SlideShare a Scribd company logo
1 of 110
Download to read offline
HTTP
HTTP 5G
html5 conference 2018 on 2018.11.25
WebDINO Japan - Tomoya ASAI
with Softbank - Yasuhiro NAGAI
about:me
Tomoya ASAI - dynamis webdino.org
CTO
Tech Speaker
dynamis @ Community
Twitter: @dynamitter
facebook.com/dynamis
I LOVE Firefox = Red Panda = Petit Panda = Lesser Panda2
@
about: WebDINO Japan
Web, Browser, Open
( : )
(Chromium, Firefox )
( : Gecko )
Web & Open
Web IoT
2017 : Mozilla Japan WebDINO Japan
https://www.webdino.org/3
Today's Topics
Introduction
5G
Softbank 結 5G
5G
5G x IoT Studio
4
Introduction
: Web
2014/10 - HTML5
2015/02 - HTTP/2 (RFC 7540, SPDY)
2015/10 - CSS snapshot 2015
2016/06 - ECMAScript 2016
2016/09 - TCP BBR Linux
2018/08 - TLS 1.3 (RFC 8446)
2019/xx - HTTP/3 (RFC TBD)
6
: HTTP over QUIC HTTP/3
IETF 103 (2018/11)
QUIC WG HTTPbis WG 

HTTPbis WG
2018/11
Chrome gQUIC IETF QUIC
HTTP/3 Litespeed
Facebook
: https://mailarchive.ietf.org/arch/msg/quic/RLRs4nB1lwFCZ_7k0iuz0ZBa35s7
Web
/
8
:
1.
×
Minify
Gzip Brotli (2 )
HTTP/2 QUIC
2.
×
TLS1.3 QUIC 0-RTT
ほ BBR
駄 駄9
Web
201x
HTTP/3 HTTP/2 + BBR
#html5conf #html5j_h
a.
b. 5G MEC
:
Softbank WebDINO
5G x IoT Studio
WebDINO Japan
5G ( )
Softbank & WebDINO Japan
#html5conf #html5j_h
5G
about:me
15
Yasuhiro Nagai
yasuhiro.nagai@g.softbank.co.jp
LTE, LTE-Advanced, 5G
IoT-platform
IoT (NIDD)
MaaS
1Gbps 10Gbps
10ms
10 /
1ms
100 /
5G4G
35
4
35 35
0
?
?
0
GC 4
1
N G
N
N
4
5
1
1
1
00
GC E C E
N
N
5
( )( -)
()
X
U
NW 1
6 C
5
1
JShtml
CSS
5 G
T
8 C
A82
A82 V
I
G5 N
0
G
D
/ 1
F e
C
M
tr n E U
2 / 2/
P
tr n e
d i r I
g g BG
P
r A
0
HTTP/2 & TCP
Web
HTTP/1.1 + TLS/1.2
HTTP/1.1
HTTP (HOL)
(RTT )

TLS 1.2 2-RTT (false start 1-RTT)
...
TLS/1.2
CRIME ...
:http://bit.ly/1gqR7WN (https://www.youtube.com/watch?v=hQZ-0mXFmk8)36
TCP 3-way 

1~3 RTT

(RTT = 100ms )
HTTP 1.1
TCP 1 1
CSS JS
6
Softbank37
TLS 1.2 (full handshake)
RTT (Round Trip Time) =
2-RTT
TLS False Start 1-RTT 

(Finished Application Data )
HTTP Application Data
1-2
session id Hello 1-RTT
Application Data
38
clientHello
serverHello

ServerCertificate

(ServerKeyExchange)

(CertificateRequest)

ServerHelloDone
(ClientCertificate)

ClientKeyExchange

(CertificateVerify)

ChangeCipherSpec

Finished

(Application Data)
ChangeCipherSpec
Finished
Application Data
( )
TCP
TCP
TCP (HOL)
( )
( )
BBR
39
TCP
TCP
TCP ACK
CWND
( )
TCP N 1/N
TCP
(1 )
: https://csperkins.org/research/tcp-hollywood/2016-05-19-networking/40
HTTP/1.1 HTTP/2
TCP
HTTP
TCP 1 TCP
HPACK (HTTP )
(
)
Google SPDY HTTP/241
H2 H2
HTTP/1.1 TCP


HTTP/2 TCP
TLS 1.3 :
0-RTT ( 1-RTT)
(TLS 1.2 1 RTT )
( )
TCP
42
TLS 1.3 (full handshake)
Full Handshake 1-RTT
PSK Application
Data clientHello 0-RTT
0-RTT
Hello
43
clientHello
(KeyShare)
serverHello
(KeyShare)

EncryptedExtensions

(CertificateRequest)

(Certificate)

(CertificateVerify)

Finished

Application Data
(Certificate)

(CertificateVerify)

Finished

Application Data
Application Data
( )
0-RTT
Hello
Application Data
(PSK)
PSK 

(PSK Hello )
(TLS )
POST44
clientHello
(Application Data)
serverHello

EncryptedExtensions

Finished

Application Data
EndOfEarlyData

Finished

Application Data
Application Data
( )
TCP
:
BDP ( x RTT) CWND
RTT
(Slow Start)
45
25
Deliveryrate
BDP BDP+BufSize
RTT
Optimal: max BW and min RTT (Kleinrock)
amount in flight
Optimal operating point
23
Deliveryrate
BDP BDP+BufSize
RTT
Loss based CC (CUBIC / Reno)
amount in flight
Loss based congestion control in deep buffers
BDP = (max BW) * (min RTT)
26
Deliveryrate
BDP BDP+BufSize
RTT
amount in flight
Est min RTT = windowed min of RTT samples
Est max BW = windowed max of BW samples
Estimating optimal point (max BW, min RTT)
(BDP )
https://datatracker.ietf.org/meeting/101/materials/slides-101-iccrg-an-update-on-bbr-work-at-google-0046
25
Deliveryrate
BDP BDP+BufSize
RTT
Optimal: max BW and min RTT (Kleinrock)
amount in flight
Optimal operating point
( )
https://datatracker.ietf.org/meeting/101/materials/slides-101-iccrg-an-update-on-bbr-work-at-google-0047
23
Deliveryrate
BDP BDP+BufSize
RTT
Loss based CC (CUBIC / Reno)
amount in flight
Loss based congestion control in deep buffers
: BBR
RTT
RTT
RTT 駄
Google
google.com 2%
YouTube 13%
YouTube RTT 32%
Loss 1% 2%
https://queue.acm.org/detail.cfm?id=302218448
BBR ( BW RTT )
https://datatracker.ietf.org/meeting/101/materials/slides-101-iccrg-an-update-on-bbr-work-at-google-0049
BDP = (max BW) * (min RTT)
26
Deliveryrate
BDP BDP+BufSize
RTT
amount in flight
Est min RTT = windowed min of RTT samples
Est max BW = windowed max of BW samples
Estimating optimal point (max BW, min RTT)
HTTP/3 & QUIC
Web
QUIC
HTTP + TLS over TCP UDP
HTTP/2 ( )
HTTP/2 + TLS1.2 + TCP HOL
0-RTT ( TLS 1.3 )
Multipath (5G + LTE + WiFi )
http://www.davidromerotrejo.com/2016/09/moving-web-from-tcp-to-udp.html?m=151


TLS 1.3
HTTP/2 TCP HOL
: http://bit.ly/1gqR7WN (https://www.youtube.com/watch?v=hQZ-0mXFmk8)52
H2 H2
H2 H2
HTTP/2 TCP 



( )
QUIC UDP 



( )
HTTP/3 ( HTTP over QUIC)
Google QUIC IETF QUIC
Google HTTP + TLS UDP
gQUIC IETF QUIC (iQUIC)
IETF iQUIC QUIC Transport HTTP over
QUIC (hq)
QPACK ( ) /
HTTP over QUIC = hq HTTP/3
IETF 103 hq HTTP/3
Transport QUIC
https://daniel.haxx.se/blog/2018/11/11/http-3/53
IETF QUIC
https://datatracker.ietf.org/wg/quic/deps/svg/54
HTTP/3

( QUIC)
HTTP/3 + QUIC Transport
HTTP/2 + TCP
UDP TCP


( )
LTE, 5G, WiFi IP
ID 

( / IP+Port )
255 range Negative ACK (NACK)
HTTP/2 TCP
55
QUIC Transport MTU
Google MTU = 1350,1370 (IPv6,v4)
Path MTU
MTU MTU
HTTP/2
駄 MTU 1450
MTU
(MEC on 5G )
:
DDoS 1200 PMTU
1280 (IPv6 PMTU)
56
HTTP/3, QUIC
Server: Google Frontend (GCP) or LiteSpeed
Apach, Nginx QUIC
Client: Chrome
QUIC alt-svc HTTP/2
(
)
QUIC
--origin-port-to-force-quic-on
QUIC57
Google Quic
Google Front End ( )
Google QUIC GCP
LiteSpeed ( )
QUIC (2017/06 )
Caddy
GO LTE 駄
issue 5G 駄
Satellite (by LINE)
Google QUIC
: Chrome IETF QUIC Server58
: Google OSS QUIC
QUIC
quic_server, quic_client
toy server.
(HTTP
)
FYI: Chrome 2012 10 659
LiteSpeed
HTTP/2 OSS QUIC
Google Frontend
HTTP/2 QUIC
NIC
(by LiteSpeed )
Google
Web QUIC60
5G x IoT Studio
5G端末
5G基地局
5Gコア
シールドルーム
client server
UDP
計測時設定の
ダウンロード速度
計測時設定の
アップロード速度
往復遅延時間
( 最小 RTT )
2Gbps 200Mbps 5~7msec
5G 環境 計測環境概要
4.7GHz


19 2 +63
4.7GHz
5G 5G
SYSTEM WORKS R8151
( )
64
CPU Intel Core i7-8700 (6core/3.2GHz)
Memory Server: 16GB (DDR4-2666)

Client: 32GB (DDR4-2666)
HDD 256GB (NVMe SSD)
NIC Intel X550-T1, PCIe3.0 (10Gbps)
OS Linux (Ubuntu16.04LTS)
5G端末
5G基地局
シールドルーム
4.7GHz
5Gコア
(有線計測時のみ)
Ixia Network Emulator II
サーバマシン x 2 クライアント x 2
MTU=140010Gbps
Nginx 1.10.3 (HTTP/1.1, HTTP/2 )
Lite Speed Enterprise 5.3 RC (QUIC )
Chrome 68.0.3440.106
TCP BBR Kernel Update
OS Ubuntu 16.04LTS
Let's Encrypt HTTPS
Let's Deprecate HTTP!
Chrome65
Chrome + Puppeteer ( )
JavaScript fetch Resource Timing
API (5μs ) DL
(
)
ping RTT (0.02 )
sar NIC/CPU/Memory
sar
tcpdump ( )
tcpdump 1 40GB66
HTTP/1.1 (cubic, bbr), HTTP/2 (cubic, bbr), QUIC 5
駄 5G 駄
駄 (DL )
fetch 4 x 5 = 20 467
fetch
single 5GB
movie 340MB MP4 (16 files)

BigBuckBunny 1080p 60fps
DL
image 62KB 22MB PNG (712 files)
BigBuckBunny
movie chunk
100
chunk 1 2MB (139 files x 10)
YouTube BBB
( 10 )
(ping, sar)
Client : ping i 0.02 $server > $ lename
RTT 0.02
chart.js ( )
Server/Client : sar A o $ lename
sadf ( )
1 :
CPU Memory NIC (TCP,
UDP
) block device I/O Transfer
68
5G RTT ( )
http/1.1, cubic, movie (9/22)69
RTT
(50ms )
RTT 
 

RTT
RTT 10ms
... 1791
...
Chrome
5G
( )
5G 駄
( ) 5G
5G 5G ( )
MEC
駄
5G
駄
72
5G
CUBIC BBR
HTTP/2 TCP 1
QUIC73
HTTP/1.1 (CUBIC) HTTP/2 (CUBIC) HTTP/1.1 (BBR) HTTP/2 (BBR) QUIC
single movie image chunk
: QUIC 



( )
5G
CUBIC BBR
HTTP/2 TCP 1
QUIC74
HTTP/1.1 (CUBIC) HTTP/2 (CUBIC) HTTP/1.1 (BBR) HTTP/2 (BBR) QUIC
single movie image chunk
: QUIC 



( )
TCP BBR
TCP CUBIC vs BBR 6 x TCP CUBIC vs BBR
(HTTP/1.1)
movie, image
TCP BBR CUBIC ( )
: 9/5 ( )75
( , 9/5) (Mbps)
http1.1, cubic, single 476, 697, 694, 746 653
http1.1, cubic, movie 969, 948, 878, 928 931
http1.1, cubic, image 1030, 1010, 902, 992 984
http1.1, cubic, chunk 864, 875, 885, 883 877
http1.1, bbr, single 555, 609, 578, 604 587
http1.1, bbr, movie 890, 866, 834, 867 864
http1.1, bbr, image 794, 790, 788, 634 751
http1.1, bbr, chunk 735, 818, 746, 767 767
( , 8/23) (Gbps)
http1.1, cubic, single 3.17, 3.18, 3.14, 3.12 3.15
http1.1, cubic, movie 2.73, 2.77, 2.72, 2.76 2.74
http1.1, cubic, image 2.00, 1.86, 1.86, 2.00 1.93
http1.1, cubic, chunk 1.30, 1.27, 1.28, 1.28 1.28
http1.1, bbr, single 3.13, 3.24, 3.15, 3.13 3.18
http1.1, bbr, movie 2.82, 2.90, 2.88, 2.88 2.87
http1.1, bbr, image 2.02, 1.86, 1.98, 1.95 1.95
http1.1, bbr, chunk 1.30, 1.27, 1.28, 1.28 1.28
(HTTP/2)
HTTP/1.1 vs HTTP/2 CUBIC vs BBR
HTTP/2
TCP 1
: 9/5 ( )76
( , 8/23) (Gbps)
http2, cubic, single 3.22, 3.11, 3.22, 3.20 3.19
http2, cubic, movie 2.83, 2.74, 2.80, 2.81 2.79
http2, cubic, image 1.93, 1.68, 1.91, 1.65 1.79
http2, cubic, chunk 1.35, 1.27, 1.34, 1.35 1.33
http2, bbr, single 3.22, 3.11, 3.22, 3.20 3.19
http2, bbr, movie 2.83, 2.74, 2.80, 2.81 2.79
http2, bbr, image 1.93, 1.68, 1.91, 1.65 1.79
http2, bbr, chunk 1.35, 1.27, 1.34, 1.35 1.33
( , 9/5) (Mbps)
http2, cubic, single 700, 896, 816, 959 823
http2, cubic, movie 826, 901, 699, 676 776
http2, cubic, image 740, 704, 560, 725 682
http2, cubic, chunk 875, 881, 878, 880 879
http2, bbr, single 700, 896, 816, 959 843
http2, bbr, movie 826, 901, 699, 676 776
http2, bbr, image 740, 704, 560, 725 682
http2, bbr, chunk 875, 881, 878, 880 879
(QUIC)
QUIC movie
HTTP/1.1 HTTP/2
QUIC Chrome ( )
Disk I/O ( )
QUIC, single 駄 n/a77
( , 8/23) (Gbps)
quic, single 3.22, 3.19, 3.22, 3.24 3.22
quic, movie 3.23, 3.20, 3.18, 3.14 3.19
quic, image 2.10, 1.89, 2.19, 2.15 2.08
quic, chunk 1.35, 1.28, 1.35, 1.32 1.32
( , 9/21) (Mbps)
quic, single n/a n/a
quic, movie 374, 365, 395, 378 378
quic, image 492, 472, 488, 451 476
quic, chunk 495, 504, 540, 531 518
5G
1.
CUBIC RTT
BBR
RTT
5G 駄
2.
QUIC HOL
78
5G
1.
a. 5G
OR
b. RTT
2.
HTTP, TCP HOL
QUIC
note:
NEXT TODO: 駄79
5G HTTP/2
TCP LOH HTTP/1.1
TCP N
( 1/N )
(HTTP/1.1 )
TCP
HTTP + TCP QUIC
TCP LOH QUIC
QUIC
5G RTT HTTP/280
YES.
HTTP/2

is slow
on 5G.
5G BBR
CUBIC
5G 駄


0.1%
BBR RTT
5G 駄
(TCP/IP )
RTT
BBR RTT
note: 50ping/sec81
YES.
BBR

is slow
on 5G.
5G RTT
http/2, cubic, movie RTT82


RTT


RTT
10ms
HTTP/1.1, CUBIC, movie RTT
CUBIC RTT 50ms RTT83
Average Variance Standard
Deviation
Max Min
18.1362 514.634 22.68553986 425 2.35
Mbps
1 935
2 928
3 928
4 878
50ms
HTTP/1.1, BBR, Movie RTT
BBR RTT 50ms 10ms CUBIC84
Average Variance Standard
Deviation
Max Min
10.9638 88.354 9.399678951 81.3 2.21
Mbps
1 559
2 435
3 510
4 556
50ms
10ms
: TCP (CUBIC) iperf
60 ( )
1.8Gbps 3 775Mbps
85
180s 1810Mbps

: TCP (BBR) iperf
CUBIC 500Mbps
400Mbps
RTT86
5G CUBIC
CUBIC
BBR 4 60 80%
CUBIC
note: BBR 駄 CUBIC
駄
note: 50ping/sec87
NO.
CUBIC

CAN be
slow.
( , 9/20) 1 2 3 4
http2, cubic, movie 634Mbps 686Mbps 905Mbps 500Mbps
http2, cubic, chunk 240Mbps 549Mbps 264Mbps 339Mbps
http2, bbr, movie 291Mbps 301Mbps 300Mbps 280Mbps
http2, bbr, chunk 284Mbps 321Mbps 308Mbps 326Mbps
5G QUIC
QUIC
5G RTT
RTT
RTT 20-30ms 50ms
RTT
5G
( )
NEXT TODO:88
QUIC
CAN be
fastest
on 5G.
1 x Chrome, HTTP/2, quic, movie
364 393Mbps
750Mbps (5G 1/3 )
89
1 (374Mbps) 2 (364Mbps) 3 (393Mbps) 4 (378Mbps)
2 x Chrome, HTTP/2, quic, movie
449 650Mbps
2 2.1Gbps ( 5G )
90
1
(590/579Mbps
)
2
(590/579Mbps
)
3
(449/461Mbps
)
4 

(650/618Mbps
)
4 x Chrome,HTTP/2,QUIC,Movie
4 2.3 Gbps
91
1
(286/279/

279/273)
2
(397/325/

371/328
3
(175/264/

194/268
4
(317/269/

270/266)
RTT
Chrome QUIC RTT92
50ms
RTT
RTT
2G
( 1 40GB)
RTT
( ) RTT
(RTT )
CUBIC, BBR 縮
縮
TODO NEXT: 縮94
TCP RST
TCP RST (reset) TCP
( 縮 )
Web 

HTTP/2, QUIC fetch 100
Wireshark rst95
fetch
駄
駄 5%
5G 駄
fetch
fetch JS
96
... ...

... ...
HTTP (TCP) CUBIC BBR
5G CUBIC BBR
CUBIC
BBR
HTTP TCP
HTTP/1.1 HTTP/2
QUIC
( ) MEC
99
5G
RTT RTT
: HTTP/2 BBR QUIC RTT
fetch
catch resolve
QUIC
Web
100
5G
5G 

駄
101
5G x IoT Studio
102
https://tm.softbank.jp/form/contact/5g/index.php
5G×IoT Studio に関するお問い合わせ
5G x IoT Studio
103
https://tm.softbank.jp/form/contact/5g/index.php
5G×IoT Studio に関するお問い合わせ
5G x IoT Studio
104
https://tm.softbank.jp/form/contact/5g/index.php
5G×IoT Studio に関するお問い合わせ
Thank You!
Any Questions?
Feel free to contact me:
dynamis webdino.org

@dynamitter, facebook.com/dynamis
Slide Upload: slideshare.net/dynamis
by @4687koSourijun
@
References - TCP
TCP/IP https://www.amazon.co.jp/dp/4894713209
Internet Week 99
TCP https://www.nic.ad.jp/ja/materials/iw/1999/notes/C3.PDF
TCP http://www.ieice-hbkb.org/ les/03/03gun_04hen_01.pdf
http://sacsis.hpcc.jp/2009/SACSIS2009_TCP.pdf
CUBIC for Fast Long-Distance Networks
RFC 8312 https://tools.ietf.org/html/rfc8312
CUBIC: a new TCP-friendly high-speed TCP variant https://dl.acm.org/citation.cfm?
id=1400105
106
References - BBR
BBR
BBR: Congestion-Based Congestion Control https://queue.acm.org/
detail.cfm?id=3022184
BBR for Linux Kernel
BBR congestion control https://lwn.net/Articles/701165/
patch https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-
next.git/commit/?id=0f8782ea14974ce992618b55f0c041ef43ed0b78
Linux Kernel 4.9 https://kernelnewbies.org/Linux_4.9
107
References - Google QUIC
Chromium QUIC
https://www.chromium.org/quic
https://www.chromium.org/quic/playing-with-quic
Design Doc https://docs.google.com/document/d/
1RNHkx_VvKWyWg6Lr8SZ-saqsQx7rFV-ev2jRFUoVD34/edit?pli=1#
108
References - IETF QUIC
IETF QUIC WG https://quicwg.org/
GitHub - WG materials https://github.com/quicwg/wg-materials
IETF 103 Meeting
https://datatracker.ietf.org/meeting/103/materials
https://datatracker.ietf.org/meeting/103/session/quic
HTTP/3 https://daniel.haxx.se/blog/2018/11/11/http-3/
QUIC
RFC Drafts https://datatracker.ietf.org/wg/quic/documents/
https://github.com/ ano-yuki/my-quic-spec-translation
109
Reference - QUIC
ASnoKaze Blog - QUIC https://asnokaze.hatenablog.com/
archive/category/QUIC
: http://www.soumu.go.jp/
main_sosiki/joho_tsusin/hyojun/02tsushin04_03000123.html
110

More Related Content

What's hot

Kubernetes Jobによるバッチシステムのリソース最適化 / AbemaTV DevCon 2018 TrackB Session B6
Kubernetes Jobによるバッチシステムのリソース最適化 / AbemaTV DevCon 2018 TrackB Session B6Kubernetes Jobによるバッチシステムのリソース最適化 / AbemaTV DevCon 2018 TrackB Session B6
Kubernetes Jobによるバッチシステムのリソース最適化 / AbemaTV DevCon 2018 TrackB Session B6AbemaTV, Inc.
 
Ethernetの受信処理
Ethernetの受信処理Ethernetの受信処理
Ethernetの受信処理Takuya ASADA
 
コンテナにおけるパフォーマンス調査でハマった話
コンテナにおけるパフォーマンス調査でハマった話コンテナにおけるパフォーマンス調査でハマった話
コンテナにおけるパフォーマンス調査でハマった話Yuta Shimada
 
電子署名(PKI)ハンズオン資料 V1.00
電子署名(PKI)ハンズオン資料 V1.00電子署名(PKI)ハンズオン資料 V1.00
電子署名(PKI)ハンズオン資料 V1.00Naoto Miyachi
 
MRU : Monobit Reliable UDP ~5G世代のモバイルゲームに最適な通信プロトコルを目指して~
MRU : Monobit Reliable UDP ~5G世代のモバイルゲームに最適な通信プロトコルを目指して~MRU : Monobit Reliable UDP ~5G世代のモバイルゲームに最適な通信プロトコルを目指して~
MRU : Monobit Reliable UDP ~5G世代のモバイルゲームに最適な通信プロトコルを目指して~モノビット エンジン
 
ソーシャルゲームの為のデータベース設計
ソーシャルゲームの為のデータベース設計ソーシャルゲームの為のデータベース設計
ソーシャルゲームの為のデータベース設計kaminashi
 
MicrometerとPrometheusによる LINEファミリーアプリのモニタリング
MicrometerとPrometheusによる LINEファミリーアプリのモニタリングMicrometerとPrometheusによる LINEファミリーアプリのモニタリング
MicrometerとPrometheusによる LINEファミリーアプリのモニタリングLINE Corporation
 
DPDKによる高速コンテナネットワーキング
DPDKによる高速コンテナネットワーキングDPDKによる高速コンテナネットワーキング
DPDKによる高速コンテナネットワーキングTomoya Hibi
 
ネットワーク ゲームにおけるTCPとUDPの使い分け
ネットワーク ゲームにおけるTCPとUDPの使い分けネットワーク ゲームにおけるTCPとUDPの使い分け
ネットワーク ゲームにおけるTCPとUDPの使い分けモノビット エンジン
 
コンテナの作り方「Dockerは裏方で何をしているのか?」
コンテナの作り方「Dockerは裏方で何をしているのか?」コンテナの作り方「Dockerは裏方で何をしているのか?」
コンテナの作り方「Dockerは裏方で何をしているのか?」Masahito Zembutsu
 
Rust と Wasmの現実
Rust と Wasmの現実Rust と Wasmの現実
Rust と Wasmの現実ShogoTagami1
 
2020 0218 - パスワードのいらない世界へ:FIDOアライアンスとFIDO認証の最新状況
2020 0218 - パスワードのいらない世界へ:FIDOアライアンスとFIDO認証の最新状況2020 0218 - パスワードのいらない世界へ:FIDOアライアンスとFIDO認証の最新状況
2020 0218 - パスワードのいらない世界へ:FIDOアライアンスとFIDO認証の最新状況FIDO Alliance
 
エンジニアなら知っておきたい「仮想マシン」のしくみ v1.1 (hbstudy 17)
エンジニアなら知っておきたい「仮想マシン」のしくみ v1.1 (hbstudy 17)エンジニアなら知っておきたい「仮想マシン」のしくみ v1.1 (hbstudy 17)
エンジニアなら知っておきたい「仮想マシン」のしくみ v1.1 (hbstudy 17)Takeshi HASEGAWA
 
WebブラウザでP2Pを実現する、WebRTCのAPIと周辺技術
WebブラウザでP2Pを実現する、WebRTCのAPIと周辺技術WebブラウザでP2Pを実現する、WebRTCのAPIと周辺技術
WebブラウザでP2Pを実現する、WebRTCのAPIと周辺技術Yoshiaki Sugimoto
 
【Interop Tokyo 2018】 Telemetryの匠が解説~オープン技術を用いたマイクロバースト検知の最前線~
【Interop Tokyo 2018】 Telemetryの匠が解説~オープン技術を用いたマイクロバースト検知の最前線~【Interop Tokyo 2018】 Telemetryの匠が解説~オープン技術を用いたマイクロバースト検知の最前線~
【Interop Tokyo 2018】 Telemetryの匠が解説~オープン技術を用いたマイクロバースト検知の最前線~Juniper Networks (日本)
 
WebRTCの技術解説 公開版
WebRTCの技術解説 公開版WebRTCの技術解説 公開版
WebRTCの技術解説 公開版Contest Ntt-west
 
PSR-1 と PSR-2 を 5分でざっくり理解する
PSR-1 と PSR-2 を5分でざっくり理解するPSR-1 と PSR-2 を5分でざっくり理解する
PSR-1 と PSR-2 を 5分でざっくり理解するWataru Terada
 
Interrupt Affinityについて
Interrupt AffinityについてInterrupt Affinityについて
Interrupt AffinityについてTakuya ASADA
 

What's hot (20)

Kubernetes Jobによるバッチシステムのリソース最適化 / AbemaTV DevCon 2018 TrackB Session B6
Kubernetes Jobによるバッチシステムのリソース最適化 / AbemaTV DevCon 2018 TrackB Session B6Kubernetes Jobによるバッチシステムのリソース最適化 / AbemaTV DevCon 2018 TrackB Session B6
Kubernetes Jobによるバッチシステムのリソース最適化 / AbemaTV DevCon 2018 TrackB Session B6
 
Ethernetの受信処理
Ethernetの受信処理Ethernetの受信処理
Ethernetの受信処理
 
コンテナにおけるパフォーマンス調査でハマった話
コンテナにおけるパフォーマンス調査でハマった話コンテナにおけるパフォーマンス調査でハマった話
コンテナにおけるパフォーマンス調査でハマった話
 
電子署名(PKI)ハンズオン資料 V1.00
電子署名(PKI)ハンズオン資料 V1.00電子署名(PKI)ハンズオン資料 V1.00
電子署名(PKI)ハンズオン資料 V1.00
 
MRU : Monobit Reliable UDP ~5G世代のモバイルゲームに最適な通信プロトコルを目指して~
MRU : Monobit Reliable UDP ~5G世代のモバイルゲームに最適な通信プロトコルを目指して~MRU : Monobit Reliable UDP ~5G世代のモバイルゲームに最適な通信プロトコルを目指して~
MRU : Monobit Reliable UDP ~5G世代のモバイルゲームに最適な通信プロトコルを目指して~
 
ソーシャルゲームの為のデータベース設計
ソーシャルゲームの為のデータベース設計ソーシャルゲームの為のデータベース設計
ソーシャルゲームの為のデータベース設計
 
MicrometerとPrometheusによる LINEファミリーアプリのモニタリング
MicrometerとPrometheusによる LINEファミリーアプリのモニタリングMicrometerとPrometheusによる LINEファミリーアプリのモニタリング
MicrometerとPrometheusによる LINEファミリーアプリのモニタリング
 
DPDKによる高速コンテナネットワーキング
DPDKによる高速コンテナネットワーキングDPDKによる高速コンテナネットワーキング
DPDKによる高速コンテナネットワーキング
 
ネットワーク ゲームにおけるTCPとUDPの使い分け
ネットワーク ゲームにおけるTCPとUDPの使い分けネットワーク ゲームにおけるTCPとUDPの使い分け
ネットワーク ゲームにおけるTCPとUDPの使い分け
 
コンテナの作り方「Dockerは裏方で何をしているのか?」
コンテナの作り方「Dockerは裏方で何をしているのか?」コンテナの作り方「Dockerは裏方で何をしているのか?」
コンテナの作り方「Dockerは裏方で何をしているのか?」
 
Rust と Wasmの現実
Rust と Wasmの現実Rust と Wasmの現実
Rust と Wasmの現実
 
2020 0218 - パスワードのいらない世界へ:FIDOアライアンスとFIDO認証の最新状況
2020 0218 - パスワードのいらない世界へ:FIDOアライアンスとFIDO認証の最新状況2020 0218 - パスワードのいらない世界へ:FIDOアライアンスとFIDO認証の最新状況
2020 0218 - パスワードのいらない世界へ:FIDOアライアンスとFIDO認証の最新状況
 
PHPにおけるI/O多重化とyield
PHPにおけるI/O多重化とyieldPHPにおけるI/O多重化とyield
PHPにおけるI/O多重化とyield
 
エンジニアなら知っておきたい「仮想マシン」のしくみ v1.1 (hbstudy 17)
エンジニアなら知っておきたい「仮想マシン」のしくみ v1.1 (hbstudy 17)エンジニアなら知っておきたい「仮想マシン」のしくみ v1.1 (hbstudy 17)
エンジニアなら知っておきたい「仮想マシン」のしくみ v1.1 (hbstudy 17)
 
WebブラウザでP2Pを実現する、WebRTCのAPIと周辺技術
WebブラウザでP2Pを実現する、WebRTCのAPIと周辺技術WebブラウザでP2Pを実現する、WebRTCのAPIと周辺技術
WebブラウザでP2Pを実現する、WebRTCのAPIと周辺技術
 
【Interop Tokyo 2018】 Telemetryの匠が解説~オープン技術を用いたマイクロバースト検知の最前線~
【Interop Tokyo 2018】 Telemetryの匠が解説~オープン技術を用いたマイクロバースト検知の最前線~【Interop Tokyo 2018】 Telemetryの匠が解説~オープン技術を用いたマイクロバースト検知の最前線~
【Interop Tokyo 2018】 Telemetryの匠が解説~オープン技術を用いたマイクロバースト検知の最前線~
 
Spring と TDD
Spring と TDDSpring と TDD
Spring と TDD
 
WebRTCの技術解説 公開版
WebRTCの技術解説 公開版WebRTCの技術解説 公開版
WebRTCの技術解説 公開版
 
PSR-1 と PSR-2 を 5分でざっくり理解する
PSR-1 と PSR-2 を5分でざっくり理解するPSR-1 と PSR-2 を5分でざっくり理解する
PSR-1 と PSR-2 を 5分でざっくり理解する
 
Interrupt Affinityについて
Interrupt AffinityについてInterrupt Affinityについて
Interrupt Affinityについて
 

Similar to HTTP and 5G (fixed1)

HTTP/2 and QUICK protocols. Optimizing the Web stack for HTTP/2 era
HTTP/2 and QUICK protocols. Optimizing the Web stack for HTTP/2 eraHTTP/2 and QUICK protocols. Optimizing the Web stack for HTTP/2 era
HTTP/2 and QUICK protocols. Optimizing the Web stack for HTTP/2 erapeychevi
 
Technical Overview of QUIC
Technical  Overview of QUICTechnical  Overview of QUIC
Technical Overview of QUICshigeki_ohtsu
 
OSTU - Sake Blok on Packet Capturing with Tshark
OSTU - Sake Blok on Packet Capturing with TsharkOSTU - Sake Blok on Packet Capturing with Tshark
OSTU - Sake Blok on Packet Capturing with TsharkDenny K
 
103 Basic network concepts
103 Basic network concepts103 Basic network concepts
103 Basic network conceptsSsendiSamuel
 
HTTP/3 is next generation HTTP
HTTP/3 is next generation HTTPHTTP/3 is next generation HTTP
HTTP/3 is next generation HTTPDaniel Stenberg
 
BRKRST-3068 Troubleshooting Catalyst 2K and 3K.pdf
BRKRST-3068  Troubleshooting Catalyst 2K and 3K.pdfBRKRST-3068  Troubleshooting Catalyst 2K and 3K.pdf
BRKRST-3068 Troubleshooting Catalyst 2K and 3K.pdfssusercbaa33
 
WebRTC: A front-end perspective
WebRTC: A front-end perspectiveWebRTC: A front-end perspective
WebRTC: A front-end perspectiveshwetank
 
An Application Gateway to Deploy High-quality Video Communications in Various...
An Application Gateway to Deploy High-quality Video Communications in Various...An Application Gateway to Deploy High-quality Video Communications in Various...
An Application Gateway to Deploy High-quality Video Communications in Various...Takashi Kishida
 
[workshop] The Revolutionary WebRTC
[workshop] The Revolutionary WebRTC[workshop] The Revolutionary WebRTC
[workshop] The Revolutionary WebRTCGiacomo Vacca
 
Iot Conference Berlin M2M,IoT, device management: one protocol to rule them all?
Iot Conference Berlin M2M,IoT, device management: one protocol to rule them all?Iot Conference Berlin M2M,IoT, device management: one protocol to rule them all?
Iot Conference Berlin M2M,IoT, device management: one protocol to rule them all?Julien Vermillard
 
Linux HTTPS/TCP/IP Stack for the Fast and Secure Web
Linux HTTPS/TCP/IP Stack for the Fast and Secure WebLinux HTTPS/TCP/IP Stack for the Fast and Secure Web
Linux HTTPS/TCP/IP Stack for the Fast and Secure WebAll Things Open
 
03_clere-HTTP2 HTTP3 the State of the Art in Our Servers.pdf
03_clere-HTTP2 HTTP3 the State of the Art in Our Servers.pdf03_clere-HTTP2 HTTP3 the State of the Art in Our Servers.pdf
03_clere-HTTP2 HTTP3 the State of the Art in Our Servers.pdfJean-Frederic Clere
 
Short Introduction to IPv6
Short Introduction to IPv6Short Introduction to IPv6
Short Introduction to IPv6Martin Schütte
 
Primer to Browser Netwroking
Primer to Browser NetwrokingPrimer to Browser Netwroking
Primer to Browser NetwrokingShuya Osaki
 

Similar to HTTP and 5G (fixed1) (20)

HTTP/2 and QUICK protocols. Optimizing the Web stack for HTTP/2 era
HTTP/2 and QUICK protocols. Optimizing the Web stack for HTTP/2 eraHTTP/2 and QUICK protocols. Optimizing the Web stack for HTTP/2 era
HTTP/2 and QUICK protocols. Optimizing the Web stack for HTTP/2 era
 
Technical Overview of QUIC
Technical  Overview of QUICTechnical  Overview of QUIC
Technical Overview of QUIC
 
OSTU - Sake Blok on Packet Capturing with Tshark
OSTU - Sake Blok on Packet Capturing with TsharkOSTU - Sake Blok on Packet Capturing with Tshark
OSTU - Sake Blok on Packet Capturing with Tshark
 
103 Basic network concepts
103 Basic network concepts103 Basic network concepts
103 Basic network concepts
 
HTTP/3 is next generation HTTP
HTTP/3 is next generation HTTPHTTP/3 is next generation HTTP
HTTP/3 is next generation HTTP
 
Stu t17 a
Stu t17 aStu t17 a
Stu t17 a
 
Lab telematicos
Lab telematicosLab telematicos
Lab telematicos
 
Lab telematicos
Lab telematicosLab telematicos
Lab telematicos
 
Quic illustrated
Quic illustratedQuic illustrated
Quic illustrated
 
BRKRST-3068 Troubleshooting Catalyst 2K and 3K.pdf
BRKRST-3068  Troubleshooting Catalyst 2K and 3K.pdfBRKRST-3068  Troubleshooting Catalyst 2K and 3K.pdf
BRKRST-3068 Troubleshooting Catalyst 2K and 3K.pdf
 
WebRTC: A front-end perspective
WebRTC: A front-end perspectiveWebRTC: A front-end perspective
WebRTC: A front-end perspective
 
An Application Gateway to Deploy High-quality Video Communications in Various...
An Application Gateway to Deploy High-quality Video Communications in Various...An Application Gateway to Deploy High-quality Video Communications in Various...
An Application Gateway to Deploy High-quality Video Communications in Various...
 
[workshop] The Revolutionary WebRTC
[workshop] The Revolutionary WebRTC[workshop] The Revolutionary WebRTC
[workshop] The Revolutionary WebRTC
 
Iot Conference Berlin M2M,IoT, device management: one protocol to rule them all?
Iot Conference Berlin M2M,IoT, device management: one protocol to rule them all?Iot Conference Berlin M2M,IoT, device management: one protocol to rule them all?
Iot Conference Berlin M2M,IoT, device management: one protocol to rule them all?
 
Linux HTTPS/TCP/IP Stack for the Fast and Secure Web
Linux HTTPS/TCP/IP Stack for the Fast and Secure WebLinux HTTPS/TCP/IP Stack for the Fast and Secure Web
Linux HTTPS/TCP/IP Stack for the Fast and Secure Web
 
03_clere-HTTP2 HTTP3 the State of the Art in Our Servers.pdf
03_clere-HTTP2 HTTP3 the State of the Art in Our Servers.pdf03_clere-HTTP2 HTTP3 the State of the Art in Our Servers.pdf
03_clere-HTTP2 HTTP3 the State of the Art in Our Servers.pdf
 
Short Introduction to IPv6
Short Introduction to IPv6Short Introduction to IPv6
Short Introduction to IPv6
 
Primer to Browser Netwroking
Primer to Browser NetwrokingPrimer to Browser Netwroking
Primer to Browser Netwroking
 
UDT
UDTUDT
UDT
 
UDT
UDTUDT
UDT
 

More from dynamis

HTTP and 5G
HTTP and 5GHTTP and 5G
HTTP and 5Gdynamis
 
HTTP and 5G partial draft
HTTP and 5G partial draftHTTP and 5G partial draft
HTTP and 5G partial draftdynamis
 
Web App Platform Strategy
Web App Platform StrategyWeb App Platform Strategy
Web App Platform Strategydynamis
 
HTML5 & Renesas RZ/G
HTML5 & Renesas RZ/GHTML5 & Renesas RZ/G
HTML5 & Renesas RZ/Gdynamis
 
Life of html5 (osaka)
Life of html5 (osaka)Life of html5 (osaka)
Life of html5 (osaka)dynamis
 
Web updates 2017
Web updates 2017Web updates 2017
Web updates 2017dynamis
 
Life of HTML5
Life of HTML5Life of HTML5
Life of HTML5dynamis
 
Browsers in IoT Era
Browsers in IoT EraBrowsers in IoT Era
Browsers in IoT Eradynamis
 
New Norm of HTML5
New Norm of HTML5New Norm of HTML5
New Norm of HTML5dynamis
 
Edge Web Technologies and Browser Vendors (Updated on 2016/09/06)
Edge Web Technologies and Browser Vendors (Updated on 2016/09/06)Edge Web Technologies and Browser Vendors (Updated on 2016/09/06)
Edge Web Technologies and Browser Vendors (Updated on 2016/09/06)dynamis
 
OSC2016.Enterprise Lightnig Talk
OSC2016.Enterprise Lightnig TalkOSC2016.Enterprise Lightnig Talk
OSC2016.Enterprise Lightnig Talkdynamis
 
Demo for Gecko Embedded
Demo for Gecko EmbeddedDemo for Gecko Embedded
Demo for Gecko Embeddeddynamis
 
Project Gecko Embedded
Project Gecko EmbeddedProject Gecko Embedded
Project Gecko Embeddeddynamis
 
The New Norm of The Web
The New Norm of The WebThe New Norm of The Web
The New Norm of The Webdynamis
 
Progressive Mobile Web Apps
Progressive Mobile Web AppsProgressive Mobile Web Apps
Progressive Mobile Web Appsdynamis
 
Modern Mobile Web Apps
Modern Mobile Web AppsModern Mobile Web Apps
Modern Mobile Web Appsdynamis
 
Web Tech & Architecture
Web Tech & ArchitectureWeb Tech & Architecture
Web Tech & Architecturedynamis
 
Java script.trend(spec)
Java script.trend(spec)Java script.trend(spec)
Java script.trend(spec)dynamis
 
Data Privacy meeting
Data Privacy meetingData Privacy meeting
Data Privacy meetingdynamis
 
Firefox OS TV
Firefox OS TVFirefox OS TV
Firefox OS TVdynamis
 

More from dynamis (20)

HTTP and 5G
HTTP and 5GHTTP and 5G
HTTP and 5G
 
HTTP and 5G partial draft
HTTP and 5G partial draftHTTP and 5G partial draft
HTTP and 5G partial draft
 
Web App Platform Strategy
Web App Platform StrategyWeb App Platform Strategy
Web App Platform Strategy
 
HTML5 & Renesas RZ/G
HTML5 & Renesas RZ/GHTML5 & Renesas RZ/G
HTML5 & Renesas RZ/G
 
Life of html5 (osaka)
Life of html5 (osaka)Life of html5 (osaka)
Life of html5 (osaka)
 
Web updates 2017
Web updates 2017Web updates 2017
Web updates 2017
 
Life of HTML5
Life of HTML5Life of HTML5
Life of HTML5
 
Browsers in IoT Era
Browsers in IoT EraBrowsers in IoT Era
Browsers in IoT Era
 
New Norm of HTML5
New Norm of HTML5New Norm of HTML5
New Norm of HTML5
 
Edge Web Technologies and Browser Vendors (Updated on 2016/09/06)
Edge Web Technologies and Browser Vendors (Updated on 2016/09/06)Edge Web Technologies and Browser Vendors (Updated on 2016/09/06)
Edge Web Technologies and Browser Vendors (Updated on 2016/09/06)
 
OSC2016.Enterprise Lightnig Talk
OSC2016.Enterprise Lightnig TalkOSC2016.Enterprise Lightnig Talk
OSC2016.Enterprise Lightnig Talk
 
Demo for Gecko Embedded
Demo for Gecko EmbeddedDemo for Gecko Embedded
Demo for Gecko Embedded
 
Project Gecko Embedded
Project Gecko EmbeddedProject Gecko Embedded
Project Gecko Embedded
 
The New Norm of The Web
The New Norm of The WebThe New Norm of The Web
The New Norm of The Web
 
Progressive Mobile Web Apps
Progressive Mobile Web AppsProgressive Mobile Web Apps
Progressive Mobile Web Apps
 
Modern Mobile Web Apps
Modern Mobile Web AppsModern Mobile Web Apps
Modern Mobile Web Apps
 
Web Tech & Architecture
Web Tech & ArchitectureWeb Tech & Architecture
Web Tech & Architecture
 
Java script.trend(spec)
Java script.trend(spec)Java script.trend(spec)
Java script.trend(spec)
 
Data Privacy meeting
Data Privacy meetingData Privacy meeting
Data Privacy meeting
 
Firefox OS TV
Firefox OS TVFirefox OS TV
Firefox OS TV
 

Recently uploaded

Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
Sample pptx for embedding into website for demo
Sample pptx for embedding into website for demoSample pptx for embedding into website for demo
Sample pptx for embedding into website for demoHarshalMandlekar2
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .Alan Dix
 
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESSALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESmohitsingh558521
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embeddingZilliz
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxLoriGlavin3
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfMounikaPolabathina
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningLars Bell
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxLoriGlavin3
 
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxLoriGlavin3
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxLoriGlavin3
 

Recently uploaded (20)

Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
Sample pptx for embedding into website for demo
Sample pptx for embedding into website for demoSample pptx for embedding into website for demo
Sample pptx for embedding into website for demo
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .
 
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESSALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embedding
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdf
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine Tuning
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
 
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
 

HTTP and 5G (fixed1)

  • 1. HTTP HTTP 5G html5 conference 2018 on 2018.11.25 WebDINO Japan - Tomoya ASAI with Softbank - Yasuhiro NAGAI
  • 2. about:me Tomoya ASAI - dynamis webdino.org CTO Tech Speaker dynamis @ Community Twitter: @dynamitter facebook.com/dynamis I LOVE Firefox = Red Panda = Petit Panda = Lesser Panda2 @
  • 3. about: WebDINO Japan Web, Browser, Open ( : ) (Chromium, Firefox ) ( : Gecko ) Web & Open Web IoT 2017 : Mozilla Japan WebDINO Japan https://www.webdino.org/3
  • 6. : Web 2014/10 - HTML5 2015/02 - HTTP/2 (RFC 7540, SPDY) 2015/10 - CSS snapshot 2015 2016/06 - ECMAScript 2016 2016/09 - TCP BBR Linux 2018/08 - TLS 1.3 (RFC 8446) 2019/xx - HTTP/3 (RFC TBD) 6
  • 7. : HTTP over QUIC HTTP/3 IETF 103 (2018/11) QUIC WG HTTPbis WG 
 HTTPbis WG 2018/11 Chrome gQUIC IETF QUIC HTTP/3 Litespeed Facebook : https://mailarchive.ietf.org/arch/msg/quic/RLRs4nB1lwFCZ_7k0iuz0ZBa35s7
  • 9. : 1. × Minify Gzip Brotli (2 ) HTTP/2 QUIC 2. × TLS1.3 QUIC 0-RTT ほ BBR 駄 駄9
  • 10. Web 201x HTTP/3 HTTP/2 + BBR #html5conf #html5j_h
  • 12. Softbank WebDINO 5G x IoT Studio WebDINO Japan 5G ( )
  • 13. Softbank & WebDINO Japan #html5conf #html5j_h 5G
  • 14.
  • 17.
  • 18.
  • 19.
  • 20.
  • 21.
  • 22.
  • 24.
  • 25. 0
  • 26. ? ?
  • 28. 1 1 00 GC E C E N N 5 ( )( -)
  • 33. F e C M tr n E U 2 / 2/ P tr n e d i r I g g BG P r A 0
  • 34.
  • 36. HTTP/1.1 + TLS/1.2 HTTP/1.1 HTTP (HOL) (RTT )
 TLS 1.2 2-RTT (false start 1-RTT) ... TLS/1.2 CRIME ... :http://bit.ly/1gqR7WN (https://www.youtube.com/watch?v=hQZ-0mXFmk8)36 TCP 3-way 
 1~3 RTT
 (RTT = 100ms )
  • 37. HTTP 1.1 TCP 1 1 CSS JS 6 Softbank37
  • 38. TLS 1.2 (full handshake) RTT (Round Trip Time) = 2-RTT TLS False Start 1-RTT 
 (Finished Application Data ) HTTP Application Data 1-2 session id Hello 1-RTT Application Data 38 clientHello serverHello
 ServerCertificate
 (ServerKeyExchange)
 (CertificateRequest)
 ServerHelloDone (ClientCertificate)
 ClientKeyExchange
 (CertificateVerify)
 ChangeCipherSpec
 Finished
 (Application Data) ChangeCipherSpec Finished Application Data ( )
  • 40. TCP TCP TCP ACK CWND ( ) TCP N 1/N TCP (1 ) : https://csperkins.org/research/tcp-hollywood/2016-05-19-networking/40
  • 41. HTTP/1.1 HTTP/2 TCP HTTP TCP 1 TCP HPACK (HTTP ) ( ) Google SPDY HTTP/241 H2 H2 HTTP/1.1 TCP 
 HTTP/2 TCP
  • 42. TLS 1.3 : 0-RTT ( 1-RTT) (TLS 1.2 1 RTT ) ( ) TCP 42
  • 43. TLS 1.3 (full handshake) Full Handshake 1-RTT PSK Application Data clientHello 0-RTT 0-RTT Hello 43 clientHello (KeyShare) serverHello (KeyShare)
 EncryptedExtensions
 (CertificateRequest)
 (Certificate)
 (CertificateVerify)
 Finished
 Application Data (Certificate)
 (CertificateVerify)
 Finished
 Application Data Application Data ( )
  • 44. 0-RTT Hello Application Data (PSK) PSK 
 (PSK Hello ) (TLS ) POST44 clientHello (Application Data) serverHello
 EncryptedExtensions
 Finished
 Application Data EndOfEarlyData
 Finished
 Application Data Application Data ( )
  • 45. TCP : BDP ( x RTT) CWND RTT (Slow Start) 45 25 Deliveryrate BDP BDP+BufSize RTT Optimal: max BW and min RTT (Kleinrock) amount in flight Optimal operating point 23 Deliveryrate BDP BDP+BufSize RTT Loss based CC (CUBIC / Reno) amount in flight Loss based congestion control in deep buffers BDP = (max BW) * (min RTT) 26 Deliveryrate BDP BDP+BufSize RTT amount in flight Est min RTT = windowed min of RTT samples Est max BW = windowed max of BW samples Estimating optimal point (max BW, min RTT)
  • 48. : BBR RTT RTT RTT 駄 Google google.com 2% YouTube 13% YouTube RTT 32% Loss 1% 2% https://queue.acm.org/detail.cfm?id=302218448
  • 49. BBR ( BW RTT ) https://datatracker.ietf.org/meeting/101/materials/slides-101-iccrg-an-update-on-bbr-work-at-google-0049 BDP = (max BW) * (min RTT) 26 Deliveryrate BDP BDP+BufSize RTT amount in flight Est min RTT = windowed min of RTT samples Est max BW = windowed max of BW samples Estimating optimal point (max BW, min RTT)
  • 51. QUIC HTTP + TLS over TCP UDP HTTP/2 ( ) HTTP/2 + TLS1.2 + TCP HOL 0-RTT ( TLS 1.3 ) Multipath (5G + LTE + WiFi ) http://www.davidromerotrejo.com/2016/09/moving-web-from-tcp-to-udp.html?m=151 
 TLS 1.3
  • 52. HTTP/2 TCP HOL : http://bit.ly/1gqR7WN (https://www.youtube.com/watch?v=hQZ-0mXFmk8)52 H2 H2 H2 H2 HTTP/2 TCP 
 
 ( ) QUIC UDP 
 
 ( )
  • 53. HTTP/3 ( HTTP over QUIC) Google QUIC IETF QUIC Google HTTP + TLS UDP gQUIC IETF QUIC (iQUIC) IETF iQUIC QUIC Transport HTTP over QUIC (hq) QPACK ( ) / HTTP over QUIC = hq HTTP/3 IETF 103 hq HTTP/3 Transport QUIC https://daniel.haxx.se/blog/2018/11/11/http-3/53
  • 55. HTTP/3 + QUIC Transport HTTP/2 + TCP UDP TCP 
 ( ) LTE, 5G, WiFi IP ID 
 ( / IP+Port ) 255 range Negative ACK (NACK) HTTP/2 TCP 55
  • 56. QUIC Transport MTU Google MTU = 1350,1370 (IPv6,v4) Path MTU MTU MTU HTTP/2 駄 MTU 1450 MTU (MEC on 5G ) : DDoS 1200 PMTU 1280 (IPv6 PMTU) 56
  • 57. HTTP/3, QUIC Server: Google Frontend (GCP) or LiteSpeed Apach, Nginx QUIC Client: Chrome QUIC alt-svc HTTP/2 ( ) QUIC --origin-port-to-force-quic-on QUIC57
  • 58. Google Quic Google Front End ( ) Google QUIC GCP LiteSpeed ( ) QUIC (2017/06 ) Caddy GO LTE 駄 issue 5G 駄 Satellite (by LINE) Google QUIC : Chrome IETF QUIC Server58
  • 59. : Google OSS QUIC QUIC quic_server, quic_client toy server. (HTTP ) FYI: Chrome 2012 10 659
  • 60. LiteSpeed HTTP/2 OSS QUIC Google Frontend HTTP/2 QUIC NIC (by LiteSpeed ) Google Web QUIC60
  • 61. 5G x IoT Studio
  • 64. SYSTEM WORKS R8151 ( ) 64 CPU Intel Core i7-8700 (6core/3.2GHz) Memory Server: 16GB (DDR4-2666)
 Client: 32GB (DDR4-2666) HDD 256GB (NVMe SSD) NIC Intel X550-T1, PCIe3.0 (10Gbps) OS Linux (Ubuntu16.04LTS) 5G端末 5G基地局 シールドルーム 4.7GHz 5Gコア (有線計測時のみ) Ixia Network Emulator II サーバマシン x 2 クライアント x 2 MTU=140010Gbps
  • 65. Nginx 1.10.3 (HTTP/1.1, HTTP/2 ) Lite Speed Enterprise 5.3 RC (QUIC ) Chrome 68.0.3440.106 TCP BBR Kernel Update OS Ubuntu 16.04LTS Let's Encrypt HTTPS Let's Deprecate HTTP! Chrome65
  • 66. Chrome + Puppeteer ( ) JavaScript fetch Resource Timing API (5μs ) DL ( ) ping RTT (0.02 ) sar NIC/CPU/Memory sar tcpdump ( ) tcpdump 1 40GB66
  • 67. HTTP/1.1 (cubic, bbr), HTTP/2 (cubic, bbr), QUIC 5 駄 5G 駄 駄 (DL ) fetch 4 x 5 = 20 467 fetch single 5GB movie 340MB MP4 (16 files)
 BigBuckBunny 1080p 60fps DL image 62KB 22MB PNG (712 files) BigBuckBunny movie chunk 100 chunk 1 2MB (139 files x 10) YouTube BBB ( 10 )
  • 68. (ping, sar) Client : ping i 0.02 $server > $ lename RTT 0.02 chart.js ( ) Server/Client : sar A o $ lename sadf ( ) 1 : CPU Memory NIC (TCP, UDP ) block device I/O Transfer 68
  • 69. 5G RTT ( ) http/1.1, cubic, movie (9/22)69 RTT (50ms ) RTT 
 
 RTT RTT 10ms
  • 71. 5G
  • 72. ( ) 5G 駄 ( ) 5G 5G 5G ( ) MEC 駄 5G 駄 72
  • 73. 5G CUBIC BBR HTTP/2 TCP 1 QUIC73 HTTP/1.1 (CUBIC) HTTP/2 (CUBIC) HTTP/1.1 (BBR) HTTP/2 (BBR) QUIC single movie image chunk : QUIC 
 
 ( )
  • 74. 5G CUBIC BBR HTTP/2 TCP 1 QUIC74 HTTP/1.1 (CUBIC) HTTP/2 (CUBIC) HTTP/1.1 (BBR) HTTP/2 (BBR) QUIC single movie image chunk : QUIC 
 
 ( ) TCP BBR TCP CUBIC vs BBR 6 x TCP CUBIC vs BBR
  • 75. (HTTP/1.1) movie, image TCP BBR CUBIC ( ) : 9/5 ( )75 ( , 9/5) (Mbps) http1.1, cubic, single 476, 697, 694, 746 653 http1.1, cubic, movie 969, 948, 878, 928 931 http1.1, cubic, image 1030, 1010, 902, 992 984 http1.1, cubic, chunk 864, 875, 885, 883 877 http1.1, bbr, single 555, 609, 578, 604 587 http1.1, bbr, movie 890, 866, 834, 867 864 http1.1, bbr, image 794, 790, 788, 634 751 http1.1, bbr, chunk 735, 818, 746, 767 767 ( , 8/23) (Gbps) http1.1, cubic, single 3.17, 3.18, 3.14, 3.12 3.15 http1.1, cubic, movie 2.73, 2.77, 2.72, 2.76 2.74 http1.1, cubic, image 2.00, 1.86, 1.86, 2.00 1.93 http1.1, cubic, chunk 1.30, 1.27, 1.28, 1.28 1.28 http1.1, bbr, single 3.13, 3.24, 3.15, 3.13 3.18 http1.1, bbr, movie 2.82, 2.90, 2.88, 2.88 2.87 http1.1, bbr, image 2.02, 1.86, 1.98, 1.95 1.95 http1.1, bbr, chunk 1.30, 1.27, 1.28, 1.28 1.28
  • 76. (HTTP/2) HTTP/1.1 vs HTTP/2 CUBIC vs BBR HTTP/2 TCP 1 : 9/5 ( )76 ( , 8/23) (Gbps) http2, cubic, single 3.22, 3.11, 3.22, 3.20 3.19 http2, cubic, movie 2.83, 2.74, 2.80, 2.81 2.79 http2, cubic, image 1.93, 1.68, 1.91, 1.65 1.79 http2, cubic, chunk 1.35, 1.27, 1.34, 1.35 1.33 http2, bbr, single 3.22, 3.11, 3.22, 3.20 3.19 http2, bbr, movie 2.83, 2.74, 2.80, 2.81 2.79 http2, bbr, image 1.93, 1.68, 1.91, 1.65 1.79 http2, bbr, chunk 1.35, 1.27, 1.34, 1.35 1.33 ( , 9/5) (Mbps) http2, cubic, single 700, 896, 816, 959 823 http2, cubic, movie 826, 901, 699, 676 776 http2, cubic, image 740, 704, 560, 725 682 http2, cubic, chunk 875, 881, 878, 880 879 http2, bbr, single 700, 896, 816, 959 843 http2, bbr, movie 826, 901, 699, 676 776 http2, bbr, image 740, 704, 560, 725 682 http2, bbr, chunk 875, 881, 878, 880 879
  • 77. (QUIC) QUIC movie HTTP/1.1 HTTP/2 QUIC Chrome ( ) Disk I/O ( ) QUIC, single 駄 n/a77 ( , 8/23) (Gbps) quic, single 3.22, 3.19, 3.22, 3.24 3.22 quic, movie 3.23, 3.20, 3.18, 3.14 3.19 quic, image 2.10, 1.89, 2.19, 2.15 2.08 quic, chunk 1.35, 1.28, 1.35, 1.32 1.32 ( , 9/21) (Mbps) quic, single n/a n/a quic, movie 374, 365, 395, 378 378 quic, image 492, 472, 488, 451 476 quic, chunk 495, 504, 540, 531 518
  • 79. 5G 1. a. 5G OR b. RTT 2. HTTP, TCP HOL QUIC note: NEXT TODO: 駄79
  • 80. 5G HTTP/2 TCP LOH HTTP/1.1 TCP N ( 1/N ) (HTTP/1.1 ) TCP HTTP + TCP QUIC TCP LOH QUIC QUIC 5G RTT HTTP/280 YES. HTTP/2
 is slow on 5G.
  • 81. 5G BBR CUBIC 5G 駄 
 0.1% BBR RTT 5G 駄 (TCP/IP ) RTT BBR RTT note: 50ping/sec81 YES. BBR
 is slow on 5G.
  • 82. 5G RTT http/2, cubic, movie RTT82 
 RTT 
 RTT 10ms
  • 83. HTTP/1.1, CUBIC, movie RTT CUBIC RTT 50ms RTT83 Average Variance Standard Deviation Max Min 18.1362 514.634 22.68553986 425 2.35 Mbps 1 935 2 928 3 928 4 878 50ms
  • 84. HTTP/1.1, BBR, Movie RTT BBR RTT 50ms 10ms CUBIC84 Average Variance Standard Deviation Max Min 10.9638 88.354 9.399678951 81.3 2.21 Mbps 1 559 2 435 3 510 4 556 50ms 10ms
  • 85. : TCP (CUBIC) iperf 60 ( ) 1.8Gbps 3 775Mbps 85 180s 1810Mbps

  • 86. : TCP (BBR) iperf CUBIC 500Mbps 400Mbps RTT86
  • 87. 5G CUBIC CUBIC BBR 4 60 80% CUBIC note: BBR 駄 CUBIC 駄 note: 50ping/sec87 NO. CUBIC
 CAN be slow. ( , 9/20) 1 2 3 4 http2, cubic, movie 634Mbps 686Mbps 905Mbps 500Mbps http2, cubic, chunk 240Mbps 549Mbps 264Mbps 339Mbps http2, bbr, movie 291Mbps 301Mbps 300Mbps 280Mbps http2, bbr, chunk 284Mbps 321Mbps 308Mbps 326Mbps
  • 88. 5G QUIC QUIC 5G RTT RTT RTT 20-30ms 50ms RTT 5G ( ) NEXT TODO:88 QUIC CAN be fastest on 5G.
  • 89. 1 x Chrome, HTTP/2, quic, movie 364 393Mbps 750Mbps (5G 1/3 ) 89 1 (374Mbps) 2 (364Mbps) 3 (393Mbps) 4 (378Mbps)
  • 90. 2 x Chrome, HTTP/2, quic, movie 449 650Mbps 2 2.1Gbps ( 5G ) 90 1 (590/579Mbps ) 2 (590/579Mbps ) 3 (449/461Mbps ) 4 
 (650/618Mbps )
  • 91. 4 x Chrome,HTTP/2,QUIC,Movie 4 2.3 Gbps 91 1 (286/279/
 279/273) 2 (397/325/
 371/328 3 (175/264/
 194/268 4 (317/269/
 270/266)
  • 93.
  • 94. RTT RTT 2G ( 1 40GB) RTT ( ) RTT (RTT ) CUBIC, BBR 縮 縮 TODO NEXT: 縮94
  • 95. TCP RST TCP RST (reset) TCP ( 縮 ) Web 
 HTTP/2, QUIC fetch 100 Wireshark rst95
  • 98.
  • 99. HTTP (TCP) CUBIC BBR 5G CUBIC BBR CUBIC BBR HTTP TCP HTTP/1.1 HTTP/2 QUIC ( ) MEC 99
  • 100. 5G RTT RTT : HTTP/2 BBR QUIC RTT fetch catch resolve QUIC Web 100
  • 102. 5G x IoT Studio 102 https://tm.softbank.jp/form/contact/5g/index.php 5G×IoT Studio に関するお問い合わせ
  • 103. 5G x IoT Studio 103 https://tm.softbank.jp/form/contact/5g/index.php 5G×IoT Studio に関するお問い合わせ
  • 104. 5G x IoT Studio 104 https://tm.softbank.jp/form/contact/5g/index.php 5G×IoT Studio に関するお問い合わせ
  • 105. Thank You! Any Questions? Feel free to contact me: dynamis webdino.org
 @dynamitter, facebook.com/dynamis Slide Upload: slideshare.net/dynamis by @4687koSourijun @
  • 106. References - TCP TCP/IP https://www.amazon.co.jp/dp/4894713209 Internet Week 99 TCP https://www.nic.ad.jp/ja/materials/iw/1999/notes/C3.PDF TCP http://www.ieice-hbkb.org/ les/03/03gun_04hen_01.pdf http://sacsis.hpcc.jp/2009/SACSIS2009_TCP.pdf CUBIC for Fast Long-Distance Networks RFC 8312 https://tools.ietf.org/html/rfc8312 CUBIC: a new TCP-friendly high-speed TCP variant https://dl.acm.org/citation.cfm? id=1400105 106
  • 107. References - BBR BBR BBR: Congestion-Based Congestion Control https://queue.acm.org/ detail.cfm?id=3022184 BBR for Linux Kernel BBR congestion control https://lwn.net/Articles/701165/ patch https://git.kernel.org/pub/scm/linux/kernel/git/davem/net- next.git/commit/?id=0f8782ea14974ce992618b55f0c041ef43ed0b78 Linux Kernel 4.9 https://kernelnewbies.org/Linux_4.9 107
  • 108. References - Google QUIC Chromium QUIC https://www.chromium.org/quic https://www.chromium.org/quic/playing-with-quic Design Doc https://docs.google.com/document/d/ 1RNHkx_VvKWyWg6Lr8SZ-saqsQx7rFV-ev2jRFUoVD34/edit?pli=1# 108
  • 109. References - IETF QUIC IETF QUIC WG https://quicwg.org/ GitHub - WG materials https://github.com/quicwg/wg-materials IETF 103 Meeting https://datatracker.ietf.org/meeting/103/materials https://datatracker.ietf.org/meeting/103/session/quic HTTP/3 https://daniel.haxx.se/blog/2018/11/11/http-3/ QUIC RFC Drafts https://datatracker.ietf.org/wg/quic/documents/ https://github.com/ ano-yuki/my-quic-spec-translation 109
  • 110. Reference - QUIC ASnoKaze Blog - QUIC https://asnokaze.hatenablog.com/ archive/category/QUIC : http://www.soumu.go.jp/ main_sosiki/joho_tsusin/hyojun/02tsushin04_03000123.html 110