Boruo Big Data Computing Service Platform (BR-odp) is a convenient, efficient and easy-to-manage TB/PB-level data storage and computing solution. BR-ODP is based on the big data computing service platform integrated with Apache Hadoop2.7 and independently developed. It provides users with a complete data import scheme and a variety of classic distributed application modes, which can respond to and match user needs more quickly and solve users. The problem of massive data calculation and storage effectively reduces enterprise costs, and guarantees enterprise data security, escorting enterprise big data.
< /p>
1 Faster: Low-cost and efficient deployment
Local or cloud-based services make it possible to build a big data platform within minutes. The unified management of the deployment and management platform allows you to quickly create new features, develop and test new versions of services without interrupting old versions of services. BR-odp also supports third-party applications in Docker containers and local YARN containers. Erasure coding improves storage efficiency by 50% and enables effective data replication to reduce total cost of ownership.
2 Smarter: Accelerate the insight time of agile decision-making
BR-odp provides the basis for GPU support in Apache Hadoop clusters and improves the computing performance required for data science and AI use cases. It enables GPU pooling to promote the sharing of GPU resources with more workloads to improve cost-effectiveness. It also supports GPU independence, dedicate the GPU to the application so that other applications cannot access the GPU.
3 Hybrid: Cross-cloud platform applications
Using BR-odp, you can freely deploy big data workloads in hybrid and multi-cloud environments without relying on specific cloud architectures locked in by vendors. Customers can seamlessly create and manage large data clusters in any cloud environment. BR-odp has nothing to do with the cloud and can be automatically configured to simplify big data deployment while optimizing the use of cloud resources. Cloud includes:
? Microsoft
? Vmware
? Openstack
? Aliyun
4 Real-time database: SQL interface for historical and real-time query
BR-odp includes improved Query performance, focusing on faster queries. The fastest Apache Hive engine Hive LLAP can run in a multi-tenant environment without causing resource competition. This integration greatly speeds up queries commonly used in business intelligence scenarios, such as join and aggregation queries. In addition to query optimization, Hive also allows the creation of resource pools for fine-grained resource allocation.
BR-odp enables ACID transactions by default, making it easier to update and support GDPR requirements in the Hive table. As a real-time database, Hive eliminates the performance difference between low-latency and high-throughput workloads, processing more data at a faster speed.
5 Trustworthy: Enterprise-level access control and metadata for security and governance BR-odp continues to provide comprehensive security and governance. BR-odp’s security is integrated at multiple levels, including functions for identity verification, authorization, accountability, and data protection. The integration of security and governance enables security professionals to set classification-based security policies. In addition, data governance tools enable organizations to apply consistent data classifications in the data ecosystem. Other functions allow for more refined and detailed review of events, making it easier for reviewers to complete their work. Auditors and users can see the complete chain of custody of data as it moves through the entire ecosystem. Tag dissemination allows reviewers and users to see where the data is going throughout the enterprise and preserve the context of sensitive data. Time-based policies allow temporary access to specific users.