SCREAM: Sketch Resource Allocation for Software-defined Measurement
|
|
- Laurel Hicks
- 6 years ago
- Views:
Transcription
1 SCREAM: Sketch Resource Allocation for Software-defined Measurement (CoNEXT 15) Masoud Moshref, Minlan Yu, Ramesh Govindan, Amin Vahdat
2 Measurement is Crucial for Network Management Network Management on multiple tenants: Traffic Anomaly DDoS Engineering Detection detection Accounting Anomaly Detection Need fine-grained visibility of network traffic Measurement tasks: Heavy Hitter detection Heavy hitter detection (HH) Heavy Hitter detection Hierarchical heavy hitter detection (HHH) Change detection Super source detection (SSD) 2
3 Software Defined Measurement Task 1 Task 2 DREAM [SIGCOMM 14] / SCREAM [CoNEXT 15] Controller Configure Collect Switch A Task 1 counters Task 2 counters Switch B Task 1 counters Task 2 counters 3
4 Our Focus: Sketch-based Measurement Summaries of streaming data to approximately answer specific queries E.g., Bitmap for counting unique items Memory OpenFlow Counters DREAM [SIGCOMM 14] Expensive, power-hungry TCAM Sketches SCREAM [CoNEXT 15] Cheaper SRAM Counters Volume counters Volume and Connection counters Flows Selected prefixes All traffic all-the-time Sketches use a cheaper memory and are more expressive 4
5 Sketch Example: Count-Min Sketch At packet arrival: (IP, 1 Kbytes) h1(ip) h2(ip) d h3(ip) 1+1=2 4+1=5 2+1=3 At query: What is the traffic size of IP? = row with min collision = Min(3,5,2) = 2 Resource accuracy trade-off: Provable error bound given traffic properties (e.g., skew) 5
6 Challenges: Limited Counters for Many Tasks Limited shared resources: SRAM capacity (e.g., 128 MB) Shared with other functions (e.g., routing) Too many resources to guarantee accuracy: 1 MB-32 MB per task Less than tasks in SRAM Many task instances: 3 types (Heavy hitter, Hierarchical heavy hitter, Super source) Different flow aggregates (Rack, App, Src/Dst/Port) 1000s of tenants 6
7 Goal: Many Accurate Sketch-based Measurements Users dynamically instantiate a variety of measurement tasks SCREAM supports the largest number of measurement tasks while maintaining measurement accuracy 7
8 Approach: Dynamic Resource Allocation Resource accuracy trade-off depends on traffic Count Min: Provable error bound given traffic properties Ex: Skew of traffic from each IP Required memory Worst-case uses >10x counters than average Skew Dynamic allocation for current traffic 8
9 Opportunity: Temporal Multiplexing Memory requirement varies over time Required Memory Task 1 Task 2 Time Multiplex memory among tasks over time 9
10 Opportunity: Spatial Multiplexing Memory requirement varies across switches Required Memory Task 1 Task 2 Switch A Switch B Multiplex memory among tasks across switches 10
11 Key Insight Leverage spatial and temporal multiplexing and dynamically allocate switch memory per task to achieve sufficient accuracy for many tasks DREAM has the same insight SCREAM applies it for sketches 11
12 SCREAM Contributions 2- Allocate memory among sketch-based task instances across switches while maintaining sufficient accuracy SCREAM Dynamic resource allocator Heavy hitter (HH) tasks Allocation Hierarchical heavy hitter (HHH) tasks Super Source (SSD) tasks 1- Supports 3 sketch-based task types Anomaly detection Traffic engineering DDoS detection 12
13 SCREAM Iterative Workflow Collect & report Counters from many switches Estimate accuracy Accuracy Allocate resources Memory size 13
14 SCREAM Iterative Workflow Collect & report Estimate accuracy Task1 accuracy <80% Allocate resources Give more memory to task1 Accuracy Allocated Memory (KB) Task Task 11 Task Time (s) Task Task 1 Task Task Time (s) 14
15 SCREAM Iterative Workflow Collect & report Merge counters from switches Estimate accuracy Skew of traffic for task2 changes Task2 accuracy <80% Allocate resources Give more memory to task2 Precision Accuracy Allocated Memory (KB) Task 1 Task Time (s) Task 1 Task Time (s) 15
16 SCREAM Challenges Collect & report Network-wide task implementation using sketches Estimate accuracy Accuracy estimation without the ground-truth Allocate resources Fast & Stable allocation in DREAM [SIGCOMM 14]
17 Challenge: Merge Sketches of Different Sizes Switch A Network-wide Task Heavy hitter (HH) Source IPs sending > 10Mbps Switch B d d w1 w2 17
18 SCREAM Solution to Merge Sketches for HH Detection Previous work: Min of sums Min Switch A SCREAM: Sum of mins Min + 30 Switch B Min Both over-approximate smaller is more accurate 18
19 SCREAM Solutions Collect & report Network-wide task implementation using sketches Merge sketches of different sizes for HH, HHH, SSD SSD algorithm with higher and more stable accuracy Estimate accuracy Accuracy estimation without the ground-truth Allocate resources Fast & Stable allocation in DREAM [SIGCOMM 14]
20 Precision Estimation for Heavy Hitter Detection True detected HH Precision = = Sum(P[Detected HH is true]) Detected HHs Insight: Relate probability to Error on counters of detected HHs Estimate-Threshold Threshold Error Estimate-Threshold True HH False HH Estimated Real P[Detected HH is true] = 1 - P[Error Estimate-Threshold] 20
21 Precision Estimation Step 1: Find a Bound on The Error P[Detected HH is true] = 1 - P[Error Estimate-Threshold] Insight: Relate probability to Error on counters of detected HHs Idea 1: Use average Error in Markov s inequality to bound it Idea 1 21
22 Precision Estimation Step 2: Improve The Bound Idea 2 Idea 1 A row in Count-Min: Insight: Average Error = heavy items collision + small items collision Counter indices of detected HHs show heavy collisions Idea 2: Markov s inequality only for small items 22
23 SCREAM Solutions Collect & report Network-wide task implementation using sketches Merge sketches of different sizes for HH, HHH, SSD SSD algorithm with higher and more stable accuracy Estimate accuracy Accuracy estimation without the ground-truth Precision estimators for HH, HHH and SSD tasks Allocate resources Fast & Stable allocation in DREAM [SIGCOMM 14]
24 Evaluation Metrics: Satisfaction of a task: Fraction of task s lifetime with sufficient accuracy % of rejected tasks Alternatives: OpenSketch: Allocate for bounded error for worst-case traffic at task instantiation (test with different bounds) Oracle: Knows required resource for a task in each switch in advance 24
25 Evaluation Setting Simulation for 8 switches: 256 task instances (HH, HHH, SSD, combination) Accuracy bound = 80% 5 min tasks arriving in 20 minutes 2 hours CAIDA trace 25
26 SCREAM Provides High Accuracy for More Tasks SCREAM: High satisfaction and low reject Average Satisfaction OS_10 OS_50 20 OS_90 SCREAM Switch capacity (KB) Rejected tasks (%) OS_10 OS_50 OS_90 SCREAM Switch capacity (KB) OpenSketch: Loose bound Under provision low satisfaction Tight bound Over provision high reject 26
27 SCREAM s Performance Is Close to An Oracle Average Satisfaction Oracle SCREAM Switch capacity (KB) Rejected tasks (%) Oracle SCREAM Switch capacity (KB) SCREAM performance is close to an oracle, its satisfaction is a bit lower because: Iterative allocation takes time Accuracy estimation has error 27
28 Other Evaluations Changing traffic skew SCREAM supports more accurate tasks than OpenSketch Accuracy estimation error SCREAM accuracy estimation has 5% error in average Other accuracy metrics Tasks in SCREAM have high recall (low false negative) 28
29 Conclusion Measurement is crucial for SDN management in a resource-constrained environment Practical sketch-based SDM by dynamic memory allocation Implementing network-wide tasks using sketches Estimating accuracy for 3 types of tasks SCREAM is available at github.com/usc-nsl/scream 29
30 Thanks! Questions? 30
SCREAM: Sketch Resource Allocation for Software-defined Measurement
: Sketch Resource Allocation for Software-defined Measurement Masoud Moshref Minlan Yu Ramesh Govindan Amin Vahdat University of Southern California Google ABSTRACT Software-defined networks can enable
More informationA Comparison of Performance and Accuracy of Measurement Algorithms in Software
A Comparison of Performance and Accuracy of Measurement Algorithms in Software Omid Alipourfard, Masoud Moshref 1, Yang Zhou 2, Tong Yang 2, Minlan Yu 3 Yale University, Barefoot Networks 1, Peking University
More informationSoftware Defined Traffic Measurement with OpenSketch
Software Defined Traffic Measurement with OpenSketch Minlan Yu Lavanya Jose Rui Miao University of Southern California Princeton University Abstract Most network management tasks in software-defined networks
More informationUnivMon: Software-defined Monitoring with Universal Sketch
UnivMon: Software-defined Monitoring with Universal Sketch Zaoxing (Alan) Liu Joint work with Antonis Manousis (CMU), Greg Vorsanger(JHU), Vyas Sekar (CMU), and Vladimir Braverman(JHU) Network Management:
More informationSIGCOMM 17 Preview Session: Network Monitoring
SIGCOMM 17 Preview Session: Network Monitoring Ying Zhang Software Engineer, Facebook Network monitoring is important! Performance Diagnose long delay/loss problems Utilization Traffic engineering Availability
More informationMAD 12 Monitoring the Dynamics of Network Traffic by Recursive Multi-dimensional Aggregation. Midori Kato, Kenjiro Cho, Michio Honda, Hideyuki Tokuda
MAD 12 Monitoring the Dynamics of Network Traffic by Recursive Multi-dimensional Aggregation Midori Kato, Kenjiro Cho, Michio Honda, Hideyuki Tokuda 1 Background Traffic monitoring is important to detect
More informationHeavy-Hitter Detection Entirely in the Data Plane
Heavy-Hitter Detection Entirely in the Data Plane VIBHAALAKSHMI SIVARAMAN SRINIVAS NARAYANA, ORI ROTTENSTREICH, MUTHU MUTHUKRSISHNAN, JENNIFER REXFORD 1 Heavy Hitter Flows Flows above a certain threshold
More informationScalable and Robust DDoS Detection via Universal Monitoring
Scalable and Robust DDoS Detection via Universal Monitoring Vyas Sekar Joint work with: Alan Liu, Vladimir Braverman JHU Hun Namkung, Antonis Manousis, CMU DDoS a&acks are ge-ng worse Increasing in number
More informationScalable Enterprise Networks with Inexpensive Switches
Scalable Enterprise Networks with Inexpensive Switches Minlan Yu minlanyu@cs.princeton.edu Princeton University Joint work with Alex Fabrikant, Mike Freedman, Jennifer Rexford and Jia Wang 1 Enterprises
More informationTrumpet: Timely and Precise Triggers in Data Centers
Trumpet: Timely and Precise Triggers in Data Centers Masoud Moshref (USC) Minlan Yu (USC) Ramesh Govindan (USC) Amin Vahdat (Google, inc.) Abstract As data centers grow larger and strive to provide tight
More informationRevisiting router architectures with Zipf
Revisiting router architectures with Zipf Steve Uhlig Deutsche Telekom Laboratories/TU Berlin Nadi Sarrar, Anja Feldmann Deutsche Telekom Laboratories/TU Berlin Rob Sherwood, Xin Huang Deutsche Telekom
More informationImproving Sketch Reconstruction Accuracy Using Linear Least Squares Method
Improving Sketch Reconstruction Accuracy Using Linear Least Squares Method Gene Moo Lee, Huiya Liu, Young Yoon and Yin Zhang Department of Computer Sciences University of Texas at Austin Austin, TX 7872,
More informationDetecting Heavy Flows in the SDN Match and Action Model
Detecting Heavy Flows in the SDN Match and Action Model Yehuda Afek 1, Anat Bremler-Barr 2, Shir Landau Feibish 1, and Liron Schiff 1 1 Blavatnik School of Computer Science, Tel-Aviv University, Israel
More informationSketchLearn: Relieving User Burdens in Approximate Measurement with Automated Statistical Inference
SketchLearn: Relieving User Burdens in Approximate Measurement with Automated Statistical Inference Qun Huang, Patrick P. C. Lee, and Yungang Bao State Key Lab of Computer Architecture, Institute of Computing
More informationNaaS Network-as-a-Service in the Cloud
NaaS Network-as-a-Service in the Cloud joint work with Matteo Migliavacca, Peter Pietzuch, and Alexander L. Wolf costa@imperial.ac.uk Motivation Mismatch between app. abstractions & network How the programmers
More informationBuffered Count-Min Sketch on SSD: Theory and Experiments
Buffered Count-Min Sketch on SSD: Theory and Experiments Mayank Goswami, Dzejla Medjedovic, Emina Mekic, and Prashant Pandey ESA 2018, Helsinki, Finland The heavy hitters problem (HH(k)) Given stream of
More informationEmpowering Sketches with Machine Learning for Network Measurements
Empowering Sketches with Machine Learning for Network Measurements Tong Yang, Lun Wang, Yulong Shen #, Muhammad Shahzad $, Qun Huang Xiaohong Jiang @, Kun Tan, Xiaoming Li. Peking University. $ North Carolina
More informationSSA: A Power and Memory Efficient Scheme to Multi-Match Packet Classification. Fang Yu, T.V. Lakshman, Martin Austin Motoyama, Randy H.
SSA: A Power and Memory Efficient Scheme to Multi-Match Packet Classification Fang Yu, T.V. Lakshman, Martin Austin Motoyama, Randy H. Katz Presented by: Discussion led by: Sailesh Kumar Packet Classification
More informationDevoFlow: Scaling Flow Management for High Performance Networks
DevoFlow: Scaling Flow Management for High Performance Networks SDN Seminar David Sidler 08.04.2016 1 Smart, handles everything Controller Control plane Data plane Dump, forward based on rules Existing
More informationNew Directions in Traffic Measurement and Accounting. Need for traffic measurement. Relation to stream databases. Internet backbone monitoring
New Directions in Traffic Measurement and Accounting C. Estan and G. Varghese Presented by Aaditeshwar Seth 1 Need for traffic measurement Internet backbone monitoring Short term Detect DoS attacks Long
More informationDynamically Configurable Online Statistical Flow Feature Extractor on FPGA
Dynamically Configurable Online Statistical Flow Feature Extractor on FPGA Da Tong, Viktor Prasanna Ming Hsieh Department of Electrical Engineering University of Southern California Email: {datong, prasanna}@usc.edu
More informationOne-Pass Streaming Algorithms
One-Pass Streaming Algorithms Theory and Practice Complaints and Grievances about theory in practice Disclaimer Experiences with Gigascope. A practitioner s perspective. Will be using my own implementations,
More informationSummarizing and mining inverse distributions on data streams via dynamic inverse sampling
Summarizing and mining inverse distributions on data streams via dynamic inverse sampling Presented by Graham Cormode cormode@bell-labs.com S. Muthukrishnan muthu@cs.rutgers.edu Irina Rozenbaum rozenbau@paul.rutgers.edu
More informationApplication of SDN: Load Balancing & Traffic Engineering
Application of SDN: Load Balancing & Traffic Engineering Outline 1 OpenFlow-Based Server Load Balancing Gone Wild Introduction OpenFlow Solution Partitioning the Client Traffic Transitioning With Connection
More informationDevoFlow: Scaling Flow Management for High-Performance Networks
DevoFlow: Scaling Flow Management for High-Performance Networks Andy Curtis Jeff Mogul Jean Tourrilhes Praveen Yalagandula Puneet Sharma Sujata Banerjee Software-defined networking Software-defined networking
More informationTracking Frequent Items Dynamically: What s Hot and What s Not To appear in PODS 2003
Tracking Frequent Items Dynamically: What s Hot and What s Not To appear in PODS 2003 Graham Cormode graham@dimacs.rutgers.edu dimacs.rutgers.edu/~graham S. Muthukrishnan muthu@cs.rutgers.edu Everyday
More informationCS 153 Design of Operating Systems Winter 2016
CS 153 Design of Operating Systems Winter 2016 Lecture 18: Page Replacement Terminology in Paging A virtual page corresponds to physical page/frame Segment should not be used anywhere Page out = Page eviction
More informationvcrib: Virtualized Rule Management in the Cloud
vcrib: Virtualized Rule Management in the Cloud Masoud Moshref Minlan Yu Abhishek Sharma Ramesh Govindan University of Southern California NEC Abstract Cloud operators increasingly need many fine-grained
More informationEpisode 3. Principles in Network Design
Episode 3. Principles in Network Design Part 2 Baochun Li Department of Electrical and Computer Engineering University of Toronto Recall: Designing the network as a system Last episode: Every complex computer
More informationThe University of Adelaide, School of Computer Science 13 September 2018
Computer Architecture A Quantitative Approach, Sixth Edition Chapter 2 Memory Hierarchy Design 1 Programmers want unlimited amounts of memory with low latency Fast memory technology is more expensive per
More informationScalable Rule Management for Data Centers Masoud Moshref Minlan Yu Abhishek Sharma Ramesh Govindan University of Southern California
Scalable Rule Management for Data Centers Masoud Moshref Minlan Yu Abhishek Sharma Ramesh Govindan University of Southern California NEC Labs America Abstract Cloud operators increasingly need more and
More informationPricing Intra-Datacenter Networks with
Pricing Intra-Datacenter Networks with Over-Committed Bandwidth Guarantee Jian Guo 1, Fangming Liu 1, Tao Wang 1, and John C.S. Lui 2 1 Cloud Datacenter & Green Computing/Communications Research Group
More informationTraffic Engineering with Forward Fault Correction
Traffic Engineering with Forward Fault Correction Harry Liu Microsoft Research 06/02/2016 Joint work with Ratul Mahajan, Srikanth Kandula, Ming Zhang and David Gelernter 1 Cloud services require large
More informationAdapted from David Patterson s slides on graduate computer architecture
Mei Yang Adapted from David Patterson s slides on graduate computer architecture Introduction Ten Advanced Optimizations of Cache Performance Memory Technology and Optimizations Virtual Memory and Virtual
More informationSENSS Against Volumetric DDoS Attacks
SENSS Against Volumetric DDoS Attacks Sivaram Ramanathan 1, Jelena Mirkovic 1, Minlan Yu 2 and Ying Zhang 3 1 University of Southern California/Information Sciences Institute 2 Harvard University 3 Facebook
More informationCSE 153 Design of Operating Systems
CSE 153 Design of Operating Systems Winter 18 Lecture 18/19: Page Replacement Memory Management Memory management systems Physical and virtual addressing; address translation Techniques: Partitioning,
More informationCellSDN: Software-Defined Cellular Core networks
CellSDN: Software-Defined Cellular Core networks Xin Jin Princeton University Joint work with Li Erran Li, Laurent Vanbever, and Jennifer Rexford Cellular Core Network Architecture Base Station User Equipment
More information( , *) one-to-many: e.g., scanning (*, ) many-to-one: e.g., DDoS ( /24, /28) subnet-to-subnet
(1.2.3.4, *) one-to-many: e.g., scanning (*, 5.6.7.8) many-to-one: e.g., DDoS (1.2.3.0/24, 4.5.6.0/28) subnet-to-subnet 2 c φn φ: N: 0.0.0.0/0 0.0.0.0/0 10.1/16 192.168/16 10.1/16 192.168/16 10.1.1/24
More informationSoftware Defined Network Traffic Measurement: Current Trends and Challenges
Software Defined Network Traffic Measurement: Current Trends and Challenges Abdulsalam Yassine, Hesam Rahimi, Shervin Shirmohammadi Distributed and Collaborative Virtual Environments Research Laboratory
More informationCounter Braids: A novel counter architecture
Counter Braids: A novel counter architecture Balaji Prabhakar Balaji Prabhakar Stanford University Joint work with: Yi Lu, Andrea Montanari, Sarang Dharmapurikar and Abdul Kabbani Overview Counter Braids
More informationEstimating Persistent Spread in High-speed Networks Qingjun Xiao, Yan Qiao, Zhen Mo, Shigang Chen
Estimating Persistent Spread in High-speed Networks Qingjun Xiao, Yan Qiao, Zhen Mo, Shigang Chen Southeast University of China University of Florida Motivation for Persistent Stealthy Spreaders Imagine
More informationCopyright 2018, Oracle and/or its affiliates. All rights reserved.
Beyond SQL Tuning: Insider's Guide to Maximizing SQL Performance Monday, Oct 22 10:30 a.m. - 11:15 a.m. Marriott Marquis (Golden Gate Level) - Golden Gate A Ashish Agrawal Group Product Manager Oracle
More informationTowards Deadline Guaranteed Cloud Storage Services Guoxin Liu, Haiying Shen, and Lei Yu
Towards Deadline Guaranteed Cloud Storage Services Guoxin Liu, Haiying Shen, and Lei Yu Presenter: Guoxin Liu Ph.D. Department of Electrical and Computer Engineering, Clemson University, Clemson, USA Computer
More informationDesign and Performance Analysis of a DRAM-based Statistics Counter Array Architecture
Design and Performance Analysis of a DRAM-based Statistics Counter Array Architecture Chuck Zhao 1 Hao Wang 2 Bill Lin 2 Jim Xu 1 1 Georgia Institute of Technology 2 University of California, San Diego
More informationTowards High-performance Flow-level level Packet Processing on Multi-core Network Processors
Towards High-performance Flow-level level Packet Processing on Multi-core Network Processors Yaxuan Qi (presenter), Bo Xu, Fei He, Baohua Yang, Jianming Yu and Jun Li ANCS 2007, Orlando, USA Outline Introduction
More informationFeature Rich Flow Monitoring with P4
Feature Rich Flow Monitoring with P4 John Sonchack University of Pennsylvania 1 Outline Introduction: Flow Records Design and Implementation: P4 Accelerated Flow Record Generation Benchmarks and Optimizations
More informationCourse : Data mining
Course : Data mining Lecture : Mining data streams Aristides Gionis Department of Computer Science Aalto University visiting in Sapienza University of Rome fall 2016 reading assignment LRU book: chapter
More informationSpring 2018 :: CSE 502. Cache Design Basics. Nima Honarmand
Cache Design Basics Nima Honarmand Storage Hierarchy Make common case fast: Common: temporal & spatial locality Fast: smaller, more expensive memory Bigger Transfers Registers More Bandwidth Controlled
More informationCACHE-GUIDED SCHEDULING
CACHE-GUIDED SCHEDULING EXPLOITING CACHES TO MAXIMIZE LOCALITY IN GRAPH PROCESSING Anurag Mukkara, Nathan Beckmann, Daniel Sanchez 1 st AGP Toronto, Ontario 24 June 2017 Graph processing is memory-bound
More informationNetwork Traffic Characteristics of Data Centers in the Wild. Proceedings of the 10th annual conference on Internet measurement, ACM
Network Traffic Characteristics of Data Centers in the Wild Proceedings of the 10th annual conference on Internet measurement, ACM Outline Introduction Traffic Data Collection Applications in Data Centers
More informationSimply Top Talkers Jeroen Massar, Andreas Kind and Marc Ph. Stoecklin
IBM Research - Zurich Simply Top Talkers Jeroen Massar, Andreas Kind and Marc Ph. Stoecklin 2009 IBM Corporation Motivation and Outline Need to understand and correctly handle dominant aspects within the
More informationSystems Programming and Computer Architecture ( ) Timothy Roscoe
Systems Group Department of Computer Science ETH Zürich Systems Programming and Computer Architecture (252-0061-00) Timothy Roscoe Herbstsemester 2016 AS 2016 Caches 1 16: Caches Computer Architecture
More informationTransistor: Digital Building Blocks
Final Exam Review Transistor: Digital Building Blocks Logically, each transistor acts as a switch Combined to implement logic functions (gates) AND, OR, NOT Combined to build higher-level structures Multiplexer,
More informationOutline. Motivation. Our System. Conclusion
Outline Motivation Our System Evaluation Conclusion 1 Botnet A botnet is a collection of bots controlled by a botmaster via a command and control (C&C) channel Centralized C&C, P2P-based C&C Botnets serve
More informationA Case for a RISC Architecture for Network Flow Monitoring
A Case for a RISC Architecture for Network Flow Monitoring Vyas Sekar 1, Michael K. Reiter 2, Hui Zhang 1 CMU-CS-9-125 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 1 Carnegie
More informationA Case for a RISC Architecture for Network Flow Monitoring
A Case for a RISC Architecture for Network Flow Monitoring Vyas Sekar, Michael K. Reiter, Hui Zhang Carnegie Mellon University, UNC Chapel-Hill ABSTRACT Several network management applications require
More informationI/O Characterization of Commercial Workloads
I/O Characterization of Commercial Workloads Kimberly Keeton, Alistair Veitch, Doug Obal, and John Wilkes Storage Systems Program Hewlett-Packard Laboratories www.hpl.hp.com/research/itc/csl/ssp kkeeton@hpl.hp.com
More informationCS 561, Lecture 2 : Hash Tables, Skip Lists, Bloom Filters, Count-Min sketch. Jared Saia University of New Mexico
CS 561, Lecture 2 : Hash Tables, Skip Lists, Bloom Filters, Count-Min sketch Jared Saia University of New Mexico Outline Hash Tables Skip Lists Count-Min Sketch 1 Dictionary ADT A dictionary ADT implements
More informationProgrammability, Integration and Visibility for Media Networks
C U R A T E D B Y Programmability, Integration and Visibility for Media Networks Gerard Phillips, Systems Engineer Arista Networks IP SHOWCASE THEATRE AT IBC SEPT. 14-18, 2018 The visibility challenge
More informationA Scalable DDoS Detection Framework with Victim Pinpoint Capability
660 JOURNAL OF COMMUNICATIONS, VOL. 6, NO. 9, DECEMBER 2011 A Scalable DDoS Detection Framework with Victim Pinpoint Capability Haiqin Liu, Yan Sun and Min Sik Kim School of Electrical Engineering and
More informationDynamic Pipelining: Making IP- Lookup Truly Scalable
Dynamic Pipelining: Making IP- Lookup Truly Scalable Jahangir Hasan T. N. Vijaykumar School of Electrical and Computer Engineering, Purdue University SIGCOMM 05 Rung-Bo-Su 10/26/05 1 0.Abstract IP-lookup
More informationLECTURE 11. Memory Hierarchy
LECTURE 11 Memory Hierarchy MEMORY HIERARCHY When it comes to memory, there are two universally desirable properties: Large Size: ideally, we want to never have to worry about running out of memory. Speed
More informationSOFTWARE DEFINED NETWORKS. Jonathan Chu Muhammad Salman Malik
SOFTWARE DEFINED NETWORKS Jonathan Chu Muhammad Salman Malik Credits Material Derived from: Rob Sherwood, Saurav Das, Yiannis Yiakoumis AT&T Tech Talks October 2010 (available at:www.openflow.org/wk/images/1/17/openflow_in_spnetworks.ppt)
More informationEpisode 5. Scheduling and Traffic Management
Episode 5. Scheduling and Traffic Management Part 2 Baochun Li Department of Electrical and Computer Engineering University of Toronto Outline What is scheduling? Why do we need it? Requirements of a scheduling
More informationFast and Accurate Load Balancing for Geo-Distributed Storage Systems
Fast and Accurate Load Balancing for Geo-Distributed Storage Systems Kirill L. Bogdanov 1 Waleed Reda 1,2 Gerald Q. Maguire Jr. 1 Dejan Kostic 1 Marco Canini 3 1 KTH Royal Institute of Technology 2 Université
More informationSchema-Agnostic Indexing with Azure Document DB
Schema-Agnostic Indexing with Azure Document DB Introduction Azure DocumentDB is Microsoft s multi-tenant distributed database service for managing JSON documents at Internet scale Multi-tenancy is an
More informationAdobe Analytics Product description
Adobe Analytics Product description Effective as of: March 6, 2017 What is Adobe Analytics? Adobe Analytics provides reporting, visualizations, and analysis of Customer Data that allows Customers to discover
More informationEnhancing Byte-Level Network Intrusion Detection Signatures with Context
Enhancing Byte-Level Network Intrusion Detection Signatures with Context Robin Sommer sommer@in.tum.de Technische Universität München Germany Vern Paxson vern@icir.org International Computer Science Institute
More informationOverview: motion estimation. Differential motion estimation
Overview: motion estimation Differential methods Fast algorithms for Sub-pel accuracy Rate-constrained motion estimation Bernd Girod: EE368b Image Video Compression Motion Estimation no. 1 Differential
More informationRoadmap. Java: Assembly language: OS: Machine code: Computer system:
Roadmap C: car *c = malloc(sizeof(car)); c->miles = 100; c->gals = 17; float mpg = get_mpg(c); free(c); Assembly language: Machine code: get_mpg: pushq movq... popq ret %rbp %rsp, %rbp %rbp 0111010000011000
More informationSCALING SOFTWARE DEFINED NETWORKS. Chengyu Fan (edited by Lorenzo De Carli)
SCALING SOFTWARE DEFINED NETWORKS Chengyu Fan (edited by Lorenzo De Carli) Introduction Network management is driven by policy requirements Network Policy Guests must access Internet via web-proxy Web
More informationCache Memories. From Bryant and O Hallaron, Computer Systems. A Programmer s Perspective. Chapter 6.
Cache Memories From Bryant and O Hallaron, Computer Systems. A Programmer s Perspective. Chapter 6. Today Cache memory organization and operation Performance impact of caches The memory mountain Rearranging
More informationSketchVisor: Robust Network Measurement for Software Packet Processing
SketchVisor: Robust Network Measurement for Software Packet Processing Qun Huang 1, Xin Jin 2, Patrick P. C. Lee 3, Runhui Li 1, Lu Tang 3, Yi-Chao Chen 1, Gong Zhang 1 1 Huawei Future Network Theory Lab
More informationCopyright 2012, Elsevier Inc. All rights reserved.
Computer Architecture A Quantitative Approach, Fifth Edition Chapter 2 Memory Hierarchy Design 1 Introduction Introduction Programmers want unlimited amounts of memory with low latency Fast memory technology
More informationComputer Architecture. A Quantitative Approach, Fifth Edition. Chapter 2. Memory Hierarchy Design. Copyright 2012, Elsevier Inc. All rights reserved.
Computer Architecture A Quantitative Approach, Fifth Edition Chapter 2 Memory Hierarchy Design 1 Programmers want unlimited amounts of memory with low latency Fast memory technology is more expensive per
More informationAutomated Application Signature Generation Using LASER and Cosine Similarity
Automated Application Signature Generation Using LASER and Cosine Similarity Byungchul Park, Jae Yoon Jung, John Strassner *, and James Won-ki Hong * {fates, dejavu94, johns, jwkhong}@postech.ac.kr Dept.
More informationIntroduction: Two motivating examples for the analytical approach
Introduction: Two motivating examples for the analytical approach Hongwei Zhang http://www.cs.wayne.edu/~hzhang Acknowledgement: this lecture is partially based on the slides of Dr. D. Manjunath Outline
More informationLast class: Today: Deadlocks. Memory Management
Last class: Deadlocks Today: Memory Management CPU il1 L2 Memory Bus (e.g. PC133) Main Memory dl1 On-chip I/O Bus (e.g. PCI) Disk Ctrller Net. Int. Ctrller Network Binding of Programs to Addresses Address
More informationTVA: A DoS-limiting Network Architecture L
DoS is not even close to be solved : A DoS-limiting Network Architecture L Xiaowei Yang (UC Irvine) David Wetherall (Univ. of Washington) Thomas Anderson (Univ. of Washington) 1 n Address validation is
More informationLevel 3 SM Enhanced Management - FAQs. Frequently Asked Questions for Level 3 Enhanced Management
Level 3 SM Enhanced Management - FAQs Frequently Asked Questions for Level 3 Enhanced Management 2015 Level 3 Communications, LLC. All rights reserved. 1 LAYER 3: CONVERGED SERVICES 5 Where can I find
More informationCS 240 Stage 3 Abstractions for Practical Systems
CS 240 Stage 3 Abstractions for Practical Systems Caching and the memory hierarchy Operating systems and the process model Virtual memory Dynamic memory allocation Victory lap Memory Hierarchy: Cache Memory
More informationPrinciples behind data link layer services:
Data Link Layer Goals: Principles behind data link layer services: Error detection, correction Sharing a broadcast channel: multiple access Link layer addressing Reliable data transfer, flow control: Done!
More informationCuckoo Cache a Technique to Improve Flow Monitoring Throughput
This article has been accepted for publication in IEEE Internet Computing but has not yet been fully edited. Some content may change prior to final publication. Cuckoo Cache a Technique to Improve Flow
More informationCopyright 2012, Elsevier Inc. All rights reserved.
Computer Architecture A Quantitative Approach, Fifth Edition Chapter 2 Memory Hierarchy Design 1 Introduction Programmers want unlimited amounts of memory with low latency Fast memory technology is more
More informationMemory Hierarchy. Jin-Soo Kim Computer Systems Laboratory Sungkyunkwan University
Memory Hierarchy Jin-Soo Kim (jinsookim@skku.edu) Computer Systems Laboratory Sungkyunkwan University http://csl.skku.edu Time (ns) The CPU-Memory Gap The gap widens between DRAM, disk, and CPU speeds
More informationVirtual Memory. Today.! Virtual memory! Page replacement algorithms! Modeling page replacement algorithms
Virtual Memory Today! Virtual memory! Page replacement algorithms! Modeling page replacement algorithms Reminder: virtual memory with paging! Hide the complexity let the OS do the job! Virtual address
More informationInterdomain Routing Design for MobilityFirst
Interdomain Routing Design for MobilityFirst October 6, 2011 Z. Morley Mao, University of Michigan In collaboration with Mike Reiter s group 1 Interdomain routing design requirements Mobility support Network
More information15-744: Computer Networking. Data Center Networking II
15-744: Computer Networking Data Center Networking II Overview Data Center Topology Scheduling Data Center Packet Scheduling 2 Current solutions for increasing data center network bandwidth FatTree BCube
More informationExtracting Rankings for Spatial Keyword Queries from GPS Data
Extracting Rankings for Spatial Keyword Queries from GPS Data Ilkcan Keles Christian S. Jensen Simonas Saltenis Aalborg University Outline Introduction Motivation Problem Definition Proposed Method Overview
More informationFor The following Exercises, mark the answers True and False
1 For The following Exercises, mark the answers True and False 1. An operating system is an example of application software. False 2. 3. 4. 6. 7. 9. 10. 12. 13. 14. 15. 16. 17. 18. An operating system
More informationEpisode 5. Scheduling and Traffic Management
Episode 5. Scheduling and Traffic Management Part 3 Baochun Li Department of Electrical and Computer Engineering University of Toronto Outline What is scheduling? Why do we need it? Requirements of a scheduling
More informationIndexing Word-Sequences for Ranked Retrieval
0 Indexing Word-Sequences for Ranked Retrieval SAMUEL HUSTON, University of Massachusetts Amherst J. SHANE CULPEPPER, RMIT University W. BRUCE CROFT, University of Massachusetts Amherst Formulating and
More informationJaal: Towards Network Intrusion Detection at ISP Scale
Jaal: Towards Network Intrusion Detection at ISP Scale A. Aqil, K. Khalil, A. Atya, E. Paplexakis, S. Krishnamurthy, KK. Ramakrishnan University of California Riverside T. Jaeger Penn State University
More informationMeasuring Intrusion Detection Capability: An Information- Theoretic Approach
Measuring Intrusion Detection Capability: An Information- Theoretic Approach Guofei Gu, Prahlad Fogla, David Dagon, Wenke Lee Georgia Tech Boris Skoric Philips Research Lab Outline Motivation Problem Why
More informationLecture 15: Datacenter TCP"
Lecture 15: Datacenter TCP" CSE 222A: Computer Communication Networks Alex C. Snoeren Thanks: Mohammad Alizadeh Lecture 15 Overview" Datacenter workload discussion DC-TCP Overview 2 Datacenter Review"
More informationend systems, access networks, links circuit switching, packet switching, network structure
Chapter 1: roadmap 1.1 What is the Internet? 1.2 Network edge end systems, access networks, links 1.3 Network core circuit switching, packet switching, network structure 1.4 Delay, loss and throughput
More informationCore-Stateless Fair Queueing: Achieving Approximately Fair Bandwidth Allocations in High Speed Networks. Congestion Control in Today s Internet
Core-Stateless Fair Queueing: Achieving Approximately Fair Bandwidth Allocations in High Speed Networks Ion Stoica CMU Scott Shenker Xerox PARC Hui Zhang CMU Congestion Control in Today s Internet Rely
More informationTyphoon: An SDN Enhanced Real-Time Big Data Streaming Framework
Typhoon: An SDN Enhanced Real-Time Big Data Streaming Framework Junguk Cho, Hyunseok Chang, Sarit Mukherjee, T.V. Lakshman, and Jacobus Van der Merwe 1 Big Data Era Big data analysis is increasingly common
More informationFlash Storage Complementing a Data Lake for Real-Time Insight
Flash Storage Complementing a Data Lake for Real-Time Insight Dr. Sanhita Sarkar Global Director, Analytics Software Development August 7, 2018 Agenda 1 2 3 4 5 Delivering insight along the entire spectrum
More informationTOWARDS HIGH-PERFORMANCE NETWORK APPLICATION IDENTIFICATION WITH AGGREGATE-FLOW CACHE
TOWARDS HIGH-PERFORMANCE NETWORK APPLICATION IDENTIFICATION WITH AGGREGATE-FLOW CACHE Fei He 1, 2, Fan Xiang 1, Yibo Xue 2,3 and Jun Li 2,3 1 Department of Automation, Tsinghua University, Beijing, China
More information