1. Enabling Ultra Low Latency Applications Over Ethernet
Grant Kirkwood
Chief Technology Officer
Mzima Networks

2. Services are fast becoming packet-based
Residential
Digital broadcast
IPTV, VoIP
Internet video
gaming
Circuit-switched voice
and
broadcast video
Enterprise
Ethernet Services
Virtual circuits
IP PBX
VoIP
Dedicated connections
T1/T3, FR, ATM
Digital PBX
Wireless
Data optimized
Video enabled
3G/4G/WiMax
Voice optimized
2G network

3. Services are stream-based, not packet-based
Digital broadcast
IPTV, VoIP
Internet video
gaming
Ethernet Services
Virtual circuits
IP PBX
VoIP
Data optimized
Video enabled
3G/4G/WiMax

4. Services are stream-based, not packet-based
Voice, video and other services – streams of data
Internet Protocol (IP) relies on small packets, not streams of data
Digital broadcast
IPTV, VoIP
Internet video
gaming
Ethernet Services
Virtual circuits
IP PBX
VoIP
Data optimized
Video enabled
3G/4G/WiMax

5. IP Networks designed to carry “best effort” traffic
, web browsing,
“instant” messaging…. Applications are not time-sensitive.
Networks designed to carry
packet-based data are now being asked to carry streaming data

6. Perceived value has shifted from service provider to application provider
Enterprise
Consumer
Penetration of Ethernet, fiber, collaboration, and interactive video
Increased workforce mobility requiring seamless access
Maturing virtualization, cloud-based applications & telepresence
Maturity of multiservice offerings
Increased mobile data penetration and improved ease of use
Growing adoption of online video and Web 2.0 applications

7. New applications created daily
Applications become more and more sensitive to network conditions
QoS policies are being created to support these technologies
An increasing number of QoS policies are creating challenges for service providers

8. Service provider realities
Traffic keeps growing …
66 Tbps
2007
134 Tbps
2011
Consumer
Enterprise
56 Tbps
101 Tbps
33 Tbps *
* Source: McKinsey & Company
10 Tbps
But revenue growth is slowing
2004
2006
2008
2010
10%
20%
30%
41% 3% 7%
13%
-5%
-3%
-1% 4%
Broadband
Wireless
Wireline **
** Sources: Yankee Group and Pyramid Research

9. real-time services with
How do we deliver
real-time services with
carrier-grade QoS?

10. QoS Model

11. Ethernet Performance Metrics
Packet Loss
Latency
Jitter

12. Ethernet Performance Metrics
Jitter
Packet Loss
Latency

13. Ethernet Performance Metrics
Jitter
Packet Loss
Latency

14. Ethernet Performance Metrics
Different applications are sensitive to
different performance metrics

15. Class/Quality of Service
QoS/CoS

16. QoS Model

17. Methods to separate traffic into different “buckets” or QoS policies
QoS Model
Methods to separate traffic into different “buckets” or QoS policies

18. “FIFO” is not intelligent ordering Order by priority
QoS Model
“FIFO” is not intelligent ordering Order by priority

19. Drop packets for applications not sensitive to packet loss
QoS Model
Non-stream services
Drop packets for applications not sensitive to packet loss

20. QoS Model Size throughput to availability
Limit/buffer traffic that won’t be impacted by policing

21. QoS Model

22. QoS Model

23. Policing vs Classifying
Bandwidth policing is “dumb”
Metering drops packets without discretion
Congestion causes buffering (on routers)
Buffering causes latency
Each application sensitive to specific metrics
Key is accurate classification

24. End to end QoS Schedule Transmit VoIP Gold Silver Best Effort
Classification/Policing
Schedule
Transmit
VoIP
Gold
Gold
VoIP
Silver
Silver
Gold
VoIP
Silver
Best Effort

25. End to end QoS
End-to-end QoS requires a technology that exists end-to-end
Difficult to achieve in multi-vendor, multi-carrier or multi-technology networks
New technologies are being developed to address this limitation

26. Mzima Case Study Problem: provide true Carrier Ethernet
Differentiate product from other carriers
Provide End-to-End QoS
Carry carrier-grade Services
Application-level granularity of QoS profiles
Meet requirements of true Carrier Ethernet

27. Mzima Case Study

28. Mzima Case Study VLAN bridging or tunneling Layer 2 MPLS Layer 3 MPLS
PBB-TE

29. PBB-TE Provider Backbone Bridge – Traffic Engineering End-to-End QoS
Stringent performance metrics
First Carrier Ethernet protocol not integrated into a layer 3 protocol (MPLS)

30. Y.1731 Performance Management
PBB-TE Tunnel Performance Management
Y.1731 Performance Management
PRIMARY
PBB-TE
BCBs
PBB-TE
BEB
PBB-TE
BEB
BACKUP
PBB-TE with Y.1731 Performance Management
Performance Management between Tunnel Endpoints
Provides Service Independent Tunnel Monitoring
Enhanced Scalability as 1,000’s of services may traverse the tunnel without the need to monitor every service
Leverages 802.1ag frames for reduced overhead
Multiple packets sent at 100ms interval to perform the test
Frame Delay / Frame Delay Variation / Loss Measurement
2-way Delay Roundtrip Measurement
1-way Delay Measurement (requires common time base)
Single Ended Frame-Loss (MEP to MEP)

31. Management Plane: Y.1731
Round trip delay/jitter and single ended frame loss (MEP to MEP)
Non-Service Affecting
Utilizes IEEE 802.1ag format frames for test packets
Unicast messages to a specific MEP
Multiple packets sent at 100ms interval to perform the test
Delay, Jitter, and Frame Loss measurements
Test results remain until the next test is run or until reboot of switch
MIPs do not participate in delay/jitter/frame loss measurements
MEP 12
MIP
802.1ag CCMs
MEP 10
MEP 11
MIP
MIP

32. Thank You