MapR & Cisco for Software Defined and Web-Scale Storage

Contributed by

5 min read

MapR is pleased to support our partner Cisco with today’s UCS S-Series launch. The Cisco UCS S-Series consists of storage-optimized servers configured for scale-out storage (both Software Defined Storage and Web-Scale Storage with MapR). The S-Series delivers storage for “Cisco Solutions for Data Intensive Workloads” which are end-to-end solutions that provide:

  • High performance – High IOPS
  • High capacity – Cost per GB savings (with partners, Hello MapR!)

The Cisco UCS S-Series and Cisco Solutions for Data Intensive Workloads with MapR are designed for a number of workloads including:

  • Big Data
  • Software Defined Storage
  • Scale-out Object Storage (Ceph)
  • Data Protection (backups, archiving)
  • Real-time Analytics
  • Video Capture
  • Secondary Storage (tiered storage warm to cold)

The Cisco UCS S-Series is a modular platform for Data Intensive Workloads and can be configured as follows:

  • Massive Capacity: 600TB data storage capacity in 4U; Up to 90TB SSD Flash
  • Multi-Node Power: Single or Dual Server Options; New cache acceleration capabilities with NVMe and Fusion IoMemory
  • I/O flexibility: 40Gb Cisco Virtual Interface Card (VIC) Technology; 256 virtual adapters per node plus 16Gb native Fabre Channel options
  • Total Automation: Scale to Petabytes in minutes with UCS Manager; Cisco SystemLink Technology with flexible storage profiles

So how do MapR and Cisco UCS S-Series work together to support customers’ storage needs? First, let’s level-set on MapR’s storage capabilities within the MapR Data Platform:

MapR XD provides high performance enterprise-grade storage for big data

MapR XD is a POSIX file system that provides distributed, reliable, high performance, scalable, and full read/write data storage for the MapR Data Platform. MapR XD supports the HDFS API, fast NFS access, access controls (MapR ACEs), and transparent data compression. MapR XD includes enterprise-grade features such as block-level mirroring for mission-critical disaster recovery as well as load balancing, and consistent snapshots for easy data recovery.

Key Features

Full Read/Write Access: With MapR XD, you get a complete POSIX file system that handles raw disk I/O for big data workloads. You can run it as an enterprise-wide NAS to run existing file system-based applications and systems. It supports:

Globally Scalable: You can deploy clusters that run on MapR XD throughout the world and benefit from the architectural innovations that enable speed and scalability advantages.

  • Global namespace to view multi-site clusters as one logical cluster
  • Scale to thousands of nodes, and trillions of files, with extremely high throughput
  • Scheduled, block-level, incremental mirroring to remote sites for global load balancing

Enterprise-Grade Capabilities: In your business-critical environments, you need a platform with powerful yet easy-to-administer business continuity capabilities. MapR customers have run 99.9999% uptime with no data loss.

How might this shake out in the real world? Let’s consider the financial services market and look at a credit department example. The credit risk management department within a financial services organization is tasked with pulling together consumer and business data to determine a persons credit worthiness or risk. That’s a lot of data if you think about it – personal financial records (bank accounts, loans, payment histories, legal actions and more) combined with business data around that person’s financial actions (buying and paying history, credit reporting, applications for loans and more). Additionally, this data by definition is likely already tiered in some way. Some of it will be cold (+ 5 years aging, like an existing mortgage) and some will be warm (+2 years, a recent car loan) and some will be hot (current, missed monthly credit card payment). Clearly a very storage and data driven environment where a solution like MapR and the Cisco UCS S-Series would thrive to provide:

  • System Management – through Cisco UCS Manager which is integrated with MapR Data Platform (link)
  • Cost Management – tiered storage model, high capacity at lower costs per GB
  • Business Continuity – high availability and fail-over built-in with snapshots and data protection (backups and archiving)

For more information please visit or

This blog post was published November 01, 2016.

50,000+ of the smartest have already joined!

Stay ahead of the bleeding edge...get the best of Big Data in your inbox.

Get our latest posts in your inbox

Subscribe Now