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
AWS DynamoDB Accelerator (DAX) 101
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
Ken Wagatsuma
February 14, 2020
Programming
2
7.3k
AWS DynamoDB Accelerator (DAX) 101
Introduction to AWS DynamoDB Accelerator (DAX)
Ken Wagatsuma
February 14, 2020
Tweet
Share
More Decks by Ken Wagatsuma
See All by Ken Wagatsuma
Pregel Graph Compute Engines - Supersteps Exampls
kenju
0
230
Kafka on Kubernetes with Strimzi
kenju
0
190
Moden browser introduction
kenju
1
450
Cookpad summer internship 2019 - API
kenju
0
10k
Introduction to Design Patterns
kenju
0
110
GraphQL Asia 2019 "Re-architecture of a decade-old app with BFF/GraphQL"
kenju
0
9.2k
Introduction to TypeScript
kenju
0
760
Introduction to Programmatic Ad
kenju
0
280
社内管理システムのための技術選定
kenju
0
790
Other Decks in Programming
See All in Programming
あなたはユーザーではない #PdENight
kajitack
4
280
文字コードの話
qnighy
41
15k
AIとペアプロして処理時間を97%削減した話 #pyconshizu
kashewnuts
1
150
浮動小数の比較について
kishikawakatsumi
0
350
The Ralph Wiggum Loop: First Principles of Autonomous Development
sembayui
0
3.7k
AI時代でも変わらない技術コミュニティの力~10年続く“ゆるい”つながりが生み出す価値
n_takehata
2
460
AIプロダクト時代のQAエンジニアに求められること
imtnd
1
490
CopilotKit + AG-UIを学ぶ
nearme_tech
PRO
1
110
FOSDEM 2026: STUNMESH-go: Building P2P WireGuard Mesh Without Self-Hosted Infrastructure
tjjh89017
0
190
iOSアプリでフロントエンドと仲良くする
ryunakayama
0
120
Head of Engineeringが現場で回した生産性向上施策 2025→2026
gessy0129
PRO
0
190
AI時代のキャリアプラン「技術の引力」からの脱出と「問い」へのいざない / tech-gravity
minodriven
22
8k
Featured
See All Featured
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
2
3.7k
The Cult of Friendly URLs
andyhume
79
6.8k
How to audit for AI Accessibility on your Front & Back End
davetheseo
0
200
Digital Ethics as a Driver of Design Innovation
axbom
PRO
1
200
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
460
RailsConf 2023
tenderlove
30
1.4k
The untapped power of vector embeddings
frankvandijk
2
1.6k
Data-driven link building: lessons from a $708K investment (BrightonSEO talk)
szymonslowik
1
930
GitHub's CSS Performance
jonrohan
1032
470k
Speed Design
sergeychernyshev
33
1.6k
GraphQLの誤解/rethinking-graphql
sonatard
74
11k
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
1.2k
Transcript
DAX 101 1 2020/2/15 Kenju Wagatsuma
DAX Wrap Up 2
DAX is… DynamoDB-specific in-memory cache store 3
[DAX] Glossary of Terms 4 5FSN %FTDSJQUJPO /PEFT "OPEFJTUIFNJOJNVNDPNQPOFOUGPSB%"9DMVTUFSl1SJNBSZOPEFzIBOEMFSFBE
XSJUFSFRVFTUTBOElSFQMJDBOPEFTzPOMZIBOEMFSFBESFRVFTUT $MVTUFST "DMVTUFSJTDPNQPTFEGSPN OPEFT 1BSBNFUFS(SPVQT :PVDBODIBOHF55-CZTFUUJOHDVTUPN1BSBNFUFS(SPVQT
[DAX] Comparison to other cache store 5 %"9 &MBTUJDBDIFNFNDBDIFE JONFNPSZ
.BOBHFE ✅ ✅ 4IBSFEDBDIF ✅ ✅ #BDLFOEEBUBTPVSDF %ZOBNP%#POMZ BOZUIJOH .Z42- %JTL 31$ FUD .FUSJDT ✅ ✅ 55- ⚠ HMPCBM55- ✅ ⚠ IBSEXPSLSFRVJSFE 1FSGPSNBODF ЖdNT dNT ЖdЖ
[DAX] Single-leader Replication 6 +3 nodes for different Multi-A/Z for
production Background replication (eventually consistent model) Single “primary node” handles all write requests
Subnet C Subnet B DAX Cluster Subnet A [DAX] Single-leader
Replication - Write 7 Primary Replica Replica
DAX Cluster [DAX] Single-leader Replication - Write 8 Primary Replica
Replica Application DynamoDB Table DynamoDB Table Write Read
DAX Cluster [DAX] Single-leader Replication - Replicate 9 Primary Replica
Replica Application DynamoDB Table DynamoDB Table Write Read
DAX Cluster [DAX] Single-leader Replication - Read 10 Primary Replica
Replica Application DynamoDB Table DynamoDB Table Write Read
[DAX] Cache Algorithm 11 Least Recently Used (LRU) cache Negative
cache also implemented Eviction happens when items are taken & cache is full Global Time-To-Live (TTL)
[DAX] Item Cache / Query Cache 12 Item Cache Query
Cache Operation GetItem / BatchGetItem Query / Scan Metrics ItemCacheHits/ItemCacheMisses QueryCacheHits/QueryCacheMisses ScanCacheHits/ScanCacheMisses
[DAX] Write Strategy - Write-Through 13 #write #read Application DAX
DynamoDB Application DAX DynamoDB
[DAX] Write Strategy - Write-Around 14 #write #read Application DynamoDB
Application DAX DynamoDB
[DAX] Write Strategy 15 8SJUF5ISPVHI 8SJUF"SPVOE 1SPT 4ZODISPOJ[FEJUFNTCFUXFFO%"9 BOE%ZOBNP%# 8SJUFDBOTDBMF
FHCVMLVQEBUF $POT ☹8SJUFPQFSBUJPOIBTPWFSIFBE ☹*UFNTDBOCFJODPOTJTUFOU JGPUIFS BQQXSJUFUP%ZOBNP%#EJSFDUMZ ☹&WFOUVBMMZ$POTJTUFOU JUFNTJO%"9 OPEFTDBOCFPVUEBUFE
[DAX] Within VPC + Multi-A/Z 16
[DAX] Limitation 17 Maximum nodes is 10 (1 primary node
+ ~9 replica nodes) Maximum nodes is 50 per Region. Maximum Parameter Groups is 20 per Region Maximum DAX Subnet Groups is 50 per Region. Maximum subnets per groups is 20.
Monitoring 18
[Monitoring] CloudWatch Metrics 19 NFUSJDT EFTDSJQUJPO $166UJMJ[BUJPO PG$16VUJMJ[BUJPOUTNBMMVTFW$16 ⚠:PVOFFEUPTDBMFVQJGUIJTNFUSJDTJTTBUVSBUFE *UFN$BDIF)JUT
*UFN$BDIF.JTTFT $BMDVMBUF$BDIF)JU3BUJP GSPNUIFTFNFUSJDT ⚠*UFN$BDIF2VFSZ$BDIF
[Monitoring] CloudWatch Metrics 20 NFUSJDT EFTDSJQUJPO 5ISPUUMJOH3FRVFTU$PVOU PGSFRVFTUTUISPUUMFECZUIFOPEFPSDMVTUFS ⚠5ISPUUMFEBU%"95ISPUUMFEBU%ZOBNP%# 'BJMFE3FRVFTU$PVOU
PGSFRVFTUTUIBUSFTVMUFEJOBOFSSPSSFQPSUFE ⚠&SSPS3FR$PVOU5ISPUUMFE 'BJMFE
[Monitoring] CloudWatch Metrics 21 NFUSJDT EFTDSJQUJPO &WJDUFE4J[F ⚠*G$BDIF)JU3BUJP&WJDUFE4J[FJTHSPXJOH UIF XPSLJOHTFUNJHIUJODSFBTF4IPVMEDPOTJEFSTDBMFVQ
$MJFOU$POOFDUJPOT PGTJNVMUBOFPVTDPOOFDUJPOTGSPNDMJFOUT ⚠$MJFOU$PO$PVOU㲈PG3VOOJOH5BTLT
[Monitoring] Grafana 22
[Monitoring] SLI/SLO 23
Alerting 24
[Alerting] CW Alarm - Infrastructure 25 CW Alarm SNS Topic
Lambda Slack
[Alerting] CW Alarm - CPUUtilization 26
[Alerting] CW Alarm - Cache Hit Ratio 27 ItemCacheHitRatio =
ItemCacheHits / ( ItemCacheHits + ItemCacheMisses )
[Alerting] CW Alarm - Cache Hit Ratio 28
[Alerting] DAX Events - Infrastructure 29 DAX Event SNS Topic
Lambda Slack
[Alerting] DAX Events - Infrastructure 30 failure/success in adding a
node changes to the security groups