MapR-XD Cloud-Scale Data Store to Manage Files and Containers

MapR Technologies, Inc. announced MapR-XD, a cloud-scale data store to manage files and containers.

Click to enlarge

As part of the company’s Converged Data Platform, MapR-XD supports any data type from the edge to the data center and multiple cloud environments with automatic policy-driven tiering from hot, warm or cold data. It enables customers to create vast, global data fabrics which are inherently ready for analytical and operational applications making it easier to operationalize data.

“MapR-XD will deliver a single view of data activity, which is critical for immediately identifying potential fraudulent payments,” said BD Goel, chief product strategy and innovation officer, Paysafe Group Plc. “The ability to unify, manage and act on data very quickly – whether it originated from the cloud, on-premises or at the edge – is a compelling value proposition for us. Reliably delivering a millisecond advantage in data analysis is how MapR helps us stay several steps ahead of cybercriminals.“

“As applications become more intelligent and take advantage of more diverse data in real time, for both analytical and operational uses, there arises the need for new approaches to data processing,” said Matt Aslett, research director, data platforms and analytics, 451 Research. “MapR-XD is designed to eliminate data silos and support new use cases as they emerge that require data processing from the edge, data center and to the cloud.“

Storage and data management are in-the-midst of a generational replatforming to leap forward into the data age. Key shifts underway include rapidly appealing economics of flash and NVMe technologies; the adoption of clouds and IoT at the edge; evolving use cases and workloads; new demands imposed by deep learning technologies; and the radical change in scale and types of data.

“MapR-XD is the result of years of technical innovation and collaboration with our customers to develop a mission-critical modern data platform,” said Anil Gadre, chief product officer, MapR. “By providing a robust solution to manage data movement across multiple locations with security, high performance and multi-tenancy, we believe MapR is a strategic solution for enterprises embarking on crafting and implementing a next gen data strategy. Our unique Converged Data Platform enables creating data fabric with a global view of data and metadata, supporting a wide diversity of data types for both analytics and operations.“

“Cisco UCS provides the ideal platform for data intensive workloads, while MapR-XD Cloud-Scale Data Store creates the data fabric for managing files, and containers for these workloads and legacy applications,” said Raghunath Nambiar, CTO, UCS, Cisco Systems, Inc. “This represents a positive direction for the industry in the continuing evolution of Software Defined Storage.“

Click to enlarge

MapR-XD cloud-scale data store includes:

• Files, container support – Eliminates data silos and simplifies management across files and containers. It provides unified security, data protection and HA across diverse data types. The same underlying data can be accessed through a range of industry standard APIs including NFS, POSIX and HDFS to simplify development, administration and eliminate data sprawl.

• Global EB scale – Scales to support trillions of files, exabytes of data, on thousands of commodity servers or cloud instances, all accessible through a single global namespace. Additionally it reduces operational complexity and provides a single, scalable view of resources, simplifying access for users, applications and containers.

• Cloud-grade reliability – Delivers HA, data protection and DR with no single points of failure, fully distributed metadata, point-in-time snapshots and high-performance, distributed mirroring.

• Speed at scale with flash – Utilizes the power of network interconnects and takes advantage of the available performance of underlying heterogeneous hardware, such as disk and flash to meet the demands of GPU-based architectures. Automated capabilities, such as logical partitioning, parallel processing for disparate workloads, and bottleneck avoidance with I/O shaping and optimizations, ensure maximum performance across a cluster. It includes an high-performance POSIX Client that provides up to 10x the performance of a typical NFS gateway.

• Stateful persistence for containerized applications – Includes a secure, optimized container client for providing containers with access to persisted data. The client supports both legacy and new containerized event-based microservices applications; multiple data types of files, containers, database and event streams; works with multiple schedulers such as kubernetes, mesos and docker swarm; and across any infrastructure such as on-premises, multiple clouds and edge.

• Flexibility to leverage multiple infrastructures – Supports edge, on-premises and cloud environments with the same platform. It enables multi-temperature capabilities across flash, disk and cloud tiers with support for containers and automated data movement to address performance, cost and compliance concerns.

• IoT edge made easy – MapR-XD for the edge provides the ability to deploy processing and storage capabilities close to an IoT data source, such as in a car, medical device or jet engine. It can store and process machine or sensor-generated data for integration with a centralized Converged Data Platform where global aggregation and analysis would be performed.

• Extensible architecture – Is a component of the Converged Data Platform enabling customers to easily and leverage additional capabilities including database, stream processing and integrated analytics on the same platform.

MapR-XD is available.

Resource:
How MapR-XD enables the creation of cloud-scale data fabrics