Taneja Group | IO
Join Newsletter
Forgot
password?
Register
Trusted Business Advisors, Expert Technology Analysts

Items Tagged: IO

news

Think Technology: Data Center Infrastructure Unlocking I/O: Clearing The Path To The Cloud

Pages 54-57: Interview with Jeff Byrne and Jeff Boles, Senior Analysts at Taneja Group. Although server and storage virtualization are key enabling technologies for delivering Data Center Infrastructure on-demand and on-tap, we believe the achievement of the Cloud vision of true flexibility and agility is still a distant dream in most environments today. We believe virtual machine environments place unique demands on network infrastructure. Although virtual machines can simplify the physical server infrastructure, they add complexity to the LAN and SAN fabrics within the data center. We believe most issues preventing data centers from achieving their Cloud vision today center on the network, and more specifically at the interfaces between the server and the network and storage – a.k.a the I/O. In this white paper focused on I/O, we highlight some innovative and emerging solutions to these problems and the companies leading efforts to pioneer and evangelize these solutions.

  • Premiered: 02/10/11
  • Author: Taneja Group
  • Published: ThinkEquity LLC
Topic(s): TBA IO virtualization TBA Cloud TBA IO TBA Server IO TBA SAN IO
Profiles/Reports

The Kaminario K2: Transforming the Costs and Capabilities of Storage Performance

In this product profile, we’ll take a look at what we think is required to deliver a true enterprise-class storage foundation for improving application performance, and one vendor's distinctly different approach to delivering a high performance storage solution. That solution - the Kaminario K2 – delivers a compelling approach for those enterprises in need of faster storage for greater application performance.

Publish date: 02/28/11
news

Taneja Group Research: The Costs of Performance

What's an IO worth to you? Is it worth more than a gigabyte? Less? That's a hard question for many IT and business professionals to begin to consider; yet we often see it bandied about. It certainly has merit, it just isn't easily understood.

  • Premiered: 04/18/11
  • Author: Taneja Group
  • Published: EnterpriseStorageForum.com
Topic(s): TBA IO
Profiles/Reports

The Cost of Performance

What’s an IO worth to you? Is it worth more than a gigabyte? Less? That’s a hard question for many IT and business professionals to begin to consider; yet we often see it bandied about. It certainly has merit, it just isn’t easily understood. In this industry article, Taneja Group takes a look at how big the cost of performance is, and with that understanding in mind, we’ll look at two examples of new solutions and what they suggest is a changing way to get cost-effective performance inside the data center walls.

Publish date: 04/22/11
news

I/O: The next frontier

Processors get faster, networking tech takes it up a notch and bus designs keep up the pace, but they may all be dragged down if we can’t find a fix for slow I/O performance. There’s no question I/O is the next frontier the computer industry must conquer. We’ve met the compute challenge reaffirming Moore’s Law over and over again as the industry doubles processing power every 12 months to 18 months. Memory speeds have also kept pace with the CPU, so processors and RAM can feed each other at similar speeds. In the realm of networking, the technologies seem to enjoy a big kick every three years to five years. With 10 Gigabit Ethernet (10 GbE) in the volume implementation stage and 40 Gig parts already available, we’re swimming in bandwidth.

  • Premiered: 09/21/11
  • Author: Arun Taneja
  • Published: TechTarget: SearchStorage.com
Topic(s): TBA IO
news

I/O performance in need of a fix

What you’ll learn in this tip: The computer industry has overcome a multitude of technological challenges in the past several years. Networking and memory speeds have increased, processors have gotten faster and 10 Gigabit Ethernet (10 GbE) has allowed for a massive increase in bandwidth. However none of these advances will remain beneficial if I/O performance doesn’t improve. Author Arun Taneja outlines the basics of I/O and explains why critical applications are stalled due to I/O performance issues. There are many supposed keys to this decades old issue -- while some turn to Flash, Flash memory or NAND flash memory chips, others look to solid-state and solid-state drive (SSD) controllers.

  • Premiered: 11/18/11
  • Author: Arun Taneja
  • Published: TechTarget: SearchStorage.com
Topic(s): TBA IO TBA TechTarget TBA Arun Taneja TBA IO performance
Profiles/Reports

10X The VM Density With Marvell Dragonfly: Turning up IO density, no storage change required

There’s good news this year – the long and most tenacious vexation of the storage engineer is finally receiving redress. That vexation is none other than performance. This year, the market is seemingly awash in innovators paying attention to the challenges of performance, and the solutions are very, very real.

Yet as has always been the case, most are very hard solutions to engineer into production data centers. The storage challenge is such that it isn’t easy to shoehorn a solution into the place of an existing storage system or product that simply isn’t measuring up. Aside from the basic mechanics around floor space, SAN connections and physical cabling, storage performance solutions in the past have often looked entirely different logically (different storage pool, with potentially foreign provisioning and configuration), and standard storage features such as snapshots may be completely missing. And that’s just the case with the most typical of performance solutions – when dabbling in the extremely exotic like Oracle’s Exadata, the re-engineering can become truly significant.

But amongst this backdrop, some vendors are crafting together solutions that are much different. Such products are the benefactors of significant leaps ahead in technology over the past year. It is now possible to harness extremely high power special purpose processors of all sorts, store data on high performance solid state media of many types and form factors (NAND, RAM, disk, expansion cards, appliances, and more), and the storage industry’s collective knowledge of how to architect software innovation in the path of latency sensitive IO has advanced by leaps and bounds. Emerging solutions are solving extreme IO challenges with a nearly transparent software, adapter, or appliance model, and whole new generations of performance-geared storage are entering the market.

With this in mind, Taneja Group has eagerly awaited hands-on time with one of the first products that looks poised to represent the easiest to use and most cost effective platform available to address pressing performance issues – the Marvell DragonFly storage accelerator for virtual and bare-metal applications. This product typifies a category of solution that we recently labeled “Server-based Storage Accelerators” (our recent article on this topic is available here: http://bit.ly/GU6UjS). Server-based Storage Accelerators are server-integrated devices that are coupled with a host-based software layer to intercept, cache, and optimize IO transactions so that data remains stored on backend, consolidated and feature rich storage, but the transactional IO is offloaded to an in-the-server acceleration card with massive horsepower. Market entrants have proliferated through startups, acquisitions, and major vendor announcements. Marvell was certainly one of the first to announce product development in this area, and with a long pedigree in storage intellectual property (all the way down to NAND interfaces and HDD read channels) as well as a product that embodied the perception of simplicity, we looked forward to a closer examination.

In early February of 2012, we began spending that hands-on time with the Marvell DragonFly accelerator, and as testament to our findings, we continue to run the Marvell DragonFly accelerator in our lab facility in Phoenix, Arizona to this day. 

We’ve had significant opportunity to put Marvell’s DragonFly to work in several different ways during that time.  Early on, we validated how DragonFly performed under synthetic read and write benchmarks on Linux workstations (using 4K FIO benchmarks on Redhat Enterprise Linux 5 and 6), and we’ve periodically used the Marvell DragonFly with various read/write small block workloads from various virtual and physical systems, and across both block and file storage.  But as we began intentionally evaluating the DragonFly in-depth, we most wanted to examine the DragonFly behind a meaningful, real world workload that both storage and server managers would look at as representative of their own current challenges.  With this in mind, we set out to evaluate virtual machine density, otherwise known as VM density. 

We define VM density as the maximum number of virtual machines that can be run with acceptable performance by a given set of infrastructure.  Over the past few years, the age of virtualization has rapidly changed the importance of storage performance.  Storage performance can have a drastic impact on VM density by choking off the precious IO that the hypervisor and virtual machines need, and thereby drastically increasing apparent CPU load because of IO wait cycles and latency.

The bottom line is the Marvell DragonFly accelerator can let the customer put a unique combination of commodity, off-the-shelf SSD to work behind a specialized, high performance PCIe controller, and turn solid state to the task of pure IO acceleration in a way that few others can.  Because the pure performance of SSD is unleashed without changing the centralized storage of data, and the effect is completely transparent to the infrastructure, the DragonFly accelerator’s ability to combine SSD with PCIe means massive performance without compromises.  For those who have not been watching, this is a first for a storage performance product.  A few highlights from our findings include:

  • A cost per IO that looks to be many times more cost effective than other approaches to enterprise class SSDs, or PCIe attached solid state storage.
  • Storage acceleration that can be implemented with no reconfiguration or alteration of current enterprise storage.
  • Acceleration that can optimize the sustainable IO from SSD media by as much as 19X (Marvell DragonFly + SSD, versus SSD only).  DragonFly acts as a cache for much larger backend storage by using SSD in this manner, and can deliver total IO that is well beyond the limits of dedicated server storage today (solid state or otherwise), and compares favorably to the horsepower behind entire enterprise class arrays.
  • All told, this translates into a real world 10X improvement in a tested virtual environment, specifically a 10X increase in IO-limited virtual machine density, allowing IO constrained organizations to run 10X as many desktops per physical server.

All told, the Marvell DragonFly looks like a mature product that delivers tremendous performance acceleration for enterprise and cloud data centers. For a product that may cost substantially less than any given single server, this is a notable accomplishment.  Moreover, since this technology can be deployed in front of a shared backend storage system (block or file) the performance acceleration can be applied against terabytes of capacity.  Then a business can in essence “scale-out” this performance by purchasing more accelerators for more servers, assuming a working set of data is small enough to fit inside of the SSD devices attached to the DragonFly.  The dollars per IO may not get much better than this.

Publish date: 08/20/12
news / Blog

Storage Performance - Maybe It Never Was the Array’s Problem

In one of the biggest news announcements of 2012, QLogic has announced a major product initiative that looks poised to fundamentally change customer challenges around storage performance.

  • Premiered: 09/07/12
  • Author: Taneja Group
Topic(s): Qlogic server Acceleration SSD IO Storage perfrmance
news

Astute Networks' Appliance Eliminates Virtual Machine I/O Performance Barriers...

LEADING ANALYST FIRM REPORTS THAT ASTUTE NETWORKS’ HIGH-PERFORMANCE FLASH VM STORAGE APPLIANCE ELIMINATES VIRTUAL MACHINE I/O PERFORMANCE BARRIERS FOR VIRTUAL SERVER AND VIRTUAL DESKTOP ENVIRONMENTS

  • Premiered: 09/11/12
  • Author: Taneja Group
  • Published: Astute Networks Press
Topic(s): TBA Astute Networks TBA VM TBA IO TBA Virtual Server TBA virtual desktop TBA VDI
news

Accelerating the SAN, with the Server

Just a few short months ago, a number of vendors in the market started introducing flash-based, in-the-server, storage acceleration technologies that we label Server-based Storage Accelerators (which I also refer to as “accelerators” in this article). Across the board, such devices were primarily PCIe form factor cards with on-board flash memory that plugged into a server motherboard slot. Through driver or other software inserted into the server OS’s software stack, the solution would intercept I/Os, cache data from SAN-attached disk onto a NAND-flash cache, and then redirect future I/O requests to that cache.

  • Premiered: 09/13/12
  • Author: Taneja Group
  • Published: InfoStor.com
Topic(s): TBA SAN TBA Storage Acceleration TBA accelerators TBA Storage Accelerators TBA IO TBA Qlogic TBA Jeff Boles
Profiles/Reports

Accelerating I/O Intensive Virtualized Applications

Shifting Into High Gear with Astute Networks ViSX G4 Flash VM Storage Appliances

Virtualization is a great boon to IT shops for it’s flexible and cost-efficient infrastructure that consolidates previously physically sprawling applications and servers. But current hypervisor technologies are still evolving support for high-end performance requirements, especially for shared but external-to-the-server resources like storage. Many IT shops trying to convert deeper into their portfolio based on initial virtualization success have run up against frustrating limits as to which of their more demanding applications can be effectively virtualized and still be delivered with good service. Virtualizing I/O intensive applications remains a significant challenge, especially in IT organizations that are building their virtualization environments with traditional storage arrays in order to enable virtual machine migration and provide sufficient data protection.

Most mission critical applications are I/O intensive, relying on databases or providing end-user communication channels (e.g. email). VDI efforts in particular can become I/O performance constrained even at small scales. If virtualized I/O constraints with traditional storage are limiting the number of vms per server, or preventing virtual hosting for I/O intensive apps like databases, email, and VDI, then flash technologies seem to promise a tailor-made high-performance solution. But flash can be an expensive investment to acquire and hard to deploy and manage to assure a solid ROI. With flash, performance can be bought, but cost-conscious IT organizations must choose wisely or risk implementing expensive and ultimately unsatisfactory or limiting solutions.

An ideal performance solution would drop in to an existing virtual environment, currently constrained or otherwise, and accelerate performance without re-architecting the storage layer, without re-implementing data protection, and without creating new burdens for the virtual server administrator. It should supercharge the environment to enable greater vm density, deliver better than physical performance for designated apps, and support VDI working at scales that make sense for wholesale adoption. In this product profile we will examine in detail the new Astute Networks ViSX G4 VM Storage Appliance to see how it fits this ideal profile – deploying without disruption to truly accelerate virtualization performance, increase VM density, and further the adoption of virtualization across I/O and mission-critical applications.

Publish date: 08/27/12
Profiles/Reports

Closing the Virtual IO Management Gap

Assuring Service Throughout the Data Center with Infrastructure Performance Management

There is a significant and potentially costly management gap in virtualized server environments that rely solely on hypervisor-centric solutions. As organizations virtualize more of their mission-critical applications, they are discovering that the virtual versions of these apps continue to depend on the rock-solid storage availability and top-notch IO performance they had when physically hosted. Assuring great service to virtualized clients still requires deep performance management capabilities along the whole IO infrastructure path down to and including shared storage resources.

Cohesive hypervisor management solutions like VMware’s vCenter Operations Management Suite provide a significant advantage to virtual administration by centralizing and simplifying many traditionally disparate management tasks. However, there is a significant management blind spot in the view of end-to-end IO infrastructure when looking at it from the native virtual server perspective. Enterprises relying more and more on virtualized IT delivery need to address this natural management gap with Infrastructure Performance Management (IPM). A lack of robust IPM will degrade or even prevent the deployment of critical applications into a virtual environment – at best losing out on the benefits of virtualization and the opportunities for cloud, at worst causing severe degradation and service outages for all applications sharing the same virtual infrastructure pools.

In this paper we review the virtual performance management landscape and the management strengths of the most well-known hypervisor management solution – VMware’s vCenter Operations Suite - to understand why both the market perception and resulting admin reliance on it is so high. We look at how that reliance overlooks a critical gap for IO and storage, and what the implications of that blind spot are for ensuring total performance. Finally, we examine how the unique IO-centric capabilities of Virtual Instruments’ VirtualWisdom close that gap by correlating complete IO path monitoring with both physical and virtual infrastructure, and how by using VirtualWisdom with vCenter Ops one can achieve a complete end-to-end picture that enables mission-critical applications to be successfully virtualized.
 

Publish date: 08/30/12
news

Astute ViSX Storage Removes Storage and Network I/O Constraints

Astute Networks, Inc. announced that its ViSX G4 Flash VM Storage Appliance has been featured in the Taneja Group report, Accelerating I/O-Intensive Virtualized Applications.

  • Premiered: 09/19/12
  • Author: Taneja Group
  • Published: Storagenewsletter.com
Topic(s): TBA Astute Networks TBA IO TBA Storage
news

Mainstreaming High IO Performance with Flash Cache

Servers are growing more and more powerful, but decades-old storage controller technology has not kept pace. This puts storage at an extreme disadvantage just as companies are growing huge infrastructures of virtual and physical systems, applications of all types and very large volumes of primary data.

  • Premiered: 12/20/12
  • Author: Taneja Group
  • Published: Enterprise Storage Forum
Topic(s): TBA ESF TBA Enterprise Storage Forum TBA SSD TBA Flash TBA nexsan TBA IO TBA cache TBA IOS TBA tiering TBA Enterprise
news

Taking QoS implementation to a new level

An effective QoS implementation helps tunes data storage to meet the specific needs of applications. New tools that offer more automation are emerging to help.

  • Premiered: 01/08/13
  • Author: Arun Taneja
  • Published: TechTarget: SearchStorage.com
Topic(s): TBA Arun Taneja TBA QoS TBA Performance TBA IO TBA Auto-Tier TBA software TBA TechTarget
Profiles/Reports

Mainstreaming High IO Performance with Flash Cache

Advances in solid-state drives have helped by introducing higher performance/lower latency into the computing stack, and customers do not necessarily have to sacrifice simplicity or budgets for performance improvements. However, these SSD products – which may be at the server, network or storage layers -- can be very expensive and complex to deploy and manage even at the enterprise level, let alone the mid-market. Customers want and need the performance boost from SSD products but they are asking if the improvement is worth the expense, management complexity, and confusion around different SSD offerings. The answer is: it depends. 

Publish date: 12/27/12
Profiles/Reports

Mainstreaming High IO Performance with Flash Cache

Advances in solid-state drives have helped by introducing higher performance/lower latency into the computing stack, and customers do not necessarily have to sacrifice simplicity or budgets for performance improvements. However, these SSD products – which may be at the server, network or storage layers -- can be very expensive and complex to deploy and manage even at the enterprise level, let alone the mid-market. Customers want and need the performance boost from SSD products but they are asking if the improvement is worth the expense, management complexity, and confusion around different SSD offerings. The answer is: it depends. 

Publish date: 12/27/12
news

VDI storage problem? Forget extra SAN -- use server RAM

Without some kind of storage optimization or a lot of expensive storage, VDI projects stall well before companies scale their environments.

  • Premiered: 03/20/13
  • Author: Taneja Group
  • Published: TechTarget: SearchVirtualDesktop
Topic(s): TBA VDI TBA RAM TBA Storage TBA Virtualization TBA SAN TBA IO TBA Flash TBA Atlantis Computing TBA Hybrid
Profiles/Reports

EMC PowerPath/VE: Enhancing resiliency, performance, and management

Unfortunately, too many data centers rely solely on native multipathing tools, and tolerate consequent and oftentimes unrecognized compromises in efficiency, management, and resiliency. Seemingly though, only one storage juggernaut has ever delivered a truly differentiated and distinguished approach to multipathing – EMC. EMC’s PowerPath offers multipathing for VMware, Windows, Linux, AIX, Solaris, and HP-UX. Based on a secret sauce of patented, path-optimizing algorithms, the PowerPath/VE version of the PowerPath software family optimizes and enhances management for I/O beneath VMware vSphere and the virtual data center.

However, even with VMware there is no such thing as virtualizing the complexity out of the virtualized data center, especially when it comes to storage. I/O characteristics become much more challenging to manage from multiple VMs running on a single host. Woven together into a data center of many hosts, I/O becomes even more complex. I/O suddenly becomes dependent upon both a physical fabric, plus a virtual fabric – either of which may introduce errors or less than optimal performance. This is what makes the idea of “pathing” – how I/O travels from VM to storage – critically important in the virtualized data center. Moving I/O across the lowest latency paths, and avoiding outages introduced by misconfiguration or error will ultimately determine whether the virtual data center holds up under pressure or not. Moreover, the secondary capabilities introduced by innovative pathing technologies can add even more value in complex infrastructures by enhancing management and increasing the efficiency of storage interaction.

Virtualization technology has had a transformational impact on computing domains: providing deep consolidation for servers, network fabrics, and the storage pools behind individual servers. Today, the range of capabilities has made it a natural development to weave virtualized computing into virtualized data centers. VMware is the market leader in this area and vSphere a leading product for virtualizing modern data centers.

This Product in Depth will detail the challenges around virtualizing the data center and how EMC‘s PowerPath/VE creates unique value for VMware virtual data centers.

Publish date: 03/29/13
news

AWS storage doesn't have to be a complex undertaking, experts say

Amazon Web Services (AWS) offers a variety of storage options, but choosing between them doesn't have to be a complex undertaking.

  • Premiered: 03/20/14
  • Author: Taneja Group
  • Published: Tech Target: Search Cloud Applications
Topic(s): TBA Amazon TBA AWS TBA Storage TBA Block Storage TBA Amazon EBS TBA Amazon Glacier TBA Disk TBA Rackspace TBA Microsoft TBA IBM TBA object storage TBA File Storage TBA API TBA iSCSI TBA IO