Dependable, Adaptive, and Secure Distributed Systems15th DADS Track of the35th ACM Symposium on Applied Computing Previous years: | 14th DADS 2019 13th DADS 2018 12th DADS 2017 11th DADS 2016 10th DADS 2015 9th DADS 2014 8th DADS 2013 7th DADS 2012 6th DADS 2011 5th DADS 2010 4th DADS 2009 3rd DADS 2008 2nd DADS 2007 1st DADS 2006 |
 http://www.sigapp.org/sac/sac2020/ March 30 - April 3, 2020 Brno, Czech Republic |
The Symposium on Applied Computing has been a primary gathering forum for applied computer scientists, computer engineers, software engineers, and application developers from around the world. SAC 2020 is sponsored by the ACM Special Interest Group on Applied Computing and the SRC Program is sponsored by Microsoft Research.
The track provides a forum for scientists and engineers in academia and industry to present and discuss their latest research findings on selected topics in dependable, adaptive and trustworthy distributed systems and services.
Black-box inter-application traffic monitoring for adaptive container placement
Francisco Neves, Ricardo Vilaça and Jose Pereira
A key issue in the performance of modern containerized distributed systems, such as big data storage and processing stacks or micro-service based applications, is the placement of each container, or container pod, in virtual and physical servers. Although it has been shown that inter-application traffic is an important factor in placement decisions, as it directly indicates how closely components interact, it hasn't been possible to accurately monitor it in an application independent way, thus putting it out of reach of cloud platforms. In this paper we present an efficient black-box monitoring approach for measuring data exchanged between collaborating processes in a distributed system, thus building a graph representation that can be queried for various purposes, including adaptive placement. The key to achieving high detail and low overhead without custom application instrumentation is to use a kernel-aided event driven strategy. We evaluate a prototype implementation with micro-benchmarks and demonstrate its usefulness for container placement in a distributed data storage and processing stack (i.e., Cassandra and Spark).
Benchmarking Microservice Performance: A Pattern-based Approach
Martin Grambow, Lukas Meusel, Erik Wittern and David Bermbach
Benchmarking microservices serves to understand and check their non-functional properties, for relevant workloads and over time. Performing benchmarks, however, can be costly: each microservice requires the design and implementation of a benchmark, possibly repeatedly as the service evolves. As microservice APIs differ, benchmarking tools that assume common interfaces - like ones for databases - do not exist. In this work, we present a pattern-based approach to reduce the efforts for defining microservice benchmarks, while still allowing to measure qualities of complex interactions. It assumes that microservices expose a REST API, described in a machine-understandable way, and allows developers to model interaction patterns from abstract operations that can be mapped to that API. Possible data-dependencies between operations are resolved at runtime. We implement a prototype of our approach, which we use to demonstrate that it can be applied to open-source microservices with little effort. Our work shows that pattern-based benchmarking of microservices is feasible and opens up opportunities for microservice providers and tooling developers.
QoE-Aware Auto-Scaling of Heterogeneous Containerized Services (and its application to Health Services)
Guilherme Santos, Herve' Paulino and Tomé Verdasca
Containerized service is currently a widely adopted solution to deploy services in the cloud. However, many companies offer a very diverse set of Web accessible services that, are subjected to very distinctive workloads. Consequently, to correctly provision the right amount of resources for each of these services is a challenge. In this paper we propose Autonomic ConTainerized Service Scaler (ACTS), an auto- nomic system able to horizontally and vertically scale a set of heterogeneous containerized services subjected to differ- ent workloads. The adaptation decisions depended on a set of high-level Quality of Experience (QoE) metrics centered on the services’ end-user. We have applied ACTS to some of the digital services of a public European health service provider. The experimental results show that our solution is able to adequately adapt the configuration of each service, as a direct response to alterations on its workload.
Privacy Preserving Cooperative Computation for Personalized Web Search Applications
Kaaniche Nesrine, Masmoudi Souha, Znina Souha, Laurent Maryline and Demir Levent
With the emergence of connected objects and the development of Artificial Intelligence (AI) mechanisms and algorithms, personalized applications are gaining an expanding interest, providing services tailored to each single user needs and expectations. They mainly rely on the massive collection of personal data generated by a large number of applications hosted from different connected devices. In this paper, we present CoWSA, a privacy preserving Cooperative computation framework for personalized Web Search peripheral Applications. The proposed framework is multi-fold. First, it provides the empowerment to end-users to control the disclosed personal data to third parties, while leveraging the trade-off between privacy and utility. Second, as a decentralized solution, CoWSA mitigates single points of failures, while ensuring the security of queries, the anonymity of submitting users, and the incentive of contributing nodes. Third, CoWSA is scalable as it provides acceptable computation and communication costs compared to most closely related schemes.
Details see SAC poster page.
Towards a Replication Service for Data-Intensive Fog Applications
Jonathan Hasenburg, Martin Grambow and David Bermbach
The combination of edge and cloud in the fog computing paradigm enables a new breed of data-intensive applications. These applications, however, have to face a number of fog-specific challenges which developers have to repetitively address for every single application. In this paper, we propose a replication service specifically tailored to the needs of data-intensive fog applications that aims to ease or eliminate challenges caused by the highly distributed and heterogeneous environment fog applications operate in. Furthermore, we present our prototypical proof-of-concept implementation FBase that we have made available as open source.
Spatial Bloom Filter in Named Data Networking: a Memory Efficient Solution
Filippo Berto, Luca Calderoni, Mauro Conti and Eleonora Losiouk
The number of connected devices and the huge amount of generated network traffic are long far away from what the designers of the Internet expected to. This misalignment between the expected and the real usage is leading the current architecture towards its end. Among the possible future Internet architectures, Information Centric Networking (ICN) is the most promising one and researchers working on the Named Data Networking (NDN) project are putting efforts towards its deployment in a real scenario. Being a content oriented architecture, NDN focuses on contents instead of hosts and identifies contents through human readable names. By design, content names are made of a limitless number of components, each one having potentially an unlimited number of characters. To properly handle content names, the different components of an NDN network need efficient and scalable data structures. However, from an analysis of the NDN implementation library, we found a limitation in this direction. In this paper, we propose a new data structure to support the NDN forwarding procedure by replacing the current Forwarding Information Base (FIB): the Spatial Bloom Filter (SBF), a probabilistic data structure that guarantees fast lookup and efficient memory consumption. Through a set of simulations run to compare the performance of FIB and SBF, we found that the latter uses less than 4 KB of data to handle 10^6 queried interests, with a (negligible) probability 10^(-4) of false positive events. Conversely, the FIB requires up to 2.4 GB of data in disadvantageous cases, e.g. when interests are composed of a considerable number of components.
ALISI: A Lightweight Identification System based on Iroha
Giuseppe Bernieri, Mauro Conti, Matteo Sovilla and Federico Turrin
Given their ubiquity, modern Internet of Things (IoT) devices represent a dangerous attack surface for hackers. These devices are strongly heterogeneous by manufacturer, application field, geographic area of deployment, security requirements, and computational performances. This vulnerability problem is more important in the Industrial Internet of Things (IIoT) scenario, where systems are critical for plant processes, such as power grids and water distribution. In this paper, we present ALISI: A Lightweight Identification System based on Iroha, a blockchain-based identification platform conceived for IoT and IIoT systems. The blockchain technology provides a global identification standard, following a distributed approach in order to collaborate and share responsibilities and costs to gain first-class security features. Our scheme handles the performance issues typical of the blockchain systems using a hybrid on-chain and off-chain approach, achieving low response time and small load on the single device. We evaluate ALISI in a simulated environment and our results show that it is possible to implement an identification system based on blockchain minimizing the load on the device: we achieved a client size of 8 Megabytes and query time of 6 milliseconds.
Karl M. Göschka (Main contact chair)
University of Applied Sciences Technikum Wien
Embedded Systems Institute
Hoechstaedtplatz 6
A-1200 Vienna, Austria
phone: +43 664 180 6946
fax: +43 664 188 6275
dads@dedisys.org
goeschka (at) technikum-wien dot at
Rui Oliveira
Universidade do Minho
Computer Science Department
Campus de Gualtar
4710-057 Braga, Portugal
phone: +351 253 604 452 / Internal: 4452
fax: +351 253 604 471
rco (at) di dot uminho dot pt
Peter Pietzuch
Imperial College London
Department of Computing
South Kensington Campus
180 Queen's Gate
London SW7 2AZ, United Kingdom
phone: +44 (20) 7594 8314
fax: +44 (20) 7581 8024
prp (the at sign goes here) doc (dot) ic (dot) ac (dot) uk
Giovanni Russello
University of Auckland
Department of Computer Science
Private Bag 92019
Auckland 1142, New Zealand
phone: +64 9 373 7599 ext. 86137
g dot russello at auckland dot ac dot nz
| September 29, 2019 (11:59PM Pacific Time) - extended | Paper submission |
| November 24, 2019 | Author notification |
| December 9, 2019 | Camera-ready papers |
For general information about SAC, please visit: http://www.sigapp.org/sac/sac2020/
If you have further questions, please do not hesitate to contact us: dads@dedisys.org