Measurement and Analysis of Computing Systems (POMACS)


Search Issue
enter search term and/or author name


Proceedings of the ACM on Measurement and Analysis of Computing Systems - SIGMETRICS, Volume 2 Issue 1, March 2018

PreFix: Switch Failure Prediction in Datacenter Networks
Shenglin Zhang, Yuzhi Zhang, Yu Chen, Hui Dong, Xianping Qu, Lei Song, Ying Liu, Weibin Meng, Zhiling Luo, Jiahao Bu, Sen Yang, Peixian Liang, Dan Pei, Jun Xu
Article No.: 2
DOI: 10.1145/3179405

In modern datacenter networks (DCNs), failures of network devices are the norm rather than the exception, and many research efforts have focused on dealing with failures after they happen. In this paper, we take a different approach by predicting...

Dynamic Proportional Sharing: A Game-Theoretic Approach
Rupert Freeman, Seyed Majid Zahedi, Vincent Conitzer, Benjamin C. Lee
Article No.: 3
DOI: 10.1145/3179406

Sharing computational resources amortizes cost and improves utilization and efficiency. When agents pool their resources together, each becomes entitled to a portion of the shared pool. Static allocations in each round can guarantee entitlements...

Network Resilience and the Length-Bounded Multicut Problem: Reaching the Dynamic Billion-Scale with Guarantees
Alan Kuhnle, Victoria G. Crawford, My T. Thai
Article No.: 4
DOI: 10.1145/3179407

Motivated by networked systems in which the functionality of the network depends on vertices in the network being within a bounded distance T of each other, we study the length-bounded multicut problem: given a set of pairs, find a...

On Resource Pooling and Separation for LRU Caching
Jian Tan, Guocong Quan, Kaiyi Ji, Ness Shroff
Article No.: 5
DOI: 10.1145/3179408

Caching systems using the Least Recently Used (LRU) principle have now become ubiquitous. A fundamental question for these systems is whether the cache space should be pooled together or divided to serve multiple flows of data item requests in...

Why Some Like It Loud: Timing Power Attacks in Multi-tenant Data Centers Using an Acoustic Side Channel
Mohammad A. Islam, Luting Yang, Kiran Ranganath, Shaolei Ren
Article No.: 6
DOI: 10.1145/3179409

The common practice of power infrastructure oversubscription in data centers exposes dangerous vulnerabilities to well-timed power attacks (i.e., maliciously timed power loads to overload the infrastructure capacity), possibly creating outages and...

Asymptotic Optimal Control of Markov-Modulated Restless Bandits
Santiago Duran, Ina Maria Verloop
Article No.: 7
DOI: 10.1145/3179410

This paper studies optimal control subject to changing conditions. This is an area that recently received a lot of attention as it arises in numerous situations in practice. Some applications being cloud computing systems where the arrival rates...

Supporting Mobile VR in LTE Networks: How Close Are We?
Zhaowei Tan, Yuanjie Li, Qianru Li, Zhehui Zhang, Zhehan Li, Songwu Lu
Article No.: 8
DOI: 10.1145/3179411

Mobile virtual reality (VR) headsets (e.g., Google Cardboard and Samsung Gear VR) seek to offer "anytime, anywhere" panorama, immerse 3D experiences for users. In this work, we study the viability of supporting mobile VR over operational 4G LTE...

ECI-Cache: A High-Endurance and Cost-Efficient I/O Caching Scheme for Virtualized Platforms
Saba Ahmadian, Onur Mutlu, Hossein Asadi
Article No.: 9
DOI: 10.1145/3179412

In recent years, high interest in using Virtual Machines (VMs) in data centers and Cloud computing has significantly increased the demand for high-performance data storage systems. A straightforward approach to provide a high performance storage...

Bootstrapped Graph Diffusions: Exposing the Power of Nonlinearity
Buchnik Eliav, Edith Cohen
Article No.: 10
DOI: 10.1145/3179413

Graph-based semi-supervised learning (SSL) algorithms predict labels for all nodes based on provided labels of a small set of seed nodes. Classic methods capture the graph structure through some underlying diffusion process that propagates through...

Minimizing Queue Length Regret Under Adversarial Network Models
Qingkai Liang, Eytan Modiano
Article No.: 11
DOI: 10.1145/3179414

Stochastic models have been dominant in network optimization theory for over two decades, due to their analytical tractability. However, these models fail to capture non-stationary or even adversarial network dynamics which are of increasing...

Online Learning in Weakly Coupled Markov Decision Processes: A Convergence Time Study
Xiaohan Wei, Hao Yu, Michael J. Neely
Article No.: 12
DOI: 10.1145/3179415

We consider multiple parallel Markov decision processes (MDPs) coupled by global constraints, where the time varying objective and constraint functions can only be observed after the decision is made. Special attention is given to how well...

Multi-armed Bandit with Additional Observations
Donggyu Yun, Alexandre Proutiere, Sumyeong Ahn, Jinwoo Shin, Yung Yi
Article No.: 13
DOI: 10.1145/3179416

We study multi-armed bandit (MAB) problems with additional observations, where in each round, the decision maker selects an arm to play and can also observe rewards of additional arms (within a given budget) by paying certain costs. In the case of...

Asymptotically Optimal Load Balancing Topologies
Debankur Mukherjee, Sem C. Borst, Johan S.H. van Leeuwaarden
Article No.: 14
DOI: 10.1145/3179417

We consider a system of N servers inter-connected by some underlying graph topology GN. Tasks with unit-mean exponential processing times arrive at the various servers as independent Poisson processes of rate λ. Each...

A Whittle's Index Based Approach for QoE Optimization in Wireless Networks
Arjun Anand, Gustavo de Veciana
Article No.: 15
DOI: 10.1145/3179418

The design of schedulers to optimize heterogeneous users' Quality of Experience (QoE) remains a challenging and important problem for wireless systems. This paper explores three inter-related aspects of this problem: 1) non-linear relationships...

SOAP: One Clean Analysis of All Age-Based Scheduling Policies
Ziv Scully, Mor Harchol-Balter, Alan Scheller-Wolf
Article No.: 16
DOI: 10.1145/3179419

We consider an extremely broad class of M/G/1 scheduling policies called SOAP: Schedule Ordered by Age-based Priority. The SOAP policies include almost all scheduling policies in the literature as well as an infinite number of variants which have...

Hound: Causal Learning for Datacenter-scale Straggler Diagnosis
Pengfei Zheng, Benjamin C. Lee
Article No.: 17
DOI: 10.1145/3179420

Stragglers are exceptionally slow tasks within a job that delay its completion. Stragglers, which are uncommon within a single job, are pervasive in datacenters with many jobs. A large body of research has focused on mitigating datacenter...

On a Class of Stochastic Multilayer Networks
Bo Jiang, Philippe Nain, Don Towsley, Saikat Guha
Article No.: 18
DOI: 10.1145/3179421

In this paper, we introduce a new class of stochastic multilayer networks. A stochastic multilayer network is the aggregation of M networks (one per layer) where each is a subgraph of a foundational network G. Each layer network is...

Working Set Size Estimation Techniques in Virtualized Environments: One Size Does not Fit All
Vlad Nitu, Aram Kocharyan, Hannas Yaya, Alain Tchana, Daniel Hagimont, Hrachya Astsatryan
Article No.: 19
DOI: 10.1145/3179422

Energy consumption is a primary concern for datacenters? management. Numerous datacenters are relying on virtualization, as it provides flexible resource management means such as virtual machine (VM) checkpoint/restart, migration and...

Degree of Queue Imbalance: Overcoming the Limitation of Heavy-traffic Delay Optimality in Load Balancing Systems
Xingyu Zhou, Fei Wu, Jian Tan, Kannan Srinivasan, Ness Shroff
Article No.: 21
DOI: 10.1145/3179424

Heavy-traffic delay optimality is considered to be an important metric in evaluating the delay performance of load balancing schemes. In this paper, we argue that heavy-traffic delay optimality is a coarse metric that does not necessarily imply...

Synthesis of Fault-Tolerant Distributed Router Configurations
Kausik Subramanian, Loris D'Antoni, Aditya Akella
Article No.: 22
DOI: 10.1145/3179425

Operators of modern networks require support for diverse and complex end-to-end policies, such as, middlebox traversals, isolation, and traffic engineering. While Software-defined Networking (SDN) provides centralized custom routing functionality...