Mothy received a PhD in 1995 from the Computer Laboratory of the University of Cambridge, where he was a principal designer and builder of the Nemesis OS. Although SSDs can be simplified under the current ZNS interface, its counterpart LFS must bear segment compaction overhead. Session Chairs: Ryan Huang, Johns Hopkins University, and Manos Kapritsos, University of Michigan, Jianan Yao, Runzhou Tao, Ronghui Gu, Jason Nieh, Suman Jana, and Gabriel Ryan, Columbia University. Submitted papers must be no longer than 12 single-spaced 8.5 x 11 pages, including figures and tables, plus as many pages as needed for references, using 10-point type on 12-point (single-spaced) leading, two-column format, Times Roman or a similar font, within a text block 7 wide x 9 deep. Secure Computation (SC) is a family of cryptographic primitives for computing on encrypted data in single-party and multi-party settings. To remedy this, we introduce DeSearch, the first decentralized search engine that guarantees the integrity and privacy of search results for decentralized services and blockchain apps. Despite their extensive use for debugging and vulnerability discovery, sanitizer checks often induce a high runtime cost. blk-switch uses this insight to adapt techniques from the computer networking literature (e.g., multiple egress queues, prioritized processing of individual requests, load balancing, and switch scheduling) to the Linux kernel storage stack. Our evaluation shows that DistAI successfully verifies 13 common distributed protocols automatically and outperforms alternative methods both in the number of protocols it verifies and the speed at which it does so, in some cases by more than two orders of magnitude. Accepted papers will be allowed 14 pages in the proceedings, plus references. Nico Lehmann and Rose Kunkel, UC San Diego; Jordan Brown, Independent; Jean Yang, Akita Software; Niki Vazou, IMDEA Software Institute; Nadia Polikarpova, Deian Stefan, and Ranjit Jhala, UC San Diego. You must not improperly identify a PC member as a conflict if none of these three circumstances applies, even if for some other reason you want to avoid them reviewing your paper. Welcome to the 2021 USENIX Annual Technical Conference (ATC '21) submissions site! To adapt to different workloads, prior works mix or switch between a few known algorithms using manual insights or simple heuristics. In this talk, I'll speculate on how we came to this unfortunate state of affairs, and what might be done to fix it. Finding the inductive invariant of the distributed protocol is a critical step in verifying the correctness of distributed systems, but takes a long time to do even for simple protocols. However, the existing one-size-fits-all GNN implementations are insufficient to catch up with the evolving GNN architectures, the ever-increasing graph size, and the diverse node embedding dimensionality. Paper abstracts and proceedings front matter are available to everyone now. Cores can safely and concurrently read from their local kernel replica, eliminating remote NUMA accesses. Questions? Research Impact Score 9.24. . Haojie Wang, Jidong Zhai, Mingyu Gao, Zixuan Ma, Shizhi Tang, and Liyan Zheng, Tsinghua University; Yuanzhi Li, Carnegie Mellon University; Kaiyuan Rong and Yuanyong Chen, Tsinghua University; Zhihao Jia, Carnegie Mellon University and Facebook. Authors must make a good faith effort to anonymize their submissions, and they should not identify themselves or their institutions either explicitly or by implication (e.g., through the references or acknowledgments). Using selective profiling, we build DMon, a system that can automatically locate data locality problems in production, identify access patterns that hurt locality, and repair such patterns using targeted optimizations. We implement DeSearch for two existing decentralized services that handle over 80 million records and 240 GBs of data, and show that DeSearch can scale horizontally with the number of workers and can process 128 million search queries per day. A graph embedding is a fixed length vector representation for each node (and/or edge-type) in a graph and has emerged as the de-facto approach to apply modern machine learning on graphs. Many application domains can benefit from hybrid transaction/analytical processing (HTAP) by executing queries on real-time datasets produced by concurrent transactions. We present case studies and end-to-end applications that show how Storm lets developers specify diverse policies while centralizing the trusted code to under 1% of the application, and statically enforces security with modest type annotation overhead, and no run-time cost. We demonstrate the above using design, implementation and evaluation of blk-switch, a new Linux kernel storage stack architecture. DeSearch uses trusted hardware to build a network of workers that execute a pipeline of small search engine tasks (crawl, index, aggregate, rank, query). Professor Veloso has been recognized with a multiple honors, including being a Fellow of the ACM, IEEE, AAAS, and AAAI. PLDI seeks outstanding research that extends and/or applies programming-language concepts to advance the field of computing. Amy Tai, VMware Research; Igor Smolyar, Technion Israel Institute of Technology; Michael Wei, VMware Research; Dan Tsafrir, Technion Israel Institute of Technology and VMware Research. (Oct 2018) Awarded an Intel Faculty Grant for Research on automated performance optimization (Sep. 2018) Our paper on Foreshadow is accepted to appear at USENIX Security. Writing a correct operating system kernel is notoriously hard. His work has included the Barrelfish multikernel research OS, as well as work on distributed stream processors, and using formal specifications to describe the hardware/software interfaces of modern computer systems. DeSearch then introduces a witness mechanism to make sure the completed tasks can be reused across different pipelines, and to make the final search results verifiable by end users. NrOS replicates kernel state on each NUMA node and uses operation logs to maintain strong consistency between replicas. Unfortunately, because devices lack the semantic information about which I/O requests are latency-sensitive, these heuristics can sometimes lead to disastrous results. If in doubt about whether your submission to OSDI 2021 and your upcoming submission to SOSP are the same paper or not, please contact the PC chairs by email. First, Fluffy mutates and executes multi-transaction test cases to find consensus bugs which cannot be found using existing fuzzers for Ethereum. Professor Veloso is the Past President of AAAI (the Association for the Advancement of Artificial Intelligence), and the co-founder, Trustee, and Past President of RoboCup. Youngseok Yang, Seoul National University; Taesoo Kim, Georgia Institute of Technology; Byung-Gon Chun, Seoul National University and FriendliAI. Petuum Awarded OSDI 2021 Best Paper for Goodput-Optimized Deep Learning Research Petuum CASL research and engineering team's Pollux technical paper on adaptive scheduling for optimized. PET then automatically corrects results to restore full equivalence. Important Dates Abstract registrations due: Thursday, December 3, 2020, 3:00 pm PST Complete paper submissions due: Thursday, December 10, 2020, 3:00pm PST Author Response Period Moreover, to handle dynamic workloads, Nap adopts a fast NAL switch mechanism. Widely used log-search tools like Elasticsearch and Splunk Enterprise index the logs to provide fast search performance, yet the size of the index is within the same order of magnitude as the raw log size. Mingyu Li, Jinhao Zhu, and Tianxu Zhang, Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University; Shanghai AI Laboratory; Engineering Research Center for Domain-specific Operating Systems, Ministry of Education, China; Cheng Tan, Northeastern University; Yubin Xia, Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University; Shanghai AI Laboratory; Engineering Research Center for Domain-specific Operating Systems, Ministry of Education, China; Sebastian Angel, University of Pennsylvania; Haibo Chen, Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University; Shanghai AI Laboratory; Engineering Research Center for Domain-specific Operating Systems, Ministry of Education, China. We present DistAI, a data-driven automated system for learning inductive invariants for distributed protocols. Lukas Burkhalter, Nicolas Kchler, Alexander Viand, Hossein Shafagh, and Anwar Hithnawi, ETH Zrich. Session Chairs: Gennady Pekhimenko, University of Toronto / Vector Institute, and Shivaram Venkataraman, University of WisconsinMadison, Aurick Qiao, Petuum, Inc. and Carnegie Mellon University; Sang Keun Choe and Suhas Jayaram Subramanya, Carnegie Mellon University; Willie Neiswanger, Petuum, Inc. and Carnegie Mellon University; Qirong Ho, Petuum, Inc.; Hao Zhang, Petuum, Inc. and UC Berkeley; Gregory R. Ganger, Carnegie Mellon University; Eric P. Xing, MBZUAI, Petuum, Inc., and Carnegie Mellon University. For instance, the following are not sufficient grounds to specify a conflict with a PC member: they have reviewed the work before, they are employed by your competitor, they are your personal friend, they were your post-doc advisor or advisee, or they had the same advisor as you. Ethereum is the second-largest blockchain platform next to Bitcoin. This paper presents Zeph, a system that enables users to set privacy preferences on how their data can be shared and processed. Camera-ready submission (all accepted papers): 2 April 2021; Main conference program: 27-28 April 2021; All deadline times are . We particularly encourage contributions containing highly original ideas, new approaches, and/or groundbreaking results. Each new model trained with DP increases the bound on data leakage and can be seen as consuming part of a global privacy budget that should not be exceeded. This is especially true for DPF over Rnyi DP, a highly composable form of DP. Our evaluation on the SPEC benchmarks shows that SanRazor can reduce the overhead of sanitizers significantly, from 73.8% to 28.062.0% for AddressSanitizer, and from 160.1% to 36.6124.4% for UndefinedBehaviorSanitizer (depending on the applied reduction scheme). All deadline times are 23:59 hrs UTC. Our evaluation shows that PET outperforms existing systems by up to 2.5, by unlocking previously missed opportunities from partially equivalent transformations. At a high level, Addra follows a template in which callers and callees deposit and retrieve messages from private mailboxes hosted at an untrusted server. How can we design systems that will be reliable despite misbehaving participants? This talk will discuss several examples with very different solutions. Devices employ adaptive interrupt coalescing heuristics that try to balance between these opposing goals. Mothy joined the Computer Science Department ETH Zurich in January 2007 and was named Fellow of the ACM in 2013 for contributions to operating systems and networking research. Kyuhwa Han, Sungkyunkwan University and Samsung Electronics; Hyunho Gwak and Dongkun Shin, Sungkyunkwan University; Jooyoung Hwang, Samsung Electronics. Submissions may include as many additional pages as needed for references but not for appendices. Weak Links in Authentication Chains: A Large-scale Analysis of Email Sender Spoofing Attacks DMons targeted optimizations provide 16.83% speedup on average (up to 53.14%), compared to a baseline that uses the highest level of compiler optimization. As a result, the design of a file system with respect to space management and crash consistency is simplified, requiring only 10.8K LOC for full functionality. We propose PET, the first DNN framework that optimizes tensor programs with partially equivalent transformations and automated corrections. We will look at various problems and approaches, and for each, see if blockchain would help. We observe that, due to their intended security guarantees, SC schemes are inherently oblivioustheir memory access patterns are independent of the input data. Pollux promotes fairness among DL jobs competing for resources based on a more meaningful measure of useful job progress, and reveals a new opportunity for reducing DL cost in cloud environments. Furthermore, by combining SanRazor with an existing sanitizer reduction tool ASAP, we show synergistic effect by reducing the runtime cost to only 7.0% with a reasonable tradeoff of security. A graph neural network (GNN) enables deep learning on structured graph data. Message from the Program Co-Chairs. JEL codes: Q18, Q28, Q57 . While verifying GoJournal, we found one serious concurrency bug, even though GoJournal has many unit tests. Authors are also encouraged to contact the program co-chairs, osdi21chairs@usenix.org, if needed to relate their OSDI submissions to relevant submissions of their own that are simultaneously under review or awaiting publication at other venues. The NAL maintains 1) per-node partial views in PM for serving insert/update/delete operations with failure atomicity and 2) a global view in DRAM for serving lookup operations. Just using Lambdas on top of CPU servers offers up to 2.75 more performance-per-dollar than training only with CPU servers. All papers will be available online to registered attendees before the conference. Editor in charge: Daniel Petrolia . For more details on the submission process, and for templates to use with LaTeX, Word, etc., authors should consult the detailed submission requirements. (Visa applications can take at least 30 working days to process.) Our evaluation shows that NrOS scales to 96 cores with performance that nearly always dominates Linux at scale, in some cases by orders of magnitude, while retaining much of the simplicity of a sequential kernel. Based on this observation, P3 proposes a new approach for distributed GNN training. Submitted November 12, 2021 Accepted January 20, 2022. The key insight in blk-switch is that Linux's multi-queue storage design, along with multi-queue network and storage hardware, makes the storage stack conceptually similar to a network switch. Using this property, MAGE calculates the memory access pattern ahead of time and uses it to produce a memory management plan. Prior or concurrent workshop publication does not preclude publishing a related paper in OSDI. Session Chairs: Sebastian Angel, University of Pennsylvania, and Malte Schwarzkopf, Brown University, Ishtiyaque Ahmad, Yuntian Yang, Divyakant Agrawal, Amr El Abbadi, and Trinabh Gupta, University of California Santa Barbara. OSDI takes a broad view of the systems area and solicits contributions from many fields of systems practice, including, but not limited to, operating systems, file and storage systems, distributed systems, cloud computing, mobile systems, secure and reliable systems, systems aspects of big data, embedded systems, virtualization, networking as it relates to operating systems, and management and troubleshooting of complex systems. Authors should email the program co-chairs, osdi21chairs@usenix.org, a copy of the related workshop paper and a short explanation of the new material in the conference paper beyond that published in the workshop version. Yet, existing efforts randomly select FL participants, which leads to poor model and system efficiency. We also verified a simple NFS server using GoJournals specs, which confirms that they are helpful for application verification: a significant part of the proof doesnt have to consider concurrency and crashes. She has a PhD in computer science from MIT. This paper demonstrates that it is possible to achieve s-scale latency using Linux kernel storage stack, even when tens of latency-sensitive applications compete for host resources with throughput-bound applications that perform read/write operations at throughput close to hardware capacity. These limitations require state-of-the-art systems to distribute training across multiple machines. We have made Fluffy publicly available at https://github.com/snuspl/fluffy to contribute to the security of Ethereum. We implement and evaluate a suite of applications, including MICA, Raft and Set Algebra for document retrieval; and we demonstrate that the nanoPU can be used as a high performance, programmable alternative for one-sided RDMA operations. When registering your abstract, you must provide information about conflicts with PC members. To this end, we propose GNNAdvisor, an adaptive and efficient runtime system to accelerate various GNN workloads on GPU platforms. If you have any questions about conflicts, please contact the program co-chairs. The papers will be available online to everyone beginning on the first day of the conference, July 14, 2021. . Memory allocation represents significant compute cost at the warehouse scale and its optimization can yield considerable cost savings. Collaboration: You have a collaboration on a project, publication, grant proposal, program co-chairship, or editorship within the past two years (December 2018 through March 2021). Professor Veloso is on leave from Carnegie Mellon University as the Herbert A. Simon University Professor in the School of Computer Science, and the past Head of the Machine Learning Department. Lifting predicates and crash framing make the specification easy to use for developers, and logically atomic crash specifications allow for modular reasoning in GoJournal, making the proof tractable despite complex concurrency and crash interleavings. With the help of thousands of Lambda threads, Dorylus scales GNN training to billion-edge graphs. We describe PrivateKube, an extension to the popular Kubernetes datacenter orchestrator that adds privacy as a new type of resource to be managed alongside other traditional compute resources, such as CPU, GPU, and memory. Yuke Wang, Boyuan Feng, Gushu Li, Shuangchen Li, Lei Deng, Yuan Xie, and Yufei Ding, University of California, Santa Barbara. Conference Dates: Apr 12, 2021 - Apr 14, 2021. We implemented the ZNS+ SSD at an SSD emulator and a real SSD. Calibrated interrupts increase throughput by up to 35%, reduce CPU consumption by as much as 30%, and achieve up to 37% lower latency when interrupts are coalesced. Distributed systems are notoriously hard to implement correctly due to non-determinism. We present application studies for 8 applications, improving requests-per-second (RPS) by 7.7% and reducing RAM usage 2.4%. We propose a learning-based framework that instead explicitly optimizes concurrency control via offline training to maximize performance. In addition, increasing CPU core counts further complicate kernel development. We built an FPGA prototype of the nanoPU fast path by modifying an open-source RISC-V CPU, and evaluated its performance using cycle-accurate simulations on AWS FPGAs. If your accepted paper should not be published prior to the event, please notify production@usenix.org. Our approach effectively eliminates high communication and partitioning overheads, and couples it with a new pipelined push-pull parallelism based execution strategy for fast model training. A glance at this year's OSDI program shows that Operating Systems are a small niche topic for this conference, not even meriting their own full session. The symposium emphasizes innovative research as well as quantified or insightful experiences in systems design and implementation. For conference information, . The main contribution of this paper is GoJournal, a verified, concurrent journaling system that provides atomicity for storage applications, together with Perennial 2.0, a framework for formally specifying and verifying concurrent crash-safe systems.