Dark Reading is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.


09:12 AM
George Crump
George Crump

Maximizing IOPS With SSD

In a recent series of entries I covered several storage technologies that can help a data center maximize their CAPEX. Most of that series focused on cutting costs by using less primary storage either through archiving or efficiency. Another way to maximize your CAPEX investment is to maximize IOPS with SSD (Solid State Disk) technology.

In a recent series of entries I covered several storage technologies that can help a data center maximize their CAPEX. Most of that series focused on cutting costs by using less primary storage either through archiving or efficiency. Another way to maximize your CAPEX investment is to maximize IOPS with SSD (Solid State Disk) technology.How can SSD, one of the most expensive forms of storage maximize your CAPEX? They can increase the amount of IOPS you can deliver per GB of storage. This leads to less space and power consumed per IO.

As we discussed in our white paper "Visualizing SSD Readiness" many applications today can deliver enough IO requests to the storage system that they can support drive array groups with very large spindle counts. The larger the number of mechanical spindles in an array the better it typically will perform. The problem with higher drive count is, well, higher drive count. All of these drives need to be ordered, shelved, racked, managed and powered. All of that costs money. Your application may be able to sustain 300 drives, but can your budget?

There is also a capacity utilization issue as well. While you have an application that can support 300 mechanical drives, at today's drive capacities that can lead to TB's of unused space. Its true that with a SAN you can put other applications on those spindles as well but doing so could effect the performance of the key application and the other applications more than likely have no need for the high performance storage you had to buy for the original application.

What makes more sense is targeting the capacity where its needed, an almost application specific storage tier. In block IO this is typically done by adding SSD to an existing storage system or taking an even more targeted approach and utilizing SSD specific systems from companies like Texas Memory or Violin Memory. In fact Fusion-io and Texas Memory can take this application specificity even further by leveraging one of their PCI-E based cards and put the IOPS right in the application server itself.

One of the challenges is deciding how and when to get the right data sets on SSD. Often this is a specific application or data set like a hot Oracle table and moving that table to an SSD is a straightforward process. For more broad use of SSD, especially in NAS storage, the challenge becomes greater. One solution is to use a storage virtualization appliance from companies like NetApp or DataCore to unify the management of the SSD.

In NAS IO a viable alternative is beginning to be presented by companies like Storspeed. These companies are creating an evolved form of cache technologies to intelligently move data in and out of tiered storage. This allows SSD to be used to its maximum capacity and yet always have the most active data set on that high speed tier. As well as to give the user specifc control over what applications or data leverage that tier.

Regardless of the approach, leveraging SSD, especially with its increasing affordability, is an excellent way to reduce CAPEX expenditures and one that can have an immediate payoff.

Track us on Twitter: http://twitter.com/storageswiss

Subscribe to our RSS feed.

George Crump is founder of Storage Switzerland, an analyst firm focused on the virtualization and storage marketplaces. It provides strategic consulting and analysis to storage users, suppliers, and integrators. An industry veteran of more than 25 years, Crump has held engineering and sales positions at various IT industry manufacturers and integrators. Prior to Storage Switzerland, he was CTO at one of the nation's largest integrators.


Recommended Reading:

Comment  | 
Print  | 
More Insights
Newest First  |  Oldest First  |  Threaded View
COVID-19: Latest Security News & Commentary
Dark Reading Staff 8/3/2020
Pen Testers Who Got Arrested Doing Their Jobs Tell All
Kelly Jackson Higgins, Executive Editor at Dark Reading,  8/5/2020
New 'Nanodegree' Program Provides Hands-On Cybersecurity Training
Nicole Ferraro, Contributing Writer,  8/3/2020
Register for Dark Reading Newsletters
White Papers
Cartoon Contest
Current Issue
Special Report: Computing's New Normal, a Dark Reading Perspective
This special report examines how IT security organizations have adapted to the "new normal" of computing and what the long-term effects will be. Read it and get a unique set of perspectives on issues ranging from new threats & vulnerabilities as a result of remote working to how enterprise security strategy will be affected long term.
Flash Poll
The Changing Face of Threat Intelligence
The Changing Face of Threat Intelligence
This special report takes a look at how enterprises are using threat intelligence, as well as emerging best practices for integrating threat intel into security operations and incident response. Download it today!
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
PUBLISHED: 2020-08-08
In JetBrains YouTrack before 2020.2.6881, the markdown parser could disclose hidden file existence.
PUBLISHED: 2020-08-08
In JetBrains YouTrack before 2020.2.6881, a user without permission is able to create an article draft.
PUBLISHED: 2020-08-08
JetBrains YouTrack before 2020.2.8873 is vulnerable to SSRF in the Workflow component.
PUBLISHED: 2020-08-08
In JetBrains Kotlin before 1.4.0, there is a script-cache privilege escalation vulnerability due to kotlin-main-kts cached scripts in the system temp directory, which is shared by all users by default.
PUBLISHED: 2020-08-08
In JetBrains TeamCity before 2020.1, users with the Modify Group permission can elevate other users' privileges.