Enterprise Level

MRS is based on the Huawei FusionInsight platform. It provides enterprise-level scheduling to isolate resources, and ensures Service Level Agreements (SLAs) for multi-level users. MRS has been deployed on tens of thousands of nodes.

Easy O&M

MRS leverages a dedicated enterprise-level cluster management system so you can easily manage big data platforms. Platform exceptions are reported by SMS or email. O&M has never been easier.

High Security

With Kerberos authentication, Huawei's security expertise, and Germany PSA security certification, MRS provides role-based access control and sound audit functions to ensure 360-degree protection.

Low Cost

Equipped with a diversified cloud infrastructure, MRS offers extensive computing and storage choices for those on a budget, meaning on-demand operations for MRS clusters and cluster capacities.

Application Scenarios

  • Large-Scale Data Analysis

  • Large-Scale Data Storage

  • Low-Latency Streaming Processing

Large-Scale Data Analysis

Environmental Protection

Climate data is stored on OBS and periodically dumped into HDFS for batch analysis. 10 TB of climate data can be analyzed in 1 hour.

Advantages

  • Low Cost

    OBS offers cost-effective storage.

  • Massive Data Analysis

    TB/PB-level data is analyzed by Hive.

  • Visualized Data Import and Export Tool

    Loader exports data to DWS for business intelligence (BI) analysis.

Large-Scale Data Storage

Internet of Vehicles (IoV)

An automobile company stores data on HBase, which supports PB-level storage and CDR queries in milliseconds.

Advantages

  • Real Time

    Kafka accesses massive amounts of vehicle messages in real time.

  • Massive Data Storage

    HBase stores massive volumes of data and supports data queries in milliseconds.

  • Distributed Data Query

    Spark analyzes and queries massive volumes of data.

Low-Latency Streaming Processing

Internet of Elevators & Escalators (IoEE)

Data of smart elevators and escalators is imported to MRS streaming clusters in real time for real-time alarming.

Advantages

  • Real-Time Data Ingestion

    Flume implements real-time data ingestion and provides various data collection and storage access methods.

  • Data Source Access

    Kafka accesses data of tens of thousands of elevators and escalators in real time.

Functions

On Demand

On-demand cluster creation and pay-per-use operations

  • Diversified node and disk specifications

  • On-demand cluster scale

  • Various big data software and versions

  • On-demand cluster capacity expansion

  • Temporary clusters, automatically deleted after job execution

Enterprise-Level Big Data Edition

Secure, reliable, efficient, and with high availability (HA)

  • HA deployment on all management nodes

  • Kerberos security authentication and RBAC

  • Multi-level tenant management

  • Encryption of file systems and data tables

  • Service health and performance management

  • High-performance local disks

Compatibility

Compatible with open source ecosystems, achieving seamless application migration

  • Seamlessly interconnected with OBS

  • CarbonData, a high-performance file storage format

  • Various open source computing frameworks, such as, MapReduce, Spark/SparkSQL, Hive, and Storm

  • Spark SQL, compatible with the Hive SQL syntax

Create an Account and Experience HUAWEI CLOUD for Free

Register Now