Share This Author
Cure: Strong Semantics Meets High Availability and Low Latency
- Deepthi Devaki Akkoorath, Alejandro Z. Tomsic, M. Shapiro
- Computer ScienceIEEE International Conference on Distributed…
- 27 June 2016
The protocols for highly available transactions, and an experimental evaluation showing that Cure is able to achieve scalability similar to eventually-consistent NoSQL databases, while providing stronger guarantees.
Distributed transactional reads: the strong, the quick, the fresh & the impossible
- Alejandro Z. Tomsic, Manuel Bravo, M. Shapiro
- Computer ScienceInternational Middleware Conference
- 3 October 2018
An existing protocol is modified to ensure minimal-delay reads (at the cost of freshness) under atomic-visibility and causally-consistent semantics, and experimental evaluation supports the theoretical results.
2W-FD: A Failure Detector Algorithm with QoS
- Alejandro Z. Tomsic, P. Sens, João Garcia, L. Arantes, Julien Sopena
- Computer ScienceIEEE International Parallel and Distributed…
- 25 May 2015
This work introduces the Two-Windows Failure Detector (2W-FD), an algorithm able to react to sudden changes in network conditions, property that currently existing algorithms do not satisfy.
Serverless Event-Stream Processing over Virtual Actors
- P. Bernstein, Todd Porter, Rahul Potharaju, Alejandro Z. Tomsic, S. Venkataraman, Wentao Wu
- Computer ScienceCIDR
It is argued that the virtual actor model is an ideal platform on which to build a serverless event-stream processing service with pay-for-use and SLA’s.
An empirical perspective on causal consistency
This work identifies that protocols that provide causal consistency share the well-known DUR (deferred update replication) algorithmic structure and observes that existing implementations of causal consistency fall into a sub- category of DUR that is named A-DUR (Asynchronous-D UR), and describes the empirical study it intends to perform on causal consistency.
A Failure Detector Algorithm with QoS
This work introduces the Two Windows Failure Detector (2W- FD), an algorithm that provides QoS and is able to react to sudden changes in network conditions, a property that currently existing algorithms do not satisfy.
Exploring the design space of highly-available distributed transactions
- Alejandro Z. Tomsic
- Computer Science
- 19 April 2018
A three-way trade-off between read isolation, delay (latency), and data freshness is found and demonstrated, and two isolation properties are proposed: TCC- and PSI-.
PhysiCS-NMSI: efficient consistent snapshots for scalable snapshot isolation
This work documents the design of PhysiCS-NMSI, a transactional protocol implementing NMSI in a partitioned data store that is the first protocol to rely on a single scalar taken from a physical clock for tracking causal dependencies and building causally consistent snapshots.
MW-FD, A Failure Detector Algorithm with QoS, and an Analysis Towards Failure Detection as a Service
This work introduces the Multiple Windows Failure Detector (MW-FD), a failure detector that presents an improved the QoS when compared to existing FD algorithms, and analyses the idea of multiple applications or virtual machines, with di↵erent QoS requirements in terms of failure detection, running on a single host using a single FD as a shared service.