OpenStack - based NFV Cloud at Swisscom Challenges and Experiences - - PowerPoint PPT Presentation

▶
openstack based nfv cloud at swisscom
SMART_READER_LITE
LIVE PREVIEW

OpenStack - based NFV Cloud at Swisscom Challenges and Experiences - - PowerPoint PPT Presentation

Nov 17, 2023 179 likes •461 views

OpenStack - based NFV Cloud at Swisscom Challenges and Experiences Agenda Swisscom IPTV A story of Innovation and Success E2E Signal Chain Ranga Rajagopalan E2E Service Orchestration Vision AVI Networks Inc. CTO Lessons

slide-1
SLIDE 1

OpenStack - based NFV Cloud at Swisscom

Challenges and Experiences

slide-2
SLIDE 2

Agenda

– Swisscom IPTV

– A story of Innovation and Success – E2E Signal Chain – E2E Service Orchestration Vision – Lessons Learned

– Swisscom-HPE virtual headend project

– Legacy vs virtual headend – Maturity levels of applications – Enterprise Cloud vs. Media processing platform – Virtual Network performance and Container Networking – Multicast on OpenStack

– AVI Networks: Elastic Application Services

– A distributed architecture – Application Services – Elastic scale – Demo

Marco Loetscher

Hewlett Packard Enterprise Solution Architect marco.loetscher@hpe.com

Ranga Rajagopalan

AVI Networks Inc. CTO rangar@avinetworks.com

Mihajlo Zivkovic

Swisscom (Schweiz) AG Product Owner mihajlo.zivkovic@swisscom.com

slide-3
SLIDE 3

3

Swisscom TV & Entertainment

slide-4
SLIDE 4

2008 2010 2009 2011 2012 2013 2014 2015

1.5 Mio. Customers 2 Mio. STB’s in the field

2007 2006

3.4 Mio. Households 8 Mio. Population

  • 2Mio. on Swisscom DSL

2016 2017

Swisscom is a Marketleader since December 2015

4

slide-5
SLIDE 5

Swisscom TV Some Facts and Figures

..more then 2 Mio STB’s > 650 Channels (SD, HD, UHD)

..more then 1.5 Mio Customer

25 Pbyte Storage / Year

> 2.8 Tbit/s Unicast Streaming peak from Datacenter

>90 Pbyte of Storage

> 750K unique user per month

  • n Web & Mobile

Customer Satisfaction > 8

5

slide-6
SLIDE 6

6

The Journey of Swisscom TV

It’s a Story of Innovation and Success 2012

  • 16. January

Launch Replay TV

2014

Decembar Launch Teleclub Play (Subscription VOD)

2014

April Launch TV 2.0

2015

Decembar Marketleader Switzerland

2016

April Voice Search with Swiss Dialects UHD

2006

  • 1. November

Launch Bluewin TV

2009

  • 25. February

Start HD-Sender Launch TV1.0

2010

  • 23. March

Swisscom TV Air

2011

  • 30. June

Marketleader Digital TV

2013

  • 28. Decembar

1 Million Customers

2015

April HBB TV

2017

November Mediaroom Phase-out Entertainment 0S3

slide-7
SLIDE 7

Next Generation Entertainment & TV Services

Swisscom TV E2E Signal Chain

7

slide-8
SLIDE 8

Next Generation Entertainment & TV Services

TV Platform Virtualization

1st step virtualization 2nd step virtualization 3rd step virtualization 8

slide-9
SLIDE 9

MediaCloud 9

MediaCloud: The Big Picture

Goal to have all Entertainment Service on the MediaCloud

Virtualization Layer / RedHat OpenStack / KVM CPU Hardware Virtual Network Memory Hardware Storage Hardware Network Hardware Virtual CPU Virtual Memory Virtual Storage

vHE Service Orchestration Radio AVI AppBE nPVR LiveTV

LivingDocs

xyz

VNF Mgr VNF Mgr VNF Mgr VNF Mgr VNF Mgr VNF Mgr VNF Mgr VNF Mgr

Channel/Service Definition Bussiness process workflow Monitoring and Service Monitoring

slide-10
SLIDE 10

Media Cloud - Virtual HeadEnd

Lessons learned

Organizational challenges: – Vendor management (working mode with Vendors). – Mindset of the project staff. – Transforming engineers into the new "cloud" world. – Operation of two environments (legacy and cloud). – Knowledge and the experience (combined application with infrastructure and network) – Organization and processes . Technological challenges: – Working on the bleeding edge of the technology. – Technology unknowns. – Infrastructure : very large high performance media cloud solution. – Zero packet loss in cloud environment with the multicast.

10

slide-11
SLIDE 11

11

Media Function Virtualization

slide-12
SLIDE 12

Current headend operations challenges

Video Signal Dedicated Management Transcoders A Manager Transcoders B Manager Transcoders C Manager Multiplexer X Multiplexers Y Manager Multiplexers Z Manager Transcoder A Transcoder A Transcoder A Transcoder B Transcoder B Transcoder C

  • Ch. 1
  • Ch. 2
  • Ch. 3
  • Ch. 4
  • Ch. 5
  • Ch. N

Multiplexer Y Multiplexer Z Multiplexer X Transcoder A Transcoder A Transcoder A Transcoder B Transcoder B Transcoder C

  • Ch. 1’
  • Ch. 2’
  • Ch. 3’
  • Ch. 4’
  • Ch. 5’
  • Ch. N’

Multiplexer Y Multiplexer Z Multiplexers X Manager

Backup headend Active headend Too many managers to manage Disaster Recovery expensive Costly Equipment Upgrades/Exchanges Operational complexity Missing Flexibility to add new channels

Current situation

Switch

STB

CDN

12

slide-13
SLIDE 13

Virtualized headend with HPE VHM

1 click channel deployment

One interface to manage it all

HPE Virtual Headend Manager Multiplexer X Transcoder A Transcoder A Transcoder A Transcoder A

  • Ch. 1
  • Ch. 2
  • Ch. 3

Multiplexer X

Virtualized Headend

Transcoder B Transcoder B

  • Ch. 4
  • Ch. 5

Multiplexer Y Transcoder B Multiplexer Y Transcoder C

  • Ch. N

Multiplexer Z

Backup Backup

Transcoder D Multiplexer W

Channels

  • n the fly

Switch

STB

CDN

Fast time to launch new service One click channel deployment Non-proprietary infrastructure Quick and automated lifecycles Simplicity: One interface for all CAPEX and OPEX reduction

Video Signal

13

slide-14
SLIDE 14

Virtual Headend

NFV Orchestrator EMS1 VNF1 EMS3 VNF3 EMS2 VNF2 VNF Manager(s)

NFV MANO

Virtualized Infrastructure Manager(s)

NFVI

Computing Hardware Network Hardware Storage Hardware

Hardware Resources

Virtualization Layer OSS/BSS Virtual Computing Virtual Storage Virtual Network

Service, VNF and Infrastructure Description

NS and VNF Catalogs

Standard Infrastructure

Virtualization Layer (HyperV, KVM, ESX) Transcoder Muxer Probe Service Orchestration VNFM Infrastructure Orchestration

ETSI Reference Architecture

14

slide-15
SLIDE 15

Maturity Levels of virtualized applications

Monolithic functions are decomposed into micro-services

Functions separated from underlying hardware Functions deployed on hypervisor-driven, virtualized infrastructure resources Operated as part of the cloud, lifecycle fully

  • rchestratable

Decoupled Virtualized Cloudified Decomposed Market View R&D View Bare Metal x86 Microservices Automate / Orchestrate Virtualize

15

slide-16
SLIDE 16

Enterprise cloud vs. virtual Headend workloads

  • 1. CPU, RAM or Storage bound performance
  • 2. Aggregated view of resources

(CPU, Memory, resources overcommitted)

  • 3. Endpoints

(Applications need the OS)

  • 4. Many and small virtual machines
  • 1. CPU & I/O bound performance

(DPDK, SR-IOV, etc.)

  • 2. Enhanced platform awareness

(Internal Architecture relevant for guests)

  • 3. Middlepoints

(Data-plane network bypass the OS)

  • 4. Fewer and larger VMs

IT Cloud Virtual Headend 16

slide-17
SLIDE 17

Key network performance and quality features

PCI-passtrhough

✓https://docs.openstack.org/admin-guide/compute-pci-passthrough.html

SR-IOV (Single Root I/O Virtualization)

✓http://en.wikipedia.org/wiki/X86_virtualization#PCI-SIG_Single_Root_I.2FO_Virtualization_.28SR-IOV.29 ✓https://wiki.openstack.org/wiki/SR-IOV-Passthrough-For-Networking

NUMA (Non Uniform Memory Access)

✓http://en.wikipedia.org/wiki/Non-uniform_memory_access

DPDK (Data Plane Development Kit)

✓http://en.wikipedia.org/wiki/Data_Plane_Development_Kit

17

slide-18
SLIDE 18

Containers in VMs vs. Baremetal

  • The transcoding applications from Ateme and

Harmonic are provided in Docker containers

  • We decided to put the containers into a virtual machine
  • Why?
  • Docker Networking
  • Hardware independence
  • VM as “bridge” between application and physical

environment

  • Management and Monitoring
  • Virtualization Overhead: 5-10 %
  • Additional Component (Guest OS) to be managed
  • Cost of Hypervisor

Physical Server Physical Server Operating System Operating System Docker Engine

App 1

Hypervisor

App 1 App 1 App 1 App 1 App 1 18

slide-19
SLIDE 19

Docker Networking

–net=bridge:

  • Container is connected with the Network Bridge
  • Same IP addresses per Host, 1 NIC only
  • Standard Mode

–net=none:

  • No network connection of the container (i.e. for number

crunchers, batch jobs, etc.) –net=container:<CONTAINER | ID>:

  • Container is using the NW connection of a “neighbor”
  • Allow reachability of multiple segregated processes that

under the same IP –net=host:

  • Container has direct access to physical NICs of the hos

19

slide-20
SLIDE 20

Multicast in OpenStack

  • No multicast available out-of-the-box
  • Virtual layer-2 switches support IGMP snooping:

– Open vSwitch 2.5 supports IGMP snooping – Open vSwitch 2.7 contains bugfixes to enable multicast with multiple provider VLANs –http://openvswitch.org/features/ –https://github.com/openvswitch/ovs/blob/master/FAQ.md – Linux Bridge 2.4 supports IGMP snopping –http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge#Snooping

20

slide-21
SLIDE 21

Multicast in OpenStack – recommendations

  • Neutron provider network:
  • Don’t use Neutron-L3-Agent
  • Neutron does not route any multicast traffic
  • Use Neutron provider network
  • Use routable public VLAN configured on top-of-rack switches
  • Use router outside OpenStack
  • Use gateway outside OpenStack
  • Attach Nova instances directly to provider network
  • Configure multicast routing / PIM on the physical router

21

slide-22
SLIDE 22

22

AVI Networks

slide-23
SLIDE 23

Monolithic Appliances to Modern Distributed Architecture

23 CONTROL DATA

Separate Control & Data Plane

Manage as one, not many devices

APPLICATIONS

Controller Monolithic Appliance Software Management Plane: UI/CLI Data Plane: LB Service Engines

slide-24
SLIDE 24

Avi Platform – Modern Distributed Architecture

24 CONTROL DATA

Universal Solution

Both traditional and modern use cases Service Engines Controller Public Cloud Bare Metal Virtualized Containers On Premises

Separate Control & Data Plane

Manage as one, not many devices

Visibility

Actionable insights key to automation 10x Performance

  • 4 Tbps
  • 12M SSL TPS

Elasticity

On-demand scalability up / down

REST API

Automation

Highly programmable, Plug-n- Play

slide-25
SLIDE 25

25

Application Services Out-of-Box Automation

CONTAINERS SDN OPENSTACK AUTOMATION ON-PREM or OFF

Load Balancing

L7 (HTTP) LB L4 (TCP/UDP) LB Global Load Balancing Content Switching Caching/Compression Auto-Scaling

WAF & Security

Web app firewall (WAF) SSL Termination DDoS Protection L3-4 ACLs L7 Rules/Policies Micro-Segmentation

Analytics

Application map Service Health Score Network performance App Performance Request Logging Security Insights

MESOS

Bare Metal

Platform

Central Management 100% REST API / SDK Self-Service Multi-Tenancy Service Discovery IPAM/DNS

Comprehensive Services – For All Major Environments

slide-26
SLIDE 26

26

Record Performance – On Commodity Servers

Single Fabric – Central Management and Monitoring

  • 32 cores
  • 80,000 SSL TPS

Performance scales with cores (Moore’s Law)

  • 2 core
  • 5,000 SSL TPS

Avi Fabric Performance

  • 4 Tbps
  • 12M SSL TPS
  • 2x 1-core SEs
  • 5,000 SSL TPS

Fabric performance scales with Engines Centralized API, Mgmt, Monitoring

ECC- 48K, RSA 80K

  • 1 core
  • 2,500 SSL TPS

VIPRION 4800, ~1M TPS

slide-27
SLIDE 27

27

We are happy to answer questions