Elastic MapReduce (EMR) is a secure, low-cost, and highly reliable open-source big data platform based on the cloud native technology and pan-Hadoop ecosystem. It provides diverse open-source big data components, such as Hive, Spark, HBase, Flink, StarRocks, Iceberg, and Alluxio, which are easy to deploy and manage, helping you efficiently build a cloud-based enterprise-grade data lake technology architecture.
Completely derived from the open-source community, EMR enables you to seamlessly and smoothly migrate your existing big data clusters to Tencent Cloud. It is integrated with commonly used community components such as Hadoop, Hive, HBase, Spark, Presto, Flink, Sqoop, Hue, Iceberg, Druid, and StarRocks, fully meeting your various needs like online big data business, offline/online data warehousing, cloud-native data lake formation, and real-time stream computing.
EMR seamlessly incorporates the COS service, allowing you to migrate files stored in HDFS to COS with unlimited scalability, low storage costs, and high reliability for easy computing-storage separation. With COS, a cluster can be created whenever needed and terminated after the task is completed without the concerns over data loss. In addition, on-demand clusters can greatly reduce your big data processing costs.
EMR has five node types: master, core, task, router, and common. For the purposes of each type, see Cluster Types.
Currently, EMR supports multiple resource specifications, including Standard, Standard Network Optimized, MEM Optimized, High I/O, Computing, Computing Network Enhanced, and Big Data models. If you wan to deploy a cluster on CPM, contact us for assistance.