Motivation CPUs can not keep pace with network
|
|
- Clinton Johnson
- 5 years ago
- Views:
Transcription
1 Deferred Segmentation For Wire-Speed Transmission of Large TCP Frames over Standard GbE Networks Bilic Hrvoye (Billy) Igor Chirashnya Yitzhak Birk Zorik Machulsky Technion - Israel Institute of technology Department of Electrical Engineering Motivation CPUs can not keep pace with network speed explosion processing by host CPU is performance bottleneck for TCP/IP traffic over Gigabit networks User space Host CPU Kernel space Hardware GbE Network More Intelligence is moved into networks!!! Page 1
2 Goals Solve the real problem - bottleneck for large TCP transfers over standard Gigabit Ethernet networks Reach the wire speed for large TCP/IP transfers Maximize host P/E ratio (P/E = BW/CPU load) All this BUT W/O modifications of existing (legacy) applications W/O modifications of existing OS TCP/IP protocol stacks With minimal Gigabit Ethernet NIC development efforts End system TCP/IP overhead analysis Per connection Decrease the number of packets exchanged on TCP connection establishment/termination Per byte Zero-copy techniques Checksum offload to HW Per packet overhead Interrupt Coalesing Large frames to carry data in Page 2
3 Previous approaches to TCP/IP bottleneck problem TCP/IP splitting approach - split between applications, OS and NIC Hard to implement - requires modification NIC, OS and applications TCP/IP offload - in HW Expensive HW and very hard to implement No industry acceptance, mostly research works!!! Our TCP/IP Pipelining approach Offload to NIC only small subset of functionality and reach 1GbE wire speed BUT w/o any OS or applications modifications Pros No changes of existing OSs and applications Small NIC implementation efforts & cheap HW Ideal low cost solution for 1GbE networks Cons Does not impact small TCP/IP transfers Not competitive with existing transport in H/W implementations FC and IB (higher CPU load) Does not suit 10Gb/s transfer rates Synergy with current industrial needs for 1GbE!!! Page 3
4 Previous Work on TCP/IP Acceleration Duke university reasearch TCP/IP traffic over Myrinet Gigabit Networks Performance increases with large MTUs(*) MTU (1.5KB->32KB) BW CPU Load highly decrease P/E ratio at least doubles on both Tx and Rx side (*) All results w/o zero-copy and with checksum in HW Myrinet Network has UNLIMITED MTU size (up to 32KB) Alteon Inc. proposed Jumbo Frames (MTU = 9KB) as a solution for Gigabit Ethernet networks BUT Standard GbEthernet networks MTU = 1.5KB Main Idea Gain the perfromance of large MTU networks for GbE Cheat, by causing large TCP frames transfers to NIC => Emulate Myrinet network Emulate network with large MTU size MSS spoofing - Intecept SYN packets and modify MSS value Break the large frames down to Ethernet packets with standard MTU (1.5KB) size Deferred TCP segmentation - ACK coalescing Targeted Systems Page 4
5 Advantages over Jumbo Frames Legacy Jumbo Frames Deferred TCP Segmentation User Space 18 KB 18 KB 18 KB Data Frames Kernel Space 1.5 KB 9 KB 18 KB Inter-operates with standard GbE networks TCP/IP TCP Frames Performance - Frames > 9K (up to 64KB) Network NIC 1.5 KB 9 KB 1.5 KB TCP Segments Smaller frames are more network friendly Demonstration of Completeness Ethernet Emulation Environment Two IBM Evaluation boards inter-connected by Ethernet network IBM Evaluation board Integrated PPC405 running our TCP segm - ACK coalescing firmware Connected over PCI to Pentium 450MHz host running Linux R.Hat 6.0 Demonstrate TCP segmentation - ACK coelescing mechanism with unmodified s Gigabit Ethernet Environment Two Alteon GbE AceNICs interconnected by GbE network Alteon AceNIC Device Driver perfroms TCP segm -ACK coalescing mechanism Connected over PCI to Pentium 450MHz host running Linux R.Hat 6.0 Demonstrate completeness while inter-operates with an unmodified off-the-shelf receiver Netperf used for TCP traffic generation; Tcpdump for monitoring Page 5
6 Performance Estimations TCP conn. receiver side is assumed not to be bottleneck Multiple clients compose connections Receiver side Estimated performance on the Sender side Host CPU process large TCP frames (>8KB) at wire speed - Duke perfroms its standard functions at wire speed Additional processing by NIC related to TCP seg - ACK coalescing Tx path TCP segmentation» Original TCP and IP headers used as a templates» Start processing already when headers are in Tx FIFO» Assembly TCP seg. code running on embedded uprocessor < 200 cycles (100MHz clock => 2us) << 12 us (1.5K\1Gb/s) Rx path Calculate checksum on-the-fly while receiving data from network ACK coalescing - overall ~2.5us» Flow Lookup - < 2us (100MHz; 10K entries)» ACK coal. Assembly code for embedded processor ~0.5us» ACK rate in average ~ TCP segments trans. rate ~ 12.us Summary CPUs can not keep pace with network speed explosion TCP/IP inteligance should be moved into the network Smart simple TCP/IP acceleration by ASIC (NIC) solves bottleneck for 1GbE networks Multiple Gigabit (10G) networks will require different solutions FC and IB - Implement transport protocols in HW 10GbE -TCP/IP networks will require different solution to compete in HW!!! Page 6
7 DEC Monet MHz - MB Lcache, MB RAM Sender (Tx) & Receiver (Rx) BW Bandwidth (Mb\s) MTU 1.5K 4K 8K 16K 32K DEC Monet MHz - MB Lcache, MB RAM Sender (Tx) & Receiver (Rx) Tx Rx CPU Load (%) MTU 1.5K 4K 8K 16K 32K Page 7
8 MTU Emulation Host CPU TCP/IP stack Device Drv. Emulate large MTU up to 64 KB Emulate large MTU size to Transparent to TCP/IP applications Hardware Real MTU 1.5 KB Server MSS Spoofing Legacy Client Transparent to s (4) MSS = min(mtu & MSS) = 9KB (8) MSS = min(mtu & MSS) = 1.5KB (0) MTU 9K (0) MTU 1.5K (5) MSS 9K (3) MSS 9K Device Drivers (1) MSS 1.5K (7) MSS 1.5K Our New Legacy (6) SYN/ACK (MSS 1.5K) (2) SYN (MSS 1.5K) Page 8
9 Deferred TCP Segmentation & ACK coalescing Server Legacy Client MSS = 9KB MSS = 1.5KB (1) 32K (1) 9KB Transparency ack ack ack K TCP segment. Our New ACK coales. Legacy Transparency ack ack ack... ack TCP segmentation - ACK coalescing Targeted Systems Systems with Assymetric TCP traffic Accelerates mainly Tx path (outbound traffic) Servers serving many clients with large transmit outbound traffic Enhanced ASIC/NIC required only on Server side Completely Transparent to clients Re-segmentation can be implemented but rise cost of NIC NAS boxes, File, Video & Servers Enhanced Server Data Cache Systems NIC or ASIC depend on internal architecture ISCSI HBA or RAID controller ASIC Smart ISCSI/IB/FC/SCSI boxes NIC or ASIC for Storage Routers/Gateways, Proxies etc. Page 9
QuickSpecs. 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 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 informationAn Extensible Message-Oriented Offload Model for High-Performance Applications
An Extensible Message-Oriented Offload Model for High-Performance Applications Patricia Gilfeather and Arthur B. Maccabe Scalable Systems Lab Department of Computer Science University of New Mexico pfeather@cs.unm.edu,
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 informationIntroduction to TCP/IP Offload Engine (TOE)
Introduction to TCP/IP Offload Engine (TOE) Version 1.0, April 2002 Authored By: Eric Yeh, Hewlett Packard Herman Chao, QLogic Corp. Venu Mannem, Adaptec, Inc. Joe Gervais, Alacritech Bradley Booth, Intel
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 informationOn the cost of tunnel endpoint processing in overlay virtual networks
J. Weerasinghe; NVSDN2014, London; 8 th December 2014 On the cost of tunnel endpoint processing in overlay virtual networks J. Weerasinghe & F. Abel IBM Research Zurich Laboratory Outline Motivation Overlay
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 information440GX Application Note
Overview of TCP/IP Acceleration Hardware January 22, 2008 Introduction Modern interconnect technology offers Gigabit/second (Gb/s) speed that has shifted the bottleneck in communication from the physical
More informationLarge Receive Offload implementation in Neterion 10GbE Ethernet driver
Large Receive Offload implementation in Neterion 10GbE Ethernet driver Leonid Grossman Neterion, Inc. leonid@neterion.com Abstract 1 Introduction The benefits of TSO (Transmit Side Offload) implementation
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 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 informationAn Extensible Message-Oriented Offload Model for High-Performance Applications
An Extensible Message-Oriented Offload Model for High-Performance Applications Patricia Gilfeather and Arthur B. Maccabe Scalable Systems Lab Department of Computer Science University of New Mexico pfeather@cs.unm.edu,
More informationFreeBSD Network Performance Tuning
Sucon 2004 Zurich, Switzerland Hendrik Scholz hscholz@raisdorf.net http://www.wormulon.net/ Agenda Motivation Overview Optimization approaches sysctl() tuning Measurement NIC comparision Conclusion Motivation
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 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 informationImpact of Cache Coherence Protocols on the Processing of Network Traffic
Impact of Cache Coherence Protocols on the Processing of Network Traffic Amit Kumar and Ram Huggahalli Communication Technology Lab Corporate Technology Group Intel Corporation 12/3/2007 Outline Background
More informationEvaluating the Impact of RDMA on Storage I/O over InfiniBand
Evaluating the Impact of RDMA on Storage I/O over InfiniBand J Liu, DK Panda and M Banikazemi Computer and Information Science IBM T J Watson Research Center The Ohio State University Presentation Outline
More informationTopic & Scope. Content: The course gives
Topic & Scope Content: The course gives an overview of network processor cards (architectures and use) an introduction of how to program Intel IXP network processors some ideas of how to use network processors
More informationEnd-to-End Adaptive Packet Aggregation for High-Throughput I/O Bus Network Using Ethernet
Hot Interconnects 2014 End-to-End Adaptive Packet Aggregation for High-Throughput I/O Bus Network Using Ethernet Green Platform Research Laboratories, NEC, Japan J. Suzuki, Y. Hayashi, M. Kan, S. Miyakawa,
More informationECE 650 Systems Programming & Engineering. Spring 2018
ECE 650 Systems Programming & Engineering Spring 2018 Networking Transport Layer Tyler Bletsch Duke University Slides are adapted from Brian Rogers (Duke) TCP/IP Model 2 Transport Layer Problem solved:
More informationImplementation and Analysis of Large Receive Offload in a Virtualized System
Implementation and Analysis of Large Receive Offload in a Virtualized System Takayuki Hatori and Hitoshi Oi The University of Aizu, Aizu Wakamatsu, JAPAN {s1110173,hitoshi}@u-aizu.ac.jp Abstract System
More informationINT-1010 TCP Offload Engine
INT-1010 TCP Offload Engine Product brief, features and benefits summary Highly customizable hardware IP block. Easily portable to ASIC flow, Xilinx or Altera FPGAs INT-1010 is highly flexible that is
More informationNT1210 Introduction to Networking. Unit 10
NT1210 Introduction to Networking Unit 10 Chapter 10, TCP/IP Transport Objectives Identify the major needs and stakeholders for computer networks and network applications. Compare and contrast the OSI
More informationNetwork Design Considerations for Grid Computing
Network Design Considerations for Grid Computing Engineering Systems How Bandwidth, Latency, and Packet Size Impact Grid Job Performance by Erik Burrows, Engineering Systems Analyst, Principal, Broadcom
More informationExperience in Offloading Protocol Processing to a Programmable NIC
Experience in Offloading Protocol Processing to a Programmable NIC Arthur B. Maccabe, Wenbin Zhu Computer Science Department The University of New Mexico Albuquerque, NM 87131 Jim Otto, Rolf Riesen Scalable
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 informationW H I T E P A P E R. Comparison of Storage Protocol Performance in VMware vsphere 4
W H I T E P A P E R Comparison of Storage Protocol Performance in VMware vsphere 4 Table of Contents Introduction................................................................... 3 Executive Summary............................................................
More informationQuickSpecs. Models. Standard Features Server Support. HP Integrity PCI-e 2-port 10GbE Cu Adapter. HP Integrity PCI-e 2-port 10GbE LR Adapter.
Overview The is an eight lane (x8) PCI Express (PCIe) 10 Gigabit network solution offering optimal throughput. This PCI Express Gen 2 adapter ships with two SFP+ (Small Form-factor Pluggable) cages suitable
More information10GE network tests with UDP. Janusz Szuba European XFEL
10GE network tests with UDP Janusz Szuba European XFEL Outline 2 Overview of initial DAQ architecture Slice test hardware specification Initial networking test results DAQ software UDP tests Summary 10GE
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 informationNetFPGA Hardware Architecture
NetFPGA Hardware Architecture Jeffrey Shafer Some slides adapted from Stanford NetFPGA tutorials NetFPGA http://netfpga.org 2 NetFPGA Components Virtex-II Pro 5 FPGA 53,136 logic cells 4,176 Kbit block
More informationThe Case for RDMA. Jim Pinkerton RDMA Consortium 5/29/2002
The Case for RDMA Jim Pinkerton RDMA Consortium 5/29/2002 Agenda What is the problem? CPU utilization and memory BW bottlenecks Offload technology has failed (many times) RDMA is a proven sol n to the
More informationPerformance of ORBs on Switched Fabric Transports
Performance of ORBs on Switched Fabric Transports Victor Giddings Objective Interface Systems victor.giddings@ois.com 2001 Objective Interface Systems, Inc. Switched Fabrics High-speed interconnects High-bandwidth,
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 informationThe CMS Event Builder
The CMS Event Builder Frans Meijers CERN/EP-CMD CMD on behalf of the CMS-DAQ group CHEP03, La Jolla, USA, March 24-28 28 2003 1. Introduction 2. Selected Results from the Technical Design Report R&D programme
More informationNOTE: A minimum of 1 gigabyte (1 GB) of server memory is required per each NC510F adapter. HP NC510F PCIe 10 Gigabit Server Adapter
Overview The NC510F is an eight lane (x8) PCI Express (PCIe) 10 Gigabit Ethernet SR (10GBASE-SR fiber optic) network solution offering the highest bandwidth available in a ProLiant Ethernet adapter. The
More informationInput/Output. Today. Next. Principles of I/O hardware & software I/O software layers Disks. Protection & Security
Input/Output Today Principles of I/O hardware & software I/O software layers Disks Next Protection & Security Operating Systems and I/O Two key operating system goals Control I/O devices Provide a simple,
More informationA Framework for Memory Hierarchies
Associativity schemes Scheme Number of sets Blocks per set Direct mapped Number of blocks in cache 1 Set associative Blocks in cache / Associativity Associativity (2-8) Fully associative 1 Number Blocks
More informationWindows Server 2012 and Windows Server 2012 R2 NIC Optimization and Best Practices with Dell PS Series
Windows Server 2012 and Windows Server 2012 R2 NIC Optimization and Best Practices with Dell PS Series Dell EMC Engineering January 2017 A Dell EMC Best Practices Guide Revisions Date July 2013 September
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 informationHP BladeSystem c-class Ethernet network adaptors
HP BladeSystem c-class Ethernet network adaptors Family data sheet NC325m Quad-port Gigabit NC326m Dual-port Gigabit NC360m Dual-port Gigabit NC364m Quad-port Gigabit NC382m Dual-port Multifunction Gigabit
More informationConnection Handoff Policies for TCP Offload Network Interfaces
Connection Handoff Policies for TCP Offload Network Interfaces Hyong-youb Kim and Scott Rixner Rice University Houston, TX 77005 {hykim, rixner}@rice.edu Abstract This paper presents three policies for
More informationQuickSpecs. Models. HP NC510C PCIe 10 Gigabit Server Adapter. Overview
Overview The NC510C is a x8 PCI Express (PCIe) 10 Gigabit Ethernet CX4 (10GBASE-CX4 copper) network solution offering the highest bandwidth available in a ProLiant Ethernet adapter. This high-performance,
More informationSingle Root I/O Virtualization (SR-IOV) and iscsi Uncompromised Performance for Virtual Server Environments Leonid Grossman Exar Corporation
Single Root I/O Virtualization (SR-IOV) and iscsi Uncompromised Performance for Virtual Server Environments Leonid Grossman Exar Corporation Introduction to Exar iscsi project and related datacenter trends
More informationStorage Protocol Offload for Virtualized Environments Session 301-F
Storage Protocol Offload for Virtualized Environments Session 301-F Dennis Martin, President August 2016 1 Agenda About Demartek Offloads I/O Virtualization Concepts RDMA Concepts Overlay Networks and
More informationNovel Intelligent I/O Architecture Eliminating the Bus Bottleneck
Novel Intelligent I/O Architecture Eliminating the Bus Bottleneck Volker Lindenstruth; lindenstruth@computer.org The continued increase in Internet throughput and the emergence of broadband access networks
More informationUSING ISCSI AND VERITAS BACKUP EXEC 9.0 FOR WINDOWS SERVERS BENEFITS AND TEST CONFIGURATION
WHITE PAPER Maximize Storage Networks with iscsi USING ISCSI AND VERITAS BACKUP EXEC 9.0 FOR WINDOWS SERVERS BENEFITS AND TEST CONFIGURATION For use with Windows 2000 VERITAS Software Corporation 03/05/2003
More informationCERN openlab Summer 2006: Networking Overview
CERN openlab Summer 2006: Networking Overview Martin Swany, Ph.D. Assistant Professor, Computer and Information Sciences, U. Delaware, USA Visiting Helsinki Institute of Physics (HIP) at CERN swany@cis.udel.edu,
More informationExploiting the full power of modern industry standard Linux-Systems with TSM Stephan Peinkofer
TSM Performance Tuning Exploiting the full power of modern industry standard Linux-Systems with TSM Stephan Peinkofer peinkofer@lrz.de Agenda Network Performance Disk-Cache Performance Tape Performance
More informationMyri-10G Myrinet Converges with Ethernet
Myri-10G Myrinet Converges with Ethernet David PeGan VP, Sales dave@myri.com (Substituting for Tom Leinberger) 4 October 2006 Oklahoma Supercomputing Symposium 1 New Directions for Myricom Although Myricom
More informationPerformance Analysis of iscsi Middleware Optimized for Encryption Processing in a Long-Latency Environment
Performance Analysis of iscsi Middleware Optimized for Encryption Processing in a Long-Latency Environment Kikuko Kamisaka Graduate School of Humanities and Sciences Ochanomizu University -1-1, Otsuka,
More informationRiceNIC. Prototyping Network Interfaces. Jeffrey Shafer Scott Rixner
RiceNIC Prototyping Network Interfaces Jeffrey Shafer Scott Rixner RiceNIC Overview Gigabit Ethernet Network Interface Card RiceNIC - Prototyping Network Interfaces 2 RiceNIC Overview Reconfigurable and
More informationBenefits of full TCP/IP offload in the NFS
Benefits of full TCP/IP offload in the NFS Services. Hari Ghadia Technology Strategist Adaptec Inc. hari_ghadia@adaptec.com Page Agenda Industry trend and role of NFS TCP/IP offload Adapters NACs Performance
More informationCSCI-GA Operating Systems. Networking. Hubertus Franke
CSCI-GA.2250-001 Operating Systems Networking Hubertus Franke frankeh@cs.nyu.edu Source: Ganesh Sittampalam NYU TCP/IP protocol family IP : Internet Protocol UDP : User Datagram Protocol RTP, traceroute
More informationBoosting Server-to-Server Gigabit Throughput with Jumbo Frames
Boosting Server-to-Server Gigabit Throughput with Jumbo Frames September 15, 2000 U.S.A. 2000 Hewlett-Packard Company Legal Notices The information in this document is subject to change without notice.
More informationNetworking for Data Acquisition Systems. Fabrice Le Goff - 14/02/ ISOTDAQ
Networking for Data Acquisition Systems Fabrice Le Goff - 14/02/2018 - ISOTDAQ Outline Generalities The OSI Model Ethernet and Local Area Networks IP and Routing TCP, UDP and Transport Efficiency Networking
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 informationKey Measures of InfiniBand Performance in the Data Center. Driving Metrics for End User Benefits
Key Measures of InfiniBand Performance in the Data Center Driving Metrics for End User Benefits Benchmark Subgroup Benchmark Subgroup Charter The InfiniBand Benchmarking Subgroup has been chartered by
More informationINT 1011 TCP Offload Engine (Full Offload)
INT 1011 TCP Offload Engine (Full Offload) Product brief, features and benefits summary Provides lowest Latency and highest bandwidth. Highly customizable hardware IP block. Easily portable to ASIC flow,
More informationSupport for Smart NICs. Ian Pratt
Support for Smart NICs Ian Pratt Outline Xen I/O Overview Why network I/O is harder than block Smart NIC taxonomy How Xen can exploit them Enhancing Network device channel NetChannel2 proposal I/O Architecture
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 informationIO virtualization. Michael Kagan Mellanox Technologies
IO virtualization Michael Kagan Mellanox Technologies IO Virtualization Mission non-stop s to consumers Flexibility assign IO resources to consumer as needed Agility assignment of IO resources to consumer
More informationRon Emerick, Oracle Corporation
PCI Express PRESENTATION Virtualization TITLE GOES HERE Overview Ron Emerick, Oracle Corporation SNIA Legal Notice The material contained in this tutorial is copyrighted by the SNIA unless otherwise noted.
More informationSystem Software Design for Multimedia Networking. Jonathan C.L. Liu, Ph.D. CISE Department University of Florida
System Software Design for Multimedia Networking Jonathan C.L. Liu, Ph.D. CISE Department University of Florida Multimedia Communication Applications Video Conferencing Service Distance learning; Company
More informationQuickSpecs. Integrated NC7782 Gigabit Dual Port PCI-X LOM. Overview
Overview The integrated NC7782 dual port LOM incorporates a variety of features on a single chip for faster throughput than previous 10/100 solutions using Category 5 (or better) twisted-pair cabling,
More informationUsing Switches with a PS Series Group
Cisco Catalyst 3750 and 2970 Switches Using Switches with a PS Series Group Abstract This Technical Report describes how to use Cisco Catalyst 3750 and 2970 switches with a PS Series group to create a
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 informationScaling Internet TV Content Delivery ALEX GUTARIN DIRECTOR OF ENGINEERING, NETFLIX
Scaling Internet TV Content Delivery ALEX GUTARIN DIRECTOR OF ENGINEERING, NETFLIX Inventing Internet TV Available in more than 190 countries 104+ million subscribers Lots of Streaming == Lots of Traffic
More informationWhat is the Future for High-Performance Networking?
What is the Future for High-Performance Networking? Wu-chun (Wu) Feng feng@lanl.gov RADIANT: Research And Development in Advanced Network Technology http://www.lanl.gov/radiant Computer & Computational
More informationPCI Express x8 Quad Port 10Gigabit Server Adapter (Intel XL710 Based)
NIC-PCIE-4SFP+-PLU PCI Express x8 Quad Port 10Gigabit Server Adapter (Intel XL710 Based) Key Features Quad-port 10 GbE adapters PCI Express* (PCIe) 3.0, x8 Exceptional Low Power Adapters Network Virtualization
More informationPerformance assessment of CORBA for the transport of userplane data in future wideband radios. Piya Bhaskar Lockheed Martin
Performance assessment of CORBA for the transport of userplane data in future wideband radios Piya Bhaskar Lockheed Martin 1 Outline Introduction to the problem Test Setup Results Conclusion 2 Problem
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 informationLeveraging HyperTransport for a custom high-performance cluster network
Leveraging HyperTransport for a custom high-performance cluster network Mondrian Nüssle HTCE Symposium 2009 11.02.2009 Outline Background & Motivation Architecture Hardware Implementation Host Interface
More informationMark Falco Oracle Coherence Development
Achieving the performance benefits of Infiniband in Java Mark Falco Oracle Coherence Development 1 Copyright 2011, Oracle and/or its affiliates. All rights reserved. Insert Information Protection Policy
More informationINT G bit TCP Offload Engine SOC
INT 10011 10 G bit TCP Offload Engine SOC Product brief, features and benefits summary: Highly customizable hardware IP block. Easily portable to ASIC flow, Xilinx/Altera FPGAs or Structured ASIC flow.
More informationLessons learned from MPI
Lessons learned from MPI Patrick Geoffray Opinionated Senior Software Architect patrick@myri.com 1 GM design Written by hardware people, pre-date MPI. 2-sided and 1-sided operations: All asynchronous.
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 informationNIC-PCIE-4RJ45-PLU PCI Express x4 Quad Port Copper Gigabit Server Adapter (Intel I350 Based)
NIC-PCIE-4RJ45-PLU PCI Express x4 Quad Port Copper Gigabit Server Adapter (Intel I350 Based) Quad-port Gigabit Ethernet server adapters designed with performance enhancing features and new power management
More informationIO System. CP-226: Computer Architecture. Lecture 25 (24 April 2013) CADSL
IO System Virendra Singh Associate Professor Computer Architecture and Dependable Systems Lab Department of Electrical Engineering Indian Institute of Technology Bombay http://www.ee.iitb.ac.in/~viren/
More informationLearn Your Alphabet - SRIOV, NPIV, RoCE, iwarp to Pump Up Virtual Infrastructure Performance
Learn Your Alphabet - SRIOV, NPIV, RoCE, iwarp to Pump Up Virtual Infrastructure Performance TechTarget Dennis Martin 1 Agenda About Demartek I/O Virtualization Concepts RDMA Concepts Examples Demartek
More informationIBM Network Processor, Development Environment and LHCb Software
IBM Network Processor, Development Environment and LHCb Software LHCb Readout Unit Internal Review July 24 th 2001 Niko Neufeld, CERN 1 Outline IBM NP4GS3 Architecture A Readout Unit based on the NP4GS3
More informationIntel PRO/1000 PT and PF Quad Port Bypass Server Adapters for In-line Server Appliances
Technology Brief Intel PRO/1000 PT and PF Quad Port Bypass Server Adapters for In-line Server Appliances Intel PRO/1000 PT and PF Quad Port Bypass Server Adapters for In-line Server Appliances The world
More informationImproving Cluster Performance
Improving Cluster Performance Service Offloading Larger clusters may need to have special purpose node(s) to run services to prevent slowdown due to contention (e.g. NFS, DNS, login, compilation) In cluster
More informationA-GEAR 10Gigabit Ethernet Server Adapter X520 2xSFP+
Product Specification NIC-10G-2BF A-GEAR 10Gigabit Ethernet Server Adapter X520 2xSFP+ Apply Dual-port 10 Gigabit Fiber SFP+ server connections, These Server Adapters Provide Ultimate Flexibility and Scalability
More informationMatt Wakeley 27 June, iscsi Framing Presentation
Matt Wakeley 27 June, 2001 iscsi Storage Paradigm Receive descriptors are passed to SCSI Received FC Frames No need for large receive buffer Data steered directly from receive FIFO internal to protocol
More informationStacked Vlan - Performance Improvement and Challenges
Stacked Vlan - Performance Improvement and Challenges Toshiaki Makita NTT Open Source Software Center Today's topics Stacked vlan Performance Improvement and Challenges Interoperability Problem 2 Who is
More informationA SCSI Transport Layer Extension with Separate Data and Control Paths for Scalable Storage-Area-Network Architectures
Technion - Israel Institute of technology Department of Electrical Engineering SCSI-DSDC A SCSI Transport Layer Extension with Separate Data and Control Paths for Scalable Storage-Area-Network Architectures
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 informationMeasurement-based Analysis of TCP/IP Processing Requirements
Measurement-based Analysis of TCP/IP Processing Requirements Srihari Makineni Ravi Iyer Communications Technology Lab Intel Corporation {srihari.makineni, ravishankar.iyer}@intel.com Abstract With the
More informationLegUp: Accelerating Memcached on Cloud FPGAs
0 LegUp: Accelerating Memcached on Cloud FPGAs Xilinx Developer Forum December 10, 2018 Andrew Canis & Ruolong Lian LegUp Computing Inc. 1 COMPUTE IS BECOMING SPECIALIZED 1 GPU Nvidia graphics cards are
More informationBenchmarking the Performance of the Virtex-4 10/100/1000 TEMAC System Author: Kris Chaplin
Application Note: Embedded Processing XAPP1023 (v1.0) October 3, 2007 Benchmarking the Performance of the Virtex-4 10/100/1000 TEMAC System Author: Kris Chaplin Abstract This application note provides
More informationNetwork Adapter. Increased demand for bandwidth and application processing in. Improve B2B Application Performance with Gigabit Server
Improve B2B Application Performance with Gigabit Server Network Adapter By Uri Elzur Business-to-business (B2B) applications and gigabit networking speeds increase the load on server CPUs. These challenges
More informationSTORAGE CONSOLIDATION WITH IP STORAGE. David Dale, NetApp
STORAGE CONSOLIDATION WITH IP STORAGE David Dale, NetApp SNIA Legal Notice The material contained in this tutorial is copyrighted by the SNIA. Member companies and individuals may use this material in
More informationThe Tofu Interconnect 2
The Tofu Interconnect 2 Yuichiro Ajima, Tomohiro Inoue, Shinya Hiramoto, Shun Ando, Masahiro Maeda, Takahide Yoshikawa, Koji Hosoe, and Toshiyuki Shimizu Fujitsu Limited Introduction Tofu interconnect
More informationBuilding a High IOPS Flash Array: A Software-Defined Approach
Building a High IOPS Flash Array: A Software-Defined Approach Weafon Tsao Ph.D. VP of R&D Division, AccelStor, Inc. Santa Clara, CA Clarification Myth 1: S High-IOPS SSDs = High-IOPS All-Flash Array SSDs
More informationLighting the Blue Touchpaper for UK e-science - Closing Conference of ESLEA Project The George Hotel, Edinburgh, UK March, 2007
Working with 1 Gigabit Ethernet 1, The School of Physics and Astronomy, The University of Manchester, Manchester, M13 9PL UK E-mail: R.Hughes-Jones@manchester.ac.uk Stephen Kershaw The School of Physics
More informationVirtualization Practices: Providing a Complete Virtual Solution in a Box
PRESENTATION TITLE GOES HERE Virtualization Practices: Providing a Complete Virtual Solution in a Box Jyh-shing Chen / NetApp SNIA Legal Notice The material contained in this tutorial is copyrighted by
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 informationMemory Management Strategies for Data Serving with RDMA
Memory Management Strategies for Data Serving with RDMA Dennis Dalessandro and Pete Wyckoff (presenting) Ohio Supercomputer Center {dennis,pw}@osc.edu HotI'07 23 August 2007 Motivation Increasing demands
More information