SlideShare una empresa de Scribd logo
1 de 28
Virtualized Networking Performance




Stephen Hemminger
Principal Engineer
shemminger@vyatta.com
Age nd a
Wh at is a Virtu alize d N e twork
P e rform ance b e nch m arks
Tu ning tip s
P h ys ical E nte rp ris e D atace nte r

                        BORDER ROUTER




                        FIREWALL

                        VPN

                        INTRUSION PREVENTION



                    SWITCH

                                               10.0.0.0/24

                                                      WEBSERVERS




                                                10.3.0.0/24


                                                    APPS & STORAGE



                                                10.4.0.0/24


                                                     DATABASE
Virtu al N e twork Arch ite ctu re
P e rform ance M ile s tone s
2005      2006   2007    2008       2009        2010        2011




  1G line rate          Multiqueue NIC      10G bamdwidth



                                         1M packets / second




Xen 3.0          KVM              Hyper-V
                                  drivers
Be nch m arks
F orward ing
     R F C 2544 m inim u m p acke t
Th rou gh p u t
     TC P b u lk trans fe r
Late ncy
     R e q u e s t / R e s p ons e
R ou te r Be nch m ark
                R F C 2544
                Router
                Under
                 Test
Spirent
Virtu alize d R ou te r Be nch m ark
                           Router
                           Under
                                              Guest
                            Test

                                             Hypervisor
                  Bridge            Bridge
Spirent
Router Forwarding performance

                                      1G bit/sec bidirectional


                   100%


                   80%

                                                                               Bare Metal
Frames forwarded




                   60%                                                         Vmware ESX
                                                                               Xen
                   40%                                                         KVM


                   20%


                    0%
                          0   250   500      750      1000       1250   1500


                                    Packet size
E m u late d vs Virtu al N IC
E m u late d N e twork Inte rface
           Fake PCI region



Guest                        Hypervisor




           Packet
            Buffer
Virtu al N IC


Guest                   Hypervisor




                                     Netwo
          Shared                     rk
           Memory
E m u late d vs Virtu al N IC
                           100




                            75
Throughput vs Bare Metal




                                                                 Emulated Tx
                            50
                                                                 Virtual Tx
                                                                 Emulated Rx
                                                                 Virtual Rx

                            25




                             0
                                  Hyper-V   Vmware   KVM
VN IC ch aracte ris tics
               Hyper-V   Vmware    Xen        KVM
                         vmxnet3   netfront   virtio-net

MTU               1500     9000      65521       65535
Checksum                     Y          Y          Y
offload

Segmentation                 Y          Y          Y
offload

NAPI                         Y          Y          Y

LRO                          Y

VLAN                         Y

Multiqueue                   Y          ?          ?
O ffload not always a good id e a




                LR O ??
Tip #2:Use Jumbo MTU
VM to VM p e rform ance
                             2,000
Thorouhput (10^6 bits/sec)




                                0
                                100          1,000         10,000   100,000



                                             MTU (bytes)
M TU vs Brid ge
Tip #3: Minimize overhead
Virtu al S witch Typ e s

                             10000
                                      To Hypervisor
                                      From Hypervisor
Throughput (10^6 bits/sec)




                              7500    VM to VM




                              5000




                              2500




                                 0
                                           NAT          Bridged   Tap
Tip #4: D on't C ros s th e S tre am s
C ontrol flow ↔ C P U
Creator:cairo 1.10.2 (http://cairographi
CreationDate:Thu Oct 20 16:29:57 2011
LanguageLevel:2
M u ltith re ad b e nch m ark
                         20,000                                           UP Guest
                                                                          SMP Guest
Total Transactions/sec




                         15,000




                         10,000




                          5,000




                             0
                                            Packet Steering (RPS)
                                   Baseline                    Multi Queue NIC
M u ltip le Q u e u e
          H W or S W
                        Guest VM


                                   Thread
        Device
         queue


Flow                               Thread
        Device
clas                 VNIC
  sfi    queue
  er

                                   Thread
        Device
         queue
Tip #5: H e lp ou t!
X e n P e rform ance Im p rove m e nts
                                           1G bidirectional frame loss

                    100%
                                                                                              2.6.31
                                                                                              2.6.35
                                                                                              2.6.37
                     75%
Packets forwarded




                     50%



                     25%



                      0%
                           0   200   400        600     800    1000      1200   1400   1600




                                             Packet size
O ngoing work
Im p rove d Trans m it wake u p
C op y-le s s trans fe r
M u ltiqu e u e VN IC
F low s te e ring
5 Ways to Im p rove p e rform ance
Virtu al (not e m u late d ) ne twork inte rface
M axim ize p acke t s ize
M inim ize p acke t ove rh e ad
S tay on s am e C P U
C ontrib u te to fu tu re d e ve lop m e nts

Más contenido relacionado

La actualidad más candente

From virtual to high end HW routing for the adult
From virtual to high end HW routing for the adultFrom virtual to high end HW routing for the adult
From virtual to high end HW routing for the adultMarketingArrowECS_CZ
 
DPDK summit 2015: It's kind of fun to do the impossible with DPDK
DPDK summit 2015: It's kind of fun  to do the impossible with DPDKDPDK summit 2015: It's kind of fun  to do the impossible with DPDK
DPDK summit 2015: It's kind of fun to do the impossible with DPDKLagopus SDN/OpenFlow switch
 
FD.io Vector Packet Processing (VPP)
FD.io Vector Packet Processing (VPP)FD.io Vector Packet Processing (VPP)
FD.io Vector Packet Processing (VPP)Kirill Tsym
 
Packet Framework - Cristian Dumitrescu
Packet Framework - Cristian DumitrescuPacket Framework - Cristian Dumitrescu
Packet Framework - Cristian Dumitrescuharryvanhaaren
 
MARC ONERA Toulouse2012 Altreonic
MARC ONERA Toulouse2012 AltreonicMARC ONERA Toulouse2012 Altreonic
MARC ONERA Toulouse2012 AltreonicEric Verhulst
 
ARM LPC2300/LPC2400 TCP/IP Stack Porting
ARM LPC2300/LPC2400 TCP/IP Stack PortingARM LPC2300/LPC2400 TCP/IP Stack Porting
ARM LPC2300/LPC2400 TCP/IP Stack PortingMathivanan Elangovan
 
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitchDPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitchJim St. Leger
 
The analysis of Microburs (Burstiness) on Virtual Switch
The analysis of Microburs (Burstiness) on Virtual SwitchThe analysis of Microburs (Burstiness) on Virtual Switch
The analysis of Microburs (Burstiness) on Virtual SwitchChunghan Lee
 
QsNetIII, An HPC Interconnect For Peta Scale Systems
QsNetIII, An HPC Interconnect For Peta Scale SystemsQsNetIII, An HPC Interconnect For Peta Scale Systems
QsNetIII, An HPC Interconnect For Peta Scale SystemsFederica Pisani
 
How To Train Your Calxeda EnergyCore
How To Train Your  Calxeda EnergyCoreHow To Train Your  Calxeda EnergyCore
How To Train Your Calxeda EnergyCoreNaoto MATSUMOTO
 
Quantum Computing in China: Progress on Superconducting Multi-Qubits System
Quantum Computing in China: Progress on Superconducting Multi-Qubits SystemQuantum Computing in China: Progress on Superconducting Multi-Qubits System
Quantum Computing in China: Progress on Superconducting Multi-Qubits Systeminside-BigData.com
 
OVS and DPDK - T.F. Herbert, K. Traynor, M. Gray
OVS and DPDK - T.F. Herbert, K. Traynor, M. GrayOVS and DPDK - T.F. Herbert, K. Traynor, M. Gray
OVS and DPDK - T.F. Herbert, K. Traynor, M. Grayharryvanhaaren
 
Bandwidth measurement
Bandwidth measurementBandwidth measurement
Bandwidth measurementjeromy fu
 
Evaluating the networking performance of linux based home router platforms fo...
Evaluating the networking performance of linux based home router platforms fo...Evaluating the networking performance of linux based home router platforms fo...
Evaluating the networking performance of linux based home router platforms fo...Alpen-Adria-Universität
 
Inside the Volta GPU Architecture and CUDA 9
Inside the Volta GPU Architecture and CUDA 9Inside the Volta GPU Architecture and CUDA 9
Inside the Volta GPU Architecture and CUDA 9inside-BigData.com
 

La actualidad más candente (20)

From virtual to high end HW routing for the adult
From virtual to high end HW routing for the adultFrom virtual to high end HW routing for the adult
From virtual to high end HW routing for the adult
 
DPDK summit 2015: It's kind of fun to do the impossible with DPDK
DPDK summit 2015: It's kind of fun  to do the impossible with DPDKDPDK summit 2015: It's kind of fun  to do the impossible with DPDK
DPDK summit 2015: It's kind of fun to do the impossible with DPDK
 
FD.io Vector Packet Processing (VPP)
FD.io Vector Packet Processing (VPP)FD.io Vector Packet Processing (VPP)
FD.io Vector Packet Processing (VPP)
 
NFV в сетях операторов связи
NFV в сетях операторов связиNFV в сетях операторов связи
NFV в сетях операторов связи
 
Deep Dive Into Quantum
Deep Dive Into QuantumDeep Dive Into Quantum
Deep Dive Into Quantum
 
Packet Framework - Cristian Dumitrescu
Packet Framework - Cristian DumitrescuPacket Framework - Cristian Dumitrescu
Packet Framework - Cristian Dumitrescu
 
Решения NFV в контексте операторов связи
Решения NFV в контексте операторов связиРешения NFV в контексте операторов связи
Решения NFV в контексте операторов связи
 
MARC ONERA Toulouse2012 Altreonic
MARC ONERA Toulouse2012 AltreonicMARC ONERA Toulouse2012 Altreonic
MARC ONERA Toulouse2012 Altreonic
 
ARM LPC2300/LPC2400 TCP/IP Stack Porting
ARM LPC2300/LPC2400 TCP/IP Stack PortingARM LPC2300/LPC2400 TCP/IP Stack Porting
ARM LPC2300/LPC2400 TCP/IP Stack Porting
 
Quantum Networks
Quantum NetworksQuantum Networks
Quantum Networks
 
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitchDPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
 
The analysis of Microburs (Burstiness) on Virtual Switch
The analysis of Microburs (Burstiness) on Virtual SwitchThe analysis of Microburs (Burstiness) on Virtual Switch
The analysis of Microburs (Burstiness) on Virtual Switch
 
QsNetIII, An HPC Interconnect For Peta Scale Systems
QsNetIII, An HPC Interconnect For Peta Scale SystemsQsNetIII, An HPC Interconnect For Peta Scale Systems
QsNetIII, An HPC Interconnect For Peta Scale Systems
 
How To Train Your Calxeda EnergyCore
How To Train Your  Calxeda EnergyCoreHow To Train Your  Calxeda EnergyCore
How To Train Your Calxeda EnergyCore
 
Mpls co s
Mpls co sMpls co s
Mpls co s
 
Quantum Computing in China: Progress on Superconducting Multi-Qubits System
Quantum Computing in China: Progress on Superconducting Multi-Qubits SystemQuantum Computing in China: Progress on Superconducting Multi-Qubits System
Quantum Computing in China: Progress on Superconducting Multi-Qubits System
 
OVS and DPDK - T.F. Herbert, K. Traynor, M. Gray
OVS and DPDK - T.F. Herbert, K. Traynor, M. GrayOVS and DPDK - T.F. Herbert, K. Traynor, M. Gray
OVS and DPDK - T.F. Herbert, K. Traynor, M. Gray
 
Bandwidth measurement
Bandwidth measurementBandwidth measurement
Bandwidth measurement
 
Evaluating the networking performance of linux based home router platforms fo...
Evaluating the networking performance of linux based home router platforms fo...Evaluating the networking performance of linux based home router platforms fo...
Evaluating the networking performance of linux based home router platforms fo...
 
Inside the Volta GPU Architecture and CUDA 9
Inside the Volta GPU Architecture and CUDA 9Inside the Volta GPU Architecture and CUDA 9
Inside the Volta GPU Architecture and CUDA 9
 

Similar a Virtual Network Performance Challenge

PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...
PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...
PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...PROIDEA
 
OpenStack and OpenFlow Demos
OpenStack and OpenFlow DemosOpenStack and OpenFlow Demos
OpenStack and OpenFlow DemosBrent Salisbury
 
Networking is NOT Free: Lessons in Network Design
Networking is NOT Free: Lessons in Network DesignNetworking is NOT Free: Lessons in Network Design
Networking is NOT Free: Lessons in Network DesignRandy Bias
 
An Implementation of Virtual Cluster on a Cloud
An Implementation of Virtual Cluster on a CloudAn Implementation of Virtual Cluster on a Cloud
An Implementation of Virtual Cluster on a CloudPongsakorn U-chupala
 
Acceleration for big data, hadoop and memcached it168文库
Acceleration for big data, hadoop and memcached it168文库Acceleration for big data, hadoop and memcached it168文库
Acceleration for big data, hadoop and memcached it168文库Accenture
 
Acceleration for big data, hadoop and memcached it168文库
Acceleration for big data, hadoop and memcached it168文库Acceleration for big data, hadoop and memcached it168文库
Acceleration for big data, hadoop and memcached it168文库Accenture
 
V24 Product Brief - Aggregation & Filtering Taps
V24 Product Brief - Aggregation & Filtering TapsV24 Product Brief - Aggregation & Filtering Taps
V24 Product Brief - Aggregation & Filtering TapsChris Fenton
 
Cloudstack collab talk
Cloudstack collab talkCloudstack collab talk
Cloudstack collab talkMidokura
 
Understanding CleanAir Technology to improve Wlan Spectrum Management
Understanding CleanAir Technology to improve Wlan Spectrum Management Understanding CleanAir Technology to improve Wlan Spectrum Management
Understanding CleanAir Technology to improve Wlan Spectrum Management Cisco Canada
 
Network policies
Network policiesNetwork policies
Network policiesshanj
 
Hungary Usergroup - Midonet overlay programming
Hungary Usergroup - Midonet overlay programmingHungary Usergroup - Midonet overlay programming
Hungary Usergroup - Midonet overlay programmingMarton Kiss
 
EYWA Presentation v0.1.27
EYWA Presentation v0.1.27EYWA Presentation v0.1.27
EYWA Presentation v0.1.27JungIn Jung
 
Software Defined Data Centers - June 2012
Software Defined Data Centers - June 2012Software Defined Data Centers - June 2012
Software Defined Data Centers - June 2012Brent Salisbury
 
Best Practices for Building Ultra-Low Latency Microwave Networks
Best Practices for Building Ultra-Low Latency Microwave NetworksBest Practices for Building Ultra-Low Latency Microwave Networks
Best Practices for Building Ultra-Low Latency Microwave NetworksAviat Networks
 
Am 04 track1--salvatore orlando--openstack-apac-2012-final
Am 04 track1--salvatore orlando--openstack-apac-2012-finalAm 04 track1--salvatore orlando--openstack-apac-2012-final
Am 04 track1--salvatore orlando--openstack-apac-2012-finalOpenCity Community
 

Similar a Virtual Network Performance Challenge (20)

PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...
PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...
PLNOG 5: Piotr Szołkowski - Data Center i nie tylko...
 
OpenStack and OpenFlow Demos
OpenStack and OpenFlow DemosOpenStack and OpenFlow Demos
OpenStack and OpenFlow Demos
 
Link Virtualization based on Xen
Link Virtualization based on XenLink Virtualization based on Xen
Link Virtualization based on Xen
 
Networking is NOT Free: Lessons in Network Design
Networking is NOT Free: Lessons in Network DesignNetworking is NOT Free: Lessons in Network Design
Networking is NOT Free: Lessons in Network Design
 
An Implementation of Virtual Cluster on a Cloud
An Implementation of Virtual Cluster on a CloudAn Implementation of Virtual Cluster on a Cloud
An Implementation of Virtual Cluster on a Cloud
 
Windows Server 2012 Hyper-V Networking Evolved
Windows Server 2012 Hyper-V Networking Evolved Windows Server 2012 Hyper-V Networking Evolved
Windows Server 2012 Hyper-V Networking Evolved
 
Acceleration for big data, hadoop and memcached it168文库
Acceleration for big data, hadoop and memcached it168文库Acceleration for big data, hadoop and memcached it168文库
Acceleration for big data, hadoop and memcached it168文库
 
Acceleration for big data, hadoop and memcached it168文库
Acceleration for big data, hadoop and memcached it168文库Acceleration for big data, hadoop and memcached it168文库
Acceleration for big data, hadoop and memcached it168文库
 
Apache con 2011 gd
Apache con 2011 gdApache con 2011 gd
Apache con 2011 gd
 
V24 Product Brief - Aggregation & Filtering Taps
V24 Product Brief - Aggregation & Filtering TapsV24 Product Brief - Aggregation & Filtering Taps
V24 Product Brief - Aggregation & Filtering Taps
 
Cloudstack collab talk
Cloudstack collab talkCloudstack collab talk
Cloudstack collab talk
 
Making case up
Making case upMaking case up
Making case up
 
Understanding CleanAir Technology to improve Wlan Spectrum Management
Understanding CleanAir Technology to improve Wlan Spectrum Management Understanding CleanAir Technology to improve Wlan Spectrum Management
Understanding CleanAir Technology to improve Wlan Spectrum Management
 
Network policies
Network policiesNetwork policies
Network policies
 
Usenix lisa 2011
Usenix lisa 2011Usenix lisa 2011
Usenix lisa 2011
 
Hungary Usergroup - Midonet overlay programming
Hungary Usergroup - Midonet overlay programmingHungary Usergroup - Midonet overlay programming
Hungary Usergroup - Midonet overlay programming
 
EYWA Presentation v0.1.27
EYWA Presentation v0.1.27EYWA Presentation v0.1.27
EYWA Presentation v0.1.27
 
Software Defined Data Centers - June 2012
Software Defined Data Centers - June 2012Software Defined Data Centers - June 2012
Software Defined Data Centers - June 2012
 
Best Practices for Building Ultra-Low Latency Microwave Networks
Best Practices for Building Ultra-Low Latency Microwave NetworksBest Practices for Building Ultra-Low Latency Microwave Networks
Best Practices for Building Ultra-Low Latency Microwave Networks
 
Am 04 track1--salvatore orlando--openstack-apac-2012-final
Am 04 track1--salvatore orlando--openstack-apac-2012-finalAm 04 track1--salvatore orlando--openstack-apac-2012-final
Am 04 track1--salvatore orlando--openstack-apac-2012-final
 

Más de Stephen Hemminger

Más de Stephen Hemminger (11)

Performance challenges in software networking
Performance challenges in software networkingPerformance challenges in software networking
Performance challenges in software networking
 
Staging driver sins
Staging driver sinsStaging driver sins
Staging driver sins
 
Netem -emulating real networks in the lab
Netem -emulating real networks in the labNetem -emulating real networks in the lab
Netem -emulating real networks in the lab
 
Untold story
Untold storyUntold story
Untold story
 
Llnw bufferbloat
Llnw bufferbloatLlnw bufferbloat
Llnw bufferbloat
 
Dpdk performance
Dpdk performanceDpdk performance
Dpdk performance
 
Bufferbloat is alll Wet!
Bufferbloat is alll Wet!Bufferbloat is alll Wet!
Bufferbloat is alll Wet!
 
Taking the Fear Out of Contributing
Taking the Fear Out of ContributingTaking the Fear Out of Contributing
Taking the Fear Out of Contributing
 
Integrating Linux routing with FusionCLI™
Integrating Linux routing with FusionCLI™Integrating Linux routing with FusionCLI™
Integrating Linux routing with FusionCLI™
 
A Baker's dozen of TCP
A Baker's dozen of TCPA Baker's dozen of TCP
A Baker's dozen of TCP
 
Online tools
Online toolsOnline tools
Online tools
 

Último

Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionDilum Bandara
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embeddingZilliz
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningLars Bell
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
A Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersA Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersNicole Novielli
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxLoriGlavin3
 
What is Artificial Intelligence?????????
What is Artificial Intelligence?????????What is Artificial Intelligence?????????
What is Artificial Intelligence?????????blackmambaettijean
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxLoriGlavin3
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rick Flair
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxLoriGlavin3
 
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESSALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESmohitsingh558521
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfLoriGlavin3
 

Último (20)

Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An Introduction
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embedding
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine Tuning
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
A Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersA Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software Developers
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
 
What is Artificial Intelligence?????????
What is Artificial Intelligence?????????What is Artificial Intelligence?????????
What is Artificial Intelligence?????????
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...Rise of the Machines: Known As Drones...
Rise of the Machines: Known As Drones...
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
 
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESSALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdf
 

Virtual Network Performance Challenge

  • 1. Virtualized Networking Performance Stephen Hemminger Principal Engineer shemminger@vyatta.com
  • 2. Age nd a Wh at is a Virtu alize d N e twork P e rform ance b e nch m arks Tu ning tip s
  • 3. P h ys ical E nte rp ris e D atace nte r BORDER ROUTER FIREWALL VPN INTRUSION PREVENTION SWITCH 10.0.0.0/24 WEBSERVERS 10.3.0.0/24 APPS & STORAGE 10.4.0.0/24 DATABASE
  • 4. Virtu al N e twork Arch ite ctu re
  • 5. P e rform ance M ile s tone s 2005 2006 2007 2008 2009 2010 2011 1G line rate Multiqueue NIC 10G bamdwidth 1M packets / second Xen 3.0 KVM Hyper-V drivers
  • 6. Be nch m arks F orward ing R F C 2544 m inim u m p acke t Th rou gh p u t TC P b u lk trans fe r Late ncy R e q u e s t / R e s p ons e
  • 7. R ou te r Be nch m ark R F C 2544 Router Under Test Spirent
  • 8. Virtu alize d R ou te r Be nch m ark Router Under Guest Test Hypervisor Bridge Bridge Spirent
  • 9. Router Forwarding performance 1G bit/sec bidirectional 100% 80% Bare Metal Frames forwarded 60% Vmware ESX Xen 40% KVM 20% 0% 0 250 500 750 1000 1250 1500 Packet size
  • 10. E m u late d vs Virtu al N IC
  • 11. E m u late d N e twork Inte rface Fake PCI region Guest Hypervisor Packet Buffer
  • 12. Virtu al N IC Guest Hypervisor Netwo Shared rk Memory
  • 13. E m u late d vs Virtu al N IC 100 75 Throughput vs Bare Metal Emulated Tx 50 Virtual Tx Emulated Rx Virtual Rx 25 0 Hyper-V Vmware KVM
  • 14. VN IC ch aracte ris tics Hyper-V Vmware Xen KVM vmxnet3 netfront virtio-net MTU 1500 9000 65521 65535 Checksum Y Y Y offload Segmentation Y Y Y offload NAPI Y Y Y LRO Y VLAN Y Multiqueue Y ? ?
  • 15. O ffload not always a good id e a LR O ??
  • 17. VM to VM p e rform ance 2,000 Thorouhput (10^6 bits/sec) 0 100 1,000 10,000 100,000 MTU (bytes)
  • 18. M TU vs Brid ge
  • 19. Tip #3: Minimize overhead
  • 20. Virtu al S witch Typ e s 10000 To Hypervisor From Hypervisor Throughput (10^6 bits/sec) 7500 VM to VM 5000 2500 0 NAT Bridged Tap
  • 21. Tip #4: D on't C ros s th e S tre am s
  • 22. C ontrol flow ↔ C P U Creator:cairo 1.10.2 (http://cairographi CreationDate:Thu Oct 20 16:29:57 2011 LanguageLevel:2
  • 23. M u ltith re ad b e nch m ark 20,000 UP Guest SMP Guest Total Transactions/sec 15,000 10,000 5,000 0 Packet Steering (RPS) Baseline Multi Queue NIC
  • 24. M u ltip le Q u e u e H W or S W Guest VM Thread Device queue Flow Thread Device clas VNIC sfi queue er Thread Device queue
  • 25. Tip #5: H e lp ou t!
  • 26. X e n P e rform ance Im p rove m e nts 1G bidirectional frame loss 100% 2.6.31 2.6.35 2.6.37 75% Packets forwarded 50% 25% 0% 0 200 400 600 800 1000 1200 1400 1600 Packet size
  • 27. O ngoing work Im p rove d Trans m it wake u p C op y-le s s trans fe r M u ltiqu e u e VN IC F low s te e ring
  • 28. 5 Ways to Im p rove p e rform ance Virtu al (not e m u late d ) ne twork inte rface M axim ize p acke t s ize M inim ize p acke t ove rh e ad S tay on s am e C P U C ontrib u te to fu tu re d e ve lop m e nts

Notas del editor

  1. Linux network has evolved. Able to keep with 1G data rate in 2005. Multiqueue NIC allowed distributing work across cores. Now able to 10G bandwidth 1M packets / per second / per core Hypervisor's support
  2. Forwarding measures how packets per second Throughput measures bytes per second Latency measures round trip time
  3. Hardware tester sends back-to-back packets And measures how many arrive. Bi-directional. 1G = 1.4 Mpps * 2
  4. Same test but makes 2 round trips through hypervisor
  5. QA test of 100% load frame loss test On the same hardware, Intel(R) Xeon(R) CPU X5560 @ 2.80GHz 1MB L2 / 8MB L3 cache Clock speed: 2.80 GHz, Tuned IRQ alignment. Onboard NIC not multiqueue
  6. Emulated NIC Easy to install Works with other OS Compatible (mostly) Virtual NIC Requires driver Only works with Linux Hypervisor ↔ Guest must be compatiable
  7. An emulated NIC pretends to be E1000, 8139cp, … Guest PCI space faults into Hypervisor Packet data copied by Hypervisor
  8. Guest has queue of packets in shared memory. Can avoid memory copies.
  9. These are 3 different boxes, cpu memory, NIC, etc. Hyper-V: emulated NIC performance is awful Vmware: vmxnet is almost same as emulate Realtek KVM: reaches almost 100%
  10. Hyper-V has almost no offload Vmware has most features (on Enterprise version) VLAN is important
  11. Explain Vmware LRO bug. LRO aggregates packets which is good at final target; but violates end-to-end. Router VM would get terrible performance Kernel attempts to disable LRO if doing bridging or forwarding. Driver bug.
  12. The main cost of Virt net is hypervisor context switch For bulk transfer, better to do more work on each context switch
  13. VM to VM (on KVM) Log scale Iperf
  14. IEEE 802.1d The Maximum Service Data Unit Size supported by a Bridge between two LANs is the smaller of that supported by the LANs. No attempt is made by a Bridge to relay a frame to a LAN that does not support the size of Service Data Unit conveyed by that frame”. Linux has per route MTU
  15. Super light Lotus Firewalling, iptables, etc are expensive. Ipsec Connection tracking
  16. MacVtap is simpler, fastest Bridge by default does iptables, connection tracking
  17. When doing SMP
  18. Explain parallel packet processing throgh layers. Can be done manually. Scheduler tries to help. Multiqueue NIC can help (and hurt)
  19. Doing UP guest is faster now
  20. Current KVM VNIC is single queue (bottleneck)
  21. QA test notice significant improvements in Xen. Haven't been testing KVM but similar gains. Future work: -