Titan: Fair Packet Scheduling for Commodity Multiqueue NICs. Brent Stephens, Arjun Singhvi, Aditya Akella, and Mike Swift July 13 th, 2017
|
|
- Bartholomew Burke
- 5 years ago
- Views:
Transcription
1 Titan: Fair Packet Scheduling for Commodity Multiqueue NICs Brent Stephens, Arjun Singhvi, Aditya Akella, and Mike Swift July 13 th, 2017
2 Ethernet line-rates are increasing! 2
3 Servers need: To drive increasing line-rates Low CPU utilization networking 3
4 Underlying mechanisms: Segmentation Offload Multiqueue NICs 4
5 TCP Segmentation Offload (TSO) Many operations performed by the OS are per-packet, not perbyte TSO allows the OS to send large segments to the NIC TSO NIC hardware generates packets from segments Using large segments (64KB) instead of packets can reduce CPU load 5
6 Multiqueue NICs Core 1 Core 2 Core 1 TXQ-1 Core 2 TXQ-2 Locking/Polling Packet Scheduler Multiqueue NICs enable parallelism 6
7 Fairness Problems Core 1 TXQ-1 Packet Scheduler Core 2 TXQ-2 Fair packet schedule: Actual packet schedule: Multiqueue unfairness TSO unfairness TSO and multiqueue cause pervasive unfairness 7
8 Fairness is needed so competing applications can share the network Fairness is needed for predictability Unfairness leads to unpredictable completion times across runs Perfect fairness perfect predictability Fairness is important Fairness can improve application performance Ex: Weighted Coflow Scheduling [Chowdhury SIGCOMM11, Chowdhury SIGCOMM14] 8
9 Titan Goals: Drive increasing line-rates Low CPU utilization Per-flow fairness Work on commodity NICs 9
10 Multiqueue Fairness in Linux: Flow arrivals to each transmit queue are dynamic The OS statically uses a per-flow hash to assign flows to queues The NIC scheduler statically uses deficit round-robin (DRR) to provide per-queue fairness In the datacenter, the OS statically chooses a TSO size 10
11 Titan Design: As flows dynamically arrive and complete, in Titan: The OS dynamically: Assigns weights to flows Tracks the flow occupancy of queues Picks queues for flows Updates the NIC with queue weights The NIC dynamically: Applies queue weights from the OS
12 Causes of Unfairness: Multiqueue unfairness TSO unfairness 12
13 Problem: Hash collisions TXQ-1 TXQ-2 TXQ-3 Multiqueue unfairness Packet Scheduler 13
14 Problem: Hash collisions Solution: Dynamic Queue Assignment (DQA) TXQ-1 TXQ-2 TXQ-3 OS assigns a weight to each flow Packet Scheduler DQA picks the queue with the lowest occupancy when a flow starts Queue occupancies are updated: Any time a flow starts enqueuing data Any time a flow has no enqueued bytes (at most each TX interrupt) 14
15 Problem: Hash collisions Solution: Dynamic Queue Assignment (DQA) TXQ-1 TXQ-2 TXQ-3 Packet Scheduler 15
16 Problem: Asymmetric Oversubscription TXQ-1 TXQ-2 TXQ-3 W: 1 W: 1 W: 1 and receive half throughput F4 F4 F4 F4 F4 Packet Scheduler 16
17 Problem: Asymmetric Oversubscription Solution: Dynamic Queue Weight Assignment (DQWA) TXQ-1 TXQ-2 TXQ-3 W: 2 W: 1 W: 1 F4 OS assigns weights to flows OS updates the NIC scheduler with queue occupancies as flows start and stop (at most each TX interrupt) NIC updates DRR weights Packet Scheduler ndo_set_tx_weight This is implementable on existing commodity NICs because it only needs to update DRR weights! 17
18 Problem: Asymmetric Oversubscription Solution: Dynamic Queue Weight Assignment (DQWA) TXQ-1 TXQ-2 TXQ-3 W: 2 W: 1 W: 1 DQA and DQWA provide long-term fairness F4 F4 F4 Packet Scheduler ndo_set_tx_weight This is implementable on existing commodity NICs because it only needs to update DRR weights! 18
19 Problem: TSO Unfairness TXQ-1 TXQ-2 TXQ-3 W: 2 W: 1 W: 1 Short-term unfairness can cause bursts of congestion in the network Short-term unfairness can increase latency Short-term unfairness F4 Packet Scheduler F4 F4 19
20 Problem: TSO Unfairness Solution: Dynamic Segmentation Offload Sizing (DSOS) TXQ-1 TXQ-2 TXQ-3 W: 2 W: 1 W: 1 F4 DSOS dynamically changes the segment size during oversubscription Same implementation as GSO CPU vs fairness tradeoff Segmenting after the TCP/IP stack reduces CPU costs F4 F4 Packet Scheduler 20
21 Implementation DQA, DQWA, and DSOS are implemented in Linux Support for ndo_set_tx_weight is implemented in the Intel ixgbe driver for the Intel Gbps NIC Titan is open source! 21
22 Evaluation Microbenchmarks 2 servers, 1 switch 8 queue NICs Vary number of flows (level of oversubscription) Incremental fairness benefits of DQA, DQWA, and DSOS DQA and DQWA: expected to improve long-term fairness DSOS: expected to improve short-term fairness 22
23 Evaluation Fairness Metric Metrics: Normalized fairness metric (NFM) inspired by Shreedhar and Varghese: NFM = 0 is fair NFM > 1 is very unfair Ideal packet schedule: NFM = 0 NFM = (Bytes(MaxFlow) Bytes(MinFlow)) / Bytes(FairShair) Unfair packet schedule: NFM = 1 23
24 Microbenchmarks 1s Timescale Linux is unfair at all subscription levels DQA often significantly improves fairness At 48 flows, flow churn prevents DQA from evenly spreading flows DQWA improves fairness when DQA cannot evenly spread flows across queues DSOS does not have a significant impact on longterm fairness NFM -1s Number of Flows Linux DQA DQA + DQWA DQA + DQWA + DSOS (16KB) 24
25 Microbenchmarks 1ms Timescale At short timescales and under oversubscription, DQA and DQWA do not significantly improve fairness TSO is the primary cause of unfairness DSOS (16KB) often reduces unfairness by >2x NFM -1ms Number of Flows Linux DQA DQA + DQWA DQA + DQWA + DSOS (16KB) 25
26 Cluster Experiments CDF of completion times in a 1GB all-to-all shuffle (24 servers) Ideal CDF would be a vertical line Titan makes performance more predictable Titan improves tail performance (>90 th percentile) Cumulative Probability (c) 24 servers Flow Completion Time (s) Titan improves fairness without changing the network core! Linux Vanilla Titan 26
27 Additional Evaluation Additional performance metrics: Throughput: line-rate Latency: no significant change CPU Utilization: DQA and DQWA: increase < 10% DSOS is better than statically decreasing the TSO size DSOS motivates creating a better TSO implementation (zero-copy) Linux network configuration trade-off study See paper 27
28 Summary Multi queue NICs can lead to significant flow-level unfairness Titan significantly improves fairness by allowing the OS to dynamically interact with the NIC packet scheduler Titan is implementable on commodity NICs! 28
RoGUE: 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 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 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 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 informationLinux Plumbers Conference TCP-NV Congestion Avoidance for Data Centers
Linux Plumbers Conference 2010 TCP-NV Congestion Avoidance for Data Centers Lawrence Brakmo Google TCP Congestion Control Algorithm for utilizing available bandwidth without too many losses No attempt
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 informationEXPERIENCES EVALUATING DCTCP. Lawrence Brakmo, Boris Burkov, Greg Leclercq and Murat Mugan Facebook
EXPERIENCES EVALUATING DCTCP Lawrence Brakmo, Boris Burkov, Greg Leclercq and Murat Mugan Facebook INTRODUCTION Standard TCP congestion control, which only reacts to packet losses has many problems Can
More informationByte Queue Limits. August 24, / 23
Byte Queue Limits Tomáš Hrubý August 24, 2012 1 / 23 BQL - Motivation Packets spend enough time enqueued within the stack When a packet gets to a NIC it is enqueued again HW queue length in TX descriptors
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 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 informationScheduling Data Flows using DRR
CS/CoE 535 Acceleration of Networking Algorithms in Reconfigurable Hardware Prof. Lockwood : Fall 2001 http://www.arl.wustl.edu/~lockwood/class/cs535/ Scheduling Data Flows using DRR http://www.ccrc.wustl.edu/~praveen
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 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 informationTowards a Software Defined Data Plane for Datacenters
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
More informationPresentation_ID. 2002, Cisco Systems, Inc. All rights reserved.
1 Gigabit to the Desktop Session Number 2 Gigabit to the Desktop What we are seeing: Today s driver for Gigabit Ethernet to the Desktop is not a single application but the simultaneous use of multiple
More informationParallelizing IPsec: switching SMP to On is not even half the way
Parallelizing IPsec: switching SMP to On is not even half the way Steffen Klassert secunet Security Networks AG Dresden June 11 2010 Table of contents Some basics about IPsec About the IPsec performance
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 informationG-NET: Effective GPU Sharing In NFV Systems
G-NET: Effective Sharing In NFV Systems Kai Zhang*, Bingsheng He^, Jiayu Hu #, Zeke Wang^, Bei Hua #, Jiayi Meng #, Lishan Yang # *Fudan University ^National University of Singapore #University of Science
More informationFast packet processing in the cloud. Dániel Géhberger Ericsson Research
Fast packet processing in the cloud Dániel Géhberger Ericsson Research Outline Motivation Service chains Hardware related topics, acceleration Virtualization basics Software performance and acceleration
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 informationOptimizing Performance: Intel Network Adapters User Guide
Optimizing Performance: Intel Network Adapters User Guide Network Optimization Types When optimizing network adapter parameters (NIC), the user typically considers one of the following three conditions
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 informationOptimizing TCP Receive Performance
Optimizing TCP Receive Performance Aravind Menon and Willy Zwaenepoel School of Computer and Communication Sciences EPFL Abstract The performance of receive side TCP processing has traditionally been dominated
More informationLecture Topics. Announcements. Today: Uniprocessor Scheduling (Stallings, chapter ) Next: Advanced Scheduling (Stallings, chapter
Lecture Topics Today: Uniprocessor Scheduling (Stallings, chapter 9.1-9.3) Next: Advanced Scheduling (Stallings, chapter 10.1-10.4) 1 Announcements Self-Study Exercise #10 Project #8 (due 11/16) Project
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 informationIBM POWER8 100 GigE Adapter Best Practices
Introduction IBM POWER8 100 GigE Adapter Best Practices With higher network speeds in new network adapters, achieving peak performance requires careful tuning of the adapters and workloads using them.
More informationAn Evaluation of Deficit Round Robin Fair Queuing Applied in Router Congestion Control
JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 18, 333-339 (2002) Short aper An Evaluation of Deficit Round Robin Fair ueuing Applied in Router Congestion Control Department of Electrical Engineering National
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 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 informationThroughput & Latency Control in Ethernet Backplane Interconnects. Manoj Wadekar Gary McAlpine. Intel
Throughput & Latency Control in Ethernet Backplane Interconnects Manoj Wadekar Gary McAlpine Intel Date 3/16/04 Agenda Discuss Backplane challenges to Ethernet Simulation environment and definitions Preliminary
More informationAppendix B. Standards-Track TCP Evaluation
215 Appendix B Standards-Track TCP Evaluation In this appendix, I present the results of a study of standards-track TCP error recovery and queue management mechanisms. I consider standards-track TCP error
More informationBSDCan 2015 June 13 th Extensions to FreeBSD Datacenter TCP for Incremental Deployment Support. Midori Kato
BSDCan 2015 June 13 th Extensions to FreeBSD Datacenter TCP for Incremental Deployment Support Midori Kato DCTCP has been available since FreeBSD 11.0!! 2 FreeBSD DCTCP highlight
More informationNIC TEAMING IEEE 802.3ad
WHITE PAPER NIC TEAMING IEEE 802.3ad NIC Teaming IEEE 802.3ad Summary This tech note describes the NIC (Network Interface Card) teaming capabilities of VMware ESX Server 2 including its benefits, performance
More informationCPU Scheduling. Operating Systems (Fall/Winter 2018) Yajin Zhou ( Zhejiang University
Operating Systems (Fall/Winter 2018) CPU Scheduling Yajin Zhou (http://yajin.org) Zhejiang University Acknowledgement: some pages are based on the slides from Zhi Wang(fsu). Review Motivation to use threads
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 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 informationAttaining the Promise and Avoiding the Pitfalls of TCP in the Datacenter. Glenn Judd Morgan Stanley
Attaining the Promise and Avoiding the Pitfalls of TCP in the Datacenter Glenn Judd Morgan Stanley 1 Introduction Datacenter computing pervasive Beyond the Internet services domain BigData, Grid Computing,
More informationQueuing. Congestion Control and Resource Allocation. Resource Allocation Evaluation Criteria. Resource allocation Drop disciplines Queuing disciplines
Resource allocation Drop disciplines Queuing disciplines Queuing 1 Congestion Control and Resource Allocation Handle congestion if and when it happens TCP Congestion Control Allocate resources to avoid
More informationSENIC: Scalable NIC for End-Host Rate Limiting
: Scalable NIC for End-Host Rate Limiting Sivasankar Radhakrishnan, Yilong Geng +, Vimalkumar Jeyakumar +, Abdul Kabbani, George Porter, Amin Vahdat University of California, San Diego + Stanford University
More informationCongestion Control in TCP
Congestion Control in TCP Antonio Carzaniga Faculty of Informatics University of Lugano May 6, 2005 Outline Intro to congestion control Input rate vs. output throughput Congestion window Congestion avoidance
More informationTX bulking and qdisc layer
Session: Linux packet processing performance improvements TX bulking and qdisc layer Jesper Dangaard Brouer (Red Hat) John Fastabend (Intel) John Ronciak (Intel) 1/16 Linux Plumbers Conference 16 th Oct
More informationA Probabilistic Approach for Achieving Fair Bandwidth Allocations in CSFQ
A Probabilistic Approach for Achieving Fair Bandwidth Allocations in Peng Wang David L. Mills Department of Electrical & Computer Engineering University of Delaware Newark, DE 976 pwangee@udel.edu; mills@eecis.udel.edu
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 information048866: Packet Switch Architectures
048866: Packet Switch Architectures Output-Queued Switches Deterministic Queueing Analysis Fairness and Delay Guarantees Dr. Isaac Keslassy Electrical Engineering, Technion isaac@ee.technion.ac.il http://comnet.technion.ac.il/~isaac/
More informationA Network-aware Scheduler in Data-parallel Clusters for High Performance
A Network-aware Scheduler in Data-parallel Clusters for High Performance Zhuozhao Li, Haiying Shen and Ankur Sarker Department of Computer Science University of Virginia May, 2018 1/61 Data-parallel clusters
More informationIsoStack Highly Efficient Network Processing on Dedicated Cores
IsoStack Highly Efficient Network Processing on Dedicated Cores Leah Shalev Eran Borovik, Julian Satran, Muli Ben-Yehuda Outline Motivation IsoStack architecture Prototype TCP/IP over 10GE on a single
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 informationSENIC: Scalable NIC for End-Host Rate Limiting
SENIC: Scalable NIC for End-Host Rate Limiting Sivasankar Radhakrishnan, University of California, San Diego; Yilong Geng and Vimalkumar Jeyakumar, Stanford University; Abdul Kabbani, Google Inc.; George
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 informationThe Convergence of Storage and Server Virtualization Solarflare Communications, Inc.
The Convergence of Storage and Server Virtualization 2007 Solarflare Communications, Inc. About Solarflare Communications Privately-held, fabless semiconductor company. Founded 2001 Top tier investors:
More informationÉcole Polytechnique Fédérale de Lausanne. Porting a driver for the Intel XL710 40GbE NIC to the IX Dataplane Operating System
École Polytechnique Fédérale de Lausanne Semester Project Porting a driver for the Intel XL710 40GbE NIC to the IX Dataplane Operating System Student: Andy Roulin (216690) Direct Supervisor: George Prekas
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 informationG Robert Grimm New York University
G22.3250-001 Receiver Livelock Robert Grimm New York University Altogether Now: The Three Questions What is the problem? What is new or different? What are the contributions and limitations? Motivation
More informationMeasurement Based Fair Queuing for Allocating Bandwidth to Virtual Machines
Measurement Based Fair Queuing for Allocating Bandwidth to Virtual Machines Khoa To, Jitendra Padhye, George Varghese, Daniel Firestone Microsoft ABSTRACT We wish to allocate outgoing bandwidth at a server
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 information8: Scheduling. Scheduling. Mark Handley
8: Scheduling Mark Handley Scheduling On a multiprocessing system, more than one process may be available to run. The task of deciding which process to run next is called scheduling, and is performed by
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 informationLow-Latency Datacenters. John Ousterhout Platform Lab Retreat May 29, 2015
Low-Latency Datacenters John Ousterhout Platform Lab Retreat May 29, 2015 Datacenters: Scale and Latency Scale: 1M+ cores 1-10 PB memory 200 PB disk storage Latency: < 0.5 µs speed-of-light delay Most
More informationData Center TCP (DCTCP)
Data Center TCP (DCTCP) Mohammad Alizadeh, Albert Greenberg, David A. Maltz, Jitendra Padhye Parveen Patel, Balaji Prabhakar, Sudipta Sengupta, Murari Sridharan Microsoft Research Stanford University 1
More informationvnetwork Future Direction Howie Xu, VMware R&D November 4, 2008
vnetwork Future Direction Howie Xu, VMware R&D November 4, 2008 Virtual Datacenter OS from VMware Infrastructure vservices and Cloud vservices Existing New - roadmap Virtual Datacenter OS from VMware Agenda
More informationSoftRDMA: Rekindling High Performance Software RDMA over Commodity Ethernet
SoftRDMA: Rekindling High Performance Software RDMA over Commodity Ethernet Mao Miao, Fengyuan Ren, Xiaohui Luo, Jing Xie, Qingkai Meng, Wenxue Cheng Dept. of Computer Science and Technology, Tsinghua
More informationThe Future of High-Performance Networking (The 5?, 10?, 15? Year Outlook)
Workshop on New Visions for Large-Scale Networks: Research & Applications Vienna, VA, USA, March 12-14, 2001 The Future of High-Performance Networking (The 5?, 10?, 15? Year Outlook) Wu-chun Feng feng@lanl.gov
More informationProviding Near-Optimal Fair- Queueing Guarantees at Round-Robin Amortized Cost
Providing Near-Optimal Fair- Queueing Guarantees at Round-Robin Amortized Cost Paolo Valente Department of Physics, Computer Science and Mathematics Modena - Italy Workshop PRIN SFINGI October 2013 2 Contributions
More informationThe NE010 iwarp Adapter
The NE010 iwarp Adapter Gary Montry Senior Scientist +1-512-493-3241 GMontry@NetEffect.com Today s Data Center Users Applications networking adapter LAN Ethernet NAS block storage clustering adapter adapter
More informationMultifunction Networking Adapters
Ethernet s Extreme Makeover: Multifunction Networking Adapters Chuck Hudson Manager, ProLiant Networking Technology Hewlett-Packard 2004 Hewlett-Packard Development Company, L.P. The information contained
More informationNFS/RDMA over 40Gbps iwarp Wael Noureddine Chelsio Communications
NFS/RDMA over 40Gbps iwarp Wael Noureddine Chelsio Communications Outline RDMA Motivating trends iwarp NFS over RDMA Overview Chelsio T5 support Performance results 2 Adoption Rate of 40GbE Source: Crehan
More informationThe Network Stack. Chapter Network stack functions 216 CHAPTER 21. THE NETWORK STACK
216 CHAPTER 21. THE NETWORK STACK 21.1 Network stack functions Chapter 21 The Network Stack In comparison with some other parts of OS design, networking has very little (if any) basis in formalism or algorithms
More informationUse of the Internet SCSI (iscsi) protocol
A unified networking approach to iscsi storage with Broadcom controllers By Dhiraj Sehgal, Abhijit Aswath, and Srinivas Thodati In environments based on Internet SCSI (iscsi) and 10 Gigabit Ethernet, deploying
More informationA Deficit Round Robin with Fragmentation Scheduler for Mobile WiMAX
A Deficit Round Robin with Fragmentation Scheduler for Mobile WiMAX Chakchai So-In, Raj Jain and Abdel-Karim Al Tammi Washington University in Saint Louis Saint Louis, MO 63130 jain@cse.wustl.edu Presentation
More informationTraffic Characteristics of Bulk Data Transfer using TCP/IP over Gigabit Ethernet
Traffic Characteristics of Bulk Data Transfer using TCP/IP over Gigabit Ethernet Aamir Shaikh and Kenneth J. Christensen Department of Computer Science and Engineering University of South Florida Tampa,
More informationThread Cluster Memory Scheduling: Exploiting Differences in Memory Access Behavior. Yoongu Kim Michael Papamichael Onur Mutlu Mor Harchol-Balter
Thread Cluster Memory Scheduling: Exploiting Differences in Memory Access Behavior Yoongu Kim Michael Papamichael Onur Mutlu Mor Harchol-Balter Motivation Memory is a shared resource Core Core Core Core
More informationReceive Livelock. Robert Grimm New York University
Receive Livelock Robert Grimm New York University The Three Questions What is the problem? What is new or different? What are the contributions and limitations? Motivation Interrupts work well when I/O
More informationVirtualization, Xen and Denali
Virtualization, Xen and Denali Susmit Shannigrahi November 9, 2011 Susmit Shannigrahi () Virtualization, Xen and Denali November 9, 2011 1 / 70 Introduction Virtualization is the technology to allow two
More informationRoCE vs. iwarp Competitive Analysis
WHITE PAPER February 217 RoCE vs. iwarp Competitive Analysis Executive Summary...1 RoCE s Advantages over iwarp...1 Performance and Benchmark Examples...3 Best Performance for Virtualization...5 Summary...6
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 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 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 informationLinux Network Tuning Guide for AMD EPYC Processor Based Servers
Linux Network Tuning Guide for AMD EPYC Processor Application Note Publication # 56224 Revision: 1.00 Issue Date: November 2017 Advanced Micro Devices 2017 Advanced Micro Devices, Inc. All rights reserved.
More informationReduces latency and buffer overhead. Messaging occurs at a speed close to the processors being directly connected. Less error detection
Switching Operational modes: Store-and-forward: Each switch receives an entire packet before it forwards it onto the next switch - useful in a general purpose network (I.e. a LAN). usually, there is a
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 informationCongestion Control in TCP
Congestion Control in TCP Antonio Carzaniga Faculty of Informatics University of Lugano November 11, 2014 Outline Intro to congestion control Input rate vs. output throughput Congestion window Congestion
More informationMessage Passing Architecture in Intra-Cluster Communication
CS213 Message Passing Architecture in Intra-Cluster Communication Xiao Zhang Lamxi Bhuyan @cs.ucr.edu February 8, 2004 UC Riverside Slide 1 CS213 Outline 1 Kernel-based Message Passing
More informationAnnouncements. Reading. Project #1 due in 1 week at 5:00 pm Scheduling Chapter 6 (6 th ed) or Chapter 5 (8 th ed) CMSC 412 S14 (lect 5)
Announcements Reading Project #1 due in 1 week at 5:00 pm Scheduling Chapter 6 (6 th ed) or Chapter 5 (8 th ed) 1 Relationship between Kernel mod and User Mode User Process Kernel System Calls User Process
More informationTLDK Overview. Transport Layer Development Kit Keith Wiles April Contributions from Ray Kinsella & Konstantin Ananyev
TLDK Overview Transport Layer Development Kit Keith Wiles April 2017 Contributions from Ray Kinsella & Konstantin Ananyev Notices and Disclaimers Intel technologies features and benefits depend on system
More informationMultimedia Streaming. Mike Zink
Multimedia Streaming Mike Zink Technical Challenges Servers (and proxy caches) storage continuous media streams, e.g.: 4000 movies * 90 minutes * 10 Mbps (DVD) = 27.0 TB 15 Mbps = 40.5 TB 36 Mbps (BluRay)=
More informationBuffered Distributor Proposal. Gigabit. (a.k.a. Full Duplex Repeater) (a.k.a. Buffered Repeater) Packet Engines. Bernard Daines
Gigabit Buffered Distributor Proposal (a.k.a. Full Duplex Repeater) (a.k.a. Buffered Repeater) Bernard Daines Packet Engines (59) 922-919 FAX (59) 922-9185 bernardd@packetengines.com Mailing Address Shipping
More informationGateware Defined Networking (GDN) for Ultra Low Latency Trading and Compliance
Gateware Defined Networking (GDN) for Ultra Low Latency Trading and Compliance STAC Summit: Panel: FPGA for trading today: December 2015 John W. Lockwood, PhD, CEO Algo-Logic Systems, Inc. JWLockwd@algo-logic.com
More informationALL the assignments (A1, A2, A3) and Projects (P0, P1, P2) we have done so far.
Midterm Exam Reviews ALL the assignments (A1, A2, A3) and Projects (P0, P1, P2) we have done so far. Particular attentions on the following: System call, system kernel Thread/process, thread vs process
More informationOptimizing your virtual switch for VXLAN. Ron Fuller, VCP-NV, CCIE#5851 (R&S/Storage) Staff Systems Engineer NSBU
Optimizing your virtual switch for VXLAN Ron Fuller, VCP-NV, CCIE#5851 (R&S/Storage) Staff Systems Engineer NSBU fuller@vmware.com VXLAN Protocol Overview Ethernet in IP overlay network Entire L2 frame
More informationTo Grant or Not to Grant
To Grant or Not to Grant (for the case of Xen network drivers) João Martins Principal Software Engineer Virtualization Team July 11, 2017 Safe Harbor Statement The following is intended to outline our
More informationOperating Systems. Process scheduling. Thomas Ropars.
1 Operating Systems Process scheduling Thomas Ropars thomas.ropars@univ-grenoble-alpes.fr 2018 References The content of these lectures is inspired by: The lecture notes of Renaud Lachaize. The lecture
More informationImplementation Experiments on HighSpeed and Parallel TCP
Implementation Experiments on HighSpeed and TCP Zongsheng Zhang Go Hasegawa Masayuki Murata Osaka University Outline Introduction Background of and g Why to evaluate in a test-bed network A refined algorithm
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 informationSolarflare and OpenOnload Solarflare Communications, Inc.
Solarflare and OpenOnload 2011 Solarflare Communications, Inc. Solarflare Server Adapter Family Dual Port SFP+ SFN5122F & SFN5162F Single Port SFP+ SFN5152F Single Port 10GBASE-T SFN5151T Dual Port 10GBASE-T
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 informationEvaluation of the Chelsio T580-CR iscsi Offload adapter
October 2016 Evaluation of the Chelsio T580-CR iscsi iscsi Offload makes a difference Executive Summary As application processing demands increase and the amount of data continues to grow, getting this
More informationThe NIDS Cluster: Scalable, Stateful Network Intrusion Detection on Commodity Hardware
The NIDS Cluster: Scalable, Stateful Network Intrusion Detection on Commodity Hardware Matthias Vallentin 1, Robin Sommer 2,3, Jason Lee 2, Craig Leres 2 Vern Paxson 3,2, and Brian Tierney 2 1 TU München
More informationActivity-Based Congestion Management for Fair Bandwidth Sharing in Trusted Packet Networks
Communication Networks Activity-Based Congestion Management for Fair Bandwidth Sharing in Trusted Packet Networks Michael Menth and Nikolas Zeitler http://kn.inf.uni-tuebingen.de Outline The problem Definition
More informationNVMe Direct. Next-Generation Offload Technology. White Paper
NVMe Direct Next-Generation Offload Technology The market introduction of high-speed NVMe SSDs and 25/40/50/100Gb Ethernet creates exciting new opportunities for external storage NVMe Direct enables high-performance
More informationQuickSpecs. Overview. HPE Ethernet 10Gb 2-port 535 Adapter. HPE Ethernet 10Gb 2-port 535 Adapter. 1. Product description. 2.
Overview 1. Product description 2. Product features 1. Product description HPE Ethernet 10Gb 2-port 535FLR-T adapter 1 HPE Ethernet 10Gb 2-port 535T adapter The HPE Ethernet 10GBase-T 2-port 535 adapters
More information