For Disks There Are No Good Vibrations

By Michael Feldman

January 3, 2012

Silicon Valley startup Green Platform Corporation has been promoting its vibration dampening solution for rack-based disk storage for a couple of years now. But with the increasing importance of “big data” applications, which places particular emphasis on performant I/O, the company is looking to tap into a $22 billion storage market that is still primarily based on vibration-prone spinning disks. In the process, the company has tweaked its strategy to offer what it calls a “Vibration Management System.”

From Green Platform’s perspective, its opportunity aperture is growing not only because enterprise storage capacity is increasing by leaps and bounds, but also because the disk vibration problem is getting more acute with each subsequent generation of hard drive. The drives themselves are not getting any faster, but as disk capacity grows, the increased density of the media means the head positioning on the tracks becomes more sensitive to vibration — from the disk itself as well as neighboring disks, fans, power supplies, and ambient datacenter vibration. When the head can’t position itself properly on the track due to all this shaking, it has to reposition itself until it can properly execute the read or write, thereby degrading I/O performance.

Green Platform has run tests that indicate there is a significant drop in I/O throughput and latency in high-vibration environments. To mitigate that unfortunate behavior, the company developed a standard 42U, 19-inch rack enclosure based on a carbon-fiber composite designed to dissipate vibration. The rack shelves contain anti-vibration modules, although not every shelf will require one (i.e. the power-supply shelf). When the hard drives are slid into the modules, the composite material acts as a dampener, and is able to reduce vibration up to 1000-fold compared to traditional metal racks.

Larry Gordon, Green Platform’s VP of market development, says you should be able to get at least a 15 percent performance boost if you use their vibration dampening racks. And according to him, that’s on the conservative side. Gordon says they’ve demonstrated more than a 50 percent IOPS increase in a SAN environment with their anti-vibration racks and standard Hitachi storage gear.

The ROI story is that you can avoid over provisioning disks to compensate for the lost performance due to vibration. That saves not only the upfront costs of buying the extra storage, but operational costs associated with power, cooling, maintenance and system administration, not to mention optimizing datacenter real estate. Although Green Platform doesn’t yet have the data to back it up, they also believe their anti-vibration solution will improve system reliability, especially for cheaper drives.

According to the company, an initially outlay of $21,600 for their vibration dampening gear (accommodating 10 3U shelves) can save nearly $150,000 over three years. Those numbers are based on a 1/3 SAS and 2/3 SATA hardware mix and storage needs that are growing at a 30 percent annual clip. That 7X payback is based on the aforementioned 50 percent IOPS, but even much more conservative performance numbers should yield a respectable ROI.

Even with those numbers in hand, the company had trouble convincing customers they had enough of a vibration problem in their own datacenter to warrant a solution. So Green Platform repositioned itself as a service company, offering a Vibration Management System (VMS), which they sell as a subscription.

In doing so, Green Platform has cast itself as a datacenter infrastructure management company. Over the last couple of decades, datacenters have become so large and inefficient that a whole industry of datacenter analyst firms have come into being. “We’re part of that category,” says Gordon. Green Platform is selling the idea that vibration, just like temperature, needs to be continuously monitored to run a datacenter efficiently.

In a nutshell, the company’s VMS service measures a datacenter’s vibration problem by outfitting the existing hardware with sensors, mediating the vibration with the Green Platform dampening racks, and then monitoring the vibration on a continuous basis as conditions in the datacenter evolve. The vibration sensors are attached to the storage chassis at various points, and with the help of a performance tool, the system will determine how much performance is being lost to vibration and how much can be recovered. The results are collected in Green Platform’s own cloud-based system where users can access it remotely via a dashboard.

The initial monitoring is done over months to exercise various workloads and situations. For example, cooling fans that need to continuously run because of temperature or workload stress can have a huge impact on the vibration. The idea is to pinpoint the source of problem so the anti-vibration racks can be deployed judiciously. As the datacenter infrastructure grows, monitoring will make sure vibration is dampened at the right place. Also, system administrators can use the knowledge to implement operational changes that minimizes vibration across the facility.

Green Platform’s VMS service runs $1,500 per rack/month, which includes the rack dampening hardware. To generate interest, the company will offer their monitoring system with existing metal racks at no charge. Their hope is that once the customer sees how much performance is being lost, the anti-vibration racks will seem like a no-brainer.

According to Gordon, they think there is a $1 billion opportunity in vibration management to be had. That’s based on the belief that there is a $5 billion “vibration penalty” that users are currently paying for unbeknownst to them. Basically, Green Platform is saying for every dollar you spend on their solution, you can save 5 dollars on storage hardware and operational costs.

Of course, one can solve the vibration problem completely by switching to solid state disks. But SSDs are not expected to replace hard disks anytime soon. According to iSuppli Research, SSD shipments hit just 7.2 million units in 2010 versus 662 million units of hard drives. Analysts there maintain SSDs will not threaten hard drive dominance within the next five years, mainly due to the greater expense of flash memory. “Customers still care about cost per bit,” says Gordon.

The next step for Green Platform is to collect some proof points to bolster its story, so the company is actively looking for beta customers to give their solution a whirl. In general, any application that relies on native hard drive performance (is not cache- or compression-friendly) should be a candidate. That includes essentially all Hadoop cluster applications, HPC simulations and analytics, any I/O bound application, video streaming, and most workloads that use server virtualization.  If you have such an application and think your storage is underperforming, the Green Platform solution might be worth a look.

Related Articles

Startup Takes Aim at Performance-Killing Vibration in Datacenter

GPC Announces Vibration Management System for Improving Storage Performance

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Azure Benchmarks HC-series across 20,000 cores for HPC

June 25, 2019

Cloud provider Microsoft Azure’s push into HPC continues to gain momentum. In a blog last week, Evan Burness, principal program manager, Azure HPC, announced HC-series Virtual Machine are now available in West US 2 and Read more…

By John Russell

MLPerf Expands Toolset; Launches Inferencing Suite

June 24, 2019

MLPerf today launched a benchmark suite for inferencing, v0.5, which joins the MLPerf training suite launched a little over a year ago. The new inferencing benchmark, which has been anticipated, covers models applicable Read more…

By John Russell

A Behind-the-Scenes Look at the Hardware That Powered the Black Hole Image

June 24, 2019

Two months ago, the first-ever image of a black hole took the internet by storm. A team of scientists took years to produce and verify the striking image – and now, Tom Coughlin (on behalf of Supermicro) has provided a Read more…

By Oliver Peckham

HPE Extreme Performance Solutions

HPE and Intel® Omni-Path Architecture: How to Power a Cloud

Learn how HPE and Intel® Omni-Path Architecture provide critical infrastructure for leading Nordic HPC provider’s HPCFLOW cloud service.

For decades, HPE has been at the forefront of high-performance computing, and we’ve powered some of the fastest and most robust supercomputers in the world. Read more…

IBM Accelerated Insights

Avoid AI Redo’s by Starting with the Right Infrastructure

Do you know if you have the right infrastructure for AI? Many organizations don’t have it. In a recent IDC survey, “77.1% of respondents say they ran into one or more limitations with their AI infrastructure on-premise and 90.3% ran into compute limitations in the cloud.” Read more…

U.S. Blacklists Sugon, 4 Others from Access to Advanced Technology

June 21, 2019

Just as ISC19 wrapped up yesterday, showcasing the latest in supercomputing technology, the U.S. added five Chinese entities including Sugon to its blacklist prohibiting them from access to advanced technology vital to s Read more…

By John Russell

MLPerf Expands Toolset; Launches Inferencing Suite

June 24, 2019

MLPerf today launched a benchmark suite for inferencing, v0.5, which joins the MLPerf training suite launched a little over a year ago. The new inferencing benc Read more…

By John Russell

Is Weather and Climate Prediction the Perfect ‘Pilot’ for Exascale?

June 21, 2019

At ISC 2019 this week, Peter Bauer – deputy director of research for the European Centre for Medium-Range Weather Forecasts (ECMWF) – outlined an ambitious Read more…

By Oliver Peckham

ISC Keynote: Thomas Sterling’s Take on Whither HPC

June 20, 2019

Entertaining, insightful, and unafraid to launch the occasional verbal ICBM, HPC pioneer Thomas Sterling delivered his 16th annual closing keynote at ISC yesterday. He explored, among other things: exascale machinations; quantum’s bubbling money pot; Arm’s new HPC viability; Europe’s... Read more…

By John Russell

IBM Claims No. 1 Commercial Supercomputer with Total Oil & Gas System 

June 20, 2019

IBM can now boast not only the two most powerful supercomputers in the world, it also has claimed the top spot for a supercomputer used in a commercial setting. Read more…

By Staff Report

HPC on Pace for 5-Year 6.8% CAGR; Guess Which Hyperscaler Spent $10B on IT Last Year?

June 20, 2019

In the neck-and-neck horse race for HPC server market share, HPE has hung on to a slim, shrinking lead over Dell EMC – but if server and storage market shares Read more…

By Doug Black

ISC 2019 Research Paper Award Winners Announced

June 19, 2019

At the 2019 International Supercomputing Conference (ISC) in Frankfurt this week, the ISC committee awarded the event's top prizes for outstanding research pape Read more…

By Oliver Peckham

ISC Keynote: The Algorithms of Life – Scientific Computing for Systems Biology

June 19, 2019

Systems biology has existed loosely under many definitions for a couple of decades. It’s the notion of describing living systems using first-principle physics Read more…

By John Russell

Summit Achieves 445 Petaflops on New ‘HPL-AI’ Benchmark

June 19, 2019

Summit -- the world's top-ranking supercomputer -- has been used to test-drive a new mixed-precision Linpack benchmark, which for now is being called HPL-AI. Traditionally, supercomputer performance is measured using the High-Performance Linpack (HPL) benchmark, which is the basis for the Top500 list that biannually ranks world's fastest supercomputers. Read more…

By Oliver Peckham

High Performance (Potato) Chips

May 5, 2006

In this article, we focus on how Procter & Gamble is using high performance computing to create some common, everyday supermarket products. Tom Lange, a 27-year veteran of the company, tells us how P&G models products, processes and production systems for the betterment of consumer package goods. Read more…

By Michael Feldman

Cray, AMD to Extend DOE’s Exascale Frontier

May 7, 2019

Cray and AMD are coming back to Oak Ridge National Laboratory to partner on the world’s largest and most expensive supercomputer. The Department of Energy’s Read more…

By Tiffany Trader

Graphene Surprises Again, This Time for Quantum Computing

May 8, 2019

Graphene is fascinating stuff with promise for use in a seeming endless number of applications. This month researchers from the University of Vienna and Institu Read more…

By John Russell

Why Nvidia Bought Mellanox: ‘Future Datacenters Will Be…Like High Performance Computers’

March 14, 2019

“Future datacenters of all kinds will be built like high performance computers,” said Nvidia CEO Jensen Huang during a phone briefing on Monday after Nvidia revealed scooping up the high performance networking company Mellanox for $6.9 billion. Read more…

By Tiffany Trader

AMD Verifies Its Largest 7nm Chip Design in Ten Hours

June 5, 2019

AMD announced last week that its engineers had successfully executed the first physical verification of its largest 7nm chip design – in just ten hours. The AMD Radeon Instinct Vega20 – which boasts 13.2 billion transistors – was tested using a TSMC-certified Calibre nmDRC software platform from Mentor. Read more…

By Oliver Peckham

It’s Official: Aurora on Track to Be First US Exascale Computer in 2021

March 18, 2019

The U.S. Department of Energy along with Intel and Cray confirmed today that an Intel/Cray supercomputer, "Aurora," capable of sustained performance of one exaf Read more…

By Tiffany Trader

Deep Learning Competitors Stalk Nvidia

May 14, 2019

There is no shortage of processing architectures emerging to accelerate deep learning workloads, with two more options emerging this week to challenge GPU leader Nvidia. First, Intel researchers claimed a new deep learning record for image classification on the ResNet-50 convolutional neural network. Separately, Israeli AI chip startup Hailo.ai... Read more…

By George Leopold

TSMC and Samsung Moving to 5nm; Whither Moore’s Law?

June 12, 2019

With reports that Taiwan Semiconductor Manufacturing Co. (TMSC) and Samsung are moving quickly to 5nm manufacturing, it’s a good time to again ponder whither goes the venerable Moore’s law. Shrinking feature size has of course been the primary hallmark of achieving Moore’s law... Read more…

By John Russell

Leading Solution Providers

ISC 2019 Virtual Booth Video Tour

CRAY
CRAY
DDN
DDN
DELL EMC
DELL EMC
ONE STOP SYSTEMS
ONE STOP SYSTEMS
PANASAS
PANASAS
VERNE GLOBAL
VERNE GLOBAL

Nvidia Embraces Arm, Declares Intent to Accelerate All CPU Architectures

June 17, 2019

As the Top500 list was being announced at ISC in Frankfurt today with an upgraded petascale Arm supercomputer in the top third of the list, Nvidia announced its Read more…

By Tiffany Trader

The Case Against ‘The Case Against Quantum Computing’

January 9, 2019

It’s not easy to be a physicist. Richard Feynman (basically the Jimi Hendrix of physicists) once said: “The first principle is that you must not fool yourse Read more…

By Ben Criger

Top500 Purely Petaflops; US Maintains Performance Lead

June 17, 2019

With the kick-off of the International Supercomputing Conference (ISC) in Frankfurt this morning, the 53rd Top500 list made its debut, and this one's for petafl Read more…

By Tiffany Trader

Cray – and the Cray Brand – to Be Positioned at Tip of HPE’s HPC Spear

May 22, 2019

More so than with most acquisitions of this kind, HPE’s purchase of Cray for $1.3 billion, announced last week, seems to have elements of that overused, often Read more…

By Doug Black and Tiffany Trader

Intel Launches Cascade Lake Xeons with Up to 56 Cores

April 2, 2019

At Intel's Data-Centric Innovation Day in San Francisco (April 2), the company unveiled its second-generation Xeon Scalable (Cascade Lake) family and debuted it Read more…

By Tiffany Trader

Announcing four new HPC capabilities in Google Cloud Platform

April 15, 2019

When you’re running compute-bound or memory-bound applications for high performance computing or large, data-dependent machine learning training workloads on Read more…

By Wyatt Gorman, HPC Specialist, Google Cloud; Brad Calder, VP of Engineering, Google Cloud; Bart Sano, VP of Platforms, Google Cloud

In Wake of Nvidia-Mellanox: Xilinx to Acquire Solarflare

April 25, 2019

With echoes of Nvidia’s recent acquisition of Mellanox, FPGA maker Xilinx has announced a definitive agreement to acquire Solarflare Communications, provider Read more…

By Doug Black

Nvidia Claims 6000x Speed-Up for Stock Trading Backtest Benchmark

May 13, 2019

A stock trading backtesting algorithm used by hedge funds to simulate trading variants has received a massive, GPU-based performance boost, according to Nvidia, Read more…

By Doug Black

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This