UsenixATCBoston 2018 July 11, 2018 to July 13, 2018, Boston, USA

Event Page


Tell us about missing data
Title Speakers Summary Topic Types
Keynote Address: Blockchain in the Lens of BFT Dahlia Malkhi Blockchain is a Byzantine Fault Tolerant (BFT) replicated state machine, in which each state-update is ...
Tributary: spot-dancing for elastic services with latency SLOs Alexey Tumanov , Aaron Harlap , Andrew Chung , Gregory Gibbon The Tributary elastic control system embraces the uncertain nature of transient cloud resources, such as ...
FastTrack: Foreground App-Aware I/O Management for Improving User Experience of Android Smartphones Sangwook Shane Hahn , Sungjin Lee , Jihong Kim , Inhyuk Yee , Donguk Ryu The quality of user experience on a smartphone is directly affected by how fast a ...
Mainstream: Dynamic Stem-Sharing for Multi-Tenant Video Processing Michael Kaminsky , Michael A. Kozuch , Angela H. Jiang , Daniel L.-k. Wong , Christopher Canel , Lilia Tang , Ishan Misra , Padmanabhan Pillai , David Ganger Mainstream is a new video analysis system that jointly adapts concurrent applications sharing fixed edge ...
VideoChef: Efficient Approximation for Streaming Video Processing Pipelines Jinkyu Koo , Saurabh Bagchi , Rakesh Kumar , Subrata Mitra , Ran Xu , Peter Bai , Sasa Misailovic Many video streaming applications require low-latency processing on resource-constrained devices. To meet the latency and ...
SOCK: Rapid Task Provisioning with Serverless-Optimized Containers Andrea C. Arpaci-dusseau , Tyler Harter , Edward Oakes , Leon Yang , Dennis Zhou , Kevin Houck Serverless computing promises to provide applications with cost savings and extreme elasticity. Unfortunately, slow application ...
DynaMix: Dynamic Mobile Device Integration for Efficient Cross-device Resource Sharing Joonsung Kim , Jangwoo Kim , Dongju Chae , Gwangmu Lee , Hanjun Kim , Kyung-ah Chang , Hyogun Lee In the era of the Internet of Things, users desire more valuable services by simultaneously ...
The Battle of the Schedulers: FreeBSD ULE vs. Linux CFS Gilles Muller , Baptiste Lepers , Julia Lawall , Justinien Bouron , Sebastien Chevalley , Zwaenepoel , Redha Gouicem , And Julien Sopena This paper analyzes the impact on application performance of the design and implementation choices made ...
The Design and Implementation of Hyperupcalls Nadav Wei The virtual machine abstraction provides a wide variety of benefits which have undeniably enabled cloud ...
AIQL: Enabling Efficient Attack Investigation from System Monitoring Data Fengyuan Xu , Xusheng Xiao , Kangkook Jee , Zhichun Li , Peng Gao , Sanjeev Mittal The need for countering Advanced Persistent Threat (APT) attacks has led to the solutions that ...
Application Memory Isolation on Ultra-Low-Power MCUs David Kotz , Jacob Sorber , Taylor Hardin , Ryan Scott , Patrick Proctor , Josiah Hester The proliferation of applications that handle sensitive user data on wearable platforms generates a critical ...
Peeking Behind the Curtains of Serverless Platforms Thomas Ristenpart , Michael M. Swift , Yinqian Zhang , Liang Wang , Mengyuan Li Serverless computing is an emerging paradigm in which an application's resource provisioning and scaling are ...
Soteria: Automated IoT Safety and Security Analysis Patrick Mcdaniel , Z. Berkay Celik , And Gang Tan Broadly defined as the Internet of Things (IoT), the growth of commodity devices that integrate ...
Scaling Guest OS Critical Sections with eCS Taesoo Kim , Changwoo Min , Sanidhya Kashyap Multi-core virtual machines (VMs) are now a norm in data center environments. However, one of ...
KylinX: A Dynamic Library Operating System for Simplified and Efficient Cloud Virtualization Jon Crowcroft , Yongqiang Xiong , Huiba Li , Yiming Zhang , Dongsheng Li , Chengfen Zhang , Yaozheng Wang , Kai Yu , Guihai Chen Unikernel specializes a minimalistic LibOS and a target application into a standalone single-purpose virtual machine ...
Virtualizing Energy Storage Management Using RAIBA Tzi-cker Chiueh , Mao-cheng Huang , Kai-cheung Juang , Shih-hao Liang , And Welkin Ling Because of the intermittent nature of renewable energy-based electricity generation, a key building block for ...
Cntr: Lightweight OS Containers Pramod Bhatotia , Baris Kasikci , Pedro Fonseca , Jörg Thalheim Container-based virtualization has become the de-facto standard for deploying applications in data centers. However, deployed ...
Throwhammer: Rowhammer Attacks over the Network and Defenses Herbert Bos , Elias Athanasopoulos , Cristiano Giuffrida , Andrei Tatar , Radhesh Krishnan Konoth , And Kaveh Razavi Increasingly sophisticated Rowhammer exploits allow an attacker that can execute code on a vulnerable system ...
Varys: Protecting SGX Enclaves from Practical Side-Channel Attacks Christof Fetzer , Mark Silberstein , Oleksii Oleksenko , Bohdan Trach , Robert Krahn , André Martin Numerous recent works have experimentally shown that Intel Software Guard Extensions (SGX) are vulnerable to ...
Kernel-Supported Cost-Effective Audit Logging for Causality Tracking Somesh Jha , Dongyan Xu , Vinod Yegneswaran , Gabriela Ciocarlie , Xiangyu Zhang , Ashish Gehani , Juan Zhai , Yonghwi Kwon , Shiqing Ma , Kyu Hyung Lee The Linux Audit system is widely used as a causality tracking system in real-world deployments ...
EPTI: Efficient Defence against Meltdown Attack for Unpatched VMs Haibo Chen , Yubin Xia , Zhichao Hua , Dong Du , And Binyu Zang The Meltdown vulnerability, which exploits the inherent out-of-order execution in common processors like x86, ARM ...
Effectively Mitigating I/O Inactivity in vCPU Scheduling Xiaoning Ding , Jianchen Shan , Heming Cui , Cheng Wang , Luwei Cheng , Weiwei Jia , Xusheng Chen , Xiaowei Shang , Francis Lau , Yuexuan Wang , Yuangang Wang In clouds where CPU cores are time-shared by virtual CPUs (vCPU), vCPUs are scheduled and ...
Placement of Virtual Containers on NUMA systems: A Practical and Comprehensive Model Baptiste Lepers , Justin Funston , Alexandra Fedorova , Vivien Quéma , Maxime Lorrillere , David Vengerov , Jean-pierre Lozi Our work addresses the problem of placement of threads, or virtual cores, onto physical cores ...
Getting to the Root of Concurrent Binary Search Tree Performance Adam Morrison , Maya Arbel-raviv , Trevor Brown Many systems rely on optimistic concurrent search trees for multi-core scalability. In principle, optimistic trees ...
Troubleshooting Transiently-Recurring Errors in Production Systems with Blame-Proportional Logging Suman Nath , Liang Luo , Lenin Ravindranath Sivalingam , And Madan Musuvathi Many problems in production systems are transiently recurring— they occur rarely, but when they do, ...
NanoLog: A Nanosecond Scale Logging System John Ousterhout , Seo Jin Park , Stephen Yang NanoLog is a nanosecond scale logging system that is 1-2 orders of magnitude faster than ...
Model Governance: Reducing the Anarchy of Production ML Swaminathan Sundararaman , Sriram Subramanian , Vinay Sridhar , Dulcardo Arteaga , Drew Roselli , And Nisha Talagala As the influence of machine learning grows over decisions in businesses and human life, so ...
Fine-grained consistency for geo-replicated systems Rodrigo Rodrigues , Cheng Li , Nuno Preguiça To deliver fast responses to users worldwide, major Internet providers rely on geo-replication to serve ...
Log-Free Concurrent Data Structures Aleksandar Dragojević , Tudor David , Rachid Zablotchi Non-volatile RAM (NVRAM) makes it possible for data structures to tolerate transient failures, assuming however ...
On Smart Query Routing: For Distributed Graph Querying with Decoupled Storage Donald Kossmann , Arijit Khan , Gustavo Segovia We study online graph queries that retrieve nearby nodes of a query node in a ...
Locality-Aware Software Throttling for Sparse Matrix Operation on GPUs Chi Zhang , Ari B. Hayes , Yanhao Chen , Timothy Zhang This paper tackles the cache thrashing problem caused by the non-deterministic scheduling feature of bulk ...
Accelerating PageRank using Partition-Centric Processing Viktor Prasanna , Kartik Lakhotia , Rajgopal Kannan PageRank is a fundamental link analysis algorithm that also functions as a key representative of ...
CGraph: A Correlations-aware Approach for Efficient Concurrent Iterative Graph Processing Yu Zhang , Hai Jin , Bingsheng He , Xiaofei Liao , Lin Gu , Ligang He , Haikun Liu With the fast growing of iterative graph analysis applications, the graph processing platform have to ...
Don't share, Don't lock: Large-scale Software Connection Tracking with Krononat Nicolas Le Scouarnec , Fabien André , Stéphane Gouache , And Antoine Monsifrot To simplify software updates and provide new services, ISPs are interested in migrating network functions ...
Accurate Timeout Detection Despite Arbitrary Processing Delays Sixiang Wang Timeout is widely used for failure detection. This paper proposes SafeTimer, a mechanism to enhance ...
RAFI: Risk-Aware Failure Identification to Improve the RAS in Erasure-coded Data Centers Xubin He , Juntao Fang , Shenggang Wan Data reliability and availability, and serviceability (RAS) of erasure-coded data centers are highly affected by ...
Siphon: Expediting Inter-Datacenter Coflows in Wide-Area Data Analytics Li Chen , Shuhao Liu , And Baochun Li It is increasingly common that large volumes of production data originate from geographically distributed datacenters. ...
PerfIso: Performance Isolation for Commercial Latency-Sensitive Services Reza Azimi , Calin Iorgulescu , Youngjin Kwon , Sameh Elnikety , Manoj Syamala , Vivek Narasayya , Paulo Tomita , Alex Chen , Jack Zhang , And Junhua Wang Large commercial latency-sensitive services, such as web search, run on dedicated clusters provisioned for peak ...
On the diversity of cluster workloads and its impact on research results Nathan Debardeleben , Gregory R. Ganger , Garth A. Gibson , Jun Woo Park , George Amvrosiadis , Elisabeth Baseman Six years ago, Google released an invaluable set of scheduler logs which has already been ...
SLAOrchestrator: Reducing the Cost of Performance SLAs for Cloud Data Analytics Johannes Gehrke , Jennifer Ortiz , Magdalena Balazinska , Brendan Lee , Joseph L. Hellerstein SLAOrchestrator is a new system designed to reduce the price increases necessary to support performance ...
Spindle: Informed Memory Access Monitoring Xiaosong Ma , Wenguang Chen , Haojie Wang , Jidong Zhai , Xiongchao Tang , Bowen Yu Memory monitoring is of critical use in understanding applications and evaluating systems. Due to the ...
Touchstone: Generating Enormous Query-Aware Test Databases Yuming Li , Rong Zhang , Xiaoyan Yang , Zhenjie Zhang , Aoying Zhou Query-aware synthetic data generation is an essential and highly challenging task, important for database management ...
DSAC: Effective Static Analysis of Sleep-in-Atomic-Context Bugs in Kernel Modules Julia Lawall , Shi-min Hu , Jia-ju Bai , Yu-ping Wang In a modern OS, kernel modules often use spinlocks and interrupt handlers to monopolize a ...
Coccinelle: 10 Years of Automated Evolution in the Linux Kernel Julia Muller The Coccinelle C-program matching and transformation tool was first released in 2008 to facilitate specification ...
Albis: High-Performance File Format for Big Data Systems Jonas Pfefferle , Patrick Stuedi , Animesh Trivedi , Bernard Metzler , Adrian Schuepbach Over the last decade, a variety of external file formats such as Parquet, ORC, Arrow, ...
Litz: Elastic Framework for High-Performance Distributed Machine Learning Qirong Ho , Garth A. Gibson , Eric P. Xing , Abutalib Aghayev , Weiren Yu , Aurick Qiao , Haoyang Chen Machine Learning (ML) is an increasingly popular application in the cloud and data-center, inspiring new ...
Putting the "Micro" Back in Microservice Michael Kaminsky , David g. Andersen , Sol Boucher , Anuj Kalia Modern cloud computing environments strive to provide users with fine-grained scheduling and accounting, as well ...
Fast and Concurrent RDF Queries using RDMA-assisted GPU Graph Exploration Rong Chen , And Haibo Chen , Siyuan Wang , Chang Lou RDF graph has been increasingly used to store and represent information shared over the Web, ...
MDev-NVMe: A NVMe Storage Virtualization Solution with Mediated Pass-Through Yaozu Dong , Haibing Guan , Bo Peng , Haozhong Zhang , Ianguo Yao , Yu Xu The fast access to data and high parallel processing in high-performance computing instigates an urgent ...
AutoSSD: an Autonomic SSD Architecture Bryan S. Kim , Hyun Suk Yang , Sang Lyul Min From small mobile devices to large-scale storage arrays, flash memory-based storage systems have gained a ...
Geriatrix: Aging what you see and what you don’t see. A file system aging approach for modern storage systems Gregory R. Ganger , Garth A. Gibson , Saurabh Kadekodi , Vaishnavh Nagarajan File system performance on modern primary storage devices (Flash-based SSDs) is greatly affected by aging ...
Can’t We All Get Along? Redesigning Protection Storage for Modern Workloads Fred Douglis , Philip Shilane , Yamini Allu , Mahesh Kamat , Ramya Prabhakar , And Rahul Ugale Deduplication systems for traditional backups have optimized for large sequential writes and reads. Over time, ...
STMS: Improving MPTCP Throughput Under Heterogeneous Networks Xin Wang , Yong Cui , Hang Shi , Yuming Hu , Minglong Dai , Fanzhao Zheng Using multiple interfaces on mobile devices to get high throughput is promising to improve the ...
Pantheon: the training ground for Internet congestion-control research Philip Levis , Riad S. Wahby , Francis Y. Yan , Jestin Ma , Greg D. Hill , Deepti Raghavan , And Keith Winstein Internet transport algorithms are foundational to the performance of network applications. But a number of ...
ClickNF: a Modular Stack for Custom Network Functions Massimo Laufer Network function virtualization has recently allowed specialized equipment to be replaced with equivalent software implementation. ...
Selecta: Heterogeneous Cloud Storage Configuration for Data Analytics Christos Kozyrakis , Ana Klimovic , Heiner Litz Data analytics are an important class of data-intensive workloads on public cloud services. However, selecting ...
Remote regions: a simple abstraction for remote memory Michael Wei , Marcos k. Aguilera , Lalith Suresh , Nadav Amit , Irina Calciu , Xavier Deguillard , Jayneel Gandhi , Stanko Novakovic , Arun Ramanathan , Pratap Subrahmanyam , Kiran Tati , Rajesh Venkatasubramanian We propose an intuitive abstraction for a process to export its memory to remote hosts, ...
Understanding Ephemeral Storage for Serverless Analytics Christos Kozyrakis , Ana Klimovic , Jonas Pfefferle , Patrick Stuedi , Yawen Wang , And Animesh Trivedi Serverless computing frameworks allow users to launch thousands of concurrent tasks with high elasticity and ...
Solar: Towards a Shared-Everything Database on Distributed Log-Structured Storage Dong Xie , Tao Zhu , Ryan Stutsman , Aoying Zhou , Zhuoyue Zhao , Feifei Li , Weining Qian , Haining Li , Huiqi Hu Efficient transaction processing over large databases is a key requirement for many mission-critical applications. Though ...
Toward Coordination-free and Reconfigurable Mixed Concurrency Control Dixin Elmore Recent studies show that mixing concurrency control protocols within a single database can significantly outperform ...
Scaling Hardware Accelerated Network Monitoring to Concurrent and Dynamic Queries With *Flow Adam J. Aviv , Jonathan M. Smith , Eric Keller , John Sonchack , Oliver Michel Measurement plays a key role in network operation and management. An important but unaddressed practical ...
Applying Hardware Transactional Memory for Concurrency-Bug Failure Recovery in Production Runs Yuxi Chen , Shu Wang , And Shan Lu Concurrency bugs widely exist and severely threaten system availability. Techniques that help recover from concurrency-bug ...
Tailwind: Fast and Atomic RDMA-based Replication Toni Cortes , Ryan Stutsman , Yacine Taleb , Gabriel Antoniu Replication is essential for fault-tolerance. However, in in-memory systems, it is a source of high ...
On Fault Tolerance, Locality, and Optimality in Locally Repairable Codes Gala Yadgar , Oleg Kolosov , Matan Liram , Itzhak Tamo , Alexander Barg Erasure codes are used in large-scale storage systems to allow recovery of data from a ...
TxFS: Leveraging File-System Crash Consistency to Provide ACID Transactions Vijay Chidambaram , Emmett Witchel , Yige Hu , Youngjin Kwon , Zhiting Zhu , Ian Neal , Tianyu Cheng We introduce TxFS, a novel transactional file system that builds upon a file system’s atomic-update ...
Towards Better Understanding of Black-box Auto-Tuning: A Comparative Analysis for Storage Systems Zhen Cao , Vasily Tarasov , Sachin Zadok Modern computer systems come with a large number of configurable parameters that control their behavior. ...
HeavyKeeper: An Accurate Algorithm for Finding Top-k Elephant Flows Hao Li , Junzhi Gong , Tong Yang , Haowei Zhang , Steve Uhlig , Shigang Chen , Lorna Uden , Xiaoming Li Finding top-k elephant flows is a critical task in network traffic measurement, with many applications ...
Cavs: An Efficient Runtime System for Dynamic Neural Networks Hao Zhang , Qirong Ho , Jin Kyu Kim , Wei Dai , Eric P. Xing , Shizhen Xu , Graham Neubig , Zhijie Deng , Guangwen Yang Recent deep learning (DL) models are moving more and more to dynamic neural network (NN) ...
DeepCPU: Serving RNN-based Deep Learning Models 10x Faster Minjia Zhang , Samyam Rajbhandari , Wenhan Wang , And Yuxiong He Recurrent neural networks (RNNs) are an important class of deep learning (DL) models. Existing DL ...
Closing the Performance Gap Between Volatile and Persistent Key-Value Stores Using Cross-Referencing Logs Margo Seltzer , Tim Harris , Virendra Marathe , Yihe Huang , Matej Pavlovic , And Steve Byan Key-Value (K-V) stores are an integral building block in modern datacenter applications. With byteaddressable persistent ...
Redesigning LSMs for Nonvolatile Memory with NoveLSM Andrea C. Arpaci-dusseau , Remzi H. Arpaci-dusseau , Ada Gavrilovska , Sudarsun Kannan , Nitish Bhat We present NoveLSM, a persistent LSM-based key-value storage system designed to exploit non-volatile memories and ...
HashKV: Enabling Efficient Updates in KV Storage via Hashing Patrick Lee , Helen Chan , Yongkun Li , Yinlong Xu Persistent key-value (KV) stores mostly build on the Log-Structured Merge (LSM) tree for high write ...