Blog

• Distributed Systems
  • MapReduce (OSDI '04) (2022-01-03)
  • GFS (SOSP '03) (2022-01-09)
  • Fault-Tolerant VM (SIGOPS ‘10) (2022-01-16)
  • Raft (ATC '14) (2022-01-29)
  • ZooKeeper (ATC '10) (2022-02-03)
  • BigTable (OSDI '06) (2022-02-12)
  • Spanner (OSDI '12) (2022-03-09)
  • Hive (ICDE '10) (2022-03-28)
  • Presto (ICDE '19) (2022-04-02)
  • Dremel (VLDB ‘10) (2022-05-23)
  • FoundationDB (SIGMOD '21) (2022-06-09)
  • Monarch (VLDB '20) (2022-07-03)
  • Metastable Failures in Distributed Systems (HotOS ‘21) (2022-08-01)
  • Windows Azure Storage (SOSP '11) (2022-12-15)
• AWS
  • DynamoDB
    • Dynamo (OSDI ‘07) (2022-02-11)
    • DynamoDB Under the Hood: How We Built a Hyper-Scale Database (2022-02-20)
    • How DynamoDB provides transactions with scalability (FAST '19 Keynote) (2022-02-22)
    • DynamoDB (ATC '22) (2022-07-18)
  • S3 (2022-09-21)
  • Redshift (SIGMOD '22) (2022-06-04)
  • AWS Nitro System (2023-01-23)
  • AWS Networking Fundamental (2023-01-24)
  • AWS Lambda (2022-12-22)
• Airbnb
  • Data Quality 1 - Rebuilding at Scale (2021-10-10)
  • Data Quality 2 - A New Gold Standard (2021-10-11)
  • Data Quality 3 - Prevent Data Bugs (2021-10-12)
  • Minerva 1 - Metric Consistency (2021-10-16)
  • Minerva 2 - Design Principles for Standardized Metric (2021-10-17)
  • Minerva 3 - Consistent Data Consumption (2021-10-23)
  • Toward High Quality Data (2021-10-24)
  • Automating Data Proteciton at Scale 1 (2022-05-05)
  • Automating Data Proteciton at Scale 2 (2022-05-06)
  • Automating Data Proteciton at Scale 3 (2022-05-07)
  • Democratizing Metrics at Airbnb: Minerva 2.0 and Beyond (2022-07-25)
• Uber
  • Real-time Data Infrastructure at Uber (SIGMOD '21) (2021-11-07)
  • Kappa+ Architecture (2021-10-28)
  • Real-Time Exactly-Once Ad Event Processing (2021-11-21)
  • uMetric: The Journey Towards Metric Standardization (2022-05-08)
  • How Uber Achieves Operational Excellence in the Data Quality Experience (2022-05-13)
• Kafka
  • Exactly-Once Semantics (2021-11-12)
• Pinterest
  • Optimizing Kafka for the cloud (2021-10-31)
• Meta
  • Cache made consistent: Meta’s cache invalidation solution (2022-06-10)
• Delivery Hero
  • The Delivery Hero Reliability Manifesto (2022-07-03)
• Flink
  • Flink Overview
    • Overview (2021-11-09)
    • Monitoring 101 (2021-12-17)
    • Streaming Analytics (2021-11-10)
    • Architecture & Clusters (2021-11-29)
    • UseCases (2021-11-28)
  • Flink Exactly-Once
    • Exactly-Once Processing (2021-12-13)
    • A Deep Dive into Rescalable State (2021-12-26)
    • Incremental Checkpointing (2021-12-26)
    • Tuning Checkpoints and Large State (2021-12-28)
    • Flink's checkpointing mechanism (2021-12-14)
    • Chandy-Lamport Algorithm (2021-12-29)
    • Lightweight Asynchronous snapshots for Distributed Systems (2021-12-31)
    • Backpressure (2022-01-01)
  • Flink Programming
    • Broadcast State (2021-12-27)
    • Flink App 1: Fraud Detection (2021-12-15)
    • Flink App 2: Dynamic Update of Application Logic (2021-12-18)
    • Flink App 3: Custom Window Processing (2021-12-19)
  • spotify/flink-on-k8s-operator (2022-01-28)
• 알고리즘, 자료구조
  • 종만북1 (2022-09-30)
  • HyperLogLog (2024-06-04)
  • Bloom filter (2023-09-09)
• Go
  • A Guide to the Go Garbage Collector (2022-10-12)
• posts
  • [devsisters] data driven으로 서비스 운영 자동화 (spark) (2021-12-04)
  • Minikube (2021-09-21)
  • make help 줍줍 (2022-08-22)
  • S3 Multipart Upload와 pyarrow로 고정된 스키마를 가지는 Parquet 파일 생성 (2022-08-28)
  • crawler pod에 sidecar로 chromedriver를 띄우자 (2022-12-20)
  • Shell Script Practices (2023-07-08)
  • k3s
    • 1) k8s cluster를 묶기 위한 openVPN 설치 (2023-11-29)
    • 2) k3s 설치 (2023-11-29)
• About me
• Engineering Blogs (2022-08-22)