used in place of the single-valued refinement mappings of Abadi and Lamport. A new kind of state mapping, prophecy mappings, is defined. Prophecy mappings are the time-reversal of possibilities mappings. This definition admits greater modularity in the proofs of Abadi and Lamport's results. Additional results explore properties of products of automata, developing more fully ideas implicit in Abadi and Lamport's work.

A Bounded First-In, First-Enabled Solution to the 1-Exclusion Problem

Abstract: This paper presents a solution to the first-in, first out l-exclusion problem of [FLBB79]. Unlike the solution in [FLBB79], this solution is achieved without the use of powerful readmodify-write synchronization primitives, and it requires only bounded size shared memory. Moreover, this solution has the extra property of being first-in, first-enabled, a property which subsumes first-in, first-out. Use of the concurrent time-stamp system of [DS89] is key in solving the problem within bounded size shared memory.

Easy Impossibility Proofs for Distributed Consensus Problems

Abstract: Easy proofs are given, of the impossibility of solving several consensus problems (Byzantine agreement, weak agreement, Byzantine firing squad, approximate agreement and clock synchronization) in certain communication graphs. It is shown that, in the presence ofm faults, no solution to these problems exists for communication graphs with fewer than 3m+1 nodes or less than 2m+1 connectivity. While some of these results had previously been proved, the new proofs are much simpler, provide considerably more insight, apply to more general models of computation, and (particularly in the case of clock synchronization) significantly strengthen the results.