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.
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.
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.
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.
Migrating an On-premises Big Data Platform to the Cloud
On-premises Hadoop big data platforms (CDH/HDP/...) can be quickly migrated to the cloud, and customers' services and data can be migrated to MRS all at one time. An off-cloud system can be quickly built based on the cloud environment, making it possible to perform rapid service expansion in the future.
Online migration of service data ensures no service interruption. More than 100 TB data can be migrated to the cloud within 7 days.
During offline system migration, service codes are not modified, allowing the service to be migrated quickly.
PB-level data can be migrated to the cloud.
O&M services are provided by Huawei's professional technical team.
Internet of Vehicles (IoV)
MRS leverages the open-source ecosystem to provide a fast and efficient data processing computing engine that helps automobile enterprises quickly migrate services to the cloud. It also flexibly builds an open, unified, and full-stack big data platform for data analysis.
MRS is an enterprise-level big data platform that isolates computing from storage, providing flexibility and convenience.
MRS provides various open-source components that can be combined freely as needed, supporting real-time/offline complex service processing.
MRS Kafka and Storm can obtain real-time stream data to implement real-time computing and analysis with high throughput and low latency.
MRS is based on open source. It is fully compatible with APIs of the Apache Hadoop ecosystem.
Finance and Insurance
MRS leverages the advantages of the big data platform on DeC to meet the strict requirements of the insurance industry with regards to compliance, security, and reliability. It reconstructs the IT architecture of traditional insurance enterprises, and quickly builds and deploys insurance service systems. This helps insurance enterprises achieve fast digital transformation, easy service innovation, and agile service evolution.
Meets industry regulatory requirements and protects customers' sensitive data.
Provides dedicated MRS clusters and exclusive resources, and separates computing resources from storage resources.
Allows users to create a full-stack big data platform with just one click and provides an enterprise-class platform management interface, simplifying O&M.
Public Opinion Analysis
Centering on the MRS one-stop big data platform, components such as Kafka, Storm, and HBase are used to collect, analyze, and process massive amounts of data to provide governments and enterprises with services such as public opinion monitoring, analysis, and message push.
MRS supports elastic expansion of compute nodes and scheduled auto-scaling, significantly reducing costs.
MRS Kafka and Storm provide high-performance streaming cluster capabilities to collect and analyze tens of thousands of public opinions per second in real time, keeping delay within milliseconds.
MRS HBase provides the distributed and scalable NoSQL data storage services, which are suitable for analyzing and querying massive amounts of structured and semi-structured data.
MRS big data analysis platform is used to implement intelligent management of logistics activities, improving service operation efficiency and greatly reducing costs.
Dedicated MRS Kafka clusters with high-throughput, high availability, and low latency capabilities facilitate real-time access of millions of messages.
MRS Spark supports large-scale data computing. MRS HBase can load and update logistics data in milliseconds, and query and analyze petabytes of time series data.
MRS uses MLS for big data mining, and provides precise and intelligent prediction and analysis capabilities for logistics organizations, marketing, and operation management.
Internet of Elevators (IoE)
To adapt to the rapid business innovation and flexible service modes involved in IoE, MRS functions as an open one-stop big data processing platform to implement intelligent elevator management.
MRS provides a wide variety of computing products and storage hardware for your choices to meet scenario-specific needs and build a unified and open big data platform. In addition, it offers powerful computing engines and a massive amount of storage, and enables flexible integration of service components.
MRS Kafka works with high-performance general network enhancement (C3ne) ECSs to implement real-time data access for millions of elevators.
MRS supports GPUs that provide real-time high-speed parallel computing and floating-point computing capabilities. These are applicable to video encoding and decoding, deep learning, and scientific computing.
Smart Water Management
MRS Hadoop provides high-performance, reliable, unified big data storage and analysis functions for water management scenarios.
MRS builds an enterprise-level big data platform and provides various open-source components that can be flexibly combined, supporting real-time/offline complex service processing.
Storm can obtain real-time stream data from Kafka to implement real-time computing and analysis with high throughput and low latency.
Various structured, semi-structured, and unstructured data can be computed and processed, and traditional data warehouse data can be easily migrated, facilitating cross-source data exploration and analysis.
Game log data is accessed through Kafka and Flume in real time. Spark Streaming processes and analyzes the data in real time and stores the analysis results to HBase or Hive for quick game advertisement analysis, data query and analysis, and revenue analysis.
MRS functions as an enterprise-level big data platform and provides various open-source components that can be combined flexibly to meet even highly complex service processing needs.
MRS Kafka and Flume collect real-time data and integrate with high-performance general network enhancement (C3ne) ECSs to implement real-time access of massive amounts of data.
MRS provides enterprise-level big data cloud services that enable PV plant operators to easily run Hadoop, Spark, HBase, Storm, and other big data components for the purpose of predictive device maintenance.
MRS functions as an enterprise-level big data platform and provides various big data components that support flexible use in different combinations, meeting customers' requirements for complex service processing.
MRS Kafka and Sqoop support multiple data collection methods, facilitating real-time access of millions of messages.
SQL APIs can be used to support querying multi-dimensional data for easy data exploration and analysis.
Rolls out, supporting Hadoop, Spark, HBase, and Hive
Charges both monthly and yearly
Supports Kafka, Storm, Hue, and CarbonData
Supports Kerberos authentication
Adds Flume and Loader and upgrades Spark to version 2.1.0
Collects cluster creation logs with OBS
Allows multi-region deployment and rollout in East China
Supports general-purpose II (S2) and disk-intensive II (D2) ECSs
Upgrades HBase to version 1.3.1
Supports cluster shrinking and multi-disk mounting
Adds Task nodes and allows auto scaling
Supports clusters of the specification (4 vCPUs, 8 GB)
Supports 1 Master node cluster with at least 1 Core node
Supports cluster expansion for yearly/monthly subscriptions
Upgrades Hadoop to version 2.8.3
Upgrades Spark to version 2.2.1
Supports S3 and C3 series VMs powered by latest-generation Intel Xeon SkyLake CPUs
Upgrades Kafka to version 0.10.2.0
Provides guidance on customized operations
Supports tag resource management
Rolls out in the CN South-Guangzhou region
Supports O&M authentication
Supports general network enhancement C3ne ECSs
Upgrades Kafka to version 1.1.0
Upgrades Storm to version 1.2.1
Supports EIP-based quick cluster access
Launches the dedicated MRS big data service based on DeC
Supports rolling cluster restart
Supports ECS resource locking in MRS clusters
Supports scheduled auto scaling rules
Allows nodes with new specifications to be added during cluster resizing
Supports the upgrade of Master node specifications
Supports rolling patches
Supports Huawei-developed ARM
On-demand cluster creation and pay-per-use operations
Secure, reliable, efficient, and with high availability (HA)
Compatible with x86, ARM, and open source big data ecosystems
Diversified node and disk specifications
Various big data software and versions
Temporary clusters, automatically deleted after job execution
On-demand cluster scale
On-demand cluster capacity expansion
HA deployment on all management nodes
Multi-level tenant management
Service health and performance management
Kerberos security authentication and RBAC
Encryption of file systems and data tables
High-performance local disks
Huawei-developed ARM servers integrated with Huawei-developed OS and databases, forging a home-grown software and hardware integrated platform
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