SlideShare a Scribd company logo
1 of 34
NEUTRON HYBRID MODE
Vinay Bannai
SDN Architect, Nov 8 2013
ABOUT PAYPAL
PayPal offers flexible and innovative
payment solutions for consumers and
merchants of all sizes.

• 137 Million Active Users
• $300,000 Payments processed by PayPal
each minute
• 193 markets / 26 currencies
• PayPal is the World’s Most Widely Used
Digital Wallet

2

Confidential and Proprietary
INTRODUCTION
• Data Center Architecture
• Neutron Basics

• Overlays vs Physical Networks
• Use Cases
• Problem Definition
• Hybrid Solution
• Performance Data
• Analysis
• Q&A

3

Confidential and Proprietary
DATA CENTER ARCHITECTURE
Internet
Core

Data Center

Layer-3 router
Bisection BW

Aggregation

Layer-3 switch
Bisection BW

Access

Layer-3 switch
Bisection BW

Racks

4

Confidential and Proprietary
NEW DATACENTER ARCHITECTURE
Internet

Data Center

Layer-3 router

Core

Bisection BW

Aggregation

Layer-3 switch
Bisection BW

Layer-3 switch

Access

Bisection BW

Edge
Layer
VM

5

vswitches
VM

Confidential and Proprietary

VM

VM

VM

VM

VM

VM

VM

VM
DATACENTER WITH VSWITCHES
Data Center

Layer-3 switch

Access
VM

VM

VM

VM

VM

VM

VM

VM

VM

VM

VM

VM

VM

VM

VM

Racks
6

Confidential and Proprietary

Racks

Racks
NEUTRON BASICS

7

Confidential and Proprietary
OVERLAY NETWORKS
• Overlays provide connectivity between VMs and Network
Devices using tunnels
• The physical core network does not need to be re-provisioned
constantly
• The tunneling encap/decap is done at the edge in the virtual
switch
• Decouples the tenant network address from the physical Data
Center network address
• Easy to support overlapping address

• Tunneling techniques in vogue
− VXLAN
− STT
− NVGRE
8

Confidential and Proprietary
PHYSICAL NETWORKS
• Physical Networks connect VM’s and Network Devices using
provider network
• VM’s are first class citizens with the hypervisor and the
networking devices
• No tunneling protocols used
• Tenant separation is achieved by using VLANs or IP
subnetting
• Hard to achieve overlapping address spaces
• Underlying network needs to be provisioned with VLANs

9

Confidential and Proprietary
PHYSICAL VS OVERLAY
Tenant on
Physical
Network

VM

VM

VM

VM

VM

VM

VM

VM

VM

L2
L3

L2

L2

Network Virtualization Layer

VM

Tenant on
Overlay
Network
PROS & CONS
Function

Bridged VMs
(VLAN)

Tunneled
VM’s

Throughput

Best

Better

Worse

Latency

Best

Better

Worse

Flexibility

Worse

Better

Best

Overlapping IP
addresses

Worse

Worse

Best

Operational
Dependency

11

Hypervisor

Worse

Better

Best

Confidential and Proprietary
USE CASES
• Production Environment
− Production website across multiple data centers
− Low latency and high throughput
− Bridged Mode

• Mergers & Acquisitions Private Community Cloud
− Private Community Cloud
− Needs address isolation and overlapping
− Address isolation, Flexibility, low latency and high throughput
− Overlay Mode

• Development & QA Environment
− Production development, QA & Staging
− Flexibility, high throughput but can tolerate higher latency
− Bridged and Overlay Mode
12

Confidential and Proprietary
PROBLEM STATEMENT
• Support flexibility, low latency, high throughput and
overlapping address space all at the same time
• Support both bridged and overlay networks
• VM’s on a hypervisor should be able to choose networks
• Need a consistent deployment pattern
• Configurable by automation tools (puppet, chef, salt etc)

13

Confidential and Proprietary
TYPICAL VSWITCH
VM
Ta

VM
Tb

VM
Tc

 HYBRID VSWITCH

VLAN 200
Hypervisor

br-int

Bridged
Traffic
Overlay
Traffic
br-tun

br-bond

Bond Intf
Prod
Interface

Mgmt
Interface
14

Confidential and Proprietary

IP
Interface
CONFIGURATION OF HYBRID MODE
• Create the neutron networks
− Flat Network

− neutron net-create bridged-flat --provider:network_type=flat --provider:
physical_network=<Physnet>
− neutron subnet-create --allocation-pool start=10.x.x.100, end=10.x.x.200
bridged-flat --gateway 10.x.x.1 10.0.0.0/23 --name bridged-flat-subnet -enable_dhcp=False

− VLAN Network
− neutron net-create bridged-vlan --provider:network_type=vlan --provider:
physical_network=<Physnet> --provider:segmentation_id=<vlan-id>
− neutron subnet-create --allocation-pool start=10.x.x.100, end=10.x.x.200
bridged-vlan 10.x.x.1 10.0.0.0/23 --name bridged-vlan-subnet

15

Confidential and Proprietary
CONTD.
• Neutron networks (contd.)
− Overlay Network
− neutron net-create overylay-net
− neutron subnet-create --allocation-pool start=10.x.x.100, end=10.x.x.200
overlay-net --gateway 10.x.x.1 10.0.0.0/23 --name overlay-net-subnet

• On the compute node
− Configure the bond
− ovs-vsctl add-br br-bond0
− Configure the OVS
− ovs-vsctl br-set-external-id br-bond0 bridgeid br-bond0
− ovs-vsctl set Bridge br-bond0 fail-mode=standalone
− ovs-vsctl add-port br-bond0 eth0 eth1

16

Confidential and Proprietary
PERFORMANCE DATA
• To measure latency and throughput, we ran following tests
• Within a rack (L2 switching)
− Bare metal to Bare metal

− Bridged VM to Bridged VM
− Tunneled VM to Tunneled VM

• Across racks (L3 switching)
− Bare metal to Bare metal
− Bridged VM to Bridged VM
− tunneled VM to tunneled VM

• Across the Network Gateway
− Bare metal to Bare metal (outside the cloud)
− Bridged VM to Bare metal (outside the cloud)
17

− tunneled VM to Bare metal (outside the cloud)
Confidential and Proprietary
HYPERVISOR, VM AND OS DETAILS
• Compute Hypervisors
− 2 sockets, 16 cores/socket SandyBridge @ 2.6GHz (32 Hyper Threaded)

− 2 x 10G ports (Intel PCIe)
− RAM : 256GB
− Disk: 4 x 600GB in RAID-10
− RHEL 6.4 running OVS

• VM
− vCPUs: 2
− RAM: 8GB
− Disk: 20GB
− RHEL 6.4

18

Confidential and Proprietary
TEST SETUP

Half rack with
Two Fault Zones

X.X.X.X/23

19

L3 Gateways
For Overlays

Y.Y.Y.Y/23

Confidential and Proprietary

X.X.X.X/23

Y.Y.Y.Y/23

X.X.X.X/23

Y.Y.Y.Y/23
TESTING METHODOLOGY
• Tunneling VM uses STT (OVS)
• Bridged VM uses Flat Network (OVS)
• Used nttcp 1.47 for throughput
• Bi-directional TCP with varying buffer size
• Buffer size in bytes : [64,… 65536]
• MTU size : 1500 Bytes (on both bare metal and VM’s)
• Used ping for latency measurement (60 samples)

• Used python scripts and paramiko to run the tests
• Tests done with other traffic (Dev/QA)
− Around 470+ active VM’s
− Around 100 Hypervisors
− Multiple half racks
20

Confidential and Proprietary
TEST SETUP FOR SAME RACK

21

Confidential and Proprietary
WITHIN A RACK (L2 SWITCHING)
THROUGHPUT

22

Confidential and Proprietary
WITHIN A RACK (L2 SWITCHING)
PING LATENCY

23

Confidential and Proprietary
ANALYSIS
• Observations
• Results for buffer size < MTU size
− Tunneled VM’s tend to have best overall throughput

− Bridged VM’s tend to better than bare metal
− OVS and tunnel optimizations at play

• Results for buffer size > MTU size
− Tunneled VM’s and bare metal performance about the same
− Bridged VM’s bests both bare-metal and tunneled VMs (??)

• OVS and tunnel optimizations apply for buffer sizes smaller
than MTU
• OVS optimization apply for buffer sizes greater than MTU
• Tunneled and Bridged VM’s have a slightly higher latency
than bare metal
24

Confidential and Proprietary
TEST SETUP ACROSS RACKS

25

Confidential and Proprietary
ACROSS RACKS (L3 SWITCHING)
THROUGHPUT

26

Confidential and Proprietary
ACROSS R3ACKS (L SWITCHING)
PING LATENCY

27

Confidential and Proprietary
ANALYSIS
• No bridged VM’s in the tests (setup problem)
• Results for buffer size < MTU size
− tunneled VM’s tend to have best overall throughput
− OVS and tunnel optimizations at play

• Results for buffer size > MTU size
− tunneled VM’s and bare metal performance about the same

• OVS and tunnel optimizations apply for buffer sizes smaller
than MTU
• tunneled and Bridged VM’s have a slightly higher latency than
bare metal

28

Confidential and Proprietary
TEST SETUP ACROSS L3 GATEWAY

29

Confidential and Proprietary
ACROSS NETWORK GATEWAY
THROUGHPUT

30

Confidential and Proprietary
ACROSS NETWORK GATEWAY
PING LATENCY

31

Confidential and Proprietary
ANALYSIS
• tunneled VM’s tend to have similar if not better throughput as
bare metal or bridged VM
• tunneled VM’s have a slightly higher latency
• Bridged VM’s tend to have same overall throughput as the
hypervisor
• Bridged VM’s tend to have same latency as the hypervisor

• Latency from a tunneled VM across L3 gateway is higher than
Physical VMs due to extra hops, but need to re-run the tests

32

Confidential and Proprietary
CONCLUSION & FUTURE WORK
• Understand your network requirements
− Latency, bandwidth throughput, flexibility

• Overlay Vs Physical
• Hybrid Mode

• Performance Analysis
• Make your deployment patterns simple and repeatable
• Future work
− Additional performance tests
− VXLAN, NVGRE
− Varying MTU size
− Setup without background traffic

• Let me know if you are interested to collaborate
33

Confidential and Proprietary
THANK YOU
vbannai@paypal.com

More Related Content

What's hot

Reference design for v mware nsx
Reference design for v mware nsxReference design for v mware nsx
Reference design for v mware nsxsolarisyougood
 
Open Networking for Your OpenStack
Open Networking for Your OpenStackOpen Networking for Your OpenStack
Open Networking for Your OpenStackCumulus Networks
 
VMworld 2015: Closing the Loop: Towards a World of Software Defined Decision ...
VMworld 2015: Closing the Loop: Towards a World of Software Defined Decision ...VMworld 2015: Closing the Loop: Towards a World of Software Defined Decision ...
VMworld 2015: Closing the Loop: Towards a World of Software Defined Decision ...VMworld
 
VMworld 2015: VMware NSX Deep Dive
VMworld 2015: VMware NSX Deep DiveVMworld 2015: VMware NSX Deep Dive
VMworld 2015: VMware NSX Deep DiveVMworld
 
VMworld 2017 Core Storage
VMworld 2017 Core StorageVMworld 2017 Core Storage
VMworld 2017 Core StorageCormac Hogan
 
VDC by NETWORKERS HOME
VDC by NETWORKERS HOMEVDC by NETWORKERS HOME
VDC by NETWORKERS HOMEnetworkershome
 
Cumulus networks conversion guide
Cumulus networks conversion guideCumulus networks conversion guide
Cumulus networks conversion guideScott Suehle
 
Sysctr Track: The Capable & Scalable Cloud OS
Sysctr Track: The Capable & Scalable Cloud OSSysctr Track: The Capable & Scalable Cloud OS
Sysctr Track: The Capable & Scalable Cloud OSITProceed
 
2017 VMUG Storage Policy Based Management
2017 VMUG Storage Policy Based Management2017 VMUG Storage Policy Based Management
2017 VMUG Storage Policy Based ManagementCormac Hogan
 
vVMworld 2013: Deploying, Troubleshooting, and Monitoring VMware NSX Distribu...
vVMworld 2013: Deploying, Troubleshooting, and Monitoring VMware NSX Distribu...vVMworld 2013: Deploying, Troubleshooting, and Monitoring VMware NSX Distribu...
vVMworld 2013: Deploying, Troubleshooting, and Monitoring VMware NSX Distribu...VMworld
 
1 sysadmin vs 250 clusters de stockage
1 sysadmin vs 250 clusters de stockage1 sysadmin vs 250 clusters de stockage
1 sysadmin vs 250 clusters de stockageOVHcloud
 
PLNOG14: Konwergentność, Wydajność, Szybkość w Data Center - Kazimierz Jantas
PLNOG14: Konwergentność, Wydajność, Szybkość w Data Center - Kazimierz JantasPLNOG14: Konwergentność, Wydajność, Szybkość w Data Center - Kazimierz Jantas
PLNOG14: Konwergentność, Wydajność, Szybkość w Data Center - Kazimierz JantasPROIDEA
 
4. v sphere big data extensions hadoop
4. v sphere big data extensions   hadoop4. v sphere big data extensions   hadoop
4. v sphere big data extensions hadoopChiou-Nan Chen
 
Benefits of Multi-rail Cluster Architectures for GPU-based Nodes
Benefits of Multi-rail Cluster Architectures for GPU-based NodesBenefits of Multi-rail Cluster Architectures for GPU-based Nodes
Benefits of Multi-rail Cluster Architectures for GPU-based Nodesinside-BigData.com
 

What's hot (20)

Reference design for v mware nsx
Reference design for v mware nsxReference design for v mware nsx
Reference design for v mware nsx
 
Cumulus Linux 2.5.4
Cumulus Linux 2.5.4Cumulus Linux 2.5.4
Cumulus Linux 2.5.4
 
Open Networking for Your OpenStack
Open Networking for Your OpenStackOpen Networking for Your OpenStack
Open Networking for Your OpenStack
 
VMworld 2015: Closing the Loop: Towards a World of Software Defined Decision ...
VMworld 2015: Closing the Loop: Towards a World of Software Defined Decision ...VMworld 2015: Closing the Loop: Towards a World of Software Defined Decision ...
VMworld 2015: Closing the Loop: Towards a World of Software Defined Decision ...
 
VMworld 2015: VMware NSX Deep Dive
VMworld 2015: VMware NSX Deep DiveVMworld 2015: VMware NSX Deep Dive
VMworld 2015: VMware NSX Deep Dive
 
HP C7000 Cconfiguration Guide v.10
HP C7000 Cconfiguration Guide v.10HP C7000 Cconfiguration Guide v.10
HP C7000 Cconfiguration Guide v.10
 
VMworld 2017 Core Storage
VMworld 2017 Core StorageVMworld 2017 Core Storage
VMworld 2017 Core Storage
 
VDC by NETWORKERS HOME
VDC by NETWORKERS HOMEVDC by NETWORKERS HOME
VDC by NETWORKERS HOME
 
Cumulus networks conversion guide
Cumulus networks conversion guideCumulus networks conversion guide
Cumulus networks conversion guide
 
Sysctr Track: The Capable & Scalable Cloud OS
Sysctr Track: The Capable & Scalable Cloud OSSysctr Track: The Capable & Scalable Cloud OS
Sysctr Track: The Capable & Scalable Cloud OS
 
2017 VMUG Storage Policy Based Management
2017 VMUG Storage Policy Based Management2017 VMUG Storage Policy Based Management
2017 VMUG Storage Policy Based Management
 
vVMworld 2013: Deploying, Troubleshooting, and Monitoring VMware NSX Distribu...
vVMworld 2013: Deploying, Troubleshooting, and Monitoring VMware NSX Distribu...vVMworld 2013: Deploying, Troubleshooting, and Monitoring VMware NSX Distribu...
vVMworld 2013: Deploying, Troubleshooting, and Monitoring VMware NSX Distribu...
 
Campus
CampusCampus
Campus
 
Cumulus Linux 2.5.3
Cumulus Linux 2.5.3Cumulus Linux 2.5.3
Cumulus Linux 2.5.3
 
Решения NFV в контексте операторов связи
Решения NFV в контексте операторов связиРешения NFV в контексте операторов связи
Решения NFV в контексте операторов связи
 
1 sysadmin vs 250 clusters de stockage
1 sysadmin vs 250 clusters de stockage1 sysadmin vs 250 clusters de stockage
1 sysadmin vs 250 clusters de stockage
 
PLNOG14: Konwergentność, Wydajność, Szybkość w Data Center - Kazimierz Jantas
PLNOG14: Konwergentność, Wydajność, Szybkość w Data Center - Kazimierz JantasPLNOG14: Konwergentność, Wydajność, Szybkość w Data Center - Kazimierz Jantas
PLNOG14: Konwergentność, Wydajność, Szybkość w Data Center - Kazimierz Jantas
 
4. v sphere big data extensions hadoop
4. v sphere big data extensions   hadoop4. v sphere big data extensions   hadoop
4. v sphere big data extensions hadoop
 
Hp Virtual Connect
Hp Virtual ConnectHp Virtual Connect
Hp Virtual Connect
 
Benefits of Multi-rail Cluster Architectures for GPU-based Nodes
Benefits of Multi-rail Cluster Architectures for GPU-based NodesBenefits of Multi-rail Cluster Architectures for GPU-based Nodes
Benefits of Multi-rail Cluster Architectures for GPU-based Nodes
 

Similar to Neutron hybrid openstack hk

DevOops - Lessons Learned from an OpenStack Network Architect
DevOops - Lessons Learned from an OpenStack Network ArchitectDevOops - Lessons Learned from an OpenStack Network Architect
DevOops - Lessons Learned from an OpenStack Network ArchitectJames Denton
 
NSX: La Virtualizzazione di Rete e il Futuro della Sicurezza
NSX: La Virtualizzazione di Rete e il Futuro della SicurezzaNSX: La Virtualizzazione di Rete e il Futuro della Sicurezza
NSX: La Virtualizzazione di Rete e il Futuro della SicurezzaVMUG IT
 
Software Defined Networks (SDN) na przykładzie rozwiązania OpenContrail.
Software Defined Networks (SDN) na przykładzie rozwiązania OpenContrail.Software Defined Networks (SDN) na przykładzie rozwiązania OpenContrail.
Software Defined Networks (SDN) na przykładzie rozwiązania OpenContrail.Semihalf
 
VMworld 2015: Networking Virtual SAN's Backbone
VMworld 2015: Networking Virtual SAN's BackboneVMworld 2015: Networking Virtual SAN's Backbone
VMworld 2015: Networking Virtual SAN's BackboneVMworld
 
CC-4153, Verizon Cloud Compute and the SM15000, by Paul Curtis
CC-4153, Verizon Cloud Compute and the SM15000, by Paul CurtisCC-4153, Verizon Cloud Compute and the SM15000, by Paul Curtis
CC-4153, Verizon Cloud Compute and the SM15000, by Paul CurtisAMD Developer Central
 
Private cloud networking_cloudstack_days_austin
Private cloud networking_cloudstack_days_austinPrivate cloud networking_cloudstack_days_austin
Private cloud networking_cloudstack_days_austinChiradeep Vittal
 
Cumulus Linux 2.5 Overview
Cumulus Linux 2.5 OverviewCumulus Linux 2.5 Overview
Cumulus Linux 2.5 OverviewCumulus Networks
 
OpenStack and OpenContrail for FreeBSD platform by Michał Dubiel
OpenStack and OpenContrail for FreeBSD platform by Michał DubielOpenStack and OpenContrail for FreeBSD platform by Michał Dubiel
OpenStack and OpenContrail for FreeBSD platform by Michał Dubieleurobsdcon
 
Platforms for Accelerating the Software Defined and Virtual Infrastructure
Platforms for Accelerating the Software Defined and Virtual InfrastructurePlatforms for Accelerating the Software Defined and Virtual Infrastructure
Platforms for Accelerating the Software Defined and Virtual Infrastructure6WIND
 
NET8935_Small_DC_Shahzad_Ali
NET8935_Small_DC_Shahzad_AliNET8935_Small_DC_Shahzad_Ali
NET8935_Small_DC_Shahzad_Alishezy22
 
Cloud Networking is not Virtual Networking - London VMUG 20130425
Cloud Networking is not Virtual Networking - London VMUG 20130425Cloud Networking is not Virtual Networking - London VMUG 20130425
Cloud Networking is not Virtual Networking - London VMUG 20130425Greg Ferro
 
HP Blades Presentation
HP Blades PresentationHP Blades Presentation
HP Blades PresentationBhavin Vyas
 
[OpenStack Days Korea 2016] Track1 - Mellanox CloudX - Acceleration for Cloud...
[OpenStack Days Korea 2016] Track1 - Mellanox CloudX - Acceleration for Cloud...[OpenStack Days Korea 2016] Track1 - Mellanox CloudX - Acceleration for Cloud...
[OpenStack Days Korea 2016] Track1 - Mellanox CloudX - Acceleration for Cloud...OpenStack Korea Community
 
Red Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super StorageRed Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super StorageRed_Hat_Storage
 
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...Red_Hat_Storage
 
VMworld 2013: Virtualized Network Services Model with VMware NSX
VMworld 2013: Virtualized Network Services Model with VMware NSX VMworld 2013: Virtualized Network Services Model with VMware NSX
VMworld 2013: Virtualized Network Services Model with VMware NSX VMworld
 
Virt july-2013-meetup
Virt july-2013-meetupVirt july-2013-meetup
Virt july-2013-meetupnvirters
 

Similar to Neutron hybrid openstack hk (20)

DevOops - Lessons Learned from an OpenStack Network Architect
DevOops - Lessons Learned from an OpenStack Network ArchitectDevOops - Lessons Learned from an OpenStack Network Architect
DevOops - Lessons Learned from an OpenStack Network Architect
 
Neutron scaling
Neutron scalingNeutron scaling
Neutron scaling
 
NSX: La Virtualizzazione di Rete e il Futuro della Sicurezza
NSX: La Virtualizzazione di Rete e il Futuro della SicurezzaNSX: La Virtualizzazione di Rete e il Futuro della Sicurezza
NSX: La Virtualizzazione di Rete e il Futuro della Sicurezza
 
Software Defined Networks (SDN) na przykładzie rozwiązania OpenContrail.
Software Defined Networks (SDN) na przykładzie rozwiązania OpenContrail.Software Defined Networks (SDN) na przykładzie rozwiązania OpenContrail.
Software Defined Networks (SDN) na przykładzie rozwiązania OpenContrail.
 
10 sdn-vir-6up
10 sdn-vir-6up10 sdn-vir-6up
10 sdn-vir-6up
 
VMworld 2015: Networking Virtual SAN's Backbone
VMworld 2015: Networking Virtual SAN's BackboneVMworld 2015: Networking Virtual SAN's Backbone
VMworld 2015: Networking Virtual SAN's Backbone
 
CC-4153, Verizon Cloud Compute and the SM15000, by Paul Curtis
CC-4153, Verizon Cloud Compute and the SM15000, by Paul CurtisCC-4153, Verizon Cloud Compute and the SM15000, by Paul Curtis
CC-4153, Verizon Cloud Compute and the SM15000, by Paul Curtis
 
nested-kvm
nested-kvmnested-kvm
nested-kvm
 
Private cloud networking_cloudstack_days_austin
Private cloud networking_cloudstack_days_austinPrivate cloud networking_cloudstack_days_austin
Private cloud networking_cloudstack_days_austin
 
Cumulus Linux 2.5 Overview
Cumulus Linux 2.5 OverviewCumulus Linux 2.5 Overview
Cumulus Linux 2.5 Overview
 
OpenStack and OpenContrail for FreeBSD platform by Michał Dubiel
OpenStack and OpenContrail for FreeBSD platform by Michał DubielOpenStack and OpenContrail for FreeBSD platform by Michał Dubiel
OpenStack and OpenContrail for FreeBSD platform by Michał Dubiel
 
Platforms for Accelerating the Software Defined and Virtual Infrastructure
Platforms for Accelerating the Software Defined and Virtual InfrastructurePlatforms for Accelerating the Software Defined and Virtual Infrastructure
Platforms for Accelerating the Software Defined and Virtual Infrastructure
 
NET8935_Small_DC_Shahzad_Ali
NET8935_Small_DC_Shahzad_AliNET8935_Small_DC_Shahzad_Ali
NET8935_Small_DC_Shahzad_Ali
 
Cloud Networking is not Virtual Networking - London VMUG 20130425
Cloud Networking is not Virtual Networking - London VMUG 20130425Cloud Networking is not Virtual Networking - London VMUG 20130425
Cloud Networking is not Virtual Networking - London VMUG 20130425
 
HP Blades Presentation
HP Blades PresentationHP Blades Presentation
HP Blades Presentation
 
[OpenStack Days Korea 2016] Track1 - Mellanox CloudX - Acceleration for Cloud...
[OpenStack Days Korea 2016] Track1 - Mellanox CloudX - Acceleration for Cloud...[OpenStack Days Korea 2016] Track1 - Mellanox CloudX - Acceleration for Cloud...
[OpenStack Days Korea 2016] Track1 - Mellanox CloudX - Acceleration for Cloud...
 
Red Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super StorageRed Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super Storage
 
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
 
VMworld 2013: Virtualized Network Services Model with VMware NSX
VMworld 2013: Virtualized Network Services Model with VMware NSX VMworld 2013: Virtualized Network Services Model with VMware NSX
VMworld 2013: Virtualized Network Services Model with VMware NSX
 
Virt july-2013-meetup
Virt july-2013-meetupVirt july-2013-meetup
Virt july-2013-meetup
 

Recently uploaded

Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
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
 
Bluetooth Controlled Car with Arduino.pdf
Bluetooth Controlled Car with Arduino.pdfBluetooth Controlled Car with Arduino.pdf
Bluetooth Controlled Car with Arduino.pdfngoud9212
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Science&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfScience&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfjimielynbastida
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
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
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024The Digital Insurer
 

Recently uploaded (20)

Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
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)
 
Bluetooth Controlled Car with Arduino.pdf
Bluetooth Controlled Car with Arduino.pdfBluetooth Controlled Car with Arduino.pdf
Bluetooth Controlled Car with Arduino.pdf
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Science&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfScience&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdf
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
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
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024
 

Neutron hybrid openstack hk

  • 1. NEUTRON HYBRID MODE Vinay Bannai SDN Architect, Nov 8 2013
  • 2. ABOUT PAYPAL PayPal offers flexible and innovative payment solutions for consumers and merchants of all sizes. • 137 Million Active Users • $300,000 Payments processed by PayPal each minute • 193 markets / 26 currencies • PayPal is the World’s Most Widely Used Digital Wallet 2 Confidential and Proprietary
  • 3. INTRODUCTION • Data Center Architecture • Neutron Basics • Overlays vs Physical Networks • Use Cases • Problem Definition • Hybrid Solution • Performance Data • Analysis • Q&A 3 Confidential and Proprietary
  • 4. DATA CENTER ARCHITECTURE Internet Core Data Center Layer-3 router Bisection BW Aggregation Layer-3 switch Bisection BW Access Layer-3 switch Bisection BW Racks 4 Confidential and Proprietary
  • 5. NEW DATACENTER ARCHITECTURE Internet Data Center Layer-3 router Core Bisection BW Aggregation Layer-3 switch Bisection BW Layer-3 switch Access Bisection BW Edge Layer VM 5 vswitches VM Confidential and Proprietary VM VM VM VM VM VM VM VM
  • 6. DATACENTER WITH VSWITCHES Data Center Layer-3 switch Access VM VM VM VM VM VM VM VM VM VM VM VM VM VM VM Racks 6 Confidential and Proprietary Racks Racks
  • 8. OVERLAY NETWORKS • Overlays provide connectivity between VMs and Network Devices using tunnels • The physical core network does not need to be re-provisioned constantly • The tunneling encap/decap is done at the edge in the virtual switch • Decouples the tenant network address from the physical Data Center network address • Easy to support overlapping address • Tunneling techniques in vogue − VXLAN − STT − NVGRE 8 Confidential and Proprietary
  • 9. PHYSICAL NETWORKS • Physical Networks connect VM’s and Network Devices using provider network • VM’s are first class citizens with the hypervisor and the networking devices • No tunneling protocols used • Tenant separation is achieved by using VLANs or IP subnetting • Hard to achieve overlapping address spaces • Underlying network needs to be provisioned with VLANs 9 Confidential and Proprietary
  • 10. PHYSICAL VS OVERLAY Tenant on Physical Network VM VM VM VM VM VM VM VM VM L2 L3 L2 L2 Network Virtualization Layer VM Tenant on Overlay Network
  • 11. PROS & CONS Function Bridged VMs (VLAN) Tunneled VM’s Throughput Best Better Worse Latency Best Better Worse Flexibility Worse Better Best Overlapping IP addresses Worse Worse Best Operational Dependency 11 Hypervisor Worse Better Best Confidential and Proprietary
  • 12. USE CASES • Production Environment − Production website across multiple data centers − Low latency and high throughput − Bridged Mode • Mergers & Acquisitions Private Community Cloud − Private Community Cloud − Needs address isolation and overlapping − Address isolation, Flexibility, low latency and high throughput − Overlay Mode • Development & QA Environment − Production development, QA & Staging − Flexibility, high throughput but can tolerate higher latency − Bridged and Overlay Mode 12 Confidential and Proprietary
  • 13. PROBLEM STATEMENT • Support flexibility, low latency, high throughput and overlapping address space all at the same time • Support both bridged and overlay networks • VM’s on a hypervisor should be able to choose networks • Need a consistent deployment pattern • Configurable by automation tools (puppet, chef, salt etc) 13 Confidential and Proprietary
  • 14. TYPICAL VSWITCH VM Ta VM Tb VM Tc  HYBRID VSWITCH VLAN 200 Hypervisor br-int Bridged Traffic Overlay Traffic br-tun br-bond Bond Intf Prod Interface Mgmt Interface 14 Confidential and Proprietary IP Interface
  • 15. CONFIGURATION OF HYBRID MODE • Create the neutron networks − Flat Network − neutron net-create bridged-flat --provider:network_type=flat --provider: physical_network=<Physnet> − neutron subnet-create --allocation-pool start=10.x.x.100, end=10.x.x.200 bridged-flat --gateway 10.x.x.1 10.0.0.0/23 --name bridged-flat-subnet -enable_dhcp=False − VLAN Network − neutron net-create bridged-vlan --provider:network_type=vlan --provider: physical_network=<Physnet> --provider:segmentation_id=<vlan-id> − neutron subnet-create --allocation-pool start=10.x.x.100, end=10.x.x.200 bridged-vlan 10.x.x.1 10.0.0.0/23 --name bridged-vlan-subnet 15 Confidential and Proprietary
  • 16. CONTD. • Neutron networks (contd.) − Overlay Network − neutron net-create overylay-net − neutron subnet-create --allocation-pool start=10.x.x.100, end=10.x.x.200 overlay-net --gateway 10.x.x.1 10.0.0.0/23 --name overlay-net-subnet • On the compute node − Configure the bond − ovs-vsctl add-br br-bond0 − Configure the OVS − ovs-vsctl br-set-external-id br-bond0 bridgeid br-bond0 − ovs-vsctl set Bridge br-bond0 fail-mode=standalone − ovs-vsctl add-port br-bond0 eth0 eth1 16 Confidential and Proprietary
  • 17. PERFORMANCE DATA • To measure latency and throughput, we ran following tests • Within a rack (L2 switching) − Bare metal to Bare metal − Bridged VM to Bridged VM − Tunneled VM to Tunneled VM • Across racks (L3 switching) − Bare metal to Bare metal − Bridged VM to Bridged VM − tunneled VM to tunneled VM • Across the Network Gateway − Bare metal to Bare metal (outside the cloud) − Bridged VM to Bare metal (outside the cloud) 17 − tunneled VM to Bare metal (outside the cloud) Confidential and Proprietary
  • 18. HYPERVISOR, VM AND OS DETAILS • Compute Hypervisors − 2 sockets, 16 cores/socket SandyBridge @ 2.6GHz (32 Hyper Threaded) − 2 x 10G ports (Intel PCIe) − RAM : 256GB − Disk: 4 x 600GB in RAID-10 − RHEL 6.4 running OVS • VM − vCPUs: 2 − RAM: 8GB − Disk: 20GB − RHEL 6.4 18 Confidential and Proprietary
  • 19. TEST SETUP Half rack with Two Fault Zones X.X.X.X/23 19 L3 Gateways For Overlays Y.Y.Y.Y/23 Confidential and Proprietary X.X.X.X/23 Y.Y.Y.Y/23 X.X.X.X/23 Y.Y.Y.Y/23
  • 20. TESTING METHODOLOGY • Tunneling VM uses STT (OVS) • Bridged VM uses Flat Network (OVS) • Used nttcp 1.47 for throughput • Bi-directional TCP with varying buffer size • Buffer size in bytes : [64,… 65536] • MTU size : 1500 Bytes (on both bare metal and VM’s) • Used ping for latency measurement (60 samples) • Used python scripts and paramiko to run the tests • Tests done with other traffic (Dev/QA) − Around 470+ active VM’s − Around 100 Hypervisors − Multiple half racks 20 Confidential and Proprietary
  • 21. TEST SETUP FOR SAME RACK 21 Confidential and Proprietary
  • 22. WITHIN A RACK (L2 SWITCHING) THROUGHPUT 22 Confidential and Proprietary
  • 23. WITHIN A RACK (L2 SWITCHING) PING LATENCY 23 Confidential and Proprietary
  • 24. ANALYSIS • Observations • Results for buffer size < MTU size − Tunneled VM’s tend to have best overall throughput − Bridged VM’s tend to better than bare metal − OVS and tunnel optimizations at play • Results for buffer size > MTU size − Tunneled VM’s and bare metal performance about the same − Bridged VM’s bests both bare-metal and tunneled VMs (??) • OVS and tunnel optimizations apply for buffer sizes smaller than MTU • OVS optimization apply for buffer sizes greater than MTU • Tunneled and Bridged VM’s have a slightly higher latency than bare metal 24 Confidential and Proprietary
  • 25. TEST SETUP ACROSS RACKS 25 Confidential and Proprietary
  • 26. ACROSS RACKS (L3 SWITCHING) THROUGHPUT 26 Confidential and Proprietary
  • 27. ACROSS R3ACKS (L SWITCHING) PING LATENCY 27 Confidential and Proprietary
  • 28. ANALYSIS • No bridged VM’s in the tests (setup problem) • Results for buffer size < MTU size − tunneled VM’s tend to have best overall throughput − OVS and tunnel optimizations at play • Results for buffer size > MTU size − tunneled VM’s and bare metal performance about the same • OVS and tunnel optimizations apply for buffer sizes smaller than MTU • tunneled and Bridged VM’s have a slightly higher latency than bare metal 28 Confidential and Proprietary
  • 29. TEST SETUP ACROSS L3 GATEWAY 29 Confidential and Proprietary
  • 31. ACROSS NETWORK GATEWAY PING LATENCY 31 Confidential and Proprietary
  • 32. ANALYSIS • tunneled VM’s tend to have similar if not better throughput as bare metal or bridged VM • tunneled VM’s have a slightly higher latency • Bridged VM’s tend to have same overall throughput as the hypervisor • Bridged VM’s tend to have same latency as the hypervisor • Latency from a tunneled VM across L3 gateway is higher than Physical VMs due to extra hops, but need to re-run the tests 32 Confidential and Proprietary
  • 33. CONCLUSION & FUTURE WORK • Understand your network requirements − Latency, bandwidth throughput, flexibility • Overlay Vs Physical • Hybrid Mode • Performance Analysis • Make your deployment patterns simple and repeatable • Future work − Additional performance tests − VXLAN, NVGRE − Varying MTU size − Setup without background traffic • Let me know if you are interested to collaborate 33 Confidential and Proprietary

Editor's Notes

  1. Paypal is a Payments companyBetter for merchantsEasier for youCan be considered your digital walletWe’re not just on the internet, but we are also in store in places like Home Depot and GNCScale is importantShopping habits importantPaypal scales to meet needs worldwide and can be deployed in-country depending on local laws.