Details
Name
Nuno Filipe FariaCluster
Computer ScienceRole
ResearcherSince
23rd September 2020
Nationality
PortugalCentre
High-Assurance SoftwareContacts
+351253604477
nuno.f.faria@inesctec.pt
2022
Authors
Faria, N; Costa, D; Pereira, J; Vilaça, R; Ferreira, L; Coelho, F;
Publication
19th IEEE Annual Consumer Communications & Networking Conference, CCNC 2022, Las Vegas, NV, USA, January 8-11, 2022
Abstract
2022
Authors
Costa, D; Pereira, J; Vilaca, R; Faria, N;
Publication
37TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING
Abstract
2021
Authors
Faria, N; Pereira, J;
Publication
PaPoC@EuroSys 2021, 8th Workshop on Principles and Practice of Consistency for Distributed Data, Online Event, United Kingdom, April 26, 2021
Abstract
Distributed data management systems have increasingly been using variants of Snapshot Isolation (SI) as their transactional isolation criteria as it combines strong ACID guarantees with non-blocking reads and scalability. However, most existing proposals are limited by the performance of update propagation and stability detection, in particular, when execution and storage are disaggregated. In this paper, we propose TOPSI, an approach providing a restricted form of Parallel Snapshot Isolation (PSI) that allows partially ordering recent transactions to avoid waiting for remote updates or using a stale snapshot. Moreover, it has the interesting property of making a prefix of history in all sites converge to a common total order. This allows versions to be represented by a single scalar timestamp for certification and storage in a shared store. We demonstrate the impact on throughput and abort rate with a proof-of-concept implementation and the industry-standard TPC-C benchmark. © 2021 ACM.
2021
Authors
Faria, N; Pereira, J; Alonso, AN; Vilaça, R;
Publication
Heterogeneous Data Management, Polystores, and Analytics for Healthcare - VLDB Workshops, Poly 2021 and DMAH 2021, Virtual Event, August 20, 2021, Revised Selected Papers
Abstract
Transactional isolation is a challenge for polystores, as along with the limited capabilities of each datastore, we have to contend with their sheer diversity. However, transactional isolation is increasingly desirable as a variety of datastores are being sought after for roles that go beyond data lakes. Transactional guarantees are also relevant for reliability at scale. In this paper, we propose that transactional isolation in polystores can be achieved by leveraging the query engine, i.e., basing some of the responsibilities of a traditional transactional storage manager (TSM) on the query language itself. This has the key advantage of greatly simplifying design and implementation, as it doesn’t need to be re-invented for each datastore, and should increase performance, by taking advantage of dynamic query optimization where available. We demonstrate the feasibility of the proposal with a simple proof-of-concept and experiment. © 2021, Springer Nature Switzerland AG.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.