Matthieu Perrin

Update Consistency for Wait-Free Concurrent Objects

In large scale systems such as the Internet, replicating data is an essential feature in order to provide availability and fault-tolerance. Attila and Welch proved that using strong consistency criteria such as atomicity is costly as each operation may need an execution time linear with the latency of the communication network. Weaker consistency criteria like causal consistency and PRAM consistency do not ensure convergence. The different replicas are not guaranteed to converge towards a unique state. Eventual consistency guarantees that all replicas eventually converge when the participants stop updating. However, it fails to fully specify the semantics of the operations on shared objects and requires additional non-intuitive and error-prone distributed specification techniques. This paper introduces and formalizes a new consistency criterion, called update consistency, that requires the state of a replicated object to be consistent with a linearization of all the updates. In other words, whereas atomicity imposes a linearization of all of the operations, this criterion imposes this only on updates. Consequently some read operations may return out-dated values. Update consistency is stronger than eventual consistency, so we can replace eventually consistent objects with update consistent ones in any program. Finally, we prove that update consistency is universal, in the sense that any object can be implemented under this criterion in a distributed system where any number of nodes may crash.

Causal consistency: beyond memory

In distributed systems where strong consistency is costly when not impossible, causal consistency provides a valuable abstraction to represent program executions as partial orders. In addition to the sequential program order of each computing entity, causal order also contains the semantic links between the events that affect the shared objects -- messages emission and reception in a communication channel, reads and writes on a shared register. Usual approaches based on semantic links are very difficult to adapt to other data types such as queues or counters because they require a specific analysis of causal dependencies for each data type. This paper presents a new approach to define causal consistency for any abstract data type based on sequential specifications. It explores, formalizes and studies the differences between three variations of causal consistency and highlights them in the light of PRAM, eventual consistency and sequential consistency: weak causal consistency, that captures the notion of causality preservation when focusing on convergence; causal convergence that mixes weak causal consistency and convergence; and causal consistency, that coincides with causal memory when applied to shared memory.

A Simple Object that Spans the Whole Consensus Hierarchy

This paper presents a simple generalization of the basic atomic read/write register object, whose genericity parameter spans the whole set of integers and is such that its k-parameterized instance has exactly consensus number k. This object, whose definition is pretty natural, is a sliding window register of size k. Its interest lies in its simplicity and its genericity dimension which provides a global view capturing the whole consensus hierarchy. Hence, this short article must be seen as a simple pedagogical introduction to Herlihys consensus hierarchy.

Speed for the Elite, Consistency for the Masses: Differentiating Eventual Consistency in Large-Scale Distributed Systems

Eventual consistency is a consistency model that emphasizes liveness over safety, it is often used for its ability to scale as distributed systems grow larger. Eventual consistency tends to be uniformly applied to an entire system, but we argue that there is a growing demand for differentiated eventual consistency requirements. We address this demand with UPS, a novel consistency mechanism that offers differentiated eventual consistency and delivery speed by working in pair with a two-phase epidemic broadcast protocol. We propose a closed-form analysis of our approachs delivery speed, and we evaluate our complete mechanism experimentally on a simulated network of one million nodes. To measure the consistency trade-off, we formally define a novel and scalable consistency metric that operates at runtime. In our simulations, UPS divides by more than 4 the inconsistencies experienced by a majority of the nodes, while reducing the average latency incurred by a small fraction of the nodes from 6 rounds down to 3 rounds.

On Composition and Implementation of Sequential Consistency

It has been proved that to implement a linearizable shared memory in synchronous message-passing systems it is necessary to wait for a time proportional to the uncertainty in the latency of the network for both read and write operations, while waiting during read or during write operations is sufficient for sequential consistency. This paper extends this result to crash-prone asynchronous systems. We propose a distributed algorithm that builds a sequentially consistent shared memory abstraction with snapshot on top of an asynchronous message-passing system where less than half of the processes may crash. We prove that it is only necessary to wait when a read/snapshot is immediately preceded by a write on the same process. We also show that sequential consistency is composable in some cases commonly encountered: 1) objects that would be linearizable if they were implemented on top of a linearizable memory become sequentially consistent when implemented on top of a sequential memory while remaining composable and 2) in round-based algorithms, where each object is only accessed within one round.

Separating Lock-Freedom from Wait-Freedom

A long-standing open question has been whether lock-freedom and wait-freedom are fundamentally different progress conditions, namely, can the former be provided in situations where the latter cannot? This paper answers the question in the affirmative, by proving that there are objects with lock-free implementations, but without wait-free implementations-using objects of any finite power. We precisely define an object called n-process long-lived approximate agreement (n-LLAA), in which two sets of processes associated with two sides, 0 or 1, need to decide on a sequence of increasingly closer outputs. We prove that 2-LLAA has a lock-free implementation using reads and writes only, while n-LLAA has a lock-free implementation using reads, writes and (n - 1)-process consensus objects. In contrast, we prove that there is no wait-free implementation of the n-LLAA object using reads, writes and specific (n - 1)-process consensus objects, called (n - 1)-window registers.

Tracking Causal Dependencies in Web Services Orchestrations Defined in ORC

This article shows how the operational semantics of a language like ORC can be instrumented so that the execution of a program produces information on the causal dependencies between events. The concurrent semantics we obtain is based on asymmetric labeled event structures. The approach is illustrated using a Web service orchestration instance and the detection of race conditions.