Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Bottleneck Analysis - GOTO 2012

Adrian Cockcroft
October 03, 2024
Technology
0
8

Bottleneck Analysis - GOTO 2012

Adrian Cockcroft

October 03, 2024
Tweet

More Decks by Adrian Cockcroft

See All by Adrian Cockcroft
SC03 Sun Microsystems Keynote
adrianco
0
180
HPC Interconnect Technologies in 2004
adrianco
0
64
Microservices Workshop All Topics Deck 2016
adrianco
0
34k
Cloud Native
adrianco
1
450
Patterns for Continuous Delivery, Reactive, High Availability, DevOps & Cloud Native Open Source with NetflixOSS
adrianco
13
3.8k

Other Decks in Technology

See All in Technology
サーバーレスで楽しよう！お気軽に始められる3つのポイント / Have fun with Serverless!
_kensh
2
230
EDRからERM： PFN-SIRTが関わるセキュリティとリスクへの取り組み
pfn
PRO
0
110
NOSTR, réseau social et espace de liberté décentralisé
rlifchitz
0
130
プロダクト開発、インフラ、コーポレート、そしてAIとの共通言語としての Terraform / Terraform as a Common Language for Product Development, Infrastructure, Corporate Engineering, and AI
yuyatakeyama
6
1.6k
BLEAでAWSアカウントのセキュリティレベルを向上させよう
koheiyoshikawa
0
130
カスタムインストラクションでGitHub Copilotをカスタマイズ！
07jp27
6
360
【Λ（らむだ）】アップデート機能振り返りΛ編 / PADjp20250127
lambda
0
120
Japan AWS Jr. Championsがお届けするre:Invent2024のハイライト ～ラスベガスで見てきた景色～
fukuchiiinu
0
1.1k
ObservabilityCON on the Road Tokyoの見どころ
hamadakoji
0
210
Amazon Aurora バージョンアップについて、改めて理解する ～バージョンアップ手法と文字コードへの影響～
smt7174
1
240
Tokyo RubyKaigi 12 - Scaling Ruby at GitHub
jhawthorn
2
210
論文紹介 ”Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG” @GDG Tokyo
shukob
0
270

Featured

See All Featured
ピンチをチャンスに：未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
113
50k
No one is an island. Learnings from fostering a developers community.
thoeni
20
3.1k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
52k
Building Adaptive Systems
keathley
39
2.4k
Raft: Consensus for Rubyists
vanstee
137
6.7k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
29
990
Large-scale JavaScript Application Architecture
addyosmani
510
110k
Automating Front-end Workflow
addyosmani
1367
200k
YesSQL, Process and Tooling at Scale
rocio
171
14k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
49k
For a Future-Friendly Web
brad_frost
176
9.5k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
28
9.2k

Transcript

  1. None
  2. None
  3. None

  4. Bottle delivery data Interval Response Time Throughput 10 3.1 22

    20 1.2 41 30 7.9 32 … … …

  5. Grab some data (using R) beer <- read.csv(url("http://staash.com/beer_operation s.csv")) response

    <- beer[,2] plot(response, type="S",ylab=”response”)

  6. Bottle delivery response over time

  7. Analysis > summary(response) Min. 1st Qu. Median Mean 3rd Qu.

    Max. 1.909 2.550 2.820 3.086 3.214 67.680 > quantile(response,c(0.95,0.99)) 95% 99% 4.149556 6.922115 > sd(response) 1.941328 > mean(response) + 2 * sd(response) 6.968416

  8. chp(throughput,response,q=1.0) (See http://perfcap.blogspot.com/search?q=chp)

  9. None
  10. None
  11. None
  12. None
  13. None
  14. None
  15. None
  16. None
  17. None

  18. Scalability plots generated using appdynamics.com

  19. Well behaved Lock Contention Oscillating, thread shortage Looping autoscaled Bottlenecks

  20. http://perfcap.blogspot.com/search?q=chp @adrianco