(NET404) Making Every Packet Count

© 2015, Amazon Web Services, Inc. or its Affiliates. All rights reserved.

Kevin Miller, Sr. Manager, EC2 Networking

October 2015

NET404

Making Every Packet Count

What to Expect from this Session

Tuning TCP

on Linux

TCP Performance Application

What to Expect from this Session

Application

Watch us

increase network

performance

137%

TCP

TCP

• Transmission Control Protocol

• Underlies SSH, HTTP, *SQL, SMTP

• Stream delivery, flow control

TCP

Jack Jill

Jack Jill

Limiting in-flight data

Jack Jill

Receive

Window

Receive

Window

Congestion

Window

Congestion

Window

Round trip time

Bandwidth delay product

Jack Jill

2 ms round-trip time

Bandwidth delay product

Jack Jill

100 ms round-trip time

Receive window

Receiver controlled, signaled to sender

Congestion window

Jack Jill

Receive

Window

Receive

Window

Congestion

Window

Congestion

Window

Round trip time

Congestion window

• Sender controlled

• Window is managed by the congestion control algorithm

• Inputs – varies by algorithm

Initial congestion window

$ ip route list

default via 10.16.16.1 dev eth0

10.16.16.0/24 dev eth0 proto kernel scope link

169.254.169.254 dev eth0 scope link

1448 1448 1448 = 4344 bytes

Initial congestion window

# ip route change 10.16.16.0/24 dev eth0 \

proto kernel scope link initcwnd 16

$ ip route list



initcwnd 16


1448 1448 1448 1448[ + 12 ] = 23168 bytes

0

20

40

60

80

100

0% 2% 4% 6% 8% 10%

Loss Rate

Impact of loss on TCP throughput

Loss is visible as TCP retransmissions

$ netstat -s | grep retransmit

58496 segments retransmitted

52788 fast retransmits

135 forward retransmits

3659 retransmits in slow start

392 SACK retransmits failed

Socket level diagnostic

$ ss -ite

State Recv-Q Send-Q Local Address:Port Peer Address:Port

ESTAB 0 3829960 10.16.16.18:https 10.16.16.75:52008

timer:(on,012ms,0) uid:498 ino:7116021 sk:0001c286 <->

ts sack cubic wscale:7,7 rto:204 rtt:1.423/0.14 ato:40

mss:1448 cwnd:138 ssthresh:80 send 1123.4Mbps unacked:138

retrans:0/11737 rcv_space:26847

TCP State


$ ss -ite


ESTAB 0 3829960 10.16.16.18:https 10.16.16.75:52008





Bytes queued for

transmission


$ ss -ite


ESTAB 0 3829960 10.16.16.18:https 10.16.16.75:52008





Congestion

control algorithm


$ ss -ite


ESTAB 0 3829960 10.16.16.18:https 10.16.16.75:52008





Retransmission

timeout


$ ss -ite


ESTAB 0 3829960 10.16.16.18:https 10.16.16.75:52008





Congestion

window


$ ss -ite


ESTAB 0 3829960 10.16.16.18:https 10.16.16.75:52008





Retransmissions

Monitoring retransmissions in real time

• Observable using Linux kernel tracing

# tcpretrans

TIME PID LADDR:LPORT -- RADDR:RPORT STATE

03:31:07 106588 10.16.16.18:443 R> 10.16.16.75:52291 ESTABLISHED

https://github.com/brendangregg/perf-tools/

Congestion control algorithm

Jack Jill

Congestion control algorithms in Linux

• New Reno: Pre-2.6.8

• BIC: 2.6.8 – 2.6.18

• CUBIC: 2.6.19+

• Pluggable architecture

• Other algorithms often available

• Vegas, Illinois, Westwood, Highspeed, Scalable

Tuning congestion control algorithm

$ sysctl net.ipv4.tcp_available_congestion_control

net.ipv4.tcp_available_congestion_control = cubic reno

$ find /lib/modules -name tcp_*

[…]

# modprobe tcp_illinois

$ sysctl net.ipv4.tcp_available_congestion_control

net.ipv4.tcp_available_congestion_control = cubic reno illinois

Tuning congestion control algorithm

# sysctl net.ipv4.tcp_congestion_control=illinois

net.ipv4.tcp_congestion_control = illinois

# echo “net.ipv4.tcp_congestion_control = illinois” >

/etc/sysctl.d/01-tcp.conf

[Restart network processes]

Retransmission timer

• Input to when the congestion control

algorithm considers a packet lost

• Too low: spurious retransmission; congestion control can

over-react and be slow to re-open the congestion

window

• Too high: increased latency while algorithm determines a

packet is lost and retransmits

Tuning retransmission timer minimum

• Default minimum: 200ms

# ip route list




Route to other

instances in

our subnet

(same AZ)

Tuning retransmission timer minimum

# ip route list




# ip route change 10.16.16.0/24 dev eth0 proto kernel \

scope link rto_min 10ms

# ip route list


10.16.16.0/24 dev eth0 proto kernel scope link rto_min \

lock 10ms


Queueing along the network path

Jack Jill

Queueing along the network path

• Intermediate routers along a path have

interface buffers

• High load leads to more packets in buffer

• Latency increases due to queue time

• Can trigger retransmission timeouts

Active queue management

$ tc qdisc list

qdisc mq 0: dev eth0 root

qdisc pfifo_fast 0: dev eth0 parent :1 bands 3 […]

qdisc pfifo_fast 0: dev eth0 parent :2 bands 3 […]

# tc qdisc add dev eth0 root fq_codel

qdisc fq_codel 8006: dev eth0 root refcnt 9 limit 10240p

flows 1024 quantum 9015 target 5.0ms interval 100.0ms ecn

http://www.bufferbloat.net/projects/codel/wiki

Amazon EC2 enhanced networking

Jack Jill

Amazon EC2 enhanced networking

• Higher I/O (packets per second) performance

• Lower CPU utilization

• Lower inter-instance latency

• Low network jitter

• Instance families: M4, C4, C3, R3, I2, D2 (w/ HVM)

• Drivers built into Windows, Amazon Linux AMIs

• Questions? re:Invent 2014 – SDD419

Maximum transmission unit

3.47% overhead vs. 0.58% overhead

Improvement seen among instances in your VPC

1448B

Payload

8949B Payload

Tuning maximum transmission unit

# ip link list

2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 9001 qdisc

mq state UP mode DEFAULT group default qlen 1000

link/ether 06:f1:b7:e1:3b:e7

# ip route list




Tuning maximum transmission unit

# ip route change default via 10.16.16.1 dev eth0 mtu 1500

# ip route list

default via 10.16.16.1 dev eth0 mtu 1500



Applying our new knowledge

Test setup

• m4.10xlarge instances – Jack and Jill

• Amazon Linux 2015.09 (Kernel 4.1.7-15.23.amzn1)

• Web Server: nginx 1.8.0

• Client: ApacheBench 2.3

• TLSv1,ECDHE-RSA-AES256-SHA,2048,256

• Transferring uncompressible data (random bits)

• Origin data stored in tmpfs (RAM based; no server disk I/O)

• Data discarded once retrieved (no client disk I/O)

Example Apache Bench output

[ … ]

Concurrency Level: 100

Time taken for tests: 59.404 seconds

Complete requests: 10000

Failed requests: 0

Write errors: 0

Total transferred: 104900000 bytes

HTML transferred: 102400000 bytes

Requests per second: 168.34 [#/sec] (mean)

Time per request: 594.038 [ms] (mean)

Time per request: 5.940 [ms] (mean, across all

concurrent requests)

Transfer rate: 1724.49 [Kbytes/sec] received

[ … ]

Application 1

HTTPS with intermediate network loss

Jack Jill

0.2%

loss

Test setup

• 1 test server instance, 1 test client instance

• 80ms RTT

• 160 parallel clients retrieving a 100 MB object 5 times$ ab -n 100 -c 20 https://server/100m [* 8]

• Simulated packet loss# tc qdisc add dev eth0 root netem loss 0.2%

Goal: Minimize throughput impact with 0.2% loss

https://server/100m

Results – application 1

Test Bandwidth Mean Time

All defaults – no loss 4163 Mbps 27.9s

All defaults – 0.2% simulated loss 1469 Mbps 71.8s

Increased initial congestion window w/ loss 1328 Mbps 80.6s

Doubled server-side TCP buffers w/ loss 1366 Mbps 78.6s

Illinois congestion control algorithm w/ loss 3486 Mbps 28.2s

137% increase

in performance!

Application 2

Bulk data transfer; high RTT path

Jack Jill

Test setup


• 80 ms RTT

• 8 parallel clients retrieving a 1 GB object 2 times$ ab -n 2 -c 1 https://server/1g [* 8]

Goal: Maximize the throughput / minimize transfer time



All defaults 2164 Mbps 30.4s

Doubled TCP buffers on server end 1780 Mbps 37.4s

Doubled TCP buffers on client end 2462 Mbps 27.6s

Active queue management on server 2249 Mbps 29.3s

Client buffers + AQM 2730 Mbps 24.5s

Illinois CC + client buffers + AQM 2847 Mbps 23.0s

Illinois CC + server & client buffers + AQM 2865 Mbps 23.5s

32% increase in

performance!

Application 3

Bulk data transfer; low RTT path

Jack Jill

Test setup


• 1.2 ms RTT

• 8 parallel clients retrieving a 10GB object 2 times

$ ab -n 2 -c 1 https://server/100m [* 8]

• Start at Internet default MTU, then increase

Goal: Maximize the throughput / minimize transfer time

https://server/100m

Results


All defaults + 1500B MTU 8866 Mbps 74.0s

9001B MTU 9316 Mbps 70.4s

Active Queue Management (+MTU) 9316 Mbps 70.4s

5% increase

Application 4

High transaction rate HTTP service

Jack Jill

Test setup


• 80 ms RTT

• HTTP, not HTTPS

• 6400 parallel clients retrieving a 10k object 100 times

$ ab -n 20000 -c 200 http://server/10k [* 32]

Goal: Minimize latency

https://server/



All defaults 2580 Mbps 195.3ms

Initial congestion window – 16 packets 2691 Mbps 189.2ms

Illinois CC + initial congestion window 2649 Mbps 186.2ms

4.6% decrease

Take-aways

Take-aways

• The network doesn’t have to be a black box – Linux tools

can be used to interrogate and understand

• Simple tweaks to settings can dramatically increase

performance – test, measure, change

• Understand what your application needs from the

network, and tune accordingly

Remember to complete

your evaluations!

Thank you!

(NET404) Making Every Packet Count

Technology