Comparing IPv 6 and IPv 4 Performance John

  • Slides: 18
Download presentation
Comparing IPv 6 and IPv 4 Performance John Berg – Lead Engineer September 16,

Comparing IPv 6 and IPv 4 Performance John Berg – Lead Engineer September 16, 2014 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable.

Background • Cable. Labs has been conducting IPv 6 interops since 2009 – Observed

Background • Cable. Labs has been conducting IPv 6 interops since 2009 – Observed subtle but persistent IPv 6 performance benefit • Collected real performance data from one of our member operators • Conducted lab testing to measure IPv 4/IPv 6 performance – Native IPv 6 – IPv 4 with one layer of NAT – IPv 4 with two layers of NAT 2 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 2

How Service Provider Data Was Collected • Service Provider produced >1. 5 million IPv

How Service Provider Data Was Collected • Service Provider produced >1. 5 million IPv 4/IPv 6 data records – Analysis performed jointly by Cable. Labs and MSO • Metrics collected on data records: – Average Round Trip Time (AVGRTT) for a variety of popular IPv 4 and IPv 6 web sites – Statistics Include: Minimum, Maximum, Mean, Median, Standard Deviation, etc. • Measurement agents configured on backbone POPs in ten hubs – Randomized latency checks executed each hour – RTT interval = completion of TCP handshake between client and server TCP SYN + ACK TCP ACK 3 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 3

Where the Data Was Collected Seattle New York Chicago Washington, DC San Jose Charlotte

Where the Data Was Collected Seattle New York Chicago Washington, DC San Jose Charlotte Los Angeles Atlanta Dallas/Ft. Worth Houston 4 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 4

Is IPv 6 Really Faster? These visits to apple. com make it appear that

Is IPv 6 Really Faster? These visits to apple. com make it appear that is so…. . 5 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 5

Is IPv 6 Really Faster? RTT for wikipedia. org is still measurably faster for

Is IPv 6 Really Faster? RTT for wikipedia. org is still measurably faster for IPv 6 on average…. . 6 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 6

Is IPv 6 Really Faster? But on Facebook RTT for IPv 6 and IPv

Is IPv 6 Really Faster? But on Facebook RTT for IPv 6 and IPv 4 are nearly identical…. . 7 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 7

Is IPv 6 Really Faster? Again, nearly identical results for Netflix…. . 8 ©

Is IPv 6 Really Faster? Again, nearly identical results for Netflix…. . 8 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 8

Is IPv 6 Really Faster? And this time IPv 4 is significantly faster, by

Is IPv 6 Really Faster? And this time IPv 4 is significantly faster, by nearly 25 ms…. . 9 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 9

Is IPv 6 Really Faster? IPv 4 wins again. What are we to make

Is IPv 6 Really Faster? IPv 4 wins again. What are we to make of these results? 10 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 10

IPv 4 vs IPv 6 Aggregate View 11 © Cable Television Laboratories, Inc. 2014.

IPv 4 vs IPv 6 Aggregate View 11 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 11

Lab Testing 12 © Cable Television Laboratories, Inc. 2014. Do not share this material

Lab Testing 12 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 12

Lab Testing Methodology • Conducted matched IPv 4 -IPv 6 ping tests over the

Lab Testing Methodology • Conducted matched IPv 4 -IPv 6 ping tests over the course of an IPv 6 interop – First sets: 2 NATS enabled – Second sets: 1 NAT enabled • Identify effect of NAT without IPv 4 -IPv 6 path differences • Did NOT measure effects of traffic engineering or differentiated peering 13 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 13

Results – One Layer of NAT Common Home Network Scenario • Could NAT be

Results – One Layer of NAT Common Home Network Scenario • Could NAT be responsible for slower IPv 4 performance? • IPv 6 performed measurably better than IPv 4 – Lower mean, median, standard deviation, and minimum – Statistically significant differences 14 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 14

Results – Two Layers of NAT Possible CGN Effect • What happened? • One

Results – Two Layers of NAT Possible CGN Effect • What happened? • One NAT showed differences, two NATs show nearly identical results – 81% chance that the means are really the same* – IPv 4 in both cases still shows higher variability – IPv 6 performed better half the time across 6 test runs • Could NAT performance vary per device? *Based on Students t-test analysis 15 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 15

Interpreting The Results Data • How do we explain the disparity in test results?

Interpreting The Results Data • How do we explain the disparity in test results? – Analysis shows a subtle IPv 6 performance advantage – However, there are more questions than answers…. • Some possible explanations: – – Does NAT performance vary across some IPv 4 platforms? Is hop count a factor for IPv 4 vs. IPv 6? How do network effects, such as tunnels, traffic engineering and congestion factor in? What about Content Provider IPv 6 transition strategies? • Better tools and methodologies for gathering end-to-end performance metrics are needed • Bottom line – further research is needed 16 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 16

Cable. Labs Initiative • Cable. Labs is developing performance measurement tools and methodologies as

Cable. Labs Initiative • Cable. Labs is developing performance measurement tools and methodologies as part of our IP Performance Evaluation & Reporting (CLIPPER) project • Project will standardize testing methodologies for MSOs – Aligns with IETF IPPM & LMAP and BBF WT-143 working groups – Introduce common test platform – Gather data on jitter, delay, packet loss, throughput and DNS response time for both IPv 4 and IPv 6 – Better correlation of speed tests between home router and wireless devices • Recommendation: Systematic performance metric collection should consider differences between IPv 6 and IPv 4 17 © Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable. 17

© Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other

© Cable Television Laboratories, Inc. 2014. Do not share this material with anyone other than Cable. Labs Members, and vendors under Cable. Labs NDA if applicable.