Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
So that
was
HTTP/2,
what's
next?
February 4 2017
Questions?
I’ll hang aroundI’ll hang around
outside theoutside the
room afterwardroom afterward
Daniel Stenberg
@bagder
Request and payload growth
in the last 5 years...
8080
100100
800K800K
2.5M2.5M
the average website loads 50+ resources on...
Head of line blockingHead of line blocking
Multiplexed (1/2)
Multiple streams over a single physical connection
Max number of parallel streams set by peer
Multiplexed (2/2)
Better utilization of bandwidth
So that was HTTP/2
February 4, 2017
Adoption,
usage, support
servers
browsers
Browser stats – Feb 2017
HTTP/2:
Share of HTTPS:
30%30%
60%60%
Internetz – February 2017
12% of top 10 million
23% of top 10,000
26% of top 1000
>50% for your site
Winners and
losers
So that was HTTP/2
February 4, 2017
Did HTTP/2 meet its promises
The remote corners of Internet
Percentile Desktop Mobile
5 1 11
25 20 44
50 79 94
75 194 184
95 800 913
Milliseconds RTT
Queuing time h1 vs h2
(Time waiting internally to send off a HTTP request)
Percentile HTTP 1 HTTP 2
80 100 ms 2 ms
95 2000...
0% packet loss
Image and data by Hooman Beheshti, Fastly
2% packet loss
Image and data by Hooman Beheshti, Fastly
Packet loss, hey?
Single connection vs 6
Head of line blocking
A single dropped packet
blocks everything
Packet loss, hey?
TLS TLS TLS
HTTP/2
frame
HTTP/2
frame
HTTP/2
frame
HTTP/2
frame
HTTP/2
frame
IP IP IP IP IP IP
TCP TCP T...
Packet loss, hey?
IP
HTTP/2
frame
HTTP/2
frame
HTTP/2
frame
HTTP/2
frame
HTTP/2
frame
TCP TCP TCP TCP
TLS TLS TLS
IP IP IP...
Fixing TCP head of blocking
A non-blocking TCP + TLS + HTTP/2
Needs independent packets
… that still are stream aware
Needs new retransmissions/ACKs
N...
QUIC
“TCP”, TLS and HTTP/2 over UDP
no TCP head of line blocking
other congestion control
move across interfaces
“TCP impr...
Packet loss, hey?
IP
UDP UDP UDP UDP UDP UDP
quic quic quic quic quic quic
TLS TLS TLS TLS TLS TLS
h2 h2 h2 h2 h2 h2
IP IP...
The IETF QUIC wg
Just started
Massive interest
s/custom crypto/TLS 1.3
Will transfer more than HTTP/2 frames
First interim...
Neither 3 nor 2
Perhaps “HTTP/3”, but not in name
Perhaps “TCP/2”, but not in name
Just QUIC
Round-up
HTTP/1 is not optimal
HTTP/2 is binary and multipled
HTTP/2 is widely used
HTTP/2 makes sites faster
(IETF-)QUIC ...
Thank you!
Questions outside!
So that was HTTP/2, what's next?
Upcoming SlideShare
Loading in …5
×

So that was HTTP/2, what's next?

599 views

Published on

Talk about HTTP/2, how it has been deployed, did it meet its promises and how QUIC is going to attempt to fix some of the remaining issues. Held in FOSDEM at Febyrar 2017.

Published in: Technology
  • Be the first to comment

So that was HTTP/2, what's next?

  1. 1. So that was HTTP/2, what's next? February 4 2017
  2. 2. Questions? I’ll hang aroundI’ll hang around outside theoutside the room afterwardroom afterward
  3. 3. Daniel Stenberg @bagder
  4. 4. Request and payload growth in the last 5 years... 8080 100100 800K800K 2.5M2.5M the average website loads 50+ resources on a single domain
  5. 5. Head of line blockingHead of line blocking
  6. 6. Multiplexed (1/2) Multiple streams over a single physical connection Max number of parallel streams set by peer
  7. 7. Multiplexed (2/2)
  8. 8. Better utilization of bandwidth
  9. 9. So that was HTTP/2 February 4, 2017 Adoption, usage, support
  10. 10. servers
  11. 11. browsers
  12. 12. Browser stats – Feb 2017 HTTP/2: Share of HTTPS: 30%30% 60%60%
  13. 13. Internetz – February 2017 12% of top 10 million 23% of top 10,000 26% of top 1000 >50% for your site
  14. 14. Winners and losers So that was HTTP/2 February 4, 2017
  15. 15. Did HTTP/2 meet its promises
  16. 16. The remote corners of Internet Percentile Desktop Mobile 5 1 11 25 20 44 50 79 94 75 194 184 95 800 913 Milliseconds RTT
  17. 17. Queuing time h1 vs h2 (Time waiting internally to send off a HTTP request) Percentile HTTP 1 HTTP 2 80 100 ms 2 ms 95 2000 ms 16 ms >100ms: H1 20%, H2 3%
  18. 18. 0% packet loss Image and data by Hooman Beheshti, Fastly
  19. 19. 2% packet loss Image and data by Hooman Beheshti, Fastly
  20. 20. Packet loss, hey? Single connection vs 6 Head of line blocking A single dropped packet blocks everything
  21. 21. Packet loss, hey? TLS TLS TLS HTTP/2 frame HTTP/2 frame HTTP/2 frame HTTP/2 frame HTTP/2 frame IP IP IP IP IP IP TCP TCP TCP TCP
  22. 22. Packet loss, hey? IP HTTP/2 frame HTTP/2 frame HTTP/2 frame HTTP/2 frame HTTP/2 frame TCP TCP TCP TCP TLS TLS TLS IP IP IP IP IP IP
  23. 23. Fixing TCP head of blocking
  24. 24. A non-blocking TCP + TLS + HTTP/2 Needs independent packets … that still are stream aware Needs new retransmissions/ACKs New protocol? Fixing TCP takes decades – if even doable
  25. 25. QUIC “TCP”, TLS and HTTP/2 over UDP no TCP head of line blocking other congestion control move across interfaces “TCP improvements” - much faster Google has this widely deployed already UDP not as problematic as we thought
  26. 26. Packet loss, hey? IP UDP UDP UDP UDP UDP UDP quic quic quic quic quic quic TLS TLS TLS TLS TLS TLS h2 h2 h2 h2 h2 h2 IP IP IP IP IP IP
  27. 27. The IETF QUIC wg Just started Massive interest s/custom crypto/TLS 1.3 Will transfer more than HTTP/2 frames First interim meeting in Tokyo in Jan ‘17 IETF-QUIC vs Google-QUIC Maybe early live test around mid-2017 That meansThat means maybemaybe andand earlyearly teststests
  28. 28. Neither 3 nor 2 Perhaps “HTTP/3”, but not in name Perhaps “TCP/2”, but not in name Just QUIC
  29. 29. Round-up HTTP/1 is not optimal HTTP/2 is binary and multipled HTTP/2 is widely used HTTP/2 makes sites faster (IETF-)QUIC is coming QUIC is HTTP/2 frames over UDP
  30. 30. Thank you! Questions outside!

×