How JD.com’s Buffalo Scheduler Achieves High‑Performance, Scalable DAG Orchestration

Buffalo, JD.com’s in‑house distributed DAG scheduler, tackles massive task volumes and complex dependencies through a dual‑layer entity model, instance‑based execution, tiered scheduling, high‑availability architecture, event‑driven processing, in‑memory and cold‑hot data separation, delivering scalable, low‑latency ETL orchestration.

DAG schedulingDistributed SystemsETL orchestration

0 likes · 12 min read

How JD.com’s Buffalo Scheduler Achieves High‑Performance, Scalable DAG Orchestration

DataFunTalk

Jul 23, 2023 · Backend Development

Rearchitecting the Advertising AB Testing Platform: Service Decomposition, Data Modeling, DAG Scheduling, and DDD Practices

The article describes how Volcano Engine's DataTester team refactored the advertising AB testing platform by splitting services, redesigning the data model with MySQL and ClickHouse, introducing DAG‑based scheduling and a time‑wheel algorithm, and applying domain‑driven design and rigorous unit testing to improve stability, scalability, and maintainability.

AB testingDAG schedulingDomain-Driven Design

0 likes · 16 min read

Rearchitecting the Advertising AB Testing Platform: Service Decomposition, Data Modeling, DAG Scheduling, and DDD Practices

Meituan Technology Team

Mar 3, 2022 · Backend Development

Meituan Waimai Advertising Engine Platform Engineering Practice – Part 1

Meituan Waimai’s advertising engine team built a platformized solution that standardizes business capabilities, data handling, and development workflow through reusable Action/Stage units, a unified context container, and a robust scheduling engine, achieving 28% faster development, over 65% Action reuse, and improved quality and stability.

Backend EngineeringDAG schedulingPlatformization

0 likes · 38 min read

Meituan Waimai Advertising Engine Platform Engineering Practice – Part 1