$30 off During Our Annual Pro Sale. View Details »
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Scaling CANDDi
Search
coldclimate
July 29, 2013
Technology
0
290
Scaling CANDDi
for
http://www.supermondays.org/
coldclimate
July 29, 2013
Tweet
Share
More Decks by coldclimate
See All by coldclimate
You don't scale like servers scale
coldclimate
0
140
Quick and dirty load testing with Vegeta
coldclimate
3
4.2k
Continuously deploying https served statically compiled sites to S3 with canonical domains
coldclimate
0
73
Scripting creating AWS based servers
coldclimate
0
310
refactoring
coldclimate
1
130
Other Decks in Technology
See All in Technology
AI 時代のデータ戦略
na0
8
3.3k
MAP-7thplaceSolution
yukichi0403
2
250
法人支出管理領域におけるソフトウェアアーキテクチャに基づいたテスト戦略の実践
ogugu9
1
130
Bakuraku Engineering Team Deck
layerx
PRO
11
5.8k
AIにおける自由の追求
shujisado
3
470
ブロックテーマとこれからの WordPress サイト制作 / Toyama WordPress Meetup Vol.81
torounit
0
310
HIG学習用スライド
yuukiw00w
0
110
オープンデータの内製化から分かったGISデータを巡る行政の課題
naokim84
2
1.4k
事業部のプロジェクト進行と開発チームの改善の “時間軸" のすり合わせ
konifar
9
3k
タグ付きユニオン型を便利に使うテクニックとその注意点
uhyo
2
650
直接メモリアクセス
koba789
0
120
安いGPUレンタルサービスについて
aratako
1
2.2k
Featured
See All Featured
A Modern Web Designer's Workflow
chriscoyier
697
190k
Building Better People: How to give real-time feedback that sticks.
wjessup
370
20k
The World Runs on Bad Software
bkeepers
PRO
72
12k
Optimising Largest Contentful Paint
csswizardry
37
3.5k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
46
7.8k
jQuery: Nuts, Bolts and Bling
dougneiner
65
8.1k
Building a Scalable Design System with Sketch
lauravandoore
463
34k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
285
14k
Navigating Team Friction
lara
191
16k
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
380
Fireside Chat
paigeccino
41
3.7k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.3k
Transcript
Scaling CANDDi oli wood @coldclimate
history
measure things that matter
back of a fag packet if good enough
have somewhere to test which is not live
use realistic data
ab/siege + ec2 instances
there are no silver bullets
aim for a silver shotgun cartridge
define the scenarios
build a pipeline view
identify symptoms but solve problems
symptoms are what you can see
problems are what you can solve
bad new: the problem is your code
good news: thus you can fix it
do less big things less often
do frequent things much faster
avoid waiting
pull less data
cache the painful things
cache: in memory
cache: redis/memcache
cache: url/browser cache
hunt collisions
use the tools
iostat
sar -P
strace -p
iftop
xdebug + webgrind
statsd
mongotop
mongosniff
tail -100000 mongodb. log | awk -F' ' '{print $NF}'
| grep ms$ | sed 's/ms//g' |sort -n | tail -20 | xargs -I {} grep {} ms$ mongodb.log
and the big gestures
nginx
nodejs
redis
aim: loosely coupled components which are horizontally scalable both on
box and by box
BULLSHIT
aim: fast enough for medium term business needs
aim: not to waste time in a geek circle jerk
result: 10x the throughput
result: 2000 non- trivial inbound events a second
good luck