You see the benefits of big data, but how do you respond to the need to deliver data center infrastructures and systems that are flexible and scalable to support your big data growth initiatives?
When it comes to big data scale-out platforms, most administrators have had to make significant compromises, forgoing many of the enterprise capabilities they have taken for granted with their scale-up platforms. Not any longer.
With DriveScale, and only with DriveScale, can administrators take advantage of the unprecedented performance, scalability and economy of scale-out with the best of scale-up.
Introducing DriveScale: Smarter Scale-Out
DriveScale offers a rack scale architecture, a next generation data center infrastructure based on hardware and software interface technology that brings the advantages of proprietary scale-up infrastructure environments to the commodity scale-out world.
- Dynamically adjust compute and storage infrastructure to handle changing application and business needs
- Optimize resource allocation without overprovisioning
Application stacks can be deployed without modification on physical infrastructure that is tailored for the deployment and can be easily updated in software as needs change.
Manageability extends across clusters to data center scale, allowing administrators to share resources fluidly across clusters, maximizing responsiveness.
With DriveScale, rack scale architecture finally makes sense.
DriveScale Technology Overview
Today, commodity servers are “fixed” in their pre-integrated configurations of compute and storage. This rigid approach often forces companies to overprovision one resource (e.g., CPUs) in order to fulfill the greater need of another resource (e.g., storage). With DriveScale, the ratio of compute to storage in servers and clusters is a software defined operation using composable infrastructure technology.
Administrators can rapidly and easily provision and reconfigure physical resource ratios to optimize for different and changing applications and workloads.
DriveScale automatically discovers available physical data center resources; enables disaggregation of servers into separate pools of compute and storage resources, and reassembles servers under software control; and manages and optimizes the scale-out infrastructure.
Administrators deploy a rack scale architecture consisting of pools of compute resources (industry standard servers) and storage resources (hard disks in JBODs) and then compose these resources into logical clusters and logical nodes (software defined physical nodes) that are indistinguishable from standard physical rack servers to software running on the servers. These clusters and nodes preserve the benefits of data locality and local disk performance of traditional rack server deployments. More importantly, administrators achieve responsiveness and remove any constraints around their physical infrastructure.
The economic benefits of being able to quickly respond to changing application requirements using existing infrastructure could be considerable.
- DriveScale Management Servers
- DriveScale Adapters
- Industry standard servers, deployed with DriveScale software agents (user space)
- Industry standard JBODs
- Industry standard 10GbE network infrastructure
In contrast to the pre-integrated storage and compute resources found in rack server chassis, the DriveScale architecture differs by enabling industry standard servers to be disaggregated and deployed as pools of industry standard disk-lite compute servers and commodity hardware disks housed within commodity JBODs.
In the DriveScale rack scale architecture, the DriveScale Management Server and DriveScale agents coordinate to provide the core functionality of the DriveScale solution. This software composes compute and storage components into logical nodes via the DriveScale Adapter and 10GbE network.
To the operating systems and applications running on them, these logical nodes are indistinguishable both in function and performance from traditional rack servers with local disk.
The DriveScale Adapter chassis is a fully redundant Ethernet-to-SAS adapter that converts commodity JBODs into Ethernet connected JBODs. This 1U appliance houses four DriveScale Adapters, each with two 10GbE SFP+ ports and two 12 Gb SAS connections.
DriveScale Software Defined Infrastructure
Administrators can define and rebalance their scale-out application clusters’ physical resources via the DriveScale service using the DriveScale UI and the automation-friendly RESTful API, allowing the operator to integrate the DriveScale management software with other data center tools with impunity.
DriveScale creates clusters of servers composed of the required number of physical drives connected to physical servers. DriveScale utilizes a constraint solver that combines user requirements and information it collects about the environment to define these clusters.
Cluster and server construction is now a software defined infrastructure operation, one that can be controlled and automated at scale.
Moving data disks out of server chassis onto the network enables infrastructure actions not generally possible with standard rack servers.
For example, physical resources of servers can be tuned as the profile of deployed application stacks change; clusters can be grown or shrunk as needed through server and drive rebalancing; and server failure recovery can avoid replication by simply reassigning drives from failed servers to non-failed ones.
DriveScale Central provides easy cloud based administration of your DriveScale deployments and an off-site resource for observing behavior of your infrastructure.
DriveScale Central supports Call Home capabilities for deployments, and provides insights about how best to optimize your environments.
DriveScale Central’s own big data engine will use anonymized metadata from myriad environments to provide actionable recommendations for infrastructure optimization. For example, based on patterns gleaned from other customers, DriveScale Central could recommend a rebalancing of resources to avoid an impending capacity constraint; or it could recommend a tactical firmware update to improve performance of a cluster.
As scale-out data center best practices evolve, DriveScale Central’s ability to inform you of how best to manage your infrastructure will evolve as well.