Towards a Software Defined Data Plane for Datacenters
|
|
- Coral Howard
- 5 years ago
- Views:
Transcription
1 Towards a Software Defined Data Plane for Datacenters Arvind Krishnamurthy Joint work with: Antoine Kaufmann, Ming Liu, Naveen Sharma Tom Anderson, Kishore Atreya, Changhoon Kim, Jacob Nelson, Simon Peter
2 Programmable Networks Recent and upcoming hardware allow for per-packet data-plane processing Both at the switch and the NIC Programmable devices at line rate, but Tiny bit of computing Small amount of state Multiple hardware realizations but some convergence is taking place
3 Reconfigurable Match Table (RMT) Architecture Packet Stream Programmable Parser TCAM SRAM... REGs Egress Queues Eth TCAM/SRAM for matches port = lookup(eth.dst_mac) IPv4 Stateful memory for counter and meters ipv4.ttl = ipv4.ttl - 1 TCP UDP ALUs for modifying headers and registers counter[ipv4.dst_port]++ RCP
4 RMT Devices Growing list of RMT-like offerings at different points in the network Switches, multi-host NICs, NICs Key use cases for the reconfigurability: Allow for integration of new protocols (e.g., tunneling) Perform in-the-wild customizability (e.g., table sizes) Offload some end-host processing (e.g., filtering) Modest proposal, but it comes at a cost so we better make good use of it!
5 Research Questions What more can we do with customizable dataplanes? What are the compelling applications? Can we cope with the hardware constraints? Are the performance benefits significant enough?
6 Research Projects 1. The intelligent switch: Realize stateful network functions Leverage switch visibility Use approximation to cope with constraints 2. The intelligent NIC: Accelerate end-host applications Reduce application overheads, optimize fast path processing
7 Challenge: RMT Devices are not all powerful Processing primitives are limited Available stateful memory is constrained Limited number of stages and communication across stages Appropriate for the originally intended use cases Custom routing and tunneling protocols such as VxLAN or MPLS Most are packet-level transformations involving static tables
8 What about network-rich protocols? Decades worth of protocols involving active network elements Persistent and mutable state for cross-packet transformations Require implementing some state machine functionality Examples: Congestion Control (XCP, RCP, QCN, HULL) Load Balancing (Hedera, CONGA, WCMP, Ananta) Fairness & QoS Scheduling (Fair Queueing, Seawall, CoDel, D 3 ) Can we implement these powerful protocols on RMT Switches?
9 Case Study: RCP (Rate Control Protocol) Explicit granular network feedback for rate control R Rate = 50 R = 25 R = 20 R a R b = 25 = 20 Sender Switch A Switch B Receiver Switches periodically compute the flow rate:
10
11 Building Block: Cardinality Estimation Count the number of unique flows traversing a switch We extend an approach from streaming algorithms (HyperLoglog) pkt pkt-2 hash(5-tuple) pkt Maximum leading zeroes: Estimate = 2 4 = For each packet, we hash the 5-tuple 2. Keep track of largest number of leading zeros (say M) 3. Estimate number of unique elements as 2 M
12 RCP implementation on a flexible switch Implemented on XPliant CNX880xx 2-level FatTree topology with 4 ToRs, 2 core switches Flow Completion Time in ms TCP RCP Short Flows Medium Flows Long Flows Simulations show that the impact of approximation is minimal
13 Case Study: Fair Queueing for In-Network Enforcement Enforce fair allocation and isolation at switches Provide an illusion that every flow has its own queue Proven to have perfect isolation and fairness + Simplifies congestion control at the end-host + Protects against misbehaving traffic + Enables bounded delay guarantees However, challenging to realize in high-speed switches
14 Fair Queueing without per-flow queues
15 Fair Queueing without per-flow queues Simulates an ideal round-robin scheme where each active flow transmits a single bit of data every round. Flow 1 Round Number E A 3 7 Track global round number Sorted packet buffer Flow 2 B 0 5 E, 7 B, 5 C, 4 A, 3 D, 2 Flow 3 C 0 4 Store and update per-flow counters Flow 4 D 0 2 Ideal fair-queueing Flow Counters Simulated fair-queueing (Demers et.al.)
16 Realizing Fair Queueing on Reconfigurable Switches 1. Maintain a sorted packet buffer Requirement: O(logN) insertion complexity Constraint: Limited operations per packet 2. Store per-flow counters Requirement: Per-flow mutable state Constraint: Limited switch memory 3. Access and modify current round number Requirement: Synchronize state across switch modules Constraint: Limited cross-module communication
17 Our approach: Approximate Fair Queueing Simulate a bit-by-bit round robin scheme with approximations Flow 1 Coarse round numbers E A 7 Limited # of FIFO queues with rotating priorities to approximate a sorted buffer D C A Flow 2 Flow 3 B C 5 4 E, 7 E B, 5 B C, 4 A, 3 D, 2 Sorted packet buffer Flow 4 Ideal fair-queueing D 2 Store approximate per-flow counters using a variation Simulated of the fair-queueing count-min sketch
18 Storing Approximate Flow Counters Variation of count-min sketch to track flow s finish round number hash 1 ( ) % C C pkt hash 2 ( ) % C R hash R ( ) % C update increments all cells; read returns the minimum Never under-estimates, has provable space-accuracy trade-off
19 Customized to perform a combined read-update operation Conditional increment up to the new value for better accuracy Flow 1 Flow 2 size : size : min (0, 1000, 0, 0, 0, 0) 0) = 0 = = = Read Counter Find the minimum of all cells Bytes sent = minimum + pkt.size Update Counter Increment all cells upto new value cell x,y = max (cell x,y, new value) Implemented in hardware using predicated read-write registers
20 Buffering Packets in Approximate Sorted Order Flow 1 K K C A Round 1 D A Flow 2... B Round 2 Round K C... B K FIFO queues Flow N BpR{ Ideal per-flow queues D Approximate Fair Queueing Coarse rounds: flows transmit a quantum of bytes per round (BpR) For each packet, outgoing round number = bytes sent / BpR
21 Rotating Strict Priority Queues Flow 1 K K C A Round 1 D A Highest Priority Flow 2 B Round 32 C B Flow N... Ideal per-flow queues D Round K Approximate Fair Queueing Lowest Priority Drain queue with the lowest round number till it is empty Push queue to lowest priority; increment round number by 1
22 Realizing an RSP Scheduler RSP can be implemented in hardware Identical complexity to a Deficit Round Robin scheduler RSP can be emulated on current switches Switch CPU to periodically change priorities Hierarchical priority queues Avoid explicit round number synchronization by exposing queue metadata Utilize dynamic buffer sharing to vary size of individual queues
23 Summary of Techniques 1. Modified count-min sketch + Counters for large number of flows in limited memory - Collisions cause packets to enqueue in a later round 2. RSP queues to approximate sorted buffer + Process packets in a fixed number of operations - Packets not strictly prioritized within a round 3. Coarse round numbers + Updates to shared state are not per-packet anymore - Packets can enqueue in an earlier round
24 End-host Flow Control Protocol AFQ can be deployed without modifying end-hosts Adapt the packet-pair algorithm [Keshav et.al.] to gain even more benefits Sender transmits a pair of back-to-back packets Inter-arrival delay is an estimate of the bottleneck bandwidth End-hosts pace packets at estimated rate Lets us perform fast ramp-up and keep small queue sizes
25 Testbed Results 100 TCP DCTCP AFQ Normalized Flow Completion Time 99%tile 10 Average 1 Flow size (in bytes) Compared to TCP, 4x better average FCT, 10x better tail latency. Compared to DCTCP, 2x better average FCT, 4x better tail latency.
26 AFQ compared to Ideal Fair Queueing Evaluated using a packet-level simulator across different loads All Flows Short Flows < 100 KB TCP DCTCP Average FCT in μs SFQ AFQ Ideal FQ Network Load (%) Network Load (%)
27 More Protocols/Building Blocks
28 Discussion Feasible to implement non-trivial stateful protocols Use approximations to overcome hardware limits Breaks the vicious cycle between hardware support and protocol evaluation Building blocks reused across many protocols Possibility of having fixed function instantiations Suggests a long-term evolution strategy for programmable network devices
29 Research Projects 1. The intelligent switch: Realize stateful network functions Leverage switch visibility Use approximation to cope with constraints 2. The intelligent NIC: Accelerate end-host applications Reduce application overheads, optimize fast path processing
30 Networks: Fast and Growing Faster Ethernet Bandwidth [bits/s] 1 T 100 G 10 G 1 G 1 GbE 40 GbE 5ns inter-arrival 10 GbE time for 64B packets at 100Gbps 400 GbE 100 GbE 100 MbE 100 M Year of Standard Release
31 ... but Packet Processing is Slow Many cloud apps dominated by packet processing Key-value store, real-time analytics Particularly so with microservices Recv+send network stack processing overheads Linux: 3.4µs Kernel bypass: ~1µs Can parallelize, but still too slow RDMA API rigid: Difficult to traverse complex data structures
32 Sources of Inefficiency Wasted CPU cycles Packet parsing and validation repeated in software Poor cache locality, extra synchronization NIC steers packets to cores by connection Application locality may not match connection Many cycles spent in directing packets into data structures RMT NICs can address many of these issues!
33 Example: Key-Value Store Client 1 K = 3, 4 Client 2 K = 1, 4, 7 Client 3 K = 5, 7, 8 Receive-side scaling: core = hash(connection) % N Lock contention Core 1 Poor cache utilization NIC Core 2 Hash Table 4 7
34 Optimizing Reads: Key-based Steering Implemented using the RMT NIC model [Kaufmann et al., ASPLOS 16] Client 1 K = 4, 3 Client 2 K = 1, 4, 7 Client 3 K = 1, 7, 8 Match: IF udp.port == kvs_port Action: core = HASH(kvs.key) % 2 DMA hash, kvs TO Cores[core] No locks neededcore 1 Better cache utilization NIC Core 2 Hash Table
35 Optimizing Writes: Custom DMA Event Queue G S GET, Client SET, ID, Hash, Client Key ID, Item Pointer Item 1 Item 2 Item Log DMA to application-level data structures Requires packet validation and transformation
36 Key-based steering Throughput [m op/s] FlexKVS/Flow FlexKVS/Key FlexKVS/Linux Memcached Number of CPU Cores 6 Core Sandy Bridge Xeon 2.2GHz, 2x 10G links. Workload: 100k 32B keys, 64B values, 90% GET Per-key processing cycles: 1110 for Flow based, 690 for Key-based, 440 with custom DMA
37 Hardware Assisted TCP Transport protocols can also be optimized using RMT-NICs Data delivered directly from app to app Applications safely access NIC directly Kernel configures NIC to enforce resource limits Goals: performance, safety, and flexibility
38 NIC support for TCP TCP requires lots of state and computation E.g., corner cases like out of order packets Expensive to handle and maintain in hardware But common case is simple Increment next sequence number, send ACK Update next ACK number, free TX buffer Core Idea: Fast-Path / Slow-Path split Only fast-path needs to be done on NIC
39 SplitTCP at a Glance Kernel still responsible for slow path Setting up connections Calculating congestion control rate-limit out of band Recovering from packet drops/out-of-order packets Apps directly interact with NIC for TCP fast path Sending and receiving TCP payload NIC ensures correctness Apps can only send valid segments for fast-pathed flows Congestion information processed safely
40 FlexTCP Performance Throughput [mop/s] x vs Linux 4.1x vs mtcp Linux mtcp FlexTCP 7.2x vs Linux 2.2x vs mtcp Cores Key-value store throughput scalability Evaluated using software emulation
41 Summary Data plane programmability now a reality Can address many pressing challenges: efficient realization of stateful in-network protocol processing allow server cores to keep up with networks Many interesting research directions: application-specific acceleration systems support for data plane reconfigurability programming models and frameworks for application-specific networking
42 Additional Material Talk material is drawn from the following papers: Approximating Fair Queueing on Reconfigurable Switches N. Sharma, M. Liu, K. Atreya, A. Krishnamurthy, NSDI, Evaluating the Power of Flexible Packet Processing for Network Resource Allocation N. Sharma, A. Kaufmann, T. Anderson, C. Kim, A. Krishnamurthy, J. Nelson, S. Peter, NSDI, High Performance Packet Processing with FlexNIC A. Kaufmann, S. Peter, N. Sharma, T. Anderson, A. Krishnamurthy, ASPLOS, 2016.
High Performance Packet Processing with FlexNIC
High Performance Packet Processing with FlexNIC Antoine Kaufmann, Naveen Kr. Sharma Thomas Anderson, Arvind Krishnamurthy University of Washington Simon Peter The University of Texas at Austin Ethernet
More informationFlexNIC: Rethinking Network DMA
FlexNIC: Rethinking Network DMA Antoine Kaufmann Simon Peter Tom Anderson Arvind Krishnamurthy University of Washington HotOS 2015 Networks: Fast and Growing Faster 1 T 400 GbE Ethernet Bandwidth [bits/s]
More informationEvaluating the Power of Flexible Packet Processing for Network Resource Allocation
Evaluating the Power of Flexible Packet Processing for Network Resource Allocation Naveen Kr. Sharma, Antoine Kaufmann, and Thomas Anderson, University of Washington; Changhoon Kim, Barefoot Networks;
More informationArrakis: The Operating System is the Control Plane
Arrakis: The Operating System is the Control Plane Simon Peter, Jialin Li, Irene Zhang, Dan Ports, Doug Woos, Arvind Krishnamurthy, Tom Anderson University of Washington Timothy Roscoe ETH Zurich Building
More informationMUD: Send me your top 1 3 questions on this lecture
Administrivia Review 1 due tomorrow Email your reviews to me Office hours on Thursdays 10 12 MUD: Send me your top 1 3 questions on this lecture Guest lectures next week by Prof. Richard Martin Class slides
More informationDeTail Reducing the Tail of Flow Completion Times in Datacenter Networks. David Zats, Tathagata Das, Prashanth Mohan, Dhruba Borthakur, Randy Katz
DeTail Reducing the Tail of Flow Completion Times in Datacenter Networks David Zats, Tathagata Das, Prashanth Mohan, Dhruba Borthakur, Randy Katz 1 A Typical Facebook Page Modern pages have many components
More informationIX: A Protected Dataplane Operating System for High Throughput and Low Latency
IX: A Protected Dataplane Operating System for High Throughput and Low Latency Adam Belay et al. Proc. of the 11th USENIX Symp. on OSDI, pp. 49-65, 2014. Presented by Han Zhang & Zaina Hamid Challenges
More informationAn Implementation of the Homa Transport Protocol in RAMCloud. Yilong Li, Behnam Montazeri, John Ousterhout
An Implementation of the Homa Transport Protocol in RAMCloud Yilong Li, Behnam Montazeri, John Ousterhout Introduction Homa: receiver-driven low-latency transport protocol using network priorities HomaTransport
More informationInformation-Agnostic Flow Scheduling for Commodity Data Centers
Information-Agnostic Flow Scheduling for Commodity Data Centers Wei Bai, Li Chen, Kai Chen, Dongsu Han (KAIST), Chen Tian (NJU), Hao Wang Sing Group @ Hong Kong University of Science and Technology USENIX
More informationAdvanced Computer Networks. End Host Optimization
Oriana Riva, Department of Computer Science ETH Zürich 263 3501 00 End Host Optimization Patrick Stuedi Spring Semester 2017 1 Today End-host optimizations: NUMA-aware networking Kernel-bypass Remote Direct
More informationHomework 1. Question 1 - Layering. CSCI 1680 Computer Networks Fonseca
CSCI 1680 Computer Networks Fonseca Homework 1 Due: 27 September 2012, 4pm Question 1 - Layering a. Why are networked systems layered? What are the advantages of layering? Are there any disadvantages?
More informationIX: A Protected Dataplane Operating System for High Throughput and Low Latency
IX: A Protected Dataplane Operating System for High Throughput and Low Latency Belay, A. et al. Proc. of the 11th USENIX Symp. on OSDI, pp. 49-65, 2014. Reviewed by Chun-Yu and Xinghao Li Summary In this
More informationHIGH-PERFORMANCE NETWORKING :: USER-LEVEL NETWORKING :: REMOTE DIRECT MEMORY ACCESS
HIGH-PERFORMANCE NETWORKING :: USER-LEVEL NETWORKING :: REMOTE DIRECT MEMORY ACCESS CS6410 Moontae Lee (Nov 20, 2014) Part 1 Overview 00 Background User-level Networking (U-Net) Remote Direct Memory Access
More informationCongestion. Can t sustain input rate > output rate Issues: - Avoid congestion - Control congestion - Prioritize who gets limited resources
Congestion Source 1 Source 2 10-Mbps Ethernet 100-Mbps FDDI Router 1.5-Mbps T1 link Destination Can t sustain input rate > output rate Issues: - Avoid congestion - Control congestion - Prioritize who gets
More informationAdvanced Computer Networks. Datacenter TCP
Advanced Computer Networks 263 3501 00 Datacenter TCP Spring Semester 2017 1 Oriana Riva, Department of Computer Science ETH Zürich Today Problems with TCP in the Data Center TCP Incast TPC timeouts Improvements
More informationBuilding Efficient and Reliable Software-Defined Networks. Naga Katta
FPO Talk Building Efficient and Reliable Software-Defined Networks Naga Katta Jennifer Rexford (Advisor) Readers: Mike Freedman, David Walker Examiners: Nick Feamster, Aarti Gupta 1 Traditional Networking
More informationPacket Scheduling in Data Centers. Lecture 17, Computer Networks (198:552)
Packet Scheduling in Data Centers Lecture 17, Computer Networks (198:552) Datacenter transport Goal: Complete flows quickly / meet deadlines Short flows (e.g., query, coordination) Large flows (e.g., data
More informationTopic 6: SDN in practice: Microsoft's SWAN. Student: Miladinovic Djordje Date:
Topic 6: SDN in practice: Microsoft's SWAN Student: Miladinovic Djordje Date: 17.04.2015 1 SWAN at a glance Goal: Boost the utilization of inter-dc networks Overcome the problems of current traffic engineering
More informationApproximating Fair Queueing on Reconfigurable Switches
Approximating air Queueing on Reconfigurable Switches Naveen Kr. Sharma and Ming Liu, University of Washington; Kishore Atreya, avium; Arvind Krishnamurthy, University of Washington https://www.usenix.org/conference/nsdi/presentation/sharma
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 informationRDMA and Hardware Support
RDMA and Hardware Support SIGCOMM Topic Preview 2018 Yibo Zhu Microsoft Research 1 The (Traditional) Journey of Data How app developers see the network Under the hood This architecture had been working
More informationAdvanced Computer Networks. Flow Control
Advanced Computer Networks 263 3501 00 Flow Control Patrick Stuedi Spring Semester 2017 1 Oriana Riva, Department of Computer Science ETH Zürich Last week TCP in Datacenters Avoid incast problem - Reduce
More informationBe Fast, Cheap and in Control with SwitchKV. Xiaozhou Li
Be Fast, Cheap and in Control with SwitchKV Xiaozhou Li Goal: fast and cost-efficient key-value store Store, retrieve, manage key-value objects Get(key)/Put(key,value)/Delete(key) Target: cluster-level
More informationCS557: Queue Management
CS557: Queue Management Christos Papadopoulos Remixed by Lorenzo De Carli 1 Congestion Control vs. Resource Allocation Network s key role is to allocate its transmission resources to users or applications
More informationInformation-Agnostic Flow Scheduling for Commodity Data Centers. Kai Chen SING Group, CSE Department, HKUST May 16, Stanford University
Information-Agnostic Flow Scheduling for Commodity Data Centers Kai Chen SING Group, CSE Department, HKUST May 16, 2016 @ Stanford University 1 SING Testbed Cluster Electrical Packet Switch, 1G (x10) Electrical
More informationChapter 6 Queuing Disciplines. Networking CS 3470, Section 1
Chapter 6 Queuing Disciplines Networking CS 3470, Section 1 Flow control vs Congestion control Flow control involves preventing senders from overrunning the capacity of the receivers Congestion control
More informationTitan: Fair Packet Scheduling for Commodity Multiqueue NICs. Brent Stephens, Arjun Singhvi, Aditya Akella, and Mike Swift July 13 th, 2017
Titan: Fair Packet Scheduling for Commodity Multiqueue NICs Brent Stephens, Arjun Singhvi, Aditya Akella, and Mike Swift July 13 th, 2017 Ethernet line-rates are increasing! 2 Servers need: To drive increasing
More informationKernel Bypass. Sujay Jayakar (dsj36) 11/17/2016
Kernel Bypass Sujay Jayakar (dsj36) 11/17/2016 Kernel Bypass Background Why networking? Status quo: Linux Papers Arrakis: The Operating System is the Control Plane. Simon Peter, Jialin Li, Irene Zhang,
More informationReal-Time Protocol (RTP)
Real-Time Protocol (RTP) Provides standard packet format for real-time application Typically runs over UDP Specifies header fields below Payload Type: 7 bits, providing 128 possible different types of
More informationOverview Computer Networking What is QoS? Queuing discipline and scheduling. Traffic Enforcement. Integrated services
Overview 15-441 15-441 Computer Networking 15-641 Lecture 19 Queue Management and Quality of Service Peter Steenkiste Fall 2016 www.cs.cmu.edu/~prs/15-441-f16 What is QoS? Queuing discipline and scheduling
More informationQUIC. Internet-Scale Deployment on Linux. Ian Swett Google. TSVArea, IETF 102, Montreal
QUIC Internet-Scale Deployment on Linux TSVArea, IETF 102, Montreal Ian Swett Google 1 A QUIC History - SIGCOMM 2017 Protocol for HTTPS transport, deployed at Google starting 2014 Between Google services
More informationCSE 123A Computer Networks
CSE 123A Computer Networks Winter 2005 Lecture 14 Congestion Control Some images courtesy David Wetherall Animations by Nick McKeown and Guido Appenzeller The bad news and the good news The bad news: new
More informationFlexplane: An Experimenta0on Pla3orm for Resource Management in Datacenters. Amy Ousterhout, Jonathan Perry, Hari Balakrishnan, Petr Lapukhov
Flexplane: An Experimenta0on Pla3orm for Resource Management in Datacenters Amy Ousterhout, Jonathan Perry, Hari Balakrishnan, Petr Lapukhov Datacenter Networks Applica0ons have diverse requirements Dozens
More informationDisclaimer This presentation may contain product features that are currently under development. This overview of new technology represents no commitme
NET1343BU NSX Performance Samuel Kommu #VMworld #NET1343BU Disclaimer This presentation may contain product features that are currently under development. This overview of new technology represents no
More informationGot Loss? Get zovn! Daniel Crisan, Robert Birke, Gilles Cressier, Cyriel Minkenberg, and Mitch Gusat. ACM SIGCOMM 2013, August, Hong Kong, China
Got Loss? Get zovn! Daniel Crisan, Robert Birke, Gilles Cressier, Cyriel Minkenberg, and Mitch Gusat ACM SIGCOMM 2013, 12-16 August, Hong Kong, China Virtualized Server 1 Application Performance in Virtualized
More informationQoS Services with Dynamic Packet State
QoS Services with Dynamic Packet State Ion Stoica Carnegie Mellon University (joint work with Hui Zhang and Scott Shenker) Today s Internet Service: best-effort datagram delivery Architecture: stateless
More informationCongestion Control and Resource Allocation
Congestion Control and Resource Allocation Lecture material taken from Computer Networks A Systems Approach, Third Edition,Peterson and Davie, Morgan Kaufmann, 2007. Advanced Computer Networks Congestion
More informationNetCache: Balancing Key-Value Stores with Fast In-Network Caching
NetCache: Balancing Key-Value Stores with Fast In-Network Caching Xin Jin, Xiaozhou Li, Haoyu Zhang, Robert Soulé Jeongkeun Lee, Nate Foster, Changhoon Kim, Ion Stoica NetCache is a rack-scale key-value
More informationDesigning Distributed Systems using Approximate Synchrony in Data Center Networks
Designing Distributed Systems using Approximate Synchrony in Data Center Networks Dan R. K. Ports Jialin Li Naveen Kr. Sharma Vincent Liu Arvind Krishnamurthy University of Washington CSE Today s most
More informationNetCache: Balancing Key-Value Stores with Fast In-Network Caching
NetCache: Balancing Key-Value Stores with Fast In-Network Caching Xin Jin, Xiaozhou Li, Haoyu Zhang, Robert Soulé Jeongkeun Lee, Nate Foster, Changhoon Kim, Ion Stoica NetCache is a rack-scale key-value
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 informationTales of the Tail Hardware, OS, and Application-level Sources of Tail Latency
Tales of the Tail Hardware, OS, and Application-level Sources of Tail Latency Jialin Li, Naveen Kr. Sharma, Dan R. K. Ports and Steven D. Gribble February 2, 2015 1 Introduction What is Tail Latency? What
More informationLanguage-Directed Hardware Design for Network Performance Monitoring
Language-Directed Hardware Design for Network Performance Monitoring Srinivas Narayana, Anirudh Sivaraman, Vikram Nathan, Prateesh Goyal, Venkat Arun, Mohammad Alizadeh, Vimal Jeyakumar, and Changhoon
More information2017 Storage Developer Conference. Mellanox Technologies. All Rights Reserved.
Ethernet Storage Fabrics Using RDMA with Fast NVMe-oF Storage to Reduce Latency and Improve Efficiency Kevin Deierling & Idan Burstein Mellanox Technologies 1 Storage Media Technology Storage Media Access
More informationDIBS: Just-in-time congestion mitigation for Data Centers
DIBS: Just-in-time congestion mitigation for Data Centers Kyriakos Zarifis, Rui Miao, Matt Calder, Ethan Katz-Bassett, Minlan Yu, Jitendra Padhye University of Southern California Microsoft Research Summary
More informationQuickSpecs. HP Z 10GbE Dual Port Module. Models
Overview Models Part Number: 1Ql49AA Introduction The is a 10GBASE-T adapter utilizing the Intel X722 MAC and X557-AT2 PHY pairing to deliver full line-rate performance, utilizing CAT 6A UTP cabling (or
More informationComputer Networking. Queue Management and Quality of Service (QOS)
Computer Networking Queue Management and Quality of Service (QOS) Outline Previously:TCP flow control Congestion sources and collapse Congestion control basics - Routers 2 Internet Pipes? How should you
More informationMohammad Hossein Manshaei 1393
Mohammad Hossein Manshaei manshaei@gmail.com 1393 Voice and Video over IP Slides derived from those available on the Web site of the book Computer Networking, by Kurose and Ross, PEARSON 2 Multimedia networking:
More informationCS268: Beyond TCP Congestion Control
TCP Problems CS68: Beyond TCP Congestion Control Ion Stoica February 9, 004 When TCP congestion control was originally designed in 1988: - Key applications: FTP, E-mail - Maximum link bandwidth: 10Mb/s
More informationCongestion Control In the Network
Congestion Control In the Network Brighten Godfrey cs598pbg September 9 2010 Slides courtesy Ion Stoica with adaptation by Brighten Today Fair queueing XCP Announcements Problem: no isolation between flows
More informationFundamental Questions to Answer About Computer Networking, Jan 2009 Prof. Ying-Dar Lin,
Fundamental Questions to Answer About Computer Networking, Jan 2009 Prof. Ying-Dar Lin, ydlin@cs.nctu.edu.tw Chapter 1: Introduction 1. How does Internet scale to billions of hosts? (Describe what structure
More informationChapter 4. Routers with Tiny Buffers: Experiments. 4.1 Testbed experiments Setup
Chapter 4 Routers with Tiny Buffers: Experiments This chapter describes two sets of experiments with tiny buffers in networks: one in a testbed and the other in a real network over the Internet2 1 backbone.
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 informationTLDK Overview. Transport Layer Development Kit Ray Kinsella February ray.kinsella [at] intel.com IRC: mortderire
TLDK Overview Transport Layer Development Kit Ray Kinsella February 2017 Email : ray.kinsella [at] intel.com IRC: mortderire Contributions from Keith Wiles & Konstantin Ananyev Legal Disclaimer General
More informationCS551 Router Queue Management
CS551 Router Queue Management Bill Cheng http://merlot.usc.edu/cs551-f12 1 Congestion Control vs. Resource Allocation Network s key role is to allocate its transmission resources to users or applications
More informationChapter 4: network layer. Network service model. Two key network-layer functions. Network layer. Input port functions. Router architecture overview
Chapter 4: chapter goals: understand principles behind services service models forwarding versus routing how a router works generalized forwarding instantiation, implementation in the Internet 4- Network
More informationOptical Packet Switching
Optical Packet Switching DEISNet Gruppo Reti di Telecomunicazioni http://deisnet.deis.unibo.it WDM Optical Network Legacy Networks Edge Systems WDM Links λ 1 λ 2 λ 3 λ 4 Core Nodes 2 1 Wavelength Routing
More informationRoGUE: RDMA over Generic Unconverged Ethernet
RoGUE: RDMA over Generic Unconverged Ethernet Yanfang Le with Brent Stephens, Arjun Singhvi, Aditya Akella, Mike Swift RDMA Overview RDMA USER KERNEL Zero Copy Application Application Buffer Buffer HARWARE
More informationSoftware Datapath Acceleration for Stateless Packet Processing
June 22, 2010 Software Datapath Acceleration for Stateless Packet Processing FTF-NET-F0817 Ravi Malhotra Software Architect Reg. U.S. Pat. & Tm. Off. BeeKit, BeeStack, CoreNet, the Energy Efficient Solutions
More informationPerformance Evaluation of Myrinet-based Network Router
Performance Evaluation of Myrinet-based Network Router Information and Communications University 2001. 1. 16 Chansu Yu, Younghee Lee, Ben Lee Contents Suez : Cluster-based Router Suez Implementation Implementation
More information6.033 Spring Lecture #12. In-network resource management Queue management schemes Traffic differentiation spring 2018 Katrina LaCurts
6.033 Spring 2018 Lecture #12 In-network resource management Queue management schemes Traffic differentiation 1 Internet of Problems How do we route (and address) scalably, while dealing with issues of
More informationLecture 21: Congestion Control" CSE 123: Computer Networks Alex C. Snoeren
Lecture 21: Congestion Control" CSE 123: Computer Networks Alex C. Snoeren Lecture 21 Overview" How fast should a sending host transmit data? Not to fast, not to slow, just right Should not be faster than
More informationFlexplane: An Experimenta0on Pla3orm for Resource Management in Datacenters
Flexplane: An Experimenta0on Pla3orm for Resource Management in Datacenters Amy Ousterhout 1, Jonathan Perry 1, Hari Balakrishnan 1, Petr Lapukhov 2 1 MIT, 2 Facebook Datacenter Networks Applica0ons have
More informationNetwork Management & Monitoring
Network Management & Monitoring Network Delay These materials are licensed under the Creative Commons Attribution-Noncommercial 3.0 Unported license (http://creativecommons.org/licenses/by-nc/3.0/) End-to-end
More informationIncBricks: Toward In-Network Computation with an In-Network Cache
IncBricks: Toward In-Network Computation with an In-Network Cache Ming Liu University of Washington mgliu@cs.washington.edu Luis Ceze University of Washington luisceze@cs.washington.edu Liang Luo University
More informationLearning with Purpose
Network Measurement for 100Gbps Links Using Multicore Processors Xiaoban Wu, Dr. Peilong Li, Dr. Yongyi Ran, Prof. Yan Luo Department of Electrical and Computer Engineering University of Massachusetts
More information6.9. Communicating to the Outside World: Cluster Networking
6.9 Communicating to the Outside World: Cluster Networking This online section describes the networking hardware and software used to connect the nodes of cluster together. As there are whole books and
More informationOpenFlow Software Switch & Intel DPDK. performance analysis
OpenFlow Software Switch & Intel DPDK performance analysis Agenda Background Intel DPDK OpenFlow 1.3 implementation sketch Prototype design and setup Results Future work, optimization ideas OF 1.3 prototype
More informationLecture 21. Reminders: Homework 6 due today, Programming Project 4 due on Thursday Questions? Current event: BGP router glitch on Nov.
Lecture 21 Reminders: Homework 6 due today, Programming Project 4 due on Thursday Questions? Current event: BGP router glitch on Nov. 7 http://money.cnn.com/2011/11/07/technology/juniper_internet_outage/
More information6.888 Lecture 5: Flow Scheduling
6.888 Lecture 5: Flow Scheduling Mohammad Alizadeh Spring 2016 1 Datacenter Transport Goal: Complete flows quickly / meet deadlines Short flows (e.g., query, coordina1on) Large flows (e.g., data update,
More informationPriority Traffic CSCD 433/533. Advanced Networks Spring Lecture 21 Congestion Control and Queuing Strategies
CSCD 433/533 Priority Traffic Advanced Networks Spring 2016 Lecture 21 Congestion Control and Queuing Strategies 1 Topics Congestion Control and Resource Allocation Flows Types of Mechanisms Evaluation
More informationPacketShader: A GPU-Accelerated Software Router
PacketShader: A GPU-Accelerated Software Router Sangjin Han In collaboration with: Keon Jang, KyoungSoo Park, Sue Moon Advanced Networking Lab, CS, KAIST Networked and Distributed Computing Systems Lab,
More informationGUARANTEED END-TO-END LATENCY THROUGH ETHERNET
GUARANTEED END-TO-END LATENCY THROUGH ETHERNET Øyvind Holmeide, OnTime Networks AS, Oslo, Norway oeyvind@ontimenet.com Markus Schmitz, OnTime Networks LLC, Texas, USA markus@ontimenet.com Abstract: Latency
More informationHandles all kinds of traffic on a single network with one class
Handles all kinds of traffic on a single network with one class No priorities, no reservations required Quality? Throw bandwidth at the problem, hope for the best 1000x increase in bandwidth over 2 decades
More informationNetwork Interface Architecture and Prototyping for Chip and Cluster Multiprocessors
University of Crete School of Sciences & Engineering Computer Science Department Master Thesis by Michael Papamichael Network Interface Architecture and Prototyping for Chip and Cluster Multiprocessors
More information15-744: Computer Networking. Overview. Queuing Disciplines. TCP & Routers. L-6 TCP & Routers
TCP & Routers 15-744: Computer Networking RED XCP Assigned reading [FJ93] Random Early Detection Gateways for Congestion Avoidance [KHR02] Congestion Control for High Bandwidth-Delay Product Networks L-6
More informationUnit 2 Packet Switching Networks - II
Unit 2 Packet Switching Networks - II Dijkstra Algorithm: Finding shortest path Algorithm for finding shortest paths N: set of nodes for which shortest path already found Initialization: (Start with source
More informationLecture 14: Congestion Control"
Lecture 14: Congestion Control" CSE 222A: Computer Communication Networks Alex C. Snoeren Thanks: Amin Vahdat, Dina Katabi Lecture 14 Overview" TCP congestion control review XCP Overview 2 Congestion Control
More informationLecture 14: Congestion Control"
Lecture 14: Congestion Control" CSE 222A: Computer Communication Networks George Porter Thanks: Amin Vahdat, Dina Katabi and Alex C. Snoeren Lecture 14 Overview" TCP congestion control review Dukkipati
More informationCS 356: Computer Network Architectures Lecture 19: Congestion Avoidance Chap. 6.4 and related papers. Xiaowei Yang
CS 356: Computer Network Architectures Lecture 19: Congestion Avoidance Chap. 6.4 and related papers Xiaowei Yang xwy@cs.duke.edu Overview More on TCP congestion control Theory Macroscopic behavior TCP
More informationOverview. TCP & router queuing Computer Networking. TCP details. Workloads. TCP Performance. TCP Performance. Lecture 10 TCP & Routers
Overview 15-441 Computer Networking TCP & router queuing Lecture 10 TCP & Routers TCP details Workloads Lecture 10: 09-30-2002 2 TCP Performance TCP Performance Can TCP saturate a link? Congestion control
More informationof-service Support on the Internet
Quality-of of-service Support on the Internet Dept. of Computer Science, University of Rochester 2008-11-24 CSC 257/457 - Fall 2008 1 Quality of Service Support Some Internet applications (i.e. multimedia)
More informationEnabling ECN over Generic Packet Scheduling
Enabling ECN over Generic Packet Scheduling Wei Bai Kai Chen Li Chen Changhoon Kim Haitao Wu 3 SING Group, Hong Kong University of Science and Technology Barefoot Networks 3 Microsoft ABSTRACT Explicit
More informationXCo: Explicit Coordination for Preventing Congestion in Data Center Ethernet
XCo: Explicit Coordination for Preventing Congestion in Data Center Ethernet Vijay Shankar Rajanna, Smit Shah, Anand Jahagirdar and Kartik Gopalan Computer Science, State University of New York at Binghamton
More informationResource allocation in networks. Resource Allocation in Networks. Resource allocation
Resource allocation in networks Resource Allocation in Networks Very much like a resource allocation problem in operating systems How is it different? Resources and jobs are different Resources are buffers
More informationPCI Express x8 Single Port SFP+ 10 Gigabit Server Adapter (Intel 82599ES Based) Single-Port 10 Gigabit SFP+ Ethernet Server Adapters Provide Ultimate
NIC-PCIE-1SFP+-PLU PCI Express x8 Single Port SFP+ 10 Gigabit Server Adapter (Intel 82599ES Based) Single-Port 10 Gigabit SFP+ Ethernet Server Adapters Provide Ultimate Flexibility and Scalability in Virtual
More informationComputer Networks. Sándor Laki ELTE-Ericsson Communication Networks Laboratory
Computer Networks Sándor Laki ELTE-Ericsson Communication Networks Laboratory ELTE FI Department Of Information Systems lakis@elte.hu http://lakis.web.elte.hu Based on the slides of Laurent Vanbever. Further
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 informationRouter s Queue Management
Router s Queue Management Manages sharing of (i) buffer space (ii) bandwidth Q1: Which packet to drop when queue is full? Q2: Which packet to send next? FIFO + Drop Tail Keep a single queue Answer to Q1:
More informationCongestion Control for High-Bandwidth-Delay-Product Networks: XCP vs. HighSpeed TCP and QuickStart
Congestion Control for High-Bandwidth-Delay-Product Networks: XCP vs. HighSpeed TCP and QuickStart Sally Floyd September 11, 2002 ICIR Wednesday Lunch 1 Outline: Description of the problem. Description
More informationRecap. TCP connection setup/teardown Sliding window, flow control Retransmission timeouts Fairness, max-min fairness AIMD achieves max-min fairness
Recap TCP connection setup/teardown Sliding window, flow control Retransmission timeouts Fairness, max-min fairness AIMD achieves max-min fairness 81 Feedback Signals Several possible signals, with different
More informationRevisiting Network Support for RDMA
Revisiting Network Support for RDMA Radhika Mittal 1, Alex Shpiner 3, Aurojit Panda 1, Eitan Zahavi 3, Arvind Krishnamurthy 2, Sylvia Ratnasamy 1, Scott Shenker 1 (1: UC Berkeley, 2: Univ. of Washington,
More informationBaidu s Best Practice with Low Latency Networks
Baidu s Best Practice with Low Latency Networks Feng Gao IEEE 802 IC NEND Orlando, FL November 2017 Presented by Huawei Low Latency Network Solutions 01 1. Background Introduction 2. Network Latency Analysis
More informationProgrammable NICs. Lecture 14, Computer Networks (198:552)
Programmable NICs Lecture 14, Computer Networks (198:552) Network Interface Cards (NICs) The physical interface between a machine and the wire Life of a transmitted packet Userspace application NIC Transport
More informationQueuing Mechanisms. Overview. Objectives
Queuing Mechanisms Overview Objectives This module describes the queuing mechanisms that can be used on output interfaces. It includes the following topics: Queuing Overview FIFO Queuing Priority Queuing
More informationCS 268: Computer Networking
CS 268: Computer Networking L-6 Router Congestion Control TCP & Routers RED XCP Assigned reading [FJ93] Random Early Detection Gateways for Congestion Avoidance [KHR02] Congestion Control for High Bandwidth-Delay
More informationA Network-centric TCP for Interactive Video Delivery Networks (VDN)
A Network-centric TCP for Interactive Video Delivery Networks (VDN) MD Iftakharul Islam, Javed I Khan Department of Computer Science Kent State University Kent, OH 1 / 44 Outline 1 Interactive Video Network
More informationHigh bandwidth, Long distance. Where is my throughput? Robin Tasker CCLRC, Daresbury Laboratory, UK
High bandwidth, Long distance. Where is my throughput? Robin Tasker CCLRC, Daresbury Laboratory, UK [r.tasker@dl.ac.uk] DataTAG is a project sponsored by the European Commission - EU Grant IST-2001-32459
More informationExpeditus: Congestion-Aware Load Balancing in Clos Data Center Networks
Expeditus: Congestion-Aware Load Balancing in Clos Data Center Networks Peng Wang, Hong Xu, Zhixiong Niu, Dongsu Han, Yongqiang Xiong ACM SoCC 2016, Oct 5-7, Santa Clara Motivation Datacenter networks
More informationProviding Multi-tenant Services with FPGAs: Case Study on a Key-Value Store
Zsolt István *, Gustavo Alonso, Ankit Singla Systems Group, Computer Science Dept., ETH Zürich * Now at IMDEA Software Institute, Madrid Providing Multi-tenant Services with FPGAs: Case Study on a Key-Value
More information