Dynamic Scalable State Machine Replication

Le, Long Hoang; Bezerra, Carlos Eduardo; Pedone, Fernando

doi:10.1109/dsn.2016.11

Cited by 19 publications

(16 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Objective function (lines [21][22][23][24][25][26]. The restrictions imposed by the constraints may be satisfied by several associations of threads to classes.…”

Section: The Optimization Modelmentioning

confidence: 99%

Early Scheduling in Parallel State Machine Replication

Alchieri

Dotti

Pedone

2018

Proceedings of the ACM Symposium on Cloud Computing

Self Cite

View full text Add to dashboard Cite

State machine replication is standard approach to fault tolerance. One of the key assumptions of state machine replication is that replicas must execute operations deterministically and thus serially. To benefit from multi-core servers, some techniques allow concurrent execution of operations in state machine replication. Invariably, these techniques exploit the fact that independent operations (those that do not share any common state or do not update shared state) can execute concurrently. A promising category of solutions trades scheduling freedom for simplicity. This paper generalizes this category of scheduling solutions. In doing so, it proposes an automated mechanism to schedule operations on worker threads at replicas. We integrate our contributions to a popular state machine replication framework and experimentally compare the resulting system to more classic approaches.

show abstract

“…Objective function (lines [21][22][23][24][25][26]. The restrictions imposed by the constraints may be satisfied by several associations of threads to classes.…”

Section: The Optimization Modelmentioning

confidence: 99%

Early Scheduling in Parallel State Machine Replication

Alchieri

Dotti

Pedone

2018

Proceedings of the ACM Symposium on Cloud Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…A third group of works aims to scale SMR-based services by dividing their state among several partitions, implemented by (mostly) independent RSMs [10], [18], [27], [38], [51]. Bezerra et al [10] propose a technique for executing atomic operations spanning multiple partitions still ensuring linearizability.…”

Section: Smr Scalabilitymentioning

confidence: 99%

“…Bezerra et al [10] propose a technique for executing atomic operations spanning multiple partitions still ensuring linearizability. This work was later extended for optimizing data placement in the partition for decreasing the amount of multi-partition operations [38]. Padilha and Pedone propose Augustus [51], a storage architecture that follows a partition approach and tolerates Byzantine faults.…”

Section: Smr Scalabilitymentioning

confidence: 99%

“…A recent line of work proposes partitioning of the SMR-based systems in multiple Replicated State Machines (RSMs) [10], [18], [27], [38], [51] for addressing (3). Although partitioning solves the scalability of SMR, the existing solutions are quite limited in terms of elasticity, i.e., the capacity to dynamically increase (scaleout) and decrease (scale-in) the number of partitions at runtime.…”

Section: Introductionmentioning

confidence: 99%

“…Although partitioning solves the scalability of SMR, the existing solutions are quite limited in terms of elasticity, i.e., the capacity to dynamically increase (scaleout) and decrease (scale-in) the number of partitions at runtime. More specifically, some scalable systems consider only static partitions [10], [38], [51], with no elasticity at all, while others [18], [27] provide dynamic partitioning through ad-hoc protocols that are executed in the background to avoid performance disruption,…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Elastic State Machine Replication

Nogueira

Casimiro

Bessani

2017

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

State machine replication (SMR) is a fundamental technique for implementing stateful dependable systems. A key limitation of this technique is that the performance of a service does not scale with the number of replicas hosting it. Some works have shown that such scalability can be achieved by partitioning the state of the service into shards. The few SMR-based systems that support dynamic partitioning implement ad-hoc state transfer protocols and perform scaling operations as background tasks to minimize the performance degradation during reconfigurations. In this work we go one step further and propose a modular partition transfer protocol for creating and destroying such partitions at runtime, thus providing fast elasticity for crash and Byzantine fault tolerant replicated state machines and making them more suitable for cloud systems.

show abstract

Hybrid neural state machine for neural network

Tian

Wu²,

2021

Sci. China Inf. Sci.

View full text Add to dashboard Cite

The integration of computer-science-oriented and neuroscience-oriented approaches is believed to be a promising way for the development of artificial general intelligence (AGI). Recently, a hybrid Tianjic chip that integrates both approaches has been reported, providing a general platform to facilitate the research of AGI. The control algorithm for handling various neural networks is the key to this platform; however, it is still primitive. In this work, we propose a hybrid neural state machine (H-NSM) framework that can efficiently cooperate with artificial neural networks and spiking neural networks and control the workflows to accomplish complex tasks. The H-NSM receives input from different types of networks, makes decisions according to the fusing of various information, and sends control signals to the sub-network or actuator. The H-NSM can be trained to adapt to context-aware tasks or sequential tasks, thereby improving system robustness. The training algorithm works correctly even if only 50% of the forced state information is provided. It achieved performance comparable to the optimum algorithm on the Tower of Hanoi task and achieved multiple tasks control on a self-driving bicycle. After only 50 training epochs, the transfer accuracy reaches 100% in the test case. It proves that H-NSM has the potential to advance control logic for hybrid systems, paving the way for designing complex intelligent systems and facilitating the research towards AGI.

show abstract

Dynamic Scalable State Machine Replication

Cited by 19 publications

References 30 publications

Early Scheduling in Parallel State Machine Replication

Early Scheduling in Parallel State Machine Replication

Elastic State Machine Replication

Hybrid neural state machine for neural network

Contact Info

Product

Resources

About