Cisco and Red Hat collaborate on petabyte scale storage for OpenStack and Big Data

Enterprises are dealing with workloads that demand anywhere from a few terabytes to multiple petabytes of unstructured data. Storage-intensive enterprise workloads are ubiquitous in the data center and range across workloads such as:

• Archiving and backup, including backup images and online archives
• Rich media content storage and delivery, such as videos, images, and audio files
• Enterprise drop-box
• Cloud and business applications, including log files, and RFID and other machine-generated data
• Virtual and cloud infrastructure, such as virtual machine images as well as emerging workloads, such as co-resident applications

This rapid growth of unstructured data requires a dense storage solution as data center space becomes increasingly expensive. Organizations need to reduce the cost of both hardware and software, but at the same time need to help ensure the reliability and availability of the overall solution.

Validated, tested configurations for seamless scale

At Red Hat Summit, we’re seeing a lot of interest in the adoption of OpenStack as the defacto private cloud platform. OpenStack represents a classic workload to which seamless and reliable storage is critical.

Cisco has teamed with Red Hat on building ultra-dense, high-throughput solutions to store very large amounts of unstructured data deployed on minimal rack space using Red Hat Gluster Storage and Red Hat Ceph Storage on Cisco UCS (Unified Computing System™) servers.

Cisco recently published two whitepapers (listed in the resources section of this blog post) based on the reference architectures for each solution. The whitepapers provide testing results that showcase how Cisco UCS C3160 servers can be optimized to serve in different types of storage scenarios.

The whitepapers also include system setup information, and testing methodology for each configuration. The performance benchmark tests using FIO (Flexible I/O), SmallFile, and IOzone yield remarkable results clearly indicating these two solutions are capable of handling storage-intensive enterprise workloads in a dense datacenter footprint.

The two reference architecture whitepapers provide an overview of the use of the Red Hat storage portfolio in a highly scalable multi-node setup with petabytes of storage. These tests demonstrate the suitability of the Cisco UCS servers in file, object, and block storage environments, and the server’s dense storage capabilities, performance, and scalability as you add more nodes.

The Cisco UCS C3160 Rack Server is a modular, high-density rack server (with total raw disk capacity of 360TB in a 4RU form factor) ideal for service providers, enterprises, and industry-specific environments that require highly scalable computing with high-capacity local storage. Unlike typical high-density rack servers that require extended-depth racks, the Cisco UCS C3160 fits comfortably in a standard-depth rack, such as the Cisco UCS R42610.

Designed for a new class of cloud-scale and big data applications, it is simple to deploy and excellent for software-defined storage environments, unstructured data repositories, backup and archival, media streaming, and content distribution. The server helps organizations achieve the highest levels of data availability because its hard-disk drives are individually hot-swappable and include built-in enterprise-class Redundant Array of Independent Disks (RAID). These characteristics help reduce the overall data center space required at a very competitive price per gigabyte and per rack unit. The server uses a modular server architecture that takes advantage of Cisco’s blade technology expertise, allowing you to upgrade the computing and network nodes independently without requiring data migration from one system to another.

Resources:

Cisco UCS C3160 high Density Rack Server with Red Hat Ceph Storage

Cisco UCS C3160 and Red Hat Gluster Storage 500TB Solution

Red Hat solutions on Cisco UCS

Red Hat and Cisco – Open innovation focused on customers