Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Varnish: How We Do It
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Matt Robenolt
June 01, 2015
Technology
240
1
Share
Varnish: How We Do It
SF Varnish Meetup
June 1st, 2015
Matt Robenolt
June 01, 2015
More Decks by Matt Robenolt
See All by Matt Robenolt
Everything is broken and I don't know why.
mattrobenolt
0
44
I am bad at my job.
mattrobenolt
0
240
Everything is broken, and I don't know why. Python edition.
mattrobenolt
1
230
Everything is broken, and I don't know why. Python edition.
mattrobenolt
2
630
Everything is broken, and I don't know why.
mattrobenolt
7
1.6k
Cheating Your Way to Webscale
mattrobenolt
13
1.4k
HTTP for Great Good
mattrobenolt
85
200k
Caching is Hard: Varnish @ Disqus
mattrobenolt
52
2.1M
Developing & Deploying "Large" Scale Web Applications
mattrobenolt
25
1.3k
Other Decks in Technology
See All in Technology
Javaコミュニティをもっと楽しむための9箇条
takasyou
0
1.2k
Platform Engineering as a Product: Criteria for Improvement and Multi-Tenant Design
kumorn5s
0
490
「気づいたら仕事が終わっている」バクラクAIエージェント本番運用の裏側 / layerx-bakuraku-aie2026
yuya4
18
9.1k
「速く作る」から「正しく作る」へ ─ 生成AI時代の開発フロー改革の ロードマップと実行 ─
starfish719
0
5.8k
マーケットプレイス版Oracle WebCenter Content For OCI
oracle4engineer
PRO
5
1.8k
オンコールの負荷軽減のためのBits Assistant 活用方法 / How to Use Bits Assistant to Reduce the Workload on On-Call Staff
sms_tech
1
380
先取りMaven4 ~16年ぶりのメジャーアップデート、その進化とは?~
ogiwarat
0
140
実装は速くなった、レビューはどうする? ― 自身のレビューをAIで再現させるサーヴァントエンジニアリングのすゝめ / Implementation got faster. So what about reviews? — An invitation to Servant Engineering: Recreating your own code reviews with AI
nrslib
6
3.1k
Cloud Run のアップデート 触ってみる&紹介
gre212
0
300
ITエンジニアを取り巻く環境とキャリアパス / A career path for Japanese IT engineers
takatama
4
1.8k
生成 AI × MCP で切り拓く次世代 SRE!自律型運用への挑戦と開発者体験の進化
_awache
0
100
「嘘をつくテスト」の失敗例から学ぶ 良いテストコード #frontend_phpcon_do
asumikam
0
160
Featured
See All Featured
GraphQLの誤解/rethinking-graphql
sonatard
75
12k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
38
2.9k
Speed Design
sergeychernyshev
33
1.8k
Between Models and Reality
mayunak
4
320
WENDY [Excerpt]
tessaabrams
11
38k
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
560
Are puppies a ranking factor?
jonoalderson
1
3.5k
sira's awesome portfolio website redesign presentation
elsirapls
0
270
Building a Scalable Design System with Sketch
lauravandoore
463
34k
ラッコキーワード サービス紹介資料
rakko
1
3.5M
Music & Morning Musume
bryan
47
7.2k
Discover your Explorer Soul
emna__ayadi
2
1.1k
Transcript
Varnish: How we do it SF Varnish Meetup June 1st
2015 Matt Robenolt
Hello < me irl
Lead Operations Engineer
First Generation edge (haproxy) shield app (python) Failover
Why this sucked
Duplicate routing logic Complex Caching logic WasteD RAM for failover
Why this sucked
Failover == lose all cache Varnish held cache rules Hard
to add/remove backends Why this sucked
Current Generation edge shield app (python)
Why this is rad
App owns all caching logic Unified request routing Utilize RAM
from all nodes Why this is rad
If-Modified-Since Vary on cookie values Less deploys to Varnish Why
this is rad
60,000 15,000 13,000 Caching funnel edge shield app
edge shield app Onion skin view
edge shield app recv pass fetch hit miss hash synth
fetch deliver error Onion skin view
edge 60,000 req/s
edge Closest to users (geographically) Absorbs most traffic Blocks abuse
60,000 req/s
edge Makes decisions for shield Sort querystrings (boltsort/std) Promote cookies
to headers 60,000 req/s
Cookies. as headers? Why?
Vary: Cookie-sessionid
shield 15,000 req/s
shield Routing to app backends Serve stale content (grace) Do
If-modified-Since 15,000 req/s
shield Parse response cache rules Backend healthchecks Store lots of
content 15,000 req/s
application 13,000 req/s
application Declare response cache rules Respond to If-modified-Since 13,000 req/s
WaiT. 13,000 req/s still?
46% 53% 1% App Response Codes
46% 53% 1% App Response Codes 304 200
miss Hit Hit/update If-Modified-Since Hit/IMS 200 OK 200 OK 304
Not Modified v1 v2
tl;dr 60k req -> 7k at app Every request thru
Varinsh Complex logic written once
tl;dr App has complete control We still <3 haproxy Each
layer worth deep dive
We’re hiring people who hate comptuers. disqus.com/jobs
Check it. HTTP for Great Good speakerdeck.com/mattrobenolt/http-for-great-good Cheating Your Way
to #webscale speakerdeck.com/mattrobenolt/cheating-your-way-to-webscale
Questions? I have answers. ^ github.com/mattrobenolt @mattrobenolt some