Asynchronous Reconfiguration for Paxos State Machines

Jehl, Leander; Meling, Hein

doi:10.1007/978-3-642-45249-9_8

Cited by 7 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We focus on leader election because even at low message rates, a leader can become a bottleneck for end-to-end system performance. For reconfiguration, we point readers to protocols from prior work [35,43,44] which could be adapted for this setting.…”

Section: On Demand Applicationsmentioning

confidence: 99%

The Case For In-Network Computing On Demand

Tokusashi

Dang

Pedone

et al. 2019

Proceedings of the Fourteenth EuroSys Conference 2019

View full text Add to dashboard Cite

Programmable network hardware can run services traditionally deployed on servers, resulting in orders-of-magnitude improvements in performance. Yet, despite these performance improvements, network operators remain skeptical of in-network computing. The conventional wisdom is that the operational costs from increased power consumption outweigh any performance benefits. Unless in-network computing can justify its costs, it will be disregarded as yet another academic exercise. In this paper, we challenge that assumption, by providing a detailed power analysis of several in-network computing use cases. Our experiments show that in-network computing can be extremely power-efficient. In fact, for a single watt, a software system on commodity CPU can be improved by a factor of ×100 using an FPGA, and a factor of ×1000 utilizing ASIC implementations. However, this efficiency depends on the system load. To address changing workloads, we propose in-network computing on demand, where services can be dynamically moved between servers and the network. By shifting the placement of services on-demand, data centers can optimize for both performance and power efficiency.

show abstract

Section: On Demand Applicationsmentioning

confidence: 99%

The Case For In-Network Computing On Demand

Tokusashi

Dang

Pedone

et al. 2019

Proceedings of the Fourteenth EuroSys Conference 2019

View full text Add to dashboard Cite

show abstract

“…Consensus-based reconfiguration of an RSM was proposed in both [23,24] and has also been deployed in production systems [25]. In our previous work, we showed that an RSM can be reconfigured without relying on consensus [26]. In retrospect this work can be viewed as an application of SmartMerge.…”

Section: Related Workmentioning

confidence: 95%

SmartMerge: A New Approach to Reconfiguration for Atomic Storage

Jehl

Vitenberg

Meling

2015

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

International audienceIn this paper, we study reconfiguration mechanisms for atomic storage systems. We observe that the state of the art approach for reconfiguration in an asynchronous environment has several disadvantages compared to the classical consensus-based approach, which requires eventual synchrony. For example, an unfortunate combination of remove operations may lead to a configuration with too few or even no processes. We present SmartMerge, a novel approach that provides most of the benefits of consensus-based reconfiguration, yet can be implemented in a fully asynchronous system. SmartMerge utilizes a merge function to aptly combine concurrently issued changes to both the set of processes and the quorum system of the storage. The approach is general and can use any suitable function.In addition to the expressive reconfiguration policies enabled by SmartMerge, our atomic storage also has improved efficiency: Every reconfiguration imposes only a constant overhead on concurrent read and write operations

show abstract

“…Additionally, Matchmaker Paxos [44] is a more recent approach for reconfiguration in Paxos based protocols that adds dedicated nodes for managing reconfigurations, which decouples reconfiguration from the main processing path, preventing performance degradation during configuration changes. There has also been prior work on reconfiguration using weaker models than consensus [15], and approaches to logless implementations of Paxos based replicated state machine protocols [34], which bear conceptual similarities to our logless protocol for managing configuration state.…”

Section: Related Workmentioning

confidence: 99%

Design and Analysis of a Logless Dynamic Reconfiguration Protocol

Schultz¹,

Zhou²,

Ian³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a novel dynamic reconfiguration protocol for the MongoDB replication system that extends and generalizes the single server reconfiguration protocol of the Raft consensus algorithm. Our protocol decouples the processing of configuration changes from the main database operation log, which allows reconfigurations to proceed in cases when the main log is prevented from processing new operations. Additionally, this decoupling allows for configuration state to be managed by a logless replicated state machine, by optimizing away the explicit log and storing only the latest version of the configuration, avoiding the complexities of a log-based protocol. We provide a formal specification of the protocol along with results from automated verification of its safety properties. We also provide an experimental evaluation of the protocol benefits, showing how reconfigurations are able to quickly restore a system to healthy operation in scenarios where node failures have stalled the main operation log.

show abstract

Asynchronous Reconfiguration for Paxos State Machines

Cited by 7 publications

References 10 publications

The Case For In-Network Computing On Demand

The Case For In-Network Computing On Demand

SmartMerge: A New Approach to Reconfiguration for Atomic Storage

Design and Analysis of a Logless Dynamic Reconfiguration Protocol

Contact Info

Product

Resources

About