Parameterized algorithm for replicated objects with local reads

TL;DR

This paper introduces a parameterized algorithm for implementing linearizable replicated objects with local reads in message-passing systems, achieving minimal read latency and adaptable performance based on system synchronization and message delays.

Contribution

It presents the first partially synchronous algorithm with local reads that can guarantee worst-case read times of , generalizing previous lease-based methods with adjustable parameters.

Findings

Reads are local and can be performed immediately when not conflicting.

The algorithm guarantees worst-case read times of  in partially synchronous systems.

Parameters can be tuned to optimize performance based on message delay characteristics.

Abstract

We consider the problem of implementing linearizable objects that support both read and read-modify-write (RMW) operations in message-passing systems with process crashes. Since in many systems read operations vastly outnumber RMW operations, we are interested in implementations that emphasize the efficiency of read operations. We present a parametrized algorithm for partially synchronous systems where processes have access to external clocks that are synchronized within $\epsilon$. With this algorithm, every read operation is local (intuitively, it does not trigger messages). If a read is not concurrent with a conflicting RMW, it is performed immediately with no waiting; furthermore, even with a concurrent conflicting RMW, a read experiences very little delay in the worst-case. For example, the algorithm's parameters can be set to ensure that every read takes $\epsilon$ time in the worst-case. To the best of our knowledge this is the first algorithm to achieve this bound in the partially synchronous systems that we assume here. Our parametrized algorithm generalizes the (non-parameterized) lease-based algorithm of Chandra et al. [6] where the worst-case time for reads is $3\delta$, where $\delta$ is the maximum message delay. The algorithm's parameters can be used to trade-off the worst-case times for read and RMW operations. They can also be used to take advantage of the fact that in many message-passing systems the delay of most messages is order of magnitudes smaller than the maximum message delay~$\delta$: for example, the parameters can be set so that, in "nice" periods where message delays are $\delta^* \ll \delta$, reads take at most $\epsilon$ time while RMWs take at most $3 \delta^*$ time.