Solid State Storage

Material on this page is intended solely for the purpose of content review by SNIA members. Tutorial material may be read and commented upon by any SNIA member, but may not be saved, printed, or otherwise copied, nor may it be shared with non-members of the SNIA. Tutorial managers are responsible for responding to all comments made during the open review period. No responses will be given to comments made outside the open review period.

Jump straight to an abstract:

The Abstracts

Accelerating Applications and File Systems with Solid State Storage
Jacob Farmer

The data storage industry is experiencing a mini renaissance as a flurry of new solid state storage devices come to market. SSDs are now available in a broad spectrum of price, form factor, and performance. It is hard enough for a storage architect to sort out the myriad of choices, but that is nothing compared to the challenge of figuring out how to deploy SSD technology in an affordable and effective way.  This lecture focuses on practical approaches for integrating SSD technology into your existing storage infrastructure.  We explore different insertion points in the SNIA shared storage model to reveal a variety of methods for accelerating databases, email systems, virtualization platforms, content repositories, local file systems and network file systems (NAS).

Learning Objectives

  • Attendees will learn about different ways to apply SSD technology to the SNIA shared storage model. 
  • Attendees will learn about ways to find ROI by growing performance through SSD while expanding capacity through conventional disk and cloud storage. 
  • Attendees will learn about specific ways to accelerate applications and file services.

Using Client Solid State Drives in Datacenter Applications
Tony Roug

SSD vendors have designed drives specifically targeted for datacenter based on SAS or PCIe and on SLC NAND technology. Primarily because of the SAS performance and SLC NAND endurance.  For many usages, client drives based on the SATA interface and MLC and 3BC technology are more cost effective and can support the endurance and write performance required by the end user. This course presents how client drives can be a cost effective solution for datacenter applications.

Learning Objectives

  • Understand tradeoffs for using SSDs based on SLC NAND versus SSDs based on MLC NAND in datacenter 
  • Understand how for specific applications how SSDs based on MLC NAND are more cost effective 
  • Understand how to tune MLC NAND to your application needs

Latency: The Heartbeat of a Solid State Disk
Levi Norman

This SNW tutorial session is about the number one reason an IT manager would move away from HDDs and towards solid state disks (SSD)...latency.  More importantly low latency.  Latency becomes less of just a number and more an important metric when considering implementing any serious performance storage related solution.  Today low latency can only effectively be addressed by one particular type of storage architecture and that's an enterprise SSD design.  Latency in a technical environment is synonymous with delay.  More succinctly latency in terms of a SSD is how long it will take for a request to complete its round trip cycle from the time the request enters the device to the time that it leaves the device with the 'payload' in tow.  In a storage world where metrics such as $/GB are entrenched as a de-facto standard of measurement, and $/IOPS has arisen to become a relevant metric, we continue to miss a critical discussion point.  And that is that low latency is the most important thing that can be delivered to a performance sensitive application or a workhorse database environment.  In this session we will discuss the merits of low latency solutions and what they mean when coupled with a high IOPS and a large bandwidth design.  From a business perspective, low latency will be discussed in terms of how it saves money, makes money or ideally does both for an enterprise organization.

Learning Objectives

  1. Latency, what is it? 
  2. Why does latency matter, no one seems to be really talking about it? 
  3. How coupling low latency to high IOPS and generous bandwidth creates performance solutions.