Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
高度に発達したシステムの異常は神の怒りと見分けがつかない / IPSJ-ONE 2017 y...
Search
Yuuki Tsubouchi (yuuk1)
March 19, 2017
Technology
25k
3
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
高度に発達したシステムの異常は神の怒りと見分けがつかない / IPSJ-ONE 2017 y_uuki
IPSJ-ONE 2017 スライド。
Yuuki Tsubouchi (yuuk1)
March 19, 2017
More Decks by Yuuki Tsubouchi (yuuk1)
See All by Yuuki Tsubouchi (yuuk1)
「アラーティング」の話をしよう— SREconや論文等の最先端とのギャップをみる
yuukit
7
2.1k
SAKURAONE:An Open Ethernet-based AI HPC System And Its Observed Workload Dynamicsin a Single-Tenant LLM Development Environment
yuukit
1
680
AIスーパーコンピュータにおけるLLM学習処理性能の計測と可観測性 / AI Supercomputer LLM Benchmarking and Observability
yuukit
1
1.2k
SREはサイバネティクスの夢をみるか? / Do SREs Dream of Cybernetics?
yuukit
3
850
SREのためのテレメトリー技術の探究 / Telemetry for SRE
yuukit
14
4k
AIスパコン「さくらONE」の オブザーバビリティ / Observability for AI Supercomputer SAKURAONE
yuukit
2
1.6k
AIスパコン「さくらONE」のLLM学習ベンチマークによる性能評価 / SAKURAONE LLM Training Benchmarking
yuukit
2
1.3k
とあるSREの博士「過程」 / A Certain SRE’s Ph.D. Journey
yuukit
11
7.7k
eBPFを用いたAIネットワーク監視システム論文の実装 / eBPF Japan Meetup #4
yuukit
3
1.9k
Other Decks in Technology
See All in Technology
Loop Engineering, beyond prompt, context, and harness engineering
glaforge
0
110
Railsで挑む大量データ永続化 〜600億件を永続化するための設計とボトルネックとの戦い〜
occhi
1
340
FOSS4Gを活用した自治体業務DXの試み
470715
0
150
ゲームのリアルタイム通信から見た QUIC と MoQ
segadevtech
0
120
「事実」を「計測」して、「解釈」する 〜AWS Lambdaのメモリ最適解の見つけ方〜
maimyyym
0
150
実体験から学ぶ分析エージェントの開発と運⽤
recruitengineers
PRO
8
2.3k
無理せず続ける、子育てエンジニアの学び
codmoninc
PRO
0
730
「Docker Desktop不要の時代」は 来たのか?
ueponx
0
660
Post AI時代のリファクタリング実践記 / Refactoring in the post AI era
kaminashi
1
210
OptunaHub: ブラックボックス最適化のためのプラットフォーム
pfn
PRO
0
110
分析の民主化を支えるメタデータ整備の実践
kakehashi
PRO
4
1.3k
二歩目のフロントエンド・ウェブアクセシビリティ
camiha
2
480
Featured
See All Featured
Paper Plane (Part 1)
katiecoart
PRO
2
11k
Fantastic passwords and where to find them - at NoRuKo
philnash
53
4k
How STYLIGHT went responsive
nonsquared
100
6.3k
The Cost Of JavaScript in 2023
addyosmani
55
10k
svc-hook: hooking system calls on ARM64 by binary rewriting
retrage
2
620
We Analyzed 250 Million AI Search Results: Here's What I Found
joshbly
2
2k
Making the Leap to Tech Lead
cromwellryan
135
10k
The Straight Up "How To Draw Better" Workshop
denniskardys
239
140k
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
659
62k
RailsConf 2023
tenderlove
30
1.6k
How to Get Subject Matter Experts Bought In and Actively Contributing to SEO & PR Initiatives.
livdayseo
0
220
Digital Projects Gone Horribly Wrong (And the UX Pros Who Still Save the Day) - Dean Schuster
uxyall
1
3.4k
Transcript
ߴʹൃୡͨ͠ γεςϜͷҟৗ ਆͷౖΓͱ ݟ͚͕͔ͭͳ͍ Πϯλʔωοτͱӡ༻ٕज़ݚڀձਪન גࣜձࣾͯͳ ௶༎थ
શࣗಈ γεςϜ
શࣗಈ γεςϜ
24࣌ؒ 365
ྗ
Infrastructure as Code Ϋϥυʹ͓͚Δαʔ όཧͷݪଇͱϓϥΫ ςΟε Photo by O’reilly Media
/ CC by 3.0 https://www.oreilly.co.jp/books/9784873117966/ https://creativecommons.org/licenses/by/3.0/deed
Kief Morris ஶ ٶԼ ߶ี ༁ ඌ ߴ߂ ༁ ʰInfrastructure
As Code Ϋϥυʹ͓͚ΔαʔόཧͷݪଇͱϓϥΫςΟεʱΑΓ Φʔτϝʔγϣϯπʔϧ͕Ͳ͏ ͍͏݁ՌΛੜΉ͔ʹ͍ͭͯࣗ৴ ͕࣋ͯͳ͍ͨΊɺΦʔτϝʔγϣ ϯπʔϧʹ͖ͤΓʹͳΔͷ ා͔ͬͨɻ 1.3.5 Φʔτϝʔγϣϯڪා
அ
ߴʹൃୡ
ࣗવք
ҟৗ
ະ
ਆͷౖΓ
؍ଌ
ࢹ Monitoring
ϔϞάϩϏϯ ݂ٿ ϔϚτΫϦοτ ന݂ٿ ݂খ൘ ݂ਗ਼ΧϧγϜ .$7 .$) .$)$ ૯ίϨεςϩʔϧ
)%-ίϨεςϩʔϧ -%-ίϨεςϩʔϧ தੑࢷ ۭෲ݂࣌ ऩॖظ݂ѹ ֦ுظ݂ѹ ͨΜͺ͘ જ݂ ૉૉ ΫϨΞνχϯ જ݂ ;55 "45 "-5 Ѝ(51 "-1 ૯ϏϦϧϏϯ ϩϏϦϊʔήϯ ૯ͨΜͺ͘ Ξϧϒϛϯ )#T߅ମ )#T߅ݪ )$7߅ମ Ξϛϥʔθ $31 ϦϚτΠυҼࢠ ݈߁அ
JOUFSGBDFFUIUY#ZUFT pMFTZTUFNYWEBVTFE MPBEBWH DQVVTFS DQVJEMF DQVTUFBM NFNPSZVTFE MJOVYTT4:/3&$7 MJOVY5*.&@8"*5 MJOVY6/$0//
MJOVYTT'*/8"*5 MJOVY$-04&8"*5 MJOVY-*45&/ JOPEFYWEBUPUBM DQVOJDF DQVTZTUFN DQVHVFTU NFNPSZCV⒎FST MJOVY$-04*/( MJOVY-"45"$, MJOVYTT'*/8"*5 NFNPSZGSFF JOUFSGBDFFUISY#ZUFT NFNPSZTXBQ@VTFE MJOVYDPOUFYU@TXJUDIFT MJOVYGPSLT MJOVY6/,08/ MJOVY-*45&/ MJOVYTT4:/4&/5 MJOVYTT&45"# NFNPSZDBDIFE DQVJPXBJU DQVTPGUJSR DQVIBSEJSR NFNPSZTXBQ@UPUBM NFNPSZUPUBM EJTLYWEBSFBET EJTLYWEBXSJUFT pMFTZTUFNYWEBTJ[F JOPEFYWEBGSFF ݈߁அ
σʔλ ϕʔε
ੑೳ VS ͓ۚ
)%% 44% ϝϞϦ
)%% 44% ϝϞϦ ͍ ;ͭ͏ ͍
)%% 44% ϝϞϦ ߴ͍ ;ͭ͏ ͍҆
ݹ͍σʔλ ΄ͱΜͲΞΫηε ͞Εͳ͍ͷͰ ͯ͘Α͍
)%% 44% ϝϞϦ ݹ͍ ৽͍͠ ͍ ͍҆
)%% 44% ϝϞϦ ݹ͍ ৽͍͠ ౷ ߹
DiamonDB https://github.com/yuuki/diamondb
ࢹ͚σʔλϕʔεੈͷதʹͨ͘ ͞Μ͋Δ Facebook͍ͭͬͯ͘Δ ΞΠσΞࣗମݹయత ͔͠͠ɺ ࢹ͚σʔλϕʔεʹద ༻͍ͯ͠Δྫͳ͍
ͯͳͷݱߦσʔλϕʔε ͱൺֱ͠ 100+ഒ ͷσʔλྔͷอ͕࣋ݱ࣮త ͳίετͰՄೳ
࣮ݧ
“PRINCIPLES OF CHAOS ENGINEERING”, http://principlesofchaos.org/ ΑΓ Chaos Engineering is the
discipline of experimenting on a distributed system in order to build confidence in the system’s capability to withstand turbulent conditions in production.
Θ͟ͱ ҟৗΛى͜͢
؍ଌ ࣮ݧ γεςϜ Ϟσϧ
؍ଌͱ࣮ݧʹΑΓ γεςϜಛੑΛ ֶश͠ͳ͕Β ࣗಈ࡞͢ΔγεςϜ
γεςϜཧऀΛ ະͷڪΕ͔Β ղ์͍ͨ͠