Lock in $30 Savings on PRO—Offer Ends Soon! ⏳
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
RDS/Auroraパフォーマンスインサイトを使ってみる
Search
hmatsu47
PRO
January 28, 2021
Technology
0
650
RDS/Auroraパフォーマンスインサイトを使ってみる
JAWS-UG 名古屋 いろんなパフォーマンスを学ぶ 2021/01/28
hmatsu47
PRO
January 28, 2021
Tweet
Share
More Decks by hmatsu47
See All by hmatsu47
Claude 3.5 で Haiku
hmatsu47
PRO
0
9
HeatWave on AWS の PrivateLink インバウンドレプリケーションで Aurora フェイルオーバーに追従する
hmatsu47
PRO
0
8
大吉祥寺.pm の LT で ChatGPT の力を借りて Next.js App Router ベースの投句箱を作って、 Lambda Web Adapter を使って公開した話
hmatsu47
PRO
0
12
ある日突然 DB の性能が 1/2(サイズのインスタンス相当)になった話
hmatsu47
PRO
0
35
pgvectorscale と pgai の話(ざっくり)
hmatsu47
PRO
0
52
pgvector 0.7.0 の新機能と、これから来る(かもしれない)pgvectorscale
hmatsu47
PRO
0
40
大人の社会科見学 ~ NTT 技術史料館に行ってみよう!
hmatsu47
PRO
0
430
pgvector 0.6.0 以降の進化についてざっくり取り上げてみる
hmatsu47
PRO
0
71
Cloudflare Workes からMySQL 系 DB への接続事情(2024/4 現在)
hmatsu47
PRO
0
140
Other Decks in Technology
See All in Technology
PFN Company Deck
pfn
PRO
1
110
バクラクのデータ基盤をBigQueryからSnowflakeへ移管した理由 / The reason for migrating Bakuraku data infrastructure from BigQuery to Snowflake
civitaspo
0
110
大規模トラフィックを支える ゲームバックエンドの課題と構成の変遷 ~安定したゲーム体験を実現するために~
colopl
0
240
GAS × Discord bot × Gemini で作ったさいきょーの情報収集ツール
ysknsid25
1
130
minify の効果を最大限に引き出す TypeScript コードを書く
jsakamoto
2
130
実践/先取り「入門 Kubernetes Validating/Mutating Admission Policy」 / CloudNative Days Winter 2024
pfn
PRO
0
110
もう一度、 事業を支えるシステムに。
leveragestech
5
2.8k
LLMを「速く」「安く」 動かすには / CloudNative Days Winter 2024
pfn
PRO
4
1k
LLMアプリケーションの評価と継続的改善
pharma_x_tech
1
140
リモートだからこそ 懸念だし1on1
jimpei
1
250
RDRAとLLM
kanzaki
4
440
プルリクが全てじゃない!実は喜ばれるOSS貢献の方法8選
tkikuc
12
1.4k
Featured
See All Featured
Reflections from 52 weeks, 52 projects
jeffersonlam
346
20k
Side Projects
sachag
452
42k
Teambox: Starting and Learning
jrom
133
8.8k
Gamification - CAS2011
davidbonilla
80
5k
The World Runs on Bad Software
bkeepers
PRO
65
11k
Thoughts on Productivity
jonyablonski
67
4.3k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
665
120k
Fashionably flexible responsive web design (full day workshop)
malarkey
405
65k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
48k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
44
2.2k
Agile that works and the tools we love
rasmusluckow
327
21k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
365
24k
Transcript
None
https://qiita.com/hmatsu47 ◦ https://qiita.com/hmatsu47/items/ceb75caf46e3c761095d ◦ ◦ https://booth.pm/ja/items/2524481 2
• • ◦ ▪ ◦ ▪ 3
• ◦ https://docs.aws.amazon.com/ja_jp/AmazonRDS/latest/AuroraUserGuide/USER_ PerfInsights.Overview.html • ◦ • ◦ 4
5
6
• • ◦ ◦ ▪ ▪ 7
8
• ◦ https://docs.aws.amazon.com/ja_jp/AmazonRDS/latest/AuroraUserGuide /AuroraMySQL.Reference.html#AuroraMySQL.Reference.Waitevents • ◦ https://docs.aws.amazon.com/ja_jp/AmazonRDS/latest/AuroraUserGuide /AuroraPostgreSQL.Reference.html#AuroraPostgreSQL.Reference.Waite vents 9
• ◦ ▪ https://dev.mysql.com/doc/refman/5.7/en/wait-summary-tables.html ▪ https://dev.mysql.com/doc/refman/5.7/en/performance-schema-wait-tables.html ◦ ▪ https://dev.mysql.com/doc/refman/5.6/ja/wait-summary-tables.html ▪
https://dev.mysql.com/doc/refman/5.6/ja/performance-schema-wait-tables.html 10
• ◦ ▪ https://www.postgresql.jp/document/12/html/monitoring-stats.html#MONITORING-STAT S-VIEWS-TABLE ◦ ▪ https://www.postgresql.jp/document/12/html/monitoring-stats.html#WAIT-EVENT-TABLE 11
• ◦ mysqlslap --auto-generate-sql --auto-generate-sql-guid-primary --engine=innodb --number-int-cols=20 --number-char-cols=20 --concurrency=100 --auto-generate-sql-write-number=2500
--auto-generate-sql-execute-number=5000 --auto-generate-sql-load-type=【タイプ】 -u admin -h 【エンドポイント】 -p ◦ ▪ ◦ 12
• ◦ pgbench -i -s 1000 -U postgres -h 【エンドポイント】
-d pgbench ◦ pgbench -N -r -c 10 -j 10 -T 300 -U postgres -h 【エンドポイント】 pgbench ◦ 13
• ◦ ▪ • ◦ https://docs.aws.amazon.com/ja_jp/AmazonRDS/latest/AuroraUserGuide/USER_ PerfInsights.API.html 14
• [ { "Metric": "db.load.avg", "GroupBy": { "Group": "db.wait_event", "Limit":
10 } } ] • aws pi get-resource-metrics \ > --service-type RDS \ > --identifier 【DBリソースID】 \ > --start-time 2021-01-24T06:10:00Z \ > --end-time 2021-01-24T06:11:00Z \ > --period-in-seconds 60 \ > --metric-queries file://query.json 15
{ "Identifier": "db-S7UPJNXAX6J7ZJWZXFUBTODYRI", "AlignedStartTime": 1611468600.0, "MetricList": [ { "Key": {
"Metric": "db.load.avg" }, "DataPoints": [ { "Timestamp": 1611468660.0, "Value": 58.6 } ] }, 16
17 { "Key": { "Metric": "db.load.avg", "Dimensions": { "db.wait_event.type": "synch",
"db.wait_event.name": "wait/synch/sxlock/innodb/fil_space_latch" } }, "DataPoints": [ { "Timestamp": 1611468660.0, "Value": 0.03333333333333333 } ] },
18 { "Key": { "Metric": "db.load.avg", "Dimensions": { "db.wait_event.type": "synch",
"db.wait_event.name": "wait/synch/sxlock/innodb/fil_space_latch" } }, "DataPoints": [ { "Timestamp": 1611468660.0, "Value": 0.03333333333333333 } ] },
{ "Key": { "Metric": "db.load.avg", "Dimensions": { "db.wait_event.type": "synch", "db.wait_event.name":
"wait/synch/mutex/innodb/trx_mutex" } }, "DataPoints": [ { "Timestamp": 1611468660.0, "Value": 0.016666666666666666 } ] } ], 19
{ "Key": { "Metric": "db.load.avg", "Dimensions": { "db.wait_event.type": "synch", "db.wait_event.name":
"wait/synch/mutex/innodb/trx_mutex" } }, "DataPoints": [ { "Timestamp": 1611468660.0, "Value": 0.016666666666666666 } ] } ], 20
• ◦ ◦ 21
• ◦ ◦ 22
• ◦ ◦ 23
• ◦ • ◦ ◦ ◦ 24