ENTERPRISE AT-SCALE & HPC ENVIRONMENTS REQUIRE A DIFFERENT APPROACH

SSDs and all flash arrays are being marketed as a panacea. This may be true if you’re a small to medium enterprise that simply needs more performance for email servers or wants to speed-up just a few hundred VMs.

But, for Enterprise At-scale and High Performance Computing environments, identifying and removing I/O bottlenecks is much more complex than simply exchanging spinning disk drives with flash devices. Aside from performance – efficiency, scalability and integration are also critical success factors in larger and non-standard environments.

In this domain, selecting a partner with the tools, technology and experience to holistically examine and optimize your entire I/O path can deliver orders of magnitude greater acceleration and competitive advantage to your organization.

INTRODUCING DDN FLASHSCALE

The World’s Fastest, Cost-optimized All Flash Array

Learn More

ENTERPRISE AT-SCALE & HPC ENVIRONMENTS
HAVE UNIQUE REQUIREMENTS

Today, solving the world’s most challenging business and scientific problems require advanced analytics, modeling and simulation applications.

That must be matched with

A massively scalable, high performance, technical infrastructure capable of supporting demanding requirements and speeding time to results.

THEY ALSO HAVE UNIQUE
NON-STANDARD ENVIRONMENTS, WORKLOADS AND SCALE,
WHICH MAKE TRADITIONAL USE CASE FLASH ARRAYS COME-UP SHORT

In today’s highly competitive world, your applications and workflows can only go as fast as your slowest moving part.

Flash promises to remove I/O bottlenecks.

But, what if the bottleneck in your complex, at-scale environment isn’t merely the spinning disk drive (like those in traditional workloads)?

Many at-scale environments are unique, with specialized compute, networking, file systems and code optimization.

They also may have parallelized, complex, multi-step workflows that run on the same platform.

Any of these can be a bottleneck that can’t be broken by simply switching array or drive hardware.

DDN FLASH SOLUTIONS ARE
UNIQUELY QUALIFIED TO ACCELERATE
AT-SCALE ENTERPRISE & HPC WORKFLOWS

THE MOST EXPERIENCE.

Virtually every one of our at-scale customers’ initiatives, environments and challenges are pioneering. For nearly two decades, customers have specifically chosen DDN’s leading-edge at-scale technology and field expertise to make their vision into reality.

At-scale is Different.

Architectures that work fine when managing smaller, traditional use cases become highly inefficient and often degrade performance or break at-scale. We offer several right-sized scale-out building blocks that are many times more dense, efficient and agile than the typical 2U commodity gear designed for small to medium enterprise use cases.

IT’S A PARTNERSHIP.

We begin by collaborating with our customers to understand their vision and then redefine what is technically possible, so they can use technology to achieve their objectives.

END-TO-END.

Then we gain a deep understanding your application set, workflow and entire I/O path before prescribing the right-sized and optimally-placed flash accelerator.

MANY OPTIONS.

Our diverse user base has taught us that “one size doesn’t fit all”. In order to enable faster time to results for your objectives, our comprehensive flash portfolio is at your command: buffer caching, feature-rich and performance-first versions of all flash & hybrid arrays, application-aware software based accelerators.

FEATURED FLASH ARRAYS & TECHNOLOGIES


ULTRA LOW LATENCY, HIGH THROUGHPUT FLASH TIER FOR
ACCELERATING REAL-TIME HPC, BIG DATA & IOT APPLICATIONS

IME240-Front-View-525

DDN IME is a brand new, revolutionary flash tier that allows data to reside right next to compute in a very fast, shared pool of non-volatile memory (NVM). This new data adjacency significantly reduces latency by allowing IME software’s revolutionary, fast data communication layer to pass data without the file locking contention inherent in today’s parallel file systems.

This acceleration technology leverages the high I/O performance of flash which now enables large scale, data-intensive environments to unlock compute cycles that were previously consumed waiting for I/O. Now organizations can run more applications in less time, while compute ROI is significantly increased. This material increase of efficiency and performance is achieved by minimizing I/O bottlenecks and accelerating applications and file systems; all while reducing the erratic performance often found within storage clusters.

TARGET THESE
I/O BOTTLENECKS
WITH IME flash

POSIX & File System Locking
“Problem” Applications
Inhibitors to Real-time
Checkpoint/Restart Durations
MapReduce
System Latency
Multistep Workflows
I/O Wait Time
Redundant File Access
Out of Core Datasets
Unpredictable Performance


PERFORMANCE-FIRST, SCALE-OUT BLOCK STORAGE
ALL FLASH & HYBRID ARRAYS

DDN SFA (Storage Fusion Architecture) All Flash & Hybrid Storage Arrays are most often chosen for use cases that prioritize performance above all else. These users enjoy the flexibility and infinite customization that flash-based block arrays provide for their non-traditional applications, think: massive edge caching, rapid genomic sequencing, HPC modeling & simulation, uncompressed 4K & 8K film editing (for use cases such as VDI, email and OLTP see the EFA section below).

SFA comes in two distinctly sized scale-out building blocks that deliver massive IOPS, bandwidth and scalability in the most efficient, dense form factor.

TARGET THESE
I/O BOTTLENECKS
WITH SFA flash

HDD Latency
Storage Controller Latency
Mixed I/O
Metadata Contention
Path Contention
Encryption
RAID Overhead
System Latency
Multistep Workflows
Redundant File Access

PERFORMANCE-FIRST, SCALE-OUT BLOCK STORAGE
ALL FLASH & HYBRID ARRAYS

DDN EFA (Enterprise Fusion Architecture) leverages years of scale-out, high performance storage expertise to deliver the best-in-class server virtualization storage solution. Designed to efficiently and cost effectively meet every emerging requirement at-scale. EFA elegantly integrates the robust OpenZFS software-defined storage application with DDN’s highly optimized SFA hardware platform to deliver an all-in-one solution for today’s modern converged, virtualized data center.

Intelligent DRAM-based caching enables consistently predictable performance with zero penalty when performing operations such as: writes, dedup, compression, encryption, RAID or even during device rebuild or enclosure loss.

TARGET THESE
I/O BOTTLENECKS
WITH EFA FLASH

Metadata Contention
VDI At-scale Boot Storms HDD Latency Storage Controller Latency Large File & Mixed I/O DeDup, Compression, Encryption Overhead Write-heavy Workloads Path Contention RAID Overhead Data Transfer Between Systems/Islands

APPLICATION-AWARE FLASH CACHE
ACCELERATION SOFTWARE

DDN SFX is both intelligent and highly efficient. This application-aware software dynamically provides out-of-band hints that can allocate more control to your applications. This enables the file system to proactively pre-stage the blocks from spinning disk that will benefit from the cache accelerator and significantly reduce latency.
SFX software requires only inexpensive, commodity SSDs placed directly in your EFA, SFA or Scaler Storage System to accelerate I/O performance by reducing the time CPUs are idle waiting for data from spinning disk.

TARGET THESE
I/O BOTTLENECKS
WITH SFX FLASH

Metadata Overhead
HDD Latency
Application Latency
Small File & Mixed I/O
Read-heavy Workloads
Path Contention

ACCELERATING BOTTOM LINE RESULTS AT SOME OF THE WORLD'S SMARTEST COMPANIES



Join the 1,000+ Customers Who Are Modernizing their Datacenters with DDN Flash Solutions