No abstract

The power of two well-known consistency conditions for shared-memory multiprocessors, sequential consistency and linearizability , is compared. The cost measure studied is the worst-case response time in distributed implementations of virtual shared memory supporting one of the two conditions. Three types of shared-memory objects are considered: read/write objects, FIFO queues, and stacks. If clocks are only approximately synchronized (or do not exist), then for all three object types it is shown that linearizability is more expensive than sequential consistency. We show that, for all three data types, the worst-case response time is very sensitive to the assumptions that are made about the timing information available to the system. Under the strong assumption that processes have perfectly synchronized clocks, it is shown that sequential consistency and linearizability are equally costly. We present upper bounds for linearizability and matching lower bounds for sequential consistency. The upper bounds are shown by presenting algorithms that use atomic broadcast in a modular fashion. The lower-bound proofs for the approximate case use the technique of “shifting,” first introduced for studying the clock synchronization problem.

We initiate a study of bounded clock synchronization under a more severe fault model than that proposed by Lamport and Melliar-Smith LM-85 . Realistic aspects of the problem of synchronizing clocks in the presence of faults are considered. One aspect is that clock synchronization is an on-going task, thus the assumption that in any period of the execution at least two thirds of the processors are nonfaulty is too optimistic. To cope with this reality w e suggest self-stabilizing protocols that stabilize in any long enough period in which less than a third of the processors are faulty. Another aspect is that the clock v alue is bounded. A single transient fault may cause the clock to reach the upper bound. Therefore we suggest a bounded clock that wraps around when appropriate.We present t w o randomized self-stabilizing protocols for synchronizing bounded clocks in the presence of Byzantine processor failures. The rst protocol assumes that processors have a common pulse, while the second protocol does not. A new type of distributed counter based on the Chinese remainder theorem is used as part of the rst protocol.

No abstract

No abstract