We all acknowledge that the data is growing at unprecedented rates, but the volume of data is only one of the challenges we’re facing. Additional challenges include…
- Keeping up with constantly changing storage requirements with existing infrastructure
- Storage silos for dedicated applications and workloads that strain management resources
- Inconsistent storage utilization profiles that over burden some areas and inefficiently underutilize other areas
- Management resources spending too much time managing LUNs and volumes in existing environment
- Growing interest in organizations to leverage data more effectively for next-generation applications such as workforce mobility and big data analytics to provide more value-add to business
These challenges can be beyond daunting to even the most seasoned IT professional, but one that EMC is addressing with Isilon for data lake. The concept of the a data lake represents a paradigm shift where data no longer flows in a linear model, but rather uses an enterprise-wide consolidated storage model where data comes in via numerous sources and in many formats, including structured and unstructured. This approach allows an organization to consolidate vast amounts of data into a single store known as the data lake, where it can be secured and analyzed for real-time insights to the business.
So why is Isilon scale-out NAS such a good fit for Big Data?
- Reduced Risk: Isilon allows for the storage to be decoupled from the compute for big data analytics solutions, which then reduces the risk due to performance and capacity growth by managing them separately.
- Faster Results: The key to success with big data comes down to the speed that the data can be loaded and transferred to the analysis stage. With Isilon’s support of multiple protocols, its shared storage architecture eliminates the need to load or transfer data into Hadoop clusters, so requires less time to get results.
- Efficiency: Isilon offers greater than 80% storage utilization, making it extremely efficient with obvious cost savings.
- Hadoop Distribution Support: Isilon allows for a variety of simultaneous Hadoop distributions from Apache, Pivotal, Cloudera and Hortonworks. The key here is the ability to try various distributions without major cost or complexity.
- Performance: Isilon’s performance can be scaled up to 3.75 million file operations per second with over 200 gigabytes per second of aggregated throughput, with an additional option to boost performance with one petabyte of scale-out flash cache. This level of performance is key when supporting demanding applications or bid data analytics workloads.
- Compliance: Enterprise-grade compliance is standard with write once, read many (WORM) protection that prevents any unwanted alteration or deletion of critical data. In addition, Isilon is regulatory and governance secure, meeting the strictest SEC 17a-4 requirements for protection of business-critical data.
- High Availability: For even the toughest recovery point objectives, Isilon offers snapshot capability with almost-immediate, on-demand snapshot restores, giving you the peace of mind your critical data requires.
- Versatility: As unstructured data continues to grow exponentially, the challenges of managing it grow too. Isilon scale-out NAS continues to set the standard for managing this data, as well as numerous other enterprise storage needs.
Drowning in data? Well, now you know…
A scale-out data lake can help your organization reduce costs with a smaller storage footprint that is simple, scalable, efficient and secure. By deploying an Isilon scale-out NAS shared storage, storage silos cease to exist and storage utilization goes up—simplifying your storage infrastructure. All of this while still being able to scale capacity and performance, protect your critical data, and take advantage of big data analytics without the need to move data or invest in a separate analytics infrastructure.
Don’t drown in your data – embrace it!