5 August — the well-known big-data open-source community Hadoop has announced official support for Tencent Cloud Object Storage (COS). Developers running big-data analysis on the Hadoop framework can now read and write massive datasets on COS seamlessly and efficiently, without changing a line of code.
Big-data analysis consumes a great deal of compute and storage. In the traditional model the two are tightly coupled: when capacity runs short, both have to be scaled at the same time. In recent years, driven by cloud computing, developers have moved to cloud object storage to separate compute from storage, gaining flexibility and cutting cost.
Hadoop is the most widely used distributed big-data processing framework and the de facto standard in the field. As data becomes more valuable, Hadoop is used widely across the internet, government and financial industries.
Tencent Cloud COS is a distributed cloud storage service that is secure, stable, massive, convenient, low-latency and low-cost. It runs on Tencent’s self-developed YottaStore engine, which can in theory manage a million nodes in a single cluster, scales truly on demand, and reaches disk utilisation above 90%.
With the community’s support for Tencent Cloud object storage, developers doing big-data analysis on Hadoop can use the high-speed cloud storage COS provides without any adaptation work.
“On Tencent Cloud, developers can use elastic MapReduce (EMR) for compute and COS directly as back-end storage, without adding any extra code — simpler and faster,” said the head of Tencent Cloud Object Storage.
Xiaohongshu, Cheetah Mobile, Zhenai and others already use the EMR-on-COS model of separated compute and storage to build and deploy big-data analysis quickly and meet their data requirements.
Want to talk through what you just read?
We work end to end, from product design to launch. Tell us about your scenario and we can start there.
Shenzhen XZS Technology Co., Ltd. · Tel 0755-82494862 · 13760424861