A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Fast Flexible Paxos: Relaxing Quorum Intersection for Fast Paxos
[article]
2020
arXiv
pre-print
In this paper we observe that Fast Paxos' intersection requirements can be safely relaxed, reducing to just one additional intersection requirement between phase-1 quorums and any pair of fast round phase ...
Multi-Paxos reduces this to one phase by electing a leader but this leader is also a performance bottleneck. Fast Paxos bypasses the leader but has stronger quorum intersection requirements. ...
The resulting algorithm, which we refer to as Fast Flexible Paxos, relaxes the quorum intersection requirements of Fast Paxos. ...
arXiv:2008.02671v2
fatcat:f3gksa7otzdztdvufsgubydkda
Paxos Made EPR: Decidable Reasoning about Distributed Protocols
[article]
2017
arXiv
pre-print
We have used our methodology to verify the safety of Paxos, and several of its variants, including Multi-Paxos, Vertical Paxos, Fast Paxos, Flexible Paxos and Stoppable Paxos. ...
To the best of our knowledge, this work is the first to verify these protocols using a decidable logic, and the first formal verification of Vertical Paxos, Fast Paxos and Stoppable Paxos. ...
Flexible Paxos Flexible Paxos [Howard et al. 2016] extends Paxos based on the observation that it is only necessary for safety that every phase 1 quorum intersects with every phase 2 quorum (quorums ...
arXiv:1710.07191v1
fatcat:2xaxrs3rcramzmxyd2fpzacw4a
On the Significance of Consecutive Ballots in Paxos
[article]
2020
arXiv
pre-print
In this paper we examine the Paxos protocol and demonstrate how the discrete numbering of ballots can be leveraged to weaken the conditions for learning. ...
Specifically, we define the notion of consecutive ballots and use this to define Consecutive Quorums. ...
Safety is preserved as long as quorums used for learning values intersect with quorums used for proposing values, regardless of size. ...
arXiv:2006.01885v1
fatcat:x45ip6xnjngc5m5ogem5f6uljq
Extending Classic Paxos for High-performance Read-Modify-Write Registers
[article]
2021
arXiv
pre-print
In this work we provide a detailed specification of how we extended and implemented Classic Paxos (CP) to execute Read-Modify-Writes. ...
In addition, we also specify how we implemented All-aboard Paxos over CP and how we use carstamps, to also add ABD reads and writes, to accelerate the common case, where RMWs are not needed. ...
The theory is underpinned by a rule called Flexible Paxos and its refinement. Flexible Paxos. It is only required for propose quorums to intersect with accept quorums. Refinement. ...
arXiv:2103.14701v1
fatcat:u3y2ylr43fcnrghloabyne2pzy
WPaxos: Wide Area Network Flexible Consensus
[article]
2019
arXiv
pre-print
To achieve fast phase-2 commits, WPaxos adopts the flexible quorums idea in a novel manner, and appoints phase-2 acceptors to be close to their respective leaders. ...
The dynamic partitioning of the object-space and emphasis on zone-local commits allow WPaxos to significantly outperform both partitioned Paxos deployments and leaderless Paxos approaches. ...
module (which accommodates majority quorum, fast quorum, grid quorum and flexible quorum). ...
arXiv:1703.08905v4
fatcat:5p7nqnttbrdczn4txuyn7o7mmi
MDCC takes advantage of Generalized Paxos for transaction processing and exploits commutative updates with value constraints in a quorum-based system. ...
Replicating data across multiple data centers allows using data closer to the client, reducing latency for applications, and increases the availability in the event of a data center failure. ...
Acknowledgments We would like to thank the anonymous reviewers and our shepherd, Robbert van Renesse, for all the helpful comments and suggestions. ...
doi:10.1145/2465351.2465363
dblp:conf/eurosys/KraskaPFMF13
fatcat:p6ggj6zxy5cp7mrudoz2qmsoyu
MDCC: Multi-Data Center Consistency
[article]
2012
arXiv
pre-print
Our evaluation using the TPC-W benchmark with MDCC deployed across 5 geographically diverse data centers shows that MDCC is able to achieve throughput and latency similar to eventually consistent quorum ...
Replicating data across multiple data centers not only allows moving the data closer to the user and, thus, reduces latency for applications, but also increases the availability in the event of a data ...
After receiving responses from a classic quorum, all potential intersections with a fast quorum must be computed from the responses. ...
arXiv:1203.6049v1
fatcat:vorf7zi67jgnbgz4rklqupn6vu
SoK: A Generalized Multi-Leader State Machine Replication Tutorial
2021
Journal of Systems Research
That is, for every Phase 1 quorum Q and for every classic Phase 2 quorum Q ′ , Q ∩ Q ′ = / 0. 2. Every Phase 1 quorum and every pair of fast Phase 2 quorums intersect. ...
In [11] , Howard et. al prove that Fast Paxos is safe so long as the following two conditions are met.
Every Phase 1 quorum and every classic Phase 2 quorum intersect. ...
doi:10.5070/sr31154817
fatcat:gnstj2lg4rc3djsfrzritsoit4
Efficient Agreement Protocols in Asynchronous Distributed Systems
2011
2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum
The Quorum Requirements state that (1) any two quorums must intersect and (2) any quorum and any two fast quorums from the same round must also have a nonempty intersection. ...
These properties state that (1) any two quorums must have a nonempty intersection and (2) any quorum and any two fast quorums from the same round must also have a nonempty intersection. ...
En effet, si une proposition p j est générée très peu de temps avant la fin d'une instance c du consensus, il est très fortement probable qu'elle n'induira pas de collision pour cette instance c (un quorum ...
doi:10.1109/ipdps.2011.367
dblp:conf/ipps/Moise11
fatcat:lhpjl76et5bk7lpimxhy32pptq
Unifying consensus and atomic commitment for effective cloud data management
2019
Proceedings of the VLDB Endowment
We compare the performance of G-PAC with a Spanner-like protocol, where 2PC is used at the logical data level and Paxos is used for consistent replication of logical data. ...
We demonstrate the advantages of the C&C framework by developing a new atomic commitment protocol, Paxos Atomic Commit (PAC), which integrates commitment with recovery in a Paxos-like manner. ...
Finally, G-PAC provides flexibility in choosing any quorum definition across different phases, unlike the fast-path quorum (3/2f +1) in TAPIR. Janus by Mu et al. ...
doi:10.14778/3303753.3303765
fatcat:2m7p267odnh2dmwjwjtxd5wwpq
Reconfigurable Distributed Storage for Dynamic Networks
[chapter]
2006
Lecture Notes in Computer Science
The algorithm incorporates a quorum-based read/write algorithm and an optimized consensus protocol, based on Paxos. ...
This paper presents a new algorithm, RDS (Reconfigurable Distributed Storage), for implementing a reconfigurable distributed shared memory in an asynchronous dynamic network. ...
Combining quorum reconfiguration with optimized 3-delay "Fast Paxos" requires new techniques since (i) prior attempts to use Paxos for reconfiguration depend on each reconfiguration using the existing ...
doi:10.1007/11795490_27
fatcat:ookyq2svczciplxqwq33dmzooe
Reconfigurable distributed storage for dynamic networks
2009
Journal of Parallel and Distributed Computing
The algorithm incorporates a quorum-based read/write algorithm and an optimized consensus protocol, based on Paxos. ...
This paper presents a new algorithm, RDS (Reconfigurable Distributed Storage), for implementing a reconfigurable distributed shared memory in an asynchronous dynamic network. ...
Combining quorum reconfiguration with optimized 3-delay "Fast Paxos" requires new techniques since (i) prior attempts to use Paxos for reconfiguration depend on each reconfiguration using the existing ...
doi:10.1016/j.jpdc.2008.07.007
fatcat:j7x4nvcsrbh4pmmggg2ghzzvbm
Leveraging sharding in the design of scalable replication protocols
2013
Proceedings of the 4th annual Symposium on Cloud Computing - SOCC '13
We provide a specification for the protocol, prove its safety, analyze its liveness and availability properties, and evaluate a working implementation. ...
Most if not all datacenter services use sharding and replication for scalability and reliability. Shards are more-orless independent of one another and individually replicated. ...
Acknowledgments We would like to thank Haoyan Geng, Ken Birman, our shepherd Steve Gribble, and the anonymous reviewers for their valuable feedback. ...
doi:10.1145/2523616.2523623
dblp:conf/cloud/Abu-LibdehRV13
fatcat:ovbqrgown5gwlkz2nzwlqjfysu
Consensus Refined
2015
2015 45th Annual IEEE/IFIP International Conference on Dependable Systems and Networks
Algorithms for solving the consensus problem are fundamental to distributed computing. ...
Moreover, it also describes the algorithms used in the first round of the protocol from [7] and in the fast rounds of Fast Paxos [24] . ...
Furthermore, algorithms such as Fast Paxos [24] essentially combine several algorithms and as such they do not cleanly fit into our hierarchy. ...
doi:10.1109/dsn.2015.38
dblp:conf/dsn/MaricSB15
fatcat:fxowttki65gy7leeccjqd3hvuu
Building consistent transactions with inconsistent replication
2015
Proceedings of the 25th Symposium on Operating Systems Principles - SOSP '15
Unfortunately, existing transactional storage systems are expensive to use because they rely on expensive replication protocols like Paxos for fault-tolerance. ...
., Google's Spanner) for their strong guarantees and ease of use. ...
The equivalent holds for consensus operations with a finalized result because the quorum intersection for these is at least f 2 + 1. ...
doi:10.1145/2815400.2815404
dblp:conf/sosp/ZhangSSKP15
fatcat:3ods4xy7dff77m46exobgtzek4
« Previous
Showing results 1 — 15 out of 50 results