Fault-Tolerant Sequencer: Specification and an Implementation (original) (raw)
Related papers
A fault-tolerant sequencer for timed asynchronous systems
2002
In this paper we present the specification of a sequencer service that allows independent processes to get a sequence number that can be used to label successive operations (eg to allow a set of independent and concurrent processes to get a total order on their operations). Moreover, we provide an implementation of the sequencer service in a specific partially synchronous distributed system, namely the timed asynchronous model.
On Composition and Implementation of Sequential Consistency (Extended Version)
ArXiv, 2016
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 w...
Synchronization with eventcounts and sequencers
Communications of the ACM, 1979
Synchronization of concurrent processes requires controlling the relative ordering of events in the processes. A new synchronization mechanism is proposed, using abstract objects called eventcounts and sequencers, that allows processes to control the ordering of events directly, rather than using mutual exclusion to protect manipulations of shared variables that control ordering of events. Direct control of ordering seems to simplify correctness arguments and also simplifies implementation in distributed systems. The mechanism is defined formally, and then several examples of its use are given. The relationship of the mechanism to protection mechanisms in the system is explained; in particular, eventcounts are shown to be applicable to situations where confinement of information matters. An implementation of eventcounts and sequencers in a system with shared memory is described.
Decentralized Runtime Enforcement of Message Sequences in Message-Based Systems
2020
In the new generation of message-based systems such as network-based smart systems, distributed components collaborate via asynchronous message passing. In some cases, particular ordering among the messages may lead to violation of the desired properties such as data confidentiality. Due to the absence of a global clock and usage of off-the-shelf components, there is no control over the order of messages at design time. To make such systems safe, we propose a choreography-based runtime enforcement algorithm that given an automata-based specification of unwanted message sequences, prevents certain messages to be sent, and assures that the unwanted sequences are not formed. Our algorithm is fully decentralized in the sense that each component is equipped with a monitor, as opposed to having a centralized monitor. As there is no global clock in message-based systems, the order of messages cannot be determined exactly. In this way, the monitors behave conservatively in the sense that th...
Sequentialization and Synchronization for Distributed Programs
2017
Author(s): Bakst, Alexander Goldberg | Advisor(s): Jhala, Ranjit | Abstract: Distributed systems are essential for building services that can handle the ever increasing number of people and devices connected to the internet as well as the associated growth in data accumulation. However, building distributed programs is hard, and building confidence in the correctness of an algorithm or implementation is harder still. One fundamental reason is the highly asynchronous nature of distributed execution. Timing differences caused by network delays and variation in compute power can trigger behaviors that were unanticipated by the programmer.Unfortunately, techniques for building confidence are all up against the same problem: the combinatorial explosion in the number of behaviors of a distributed system. Testing and model checking techniques can not hope to weed out all behaviors when the state space is infinite. At the other end of the spectrum, constructing proofs by hand is a daunting ...
Fault-Tolerant Asynchronous Networks
IEEE Transactions on Computers, 2000
tuple {IB, SB, OB, 5B, WB} where IB, SB, OB are the sets of binary k-tuples, n-tuples, and p-tuples called input, state, and II. NECESSARY AND SUFFICIENT CONDITIONS output sets [these are the different values the xi, yi, and zi In the following we present some definitions for introducing can take (refer to ], and SB, CB are the next-state and certain notations. Although these notations are presented in output functions reference to asynchronous sequential machines, they are appli-8B SB X IB SB cable to all sequential machines, synchronous or asynchronous.
Total order communications over asynchronous distributed systems: Specifications and implementations
During the last two decades the design and development of total order (TO) communications has been one of the main research topics in dependable distributed computing. The huge amount of research work has produced several TO specifications and a wide variety of TO implementations with different guarantees whose differences are often left hidden or unclear. This paper presents a systematic classification of six distinct TO specifications based on a well-defined formal framework. The classification allows us (i) to define in a formal way the differences among the behaviors of faulty and correct processes admitted by each specification, and (ii) to derive a methodology that enables the classification of TO implementations with respect to their enforced specification. The paper also discusses the impact of TO specifications on the design of application logics. The methodology is then used to formally study the properties of eight variations of TO implementations based on a fixed sequencer given in a well-known context, namely primary component group communication systems.
Timestamping messages and events in a distributed system using synchronous communication
Distributed Computing, 2006
Determining order relationship between events of a distributed computation is a fundamental problem in distributed systems which has applications in many areas including debugging, visualization, checkpointing and recovery. Fidge/Mattern's vector-clock mechanism captures the order relationship using a vector of size N in a system consisting of N processes. As a result, it incurs message and space overhead of N integers. Many distributed applications use synchronous messages for communication. It is therefore natural to ask whether it is possible to reduce the timestamping overhead for such applications. In this paper, we present a new approach for timestamping messages and events of a synchronously ordered computation, that is, when processes communicate using synchronous messages.
Proceedings of the 8th Workshop on Principles and Practice of Consistency for Distributed Data, 2021
This work focuses on shared memory systems with a read-write interface (e.g., distributed datastores or multiprocessors). At the heart of such systems resides a protocol responsible for enforcing their consistency guarantees. Designing a protocol that correctly and efficiently enforces consistency is a very challenging task. Our overarching vision is to automate this task. In this work we take a step towards this vision by establishing the theoretical foundation necessary to automatically infer a protocol from a consistency specification. Specifically, we propose a set of mathematical abstractions, called real-time orderings (rt-orderings), that model the protocol. We then create a mapping from consistency guarantees to the minimal rt-orderings that enforce the guarantees. Finally, we informally relate the rt-orderings to protocol implementation techniques. Consequently, rt-orderings serve as an intermediate abstraction between consistency and protocol design, that enables the autom...