NSDI 2019
| title | author | length |
|---|---|---|
| Preview Sessions | Brent E. Stephens, Aurojit Panda, Akshay Narayan, Anirudh Sivaraman, Dinesh Bharadia, Amy Ousterhout, Anurag Khandelwal, Junchen Jiang, Radhika Mittal, David R. Choffnes, Costin Raicu, Shaddi Hasan | 02h 53m |
Ten-minute rapid tour that names concrete problems, numbers and fixes: NICs hit 120 ns per 100Gb packet so CPU cycles matter; kernel bypass shows a tradeoff… | ||
| Datacenter RPCs can be General and Fast | Anuj Kalia, Michael Kaminsky, David G. Andersen | 24m |
Anuj Kalia, Carnegie Mellon University
Awarded Best Paper!
It is commonly believed that datacenter networking software must sacrifice generality to attain… | ||
| Eiffel: Efficient and Flexible Software Packet Scheduling | Ahmed Saeed, Yimeng Zhao, Nandita Dukkipati, Ellen Zegura, Mostafa Ammar, Khaled Harras, Amin Vahdat | 22m |
Eiffel implements software packet scheduling around an FFS-based integer priority queue and a secondary queue to handle moving time ranges, plus an optional… | ||
| Loom: Flexible and Efficient NIC Packet Scheduling | Brent E. Stephens, Aditya Akella, Michael Swift | 28m |
Loom moves per-flow packet scheduling entirely into the NIC and implements a restricted DAG policy abstraction plus a programmable hierarchical scheduler and a… | ||
| Exploiting Commutativity For Practical Fast Replication | Seo Jin Park, John Ousterhout | 20m |
Proposes consistent unordered replication (CURP): clients replicate requests to small temporary witnesses without waiting for global ordering, allowing 1 RTT… | ||
| Flashield: a Hybrid Key-value Cache that Controls Flash Write Amplification | Assaf Eisenman, Asaf Cidon, Evgenya Pergament, Or Haimovich, Ryan Stutsman, Mohammad Alizadeh, Sachin Katti | 25m |
Flashield is a hybrid DRAM+SSD key‑value cache that uses DRAM as a filter and a lightweight SVM classifier (features: past reads and updates) to admit only… | ||
| Size-aware Sharding For Improving Tail Latencies in In-memory Key-value Stores | Diego Didona, Willy Zwaenepoel | 23m |
Minos implements size-aware sharding in an in-memory KV store (DPDK, 8 cores, 40 Gb NIC) by partitioning cores into disjoint small/large sets, using a runtime… | ||
| Monoxide: Scale out Blockchains with Asynchronous Consensus Zones | Jiaping Wang, Hao Wang | 29m |
Proposes Asynchronous Consensus Zones that run many independent single‑chain zones to partition state and traffic and claims linear scaling: a testbed of 1,200… | ||
| FreeFlow: Software-based Virtual RDMA Networking for Containerized Clouds | Daehyeok Kim, Tianlong Yu, Hongqiang Harry Liu, Yibo Zhu, Jitu Padhye, Shachar Raindel, Chuanxiong Guo, Vyas Sekar, Srinivasan Seshan | 26m |
FreeFlow implements a software RDMA virtualization layer that runs on commodity RDMA NICs, intercepting libibverbs’ serialized commands and presenting shadow… | ||
| Direct Universal Access: Making Data Center Resources Available to FPGA | Ran Shu, Peng Cheng, Guo Chen, Zhiyuan Guo, Lei Qu, Yongqiang Xiong, Derek Chiou, Thomas Moscibroda | 17m |
DUA implements an FPGA-side IP layer plus a CPU control plane that uses server IPs as top-level names to give FPGAs global names and a unified socket-like… | ||
| Stardust: Divide and Conquer in the Data Center Network | Noa Zilberman, Gabi Bracha, Golan Schzukin | 25m |
Stardust replaces multi-function fabric switches with simple cell switches in the fabric and richer packet-to-cell adapters at the edge, using scheduled… | ||
| Blink: Fast Connectivity Recovery Entirely in the Data Plane | Thomas Holterbach, Edgar Costa Molero, Maria Apostolaki, Alberto Dainotti, Stefano Vissicchio, Laurent Vanbever | 24m |
Blink detects remote outages from TCP retransmission waves by tracking 64 flows per prefix with an 800 ms window, counting flows with consecutive identical… | ||
| Hydra: a federated resource manager for data-center scale analytics | Carlo Curino, Subru Krishnan, Konstantinos Karanasos, Sriram Rao, Giovanni M. Fumarola, Botong Huang, Kishore Chaliparambil, Arun Suresh, Young Chen, Solom Heddaya, Roni Burd, Sarvesh Sakalanaga, Chris Douglas, Bill Ramsey, Raghu Ramakrishnan | 27m |
Hydra is a federated resource manager built by extending Apache YARN and deployed across ~250,000 servers to schedules nearly one trillion tasks and process… | ||
| Shuffling, Fast and Slow: Scalable Analytics on Serverless Infrastructure | Qifan Pu, Shivaram Venkataraman, Ion Stoica | 26m |
Locus implements a hybrid shuffle that buffers hot partitions in fast cache (Redis) and spills to cheap object storage (S3), guided by a performance/cost model… | ||
| dShark: A General, Easy to Program and Scalable Framework for Analyzing In-network | Da Yu, Yibo Zhu, Behnaz Arzani, Rodrigo Fonseca, Tianrong Zhang, Karl Deng, Lihua Yuan | 22m |
dShark provides a MapReduce-like pipeline that parses mirrored packets into compact summaries using a JSON declarative spec and runs per-group analysis with… | ||
| Minimal Rewiring: Efficient Live Expansion for Clos Data Center Networks | Shizhen Zhao, Rui Wang, Junlan Zhou, Joon Ong, Jeffrey C. Mogul, Amin Vahdat | 23m |
Claims a practical, live expansion method for Clos datacenters that avoids packet loss by adding a patch-panel layer and sequencing rewires so controllers… | ||
| Understanding Lifecycle Management Complexity of Datacenter Topologies | Mingyang Zhang, Radhika Niranjan Mysore, Sucha Supittayapornpong, Ramesh Govindan | 22m |
Awarded Best Paper! Paper defines concrete deployment and expansion metrics—number of switches, patch panels, bundle taps and expansion-step count plus… | ||
| Shoal: A Network Architecture for Disaggregated Racks | Vishal Shrivastav, Asaf Valadarsky, Hitesh Ballani, Paolo Costa, Ki Suh Lee, Han Wang, Rachit Agarwal, Hakim Weatherspoon | 25m |
Shoal presents a rack fabric built from nanosecond circuit switches and a fully decentralized, traffic‑agnostic static cyclic schedule that forces every node… | ||
| Pushing the Range Limits of Commercial Passive RFIDs | Jingxian Wang, Junbo Zhang, Rajarshi Saha, Haojian Jin, Swarun Kumar | 22m |
PushID claims it extends commercial passive RFID range without changing tags by coordinating off-the-shelf readers to do coherent distributed beamforming. It… | ||
| Towards Programming the Radio Environment with Large Arrays of Inexpensive Antennas | Zhuqi Li, Yaxiong Xie, Longfei Shangguan, Rotman Ivan Zelaya, Jeremy Gummeson, Wenjun Hu, Kyle Jamieson | 23m |
Instruments the room with a 36-element passive array of cheap two-antenna boards, each with an on-board phase shifter, and runs a two-probe channel… | ||
| SweepSense: Sensing 5 GHz in 5 Milliseconds with Low-cost Radios | Yeswanth Guddeti, Raghav Subbaraman, Moein Khazraee, Aaron Schulman, Dinesh Bharadia | 23m |
Yeswanth Guddeti, UC San Diego; Raghav Subbaraman, IIT Madras; Moein Khazraee, Aaron Schulman, and Dinesh Bharadia, UC San Diego
Wireless transmissions occur… | ||
| Slim: OS Kernel Support for a Low-Overhead Container Overlay Network | Danyang Zhuo, Kaiyuan Zhang, Yibo Zhu, Hongqiang Harry Liu, Matthew Rockett, Arvind Krishnamurthy, Thomas E. Anderson | 27m |
Slim implements connection-based virtualization that maps virtual container connections to host TCP connections via a user-space Slim router, avoiding… | ||
| Shinjuku: Preemptive Scheduling for μsecond-scale Tail Latency | Kostis Kaffes, Timothy Chong, Jack Tigar Humphries, Adam Belay, David Mazières, Christos Kozyrakis | 24m |
Kostis Kaffes, Timothy Chong, and Jack Tigar Humphries, Stanford University; Adam Belay, Massachusetts Institute of Technology; David Mazières and Christos… | ||
| Shenango: Achieving High CPU Efficiency for Latency-sensitive Datacenter Workloads | Amy Ousterhout, Joshua Fried, Jonathan Behrens, Adam Belay, Hari Balakrishnan | 25m |
Shenango builds a single busy-spinning IOKernel plus per-application runtimes (C++/Rust) and uses DPDK to steer packets and reallocate cores every 5 µs by… | ||
| End-to-end I/O Monitoring on a Leading Supercomputer | Bin Yang, Xu Ji, Xiaosong Ma, Xiyang Wang, Tianyu Zhang, Xiupeng Zhu, Nosayba El-Sayed, Haidong Lan, Yibo Yang, Jidong Zhai, Weiguo Liu, Wei Xue | 25m |
Beacon implements end-to-end I/O tracing on the 40,960‑node Sunway TaihuLight, collecting per‑job traces from compute, forwarding, storage and metadata servers… | ||
| Zeno: Diagnosing Performance Problems with Temporal Provenance | Yang Wu, Ang Chen, Linh Thi Xuan Phan | 20m |
Introduces temporal provenance and an algorithm that adds sequencing edges to provenance graphs to expose off‑path causes that only affect latency, not… | ||
| Confluo: Distributed Monitoring and Diagnosis Stack for High-speed Networks | Anurag Khandelwal, Rachit Agarwal, Ion Stoica | 24m |
Confluo claims an end-host stack that captures packet-header telemetry at line rate on 10Gbps links using a single core by storing fixed-size header fields in… | ||
| DETER: Deterministic TCP Replay for Performance Diagnosis | Yuliang Li, Rui Miao, Mohammad Alizadeh, Minlan Yu | 26m |
Deterministic replay tool DETER records lightweight socket calls plus only the packet mutations (drops, reorders, marks) and a tiny kernel log of handler… | ||
| JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative | Eunji Jeong, Sungwoo Cho, Gyeong-In Yu, Joo Seong Jeong, Dong-Jin Shin, Byung-Gon Chun | 26m |
JANUS converts unmodified Python imperative DL code into optimized symbolic dataflow graphs by speculative graph generation after lightweight profiling… | ||
| BLAS-on-flash: An Efficient Alternative for Large Scale ML Training and Inference? | Suhas Jayaram Subramanya, Harsha Vardhan Simhadri, Srajan Garg, Anil Kag, Venkatesh Balasubramanian | 24m |
Suhas Jayaram Subramanya and Harsha Vardhan Simhadri, Microsoft Research India; Srajan Garg, IIT Bombay; Anil Kag and Venkatesh Balasubramanian, Microsoft… | ||
| Tiresias: A GPU Cluster Manager for Distributed Deep Learning | Juncheng Gu, Mosharaf Chowdhury, Kang G. Shin, Yibo Zhu, Myeongjae Jeon, Junjie Qian, Hongqiang Liu, Chuanxiong Guo | 24m |
Tiresias is a GPU cluster manager that actually implements two age‑based schedulers — Discretized Two‑Dimensional Gittins index (needs a prior distribution)… | ||
| Correctness and Performance for Stateful Chained Network Functions | Junaid Khalid, Aditya Akella | 21m |
Junaid Khalid and Aditya Akella, University of Wisconsin - Madison
Network functions virtualization (NFV) allows operators to employ NF chains to realize… | ||
| Performance Contracts for Software Network Functions | Rishabh Iyer, Luis Pedrosa, Arseniy Zaostrovnykh, Solal Pirelli, Katerina Argyraki, George Candea | 26m |
Defines performance contracts that map NF packet classes to human‑readable formulas over PCVs and claims static prediction of per‑packet instruction and memory… | ||
| FlowBlaze: Stateful Packet Processing in Hardware | Salvatore Pontarelli, Roberto Bifulco, Marco Bonola, Carmelo Cascone, Marco Spaziani Brunella, Valerio Bruschi, Davide Sanvito, Giuseppe Siracusano, Antonio Capone, Michio Honda, Felipe Huici, Giuseppe Bianchi | 26m |
Salvatore Pontarelli, Axbryd/CNIT; Roberto Bifulco, NEC Laboratories Europe; Marco Bonola, Axbryd/CNIT; Carmelo Cascone, Open Networking Foundation; Marco… | ||
| SIMON: A Simple and Scalable Method for Sensing, Inference and Measurement in... | Yilong Geng, Shiyu Liu, Zi Yin, Ashish Naik, Balaji Prabhakar, Mendel Rosenblum, Amin Vahdat | 27m |
SIMON reconstructs per-switch queue averages from edge TX/RX timestamps and a small set of probes, solves an underdetermined linear system with Lasso and then… | ||
| Is advance knowledge of flow sizes a plausible assumption? | Vojislav Ðukić, Sangeetha Abdu Jyothi, Bojan Karlaš, Muhsen Owaida, Ce Zhang, Ankit Singla | 17m |
Paper evaluates whether flow sizes can be known ahead of time and finds complete clairvoyance likely intractable but partial knowledge is usable. It builds… | ||
| Stable and Practical AS Relationship Inference with ProbLink | Yuchen Jin, Colin Scott, Amogh Dhamdhere, Vasileios Giotsas, Arvind Krishnamurthy, Scott Shenker | 22m |
Presents a probabilistic AS relationship inference system that actually reduces real-world errors: ProbLink is an EM-style, unsupervised classifier built from… | ||
| NetBouncer: Active Device and Link Failure Localization in Data Center Networks | Cheng Tan, Ze Jin, Chuanxiong Guo, Tianrong Zhang, Haitao Wu, Karl Deng, Dongming Bi, Dong Xiang | 23m |
NetBouncer actively probes paths using IP-in-IP and a packet bouncing strategy from servers to measure per-path loss, sends thousands of probes every five… | ||
| Riverbed: Enforcing User-defined Privacy Constraints in Distributed Web Services | Frank Wang, Ronny Ko, James Mickens | 26m |
Riverbed implements a transparent Riverbed proxy that tags client data with simple policies and a taint-tracking Python runtime that enforces them; policies… | ||
| Hyperscan: A Fast Multi-pattern Regex Matcher for Modern CPUs | Xiang Wang, Yang Hong, Harry Chang, KyoungSoo Park, Geoff Langdale, Jiayu Hu, Heqing Zhu | 24m |
Hyperscan decomposes complex regexes into string fragments and small FA components using graph analyses (dominant path, region, max‑flow/min‑cut), compiles… | ||
| Deniable Upload and Download via Passive Participation | David Sommer | 26m |
CoverUp implements passive participation: a collaborating website serves a JavaScript snippet that stores one constant-size encrypted chunk at a time in local… | ||
| CAUDIT: Continuous Auditing of SSH Servers To Mitigate Brute-Force Attacks | Phuong M. Cao, Yuming Wu, Subho S. Banerjee, Justin Azoff, Alex Withers, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer | 21m |
Deployed at NCSA (UIUC), a /16 honeypot captures SSH metadata from ~405 million recorded attempts and feeds a continuous auditing pipeline that replays attacks… | ||
| Dataplane equivalence and its applications | Dragos Dumitrescu, Radu Stoenescu, Matei Popovici, Lorina Negreanu, Costin Raiciu | 25m |
An algorithm called netdiff models dataplanes in SEFL and uses symbolic execution plus an SMT solver to check packet-by-packet equivalence, matching sets of… | ||
| Alembic: Automated Model Inference for Stateful Network Functions | Soo-Jin Moon | 27m |
Alembic automatically synthesizes per-rule symbolic FSMs (using an L–style learner) and composes them into an offline symbolic FSM learning database and a fast… | ||
| Model-Agnostic and Efficient Exploration of Numerical State Space of Real-World... | Wei Sun, Lisong Xu, Sebastian Elbaum, Di Zhao | 21m |
Presents ACT, a model-agnostic tester that combines random testing with guided feedback to explore TCP congestion-control numerical state spaces without… | ||
| Scaling Community Cellular Networks with CommunityCellularManager | Shaddi Hasan, Mary Claire Barela, Matt Johnson, Eric Brewer, Kurtis Heimerl | 23m |
Provides a concrete system: CCM client runs a microscale mobile core at each site while a cloud CCM controller mediates spectrum, numbers and interconnection… | ||
| TrackIO: Tracking First Responders Inside-Out | Ashutosh Dhekne, Ayon Chakraborty, Karthikeyan Sundaresan, Sampath Rangarajan | 23m |
TrackIO localizes first responders from outside using UAV-mounted UWB radios and a real prototype (DJI drone + Raspberry Pi + UWB beacons) that feeds a… | ||
| 3D Backscatter Localization for Fine-Grained Robotics | Zhihong Luo, Qiping Zhang, Yunfei Ma, Manish Singh, Fadel Adib | 24m |
TurboTrack is a 3D backscatter localization system that combines a Bayesian space-time super-resolution algorithm and a time-resolution localization helper… | ||
| Many-to-Many Beam Alignment in Millimeter Wave Networks | Suraj Jog, Jiaming Wang, Junfeng Guan, Thomas Moon, Haitham Hassanieh, Romit Roy Choudhury | 25m |
Suraj Jog, Jiaming Wang, Junfeng Guan, Thomas Moon, Haitham Hassanieh, and Romit Roy Choudhury, UIUC
Millimeter Wave (mmWave) networks can deliver multi-Gbps… | ||
| NetScatter: Enabling Large-Scale Backscatter Networks | Mehrdad Hessar, Ali Najafi, Shyamnath Gollakota | 19m |
First protocol that decodes hundreds of simultaneous backscatter radios by assigning distributed chirp/cyclic-shift coding so each device maps to an FFT bin… | ||
| nothing matches | ||