A new algorithm to implement causal ordering

Schiper, André; Eggli, Jorge; Sandoz, Alain

doi:10.1007/3-540-51687-5_45

Cited by 108 publications

(55 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first protocols developed for the vector-clock-based approach by Birman et al in 1991 [17] (anticipated by Schiper et al [62] and Raynal 1 Vector clocks are compared as follows:…”

Section: Vector Clocksmentioning

confidence: 99%

Scalability approaches for causal multicast: a survey

et al. 2015

View full text Add to dashboard Cite

Many distributed services need to be scalable: internet search, electronic commerce, e-government... In order to achieve scalability those applications rely on replicated components. Because of the dynamics of growth and volatility of customer markets, applications need to be hosted by adaptive systems. In particular, the scalability of the reliable multicast mechanisms used for supporting the consistency of replicas is of crucial importance. Reliable multicast may propagate updates in a pre-defined order (e.g., FIFO, total or causal). Since total order needs more communication rounds than causal order, the latter appears to be the preferable candidate for achieving multicast scalability, although the consistency guarantees based on causal order are weaker than those of total order. This paper provides a historical survey of different scalability approaches for reliable causal multicast protocols.

show abstract

“…The first protocols developed for the vector-clock-based approach by Birman et al in 1991 [17] (anticipated by Schiper et al [62] and Raynal 1 Vector clocks are compared as follows:…”

Section: Vector Clocksmentioning

confidence: 99%

Scalability approaches for causal multicast: a survey

et al. 2015

View full text Add to dashboard Cite

show abstract

“…And the following relationship is defined: if z is an event in process Pi and b is an event in process Pj, then a b if and only if either (i) Ci(a) or (ii) Ci(b) an Pi →Pj. In other words the total ordering is a way of completing the happened before [13]. The total ordering of requests leads to ineffeciency due to more data movement and synchronization requirements than what a program may really call for.…”

Section: 3mentioning

confidence: 99%

Survey on the Event Orderings Semantics Used for Distributed System

Miaji¹,

Gazali²,

Hassan³

2010

IJCSIT

View full text Add to dashboard Cite

Abstract-Event ordering in distributed system (DS) is disputable and proactive subject in DS particularly with the emergence of multimedia synchronization. According to the literature, different type of event ordering is used for different DS mode such as asynchronous or synchronous. Recently, there are several novel implementation of these types introduced to fulfill the demand for establishing a certain order according to a specific criterion in DS with lighter complexity. Purpose -This paper demonstrates most significant implementation of types of event ordering in DS. Designing, methodology, approach -This paper firstly, present each type separately. Then it presents its implementation approaches. The comparison between those types is achieved later in the paper. Finding -Most types used in event ordering in DS share same properties with some delicate differences. However, some types which used for asynchronous mode cannot be used in the synchronous. Value -This paper is considered as a reference for scholars how desire to direct their research; develop potential investigation; or introduce new type of event orderings in DS. Keywords-component;Distributed system; event ordering; INTRODUCTIONA distributed system refers to a system that consists of a number of computers that do not share a memory or a clock and communicate with each other by exchanging messages over a communication network. A distributed operating system operates on multiple autonomous computers but appears to its users as a single machine. Figure ( Obviously, there are several benefits from using such system. Performance is improved and the cost is reduced with the exception of certain special computation intensive applications, equivalent computing power may be obtained with a network of workstations at a much lower cost than a traditional time-sharing system. Requests of services may be satisfied using hardware/software resources on other computers on the communication network which means an enormous increase in resource sharing [4]. Furthermore, concurrent execution of tasks and load distributing can lead to improved response time. Moreover, fault tolerance can be achieved through the replication of data and services. Finally, one distinct feature is new hardware and software resources can be added without replacing the existing resources which called as modular expandability [8].On the other hand, there are several drawbacks of using distributed system as highlighted next. The global knowledge problem which means that global state of the system is hard to acquire due to the unavailability of a global memory and a global clock and the unpredictability of message delays [10]. Naming is another problem which means the directory of all the named objects in the system (services, files, users, printers, etc.) must be maintained to allow proper access. Both schemes of replicated directories and partitioned directories have their strengths and weaknesses. Scalability which defined as any mechanisms or approaches adopted in a system must not resul...

show abstract

“…Receivers use the attached information to decide whether to deliver or delay a message. Applications can append different types of information; most use timestamps or sequence numbers [5,6,7,8,9]. Including this information in each message typically requires nodes to keep a view of the messages they have received and sent.…”

Section: Related Workmentioning

confidence: 99%

Decentralized Message Ordering for Publish/Subscribe Systems

Lumezanu

Spring

Bhattacharjee

2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We describe a method to order messages across groups in a publish/subscribe system without centralized control or large vector timestamps. We show that our scheme is practical-little state is required; that it is scalable-the maximum message load is limited by receivers; and that it performs well-the paths messages traverse to be ordered are not made much longer than necessary. Our insight is that only messages to groups that overlap in membership can be observed to arrive out of order: sequencing messages to these groups is sufficient to provide a consistent order, and when publishers subscribe to the groups to which they send, this message order is a causal order.

show abstract

A new algorithm to implement causal ordering

Cited by 108 publications

References 4 publications

Scalability approaches for causal multicast: a survey

Scalability approaches for causal multicast: a survey

Survey on the Event Orderings Semantics Used for Distributed System

Decentralized Message Ordering for Publish/Subscribe Systems

Contact Info

Product

Resources

About