Big Data 8 min read

JD.com’s 618 Technical Architecture: Componentization, Data Platform, and Elastic Computing at Massive Scale

The article details JD.com’s 618 shopping festival engineering, describing how componentized micro‑services, a unified data platform, and the Archimedes elastic scheduling system enabled billions of requests, real‑time data processing and seamless online‑offline integration without adding new server resources.

JD Retail Technology
JD Retail Technology
JD Retail Technology
JD.com’s 618 Technical Architecture: Componentization, Data Platform, and Elastic Computing at Massive Scale

On June 18, JD.com’s 618 promotion triggered an instantaneous surge of orders, with the real‑time order volume exploding as the clock struck midnight, showcasing the massive scale of the event.

The technical system faced extreme challenges: memory‑database request peaks rose from 550 million to 1.7 billion per second, gateway accesses exceeded 4 million per second, and real‑time big‑data processing grew from 3 billion to 11 billion records per minute, demanding robust high‑concurrency handling.

To support diverse retail scenarios, JD.com adopted a fully componentized, platform‑based architecture, turning each system into reusable building blocks that can be flexibly combined, enabling rapid iteration, lower costs, and multi‑scenario deployment across e‑commerce, social commerce, offline stores, and overseas markets.

The data middle‑platform consolidates scattered data silos into a unified asset, providing standardized services, metrics, and tags; this fine‑grained operation boosted the apparel channel’s conversion rate by 41% after adding user‑preference tags.

For the 618 event, JD.com relied on the “Archimedes” intelligent scheduling brain—an elastic computing solution that leverages container orchestration, database, storage, micro‑services, and AI‑driven traffic allocation to predict resources and perform second‑level scheduling, saving billions in hardware costs without adding new servers.

The universal transaction middle‑platform connects online and offline retail, achieving “nine‑through” integration (product, order, inventory, data, member, marketing, payment, asset, service), enabling seamless online‑offline price parity, high in‑store conversion, and significant cost reductions.

Innovative AR/VR marketing technologies, such as virtual try‑on and 360° product experiences, along with smart in‑store guides and analytics platforms, enhance brand engagement and illustrate JD.com’s shift toward an open, component‑based retail technology ecosystem.

e-commerceBig Datamicroservicesdata platformComponentizationelastic computing
JD Retail Technology
Written by

JD Retail Technology

Official platform of JD Retail Technology, delivering insightful R&D news and a deep look into the lives and work of technologists.

0 followers
Reader feedback

How this landed with the community

login Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.