Software-Defined Data Centers (SDDC) is emerging as a hot topic in my customer conversations as a means to transform data centers into IT service centers focused on increasing the agility and speed at which they support their application and increase developer productivity.
In many ways SDDC could be considered the evolution from server virtualization to data center virtualization. The SDDC architectural model seeks to define data center resources, specifically compute, network, storage and security, in software in order to free resources from their hardware boundaries and enable such service level agility.
As a pillar in the SDDC stack, Software Defined Storage (SDS) pools hardware storage resources and allows them to be programmatically defined in software. This design provides the means for storage services to be provisioned and consumed based on policies and deployed on a wide range of hardware spanning vendor optimized to commodity to cloud.
Admittedly the industry lacks a standard definition of SDS; I’d like to share with you the NetApp view of Software-Defined Storage, which I think can be clearly articulated by these three attributes.
Virtualized Storage Services “Provision Based on Service Levels” — Multiple Hardware Options “Deploy on Platform of Choice” — Application Self-Service “Deliver Services without Compromise”
Virtualized Storage Services For Software-Defined Storage to truly be dynamic, one has to abstract data access and data services from pooled hardware resources. By liberating data access from hardware one gains the ability to provide storage based on service levels versus hardware attributes. NetApp provides this capability with our Storage Virtual Machine (SVM) technology in Clustered Data ONTAP. SVMs are assigned storage resources and services, are the access point for host and user access, and are designed for delegation to an app / org / tenant.
Policy-based storage services often include…
SVMs are the next generation of our vFiler technology. Many of you may recognize by their ONTAP engineering code name vServers, which can be a confusing term when discussing virtualized servers.
Multiple Hardware Options By abstracting data access and data services with SVMs, NetApp customers gain the ability to deploy on the storage on the platform of their choice. One size doesn’t fit all deployments, so by standardizing on storage capabilities in software one can view hardware as a design choice and as the means to scale capacity and/or performance.
Data ONTAP is available on the broadest range of hardware including…
Hardware independence and the best set of data services is precisely how Data ONTAP became the #1 most deployed Storage Operating System.
Application Self-Service As stated earlier, the purpose of a Software-Defined Data Center is to empower development teams and application administrators through the acceleration of IT service delivery. From an SDS perspective this means storage services integrations in the native application administrative interfaces and by providing programmable APIs for custom applications and workflow automation.
The NetApp Zapi API library and application integrations are the broadest available within the storage industry. Below is a just a few of the partners that have integrations at the infrastructure, management and application layer.
ONTAP provides a standardized set of APIs for our customers and partners to innovate solutions to advance their business via application-driven storage services.
Wrapping Up This Post I’m very excited to see the emergence of Software-Defined Storage in support of SDDC initiatives. The broad market is beginning to recognize the value of decoupling storage services from storage devices and focusing on rich integrated, IT service delivery. Admittedly my views are biased, but I feel NetApp’s SDS portfolio is second to none.
Consider this post a mere teaser or introduction to what NetApp has in store. Over the next several weeks I will share greater details on the capabilities in this post and beyond.