HYBRID STORAGE ARRAY BUYER S GUIDE - White Papers · 20 Dell EqualLogic PS6510ES ... 31 HP 3PAR...

www.dcig.com

2014 HYBRID STORAGE ARRAY BUYER’S GUIDETHE INSIDER’S GUIDE TO EVALUATING HYBRID STORAGE ARRAYS

By Ken Clipperton

© 2013 DCIG, LLC. All rights reserved.

http://www.dciginc.com

© 2013 DCIG, LLC. All rights reserved.

DCIG 2014 HYBRID STORAGE ARRAY BUYER’S GUIDETHE INSIDER’S GUIDE TO EVALUATING HYBRID STORAGE ARRAYS

Table of ContentsTable of Contents

i

13 Hybrid Storage Array Scores and Rankings14 Overall Scores and Rankings

17 Avere FXT 4200

18 Avere FXT 4500

19 DDN SFA7700

20 Dell EqualLogic PS6510ES

21 Dot Hill AssuredSAN Pro 5000

22 EMC VNX5100

23 EMC VNX5300

24 EMC VNX5500

25 EMC VNX5700

26 EMC VNX7500

27 Fusion–io NexGen n5-50 Storage System



30 Hitachi Data Systems HUS VM

31 HP 3PAR StoreServ 7200

32 HP 3PAR StoreServ 7400

33 IBM Storwize V7000 Unified

34 Imation Nexsan NST5130 Unified Hybrid Storage System



37 NetApp FAS3250

38 Nimble Storage CS210




42 Nimble Storage CS420-X2

43 Nimble Storage CS420-X4



46 Oracle Sun ZFS Storage 7120 Appliance



49 Starboard Storage AC2000



52 Tegile Zebi HA2100

53 Tegile Zebi HA2100EP



56 Tintri VMstore T540

57 X-IO Hyper ISE 730

58 Product Rankings Dashboard

Appendices

A-1 Appendix A—Definitions, Explanations and Terminology

B-1 Appendix B—Storage Provider Contact Information

C-1 Appendix C—Author Contact Information

1 Introduction1 Explaining the Rapid Adoption

of Hybrid Storage Arrays

1 What Makes a Storage Array a Hybrid Storage Array

2 The Value This DCIG Buyer’s Guide Creates For Storage Purchasers

3 Executive Summary

5 How to Use this Hybrid Storage Array Buyer’s Guide

6 Disclosures

6 Hybrid Storage Array Inclusion and Exclusion Criteria

7 The 8-Step Process Used to Score and Rank Hybrid Storage Arrays

8 DCIG Comments & Thoughts

8 The Business Value of a Hybrid Storage Array

8 Now is the Time

8 How a Hybrid Storage Array Differs From an All-Flash Memory Storage Array

8 How a Hybrid Storage Array Differs From a Traditional Array

8 Features Important in Selecting a Hybrid Storage Array

9 Caching/Tiering Capabilities

9 Consistent Application Performance

9 VMware Integration

9 Performance Monitoring

9 Included Software

9 Crossing the Chasm by Disrupting the Market

9 Performance and Pricing

10 DCIG Observations & Recommendations

10 Best-in-Class Ranking

10 Recommended Ranking

11 Excellent Ranking

11 Good Ranking

12 Basic Ranking

16 Hybrid Storage Array Models

© 2013 DCIG, LLC. All rights reserved. 1


Introduction

Hybrid storage arrays are receiving much deserved attention for bringing low-latency, high-capacity storage to market at entry price points that make sense to many businesses. These Hybrid storage arrays enable businesses to move forward on initiatives that have otherwise been hampered by legacy storage system performance. In that regard, hybrid storage arrays enable them to improve the return they are calculating on their data center investments.

Hybrid storage arrays are relatively new to the data storage market, with most participants in this market bringing out products over the last three or four years. Enterprise storage professionals are traditionally cautious about adopting new technologies; yet a recent survey of IT professionals in small to medium enterprises found that a majority were looking at hybrid storage arrays for their next storage purchase. In that regard, two out of three organizations with more than 250TB of total storage in virtualized environments had already implemented or were planning to implement hybrid storage arrays.1

Explaining the Rapid Adoption of Hybrid Storage Arrays

Hybrid storage arrays promise to deliver the dramatic performance benefits of an all flash memory storage array but at a lower cost since they utilize both flash memory and hard disk drives. In that regard, analysis has shown that for I/O rates of over 700 I/Os per TB, a hybrid storage array is more cost-effective than a traditional array while delivering much lower latencies.2

Combining flash memory storage and high-capacity hard disk drives (HDD) in a single system accelerates access for a broader set of applications than can be housed on a smaller capacity all flash array. Hybrid storage arrays align more storage under a modern management umbrella. In that regard, storage becomes an investment with lower storage management cost.

What Makes a Storage Array a Hybrid Storage Array

Research for the DCIG Buyer’s Guide on enterprise-level midrange arrays revealed that 75% of midrange arrays support flash memory in some form or fashion.3 However, a hybrid stor-age array is not defined by the mere inclusion flash memory storage (e.g. solid state drive). Hybrid storage arrays are set apart by their software functionality. In that regard, hybrid storage arrays must support dynamic data placement in a hybrid storage pool defined by combining flash memory and traditional hard disk drives (HDDs).

More than a dozen companies—both startups and established storage system providers—are now delivering hybrid storage arrays that implement this concept of dynamic data placement in a hybrid storage pool. The secret sauce the hybrid storage array providers bring to the table is a combination of storage architecture, hardware, and software features. The resulting hybrid storage arrays generally include some combination of the following ingredients:

• Large DRAM caches. (Some providers deduplicate and compress the cache, further increasing its effective capacity and the percentage of IO requests completed from cache.)

• Multi-core CPUs

1. Imation 2013 Report. “State of Storage in Virtual Environments.”

2. Floyer, David. “Hybrid Storage Poised to Disrupt Traditional Disk Arrays.” http://wikibon.org/wiki/v/Hybrid_Storage_Poised_to_Disrupt_Traditional_Disk_Arrays#VM-Aware_Hybrid_Definition.

3. 2014 DCIG Enterprise Midrange Array Buyer’s Guide



• Flash memory to provide low-latency storage, sometimes including both SLC and MLC in a single array

• Metadata stored separately from file data on high-performance flash memory

• Multi-terabyte HDDs to provide low-cost capacity

• Sophisticated caching and/or automated storage tiering software

• Storage optimization software. May include storage efficiency capabilities like deduplication, compression, and thin provisioning; commonly achieving a 6x to 12x multiplication of effective capacity. May also include capabilities that extend the reliable life of flash memory like coalescing writes to match erasure block sizes

The Value This DCIG Buyer’s Guide Creates For Storage Purchasers

Like all prior DCIG Buyer’s Guides, this DCIG 2014 Hybrid Storage Array Buyer’s Guide does the heavy lifting for organizations as they look to purchase a hybrid storage array by:

• Listing each individual hybrid storage array model by storage provider

• Listing different hybrid storage array features, whether or not they are supported and, where appropriate, how they are implemented

• Weighting these features according to what organizations consider most important

• Scoring these features

• Ranking each hybrid storage array model

• Creating a data sheet for each hybrid storage array model

The end result is that this DCIG 2014 Hybrid Storage Array Buyer’s Guide gives organizations the opportunity to do “at-a-glance” comparisons between many different arrays. This will enable them to more quickly sort through the many arrays to identify a short list of products that meet their specific needs. Prospective purchasers can focus their product evaluation energies on those selected arrays and move more quickly to the competitive bid process.

Note that this Buyer’s Guide is not intended to be a substitute for bringing individual hybrid storage arrays models in-house for testing. That function should still be done, if possible, since every array will perform differently under different application workloads and data center environments.

I hope you find that this Buyer’s Guide meets its intended purpose in your environment.

Ken Clipperton

Senior Analyst

Introduction (continued)



Executive Summary

As the next enhancement in the array market space, hybrid storage arrays have integrated data center storage efficiencies. Hybrid storage arrays are architected for the current reali-ties of significant data growth, the highly consolidated and virtualized data center, and the business value of speed as part of their architectural design. Products evaluated in the DCIG 2014 Hybrid Storage Array Buyer’s Guide offer features like inline deduplication, data compression, and thin provisioning. Each of these features enables an array to store more data and host more applications in less space.

Deduplication and data compression began in backup appliances, these storage efficiency features are generally available to primary storage. Traditional storage arrays offer those features, but at the cost of performance. Hybrid storage arrays simultaneously deliver both storage efficiency and high performance.

Storage efficiency and high performance are not just bullet points on a page, they are tenets of a hybrid storage array. It is because of these performance-boosting space-efficient tech-nologies that some expect hybrid storage arrays to overtake the mainstream storage array market very soon.1 Although many early adopters embraced hybrid storage arrays to meet specific application performance challenges, hybrid storage arrays are now handling a wider variety of workloads and look to replace traditional storage arrays in data centers.

Much like previous DCIG Buyer’s Guides focusing on storage arrays, this Guide evaluates four core areas of a hybrid storage array: Management and Software, VMware integration, Hardware and Support.

Management and Software carries the most weight in this Guide’s scoring system because the “secret sauce” of the hybrid storage array lies in how it handles caching, data tiering (e.g. flash vs disk) and data efficiency (e.g. deduplication). Management and software deliver on storage intelligence. Hybrid storage arrays are capitalizing on that intellectual property to help buyers deliver improvements in application performance while simultaneously reducing the operation and capital expenses associated with managing storage.

Management and Software tools further reduce expenses by enabling IT staff to manage storage on the virtual machine level, and to monitor and administer storage from within VMWare’s vCenter management console. In the process of creating a virtual machine (VM) in VMware, a server administrator specifies storage for the VM. All array integration is handled by intellectual property a provider has built-in. In that regard, this VM-aware approach to storage management reduces expenses by minimizing time associated with routine storage administration and application performance diagnostic issues.

Hardware is next in importance as far as scoring weight, with VMware integration coming in third. While provider support is an important purchase criterion, its scoring weight is lower than the other three categories. Because we expect hybrid storage arrays to replace existing enterprise storage arrays for many buyers, DCIG did assess the availability of enterprise level support options, including remote monitoring and remote problem resolution, and the avail-ability of guaranteed 4-hour onsite response.

Prices for the arrays in the DCIG 2014 Hybrid Storage Array Buyer’s Guide range from start-ing list prices of under $50,000 all the way to the high six (6) figures. As in all Buyer’s Guides,

1. Lowe, Scott. “Hybrid Storage: Buy Now, Add Workloads Later and Enjoy Additional Value.”



list price does not factor into a product’s final score; however, the vast majority of the arrays trend towards a lower starting price, making a hybrid storage array a more affordable option than most might guess given its status as up-and-coming technology.

It is in this context that DCIG presents its DCIG 2014 Hybrid Storage Array Buyer’s Guide. As prior Buyer’s Guides have done, it puts at the fingertips of organizations a resource that provides them with a comprehensive list of hybrid storage arrays that can assist them in this all-important buying decision while removing much of the mystery around how hybrid stor-age arrays are configured and which ones are suitable for which purposes.

This DCIG 2014 Hybrid Storage Array Buyer’s Guide accomplishes the following objectives:

• Provides an objective, third party evaluation of hybrid storage arrays that evaluates and scores their features from an end user’s viewpoint

• Includes recommendations on how to best use this Buyer’s Guide

• Scores and ranks the features on each hybrid storage array based upon the criteria that matter most to end users so they can quickly know which hybrid storage arrays are the most appropriate for them to use and under what conditions

• Provides data sheets for 41 hybrid storage arrays from 17 different storage providers so end users can do quick comparisons of the features that are supported and not supported on each hybrid storage array

• Provides insight into which features on a hybrid storage array will result in improved performance

• Provide insights into what features hybrid storage arrays offer to optimize their VMware integration

• Gives any organization the ability to request competitive bids from different providers of hybrid storage arrays that are “apples-to-apples” comparisons

Executive Summary (continued)



How to Use this Hybrid Storage Array Buyer’s GuideIn determining how to best use the information contained in the DCIG 2014 Hybrid Storage Array Buyer’s Guide, it is important to note that it is intended to help organizations in their purchase of a hybrid storage array by significantly reducing the time they must invest in researching product features and capabilities. The purpose of this Buyer’s Guide is NOT to tell users exactly which hybrid storage array to purchase. Rather, it is to help guide them in coming up with a list of competitive products that have comparable features that meet their specific needs.

It is also important for users to note that just because a product scored the highest in a particular category or is ranked a certain way does not automatically mean that it is the right product for their organization. If anything, because of the scope of the storage array models evaluated and analyzed, it may have features that are too robust for the needs of an individual department or organization.

However, what this Buyer’s Guide does is give users some sense of how each array compares to others classified as “hybrid storage arrays”, as well as offers additional insight into what product offerings are available on the market.

DCIG recommends that you use this DCIG 2014 Hybrid

Storage Array Buyer’s Guide in the following seven (7) ways:

• Eliminate the painstaking research associated with

coming up with a short list of hybrid storage arrays

that meet their needs. This Buyer’s Guide ranks, scores and contains data sheets for 42 different models from 17 different providers. Each storage array is scored and then ranked as “Best-in-Class”, “Recommended”, “Excellent”,

“Good” and “Basic” based upon its score. On each array, 148 different features were evaluated, weighted, scored and then ranked. All an organization has to do is look at the scores and features of each product in order to come up with a short list of products for consideration.

• Identify comparable apples-to-apples hybrid

storage arrays from different storage providers. In today’s crowded storage market, it behooves organizations to get competitive bids from multiple storage providers. After all, when they compete, you win! But that tactic only works well when organizations know that they are receiving competitive bids on products that

are roughly comparable. Using this DCIG 2014 Hybrid

Storage Array Buyer’s Guide, organizations can do a better job of accomplishing that objective.

• Separate the apples from the oranges. Just as important as doing apples-to-apples comparisons is identifying when an orange is thrown into the mix. Sometimes it is very difficult for an organization to know if it is truly getting a good deal when bids come in from multiple storage providers that include different models. Now organizations can refer to the scores and rankings of each hybrid storage array in this guide so they know when they are getting a good deal, a great deal or just a “so-so” one.

• Gain perspective on how models from less well

known storage providers compare against estab-

lished and better known brands. Anyone involved with storage at all has at least heard of—and probably from—EMC, HP, IBM and other well known storage vendors. This creates a certain built-in level of comfort when buying products from these companies and a corresponding built-in resistance to buying hybrid storage arrays from companies that are perceived as unknown quantities.

This Buyer’s Guide helps to remove some of that apprehension about buying from a less well known provider or even a less well known model from an established provider. Using this Buyer’s Guide organiza-tions can see how these models from lesser known companies as well as lesser known models from established providers stack up.

• Take advantage of normalized storage terminology. Every computing industry has a proclivity to adopt acronyms and jargon that is specific to its lexicon, but the data storage industry seems to go out of its way to not only use unfamiliar terms but refer to the same technol-ogy in different ways. This Buyer’s Guide sifts through the acronyms and storage jargon and terms and normalizes them. This minimizes or even eliminates the need for users to try to understand all of the industry terminology.

• Do side-by-side comparisons. The product data sheets available from the different storage providers are rarely laid out in the same way or contain the same information. Some storage providers even have data sheet formats that vary from model to model within their



own product portfolio. This Buyer’s Guide tackles the problem by creating a standard, easy to read data sheet for every hybrid storage array. In this way, product data sheets for individual products can be printed out, laid down side by side and then quickly compared.

• Justify technical buying recommendations to

business folks. Nothing is easier for those on the business side to understand than a number. So at the top of every hybrid storage array model data sheet, a product score is included so the business side of the house can quickly see how the different storage array models compare.

DisclosuresOver the last few years the general trend in the US has been for both large and boutique analyst firms to receive some or all of their revenue from storage providers. DCIG is no different in this respect as it also receives payment for the different services it performs for storage providers. The services that DCIG provides include blogging, case studies, product reviews, executive white papers, full length white papers and special reports. For more information on DCIG, visit www.dcig.com.

In the interest of being fully transparent, a number of the storage providers included in this DCIG 2014 Hybrid

Storage Array Buyer’s Guide are, or have been DCIG clients. This is not to imply that they were given preferential treatment in the Buyer’s Guide. All it meant was that DCIG was aware that they offered arrays that might qualify for inclusion in this Buyer’s Guide and that DCIG had more initial knowledge of their hybrid storage arrays.

In that vein, there are a number of important facts to keep in mind when considering the information contained in this DCIG 2014 Hybrid Storage Array Buyer’s Guide and its merit.

• No storage provider paid DCIG any fee to develop this Buyer’s Guide

• DCIG did not guarantee any storage provider that its hybrid storage array(s) would be included in this Buyer’s Guide

• DCIG did not imply or guarantee that a specific hybrid storage array model would receive a good score on this Buyer’s Guide ahead of time

• All research was based upon publicly available informa-tion, information provided by the storage provider, and the expertise of those evaluating the information

• Because of the number of features analyzed, how these features were weighted and then how these hybrid storage array models were scored and then ranked, there was no way for DCIG to predict at the outset how individual hybrid storage array models would end up scoring or ranking

DCIG would like to emphasize that no storage provider was privy to how DCIG did the scoring and ranking of the hybrid arrays. In every case the storage providers only found out the scores and rankings of its array model(s) after the analy-sis was complete.

Hybrid Storage Array Inclusion and Exclusion CriteriaThis inaugural edition of the DCIG 2014 Hybrid Storage

Array Buyer’s Guide has incorporated input from key users and vendors into defining the criteria used to decide what arrays belonged or did not belong in this Buyer’s Guide. This Buyer’s Guide attempts to take into consideration as many of these variables as possible, but likely failed to account for all of them. While this may have resulted in a specific model not being covered in this Buyer’s Guide when it rightfully may have belonged, DCIG believes the following criteria was consistently applied as we did our research and made our decisions.

The rationale that was used to determine the inclusion and exclusion of specific models in this Buyer’s Guide is as follows:

• Must dynamically place data in a storage pool that combines flash memory and HDD storage.

• Must support one or more of the following storage networking protocols:

- Fibre Channel and/or FCoE

- iSCSI

- NFS

• Must primarily function using storage local to the array, storage expansion units and/or its direct peers (more than a cloud gateway)

www.dcig.com



• Must support scaling to a minimum of 12 disks and 10 TB of raw capacity. This requirement may be met through the use of storage expansion units

• Must be available as an appliance that is available as a single SKU and includes its own hardware and software

• Must provide sufficient information for DCIG to draw a meaningful conclusion

• Must be generally available prior to September 1st, 2013. A cut off date had to be put in place or this Buyer’s Guide would never be published

The 8-Step Process Used to Score and Rank Hybrid Storage ArraysTo score and rank each hybrid storage array model, DCIG went through an eight (8) step process to come to the most objective conclusion possible.

1. DCIG listed out all of the features available on all

of the hybrid storage arrays. Prior to selecting the features that were included in the final evaluation in the Buyer’s Guide, DCIG went through and quantified what features hybrid arrays possessed. As part of this process, DCIG “normalized” the list of features available on hybrid storage arrays such that a common name for each feature was established.

2. DCIG established which features would be included

in the Buyer’s Guide and which ones would not. One of the goals of this Buyer’s Guide was to try to only include features on each hybrid storage array model that could be objectively and authoritatively analyzed.

For example, “Raw Storage Capacity (Max SSD/Max)” was evaluated as a feature instead of “Usable Storage

Capacity.” While usable storage capacity is what users ultimately care about, a consistent objective answer cannot be arrived at as most hybrid storage arrays offer multiple RAID options and differences in data compres-sion and deduplication by type of data yield site-specific usable or effective storage capacity. Therefore, “Maximum Raw Storage Capacity” was selected as the feature to be evaluated since an objective answer could be ascertained and supported.

3. The features were broken down into four general

categories. The features included in this Buyer’s Guide broke down into a total of four broad categories that are

reflected on each hybrid storage array data sheet. These four categories include Management & Software, VMware Integration, Hardware, and Support.

4. Each feature had a weighting associated with it. The weightings were used to reflect if a feature was supported and potentially how valuable the feature is to an end-user compared to other options. For example, the “Full File Clone” feature is more of a “Yes” or “No” type of response whereas “Snapshot Methods” covers a number of snapshot options. Each of these options is weighted and scored differently.

5. A survey that asked about all of the features scored

in this Buyer’s Guide was sent to each storage

provider. Vendors were invited to complete the online survey. The survey elicits more data than was available on any vendor website to provide a more thorough analysis of each hybrid storage array. If a vendor did not respond to the invitation, a DCIG analyst filled out the survey on their behalf using the vendor’s web site, other reliable publicly available information, and prior DCIG research where available.

6. All vendors were given the opportunity to review their

data sheets before the final scores and rankings

were determined. To ensure the information presented in this Buyer’s Guide is as complete and correct as possible, DCIG provided each vendor a copy or copies of their filled-out surveys and the data sheets that appear in this Buyer’s Guide without the scores and rankings on them. In this way they had the opportunity to validate the information and correct it before it was publicly released.

7. All of the features were scored based upon

the information that was gathered. The weighting and scoring of the features were done by a DCIG research analyst.

8. The hybrid storage arrays were ranked using

standard scoring techniques. One of the goals of this Buyer’s Guide is to establish clear lines of differentiation between hybrid storage arrays with conclusions that are arrived at objectively. To accomplish this goal, the mean or average score for each classification was first determined and then the standard deviation.

Using the mean of the scores from all of the hybrid storage arrays from which the standard deviation was calculated, DCIG developed a ranking for each array model based upon the following in each classification:



• Those models that were .5 or greater standard deviations below the mean were given the rank of Basic

• Those models that were .5± standard deviations above or below the mean were ranked as Good

• Those models that were .5 – 1.25 standard devia-tions above the mean were ranked as Excellent

• Those models that were greater than 1.25 standard deviations above the mean were ranked as Recommended

• The model(s) with the highest score in each category were given the designation of Best-in-Class

• It is for this reason that in each category the number of models that achieved a certain ranking varied

DCIG Comments & ThoughtsHybrid storage arrays use flash memory in combination with hard disk drives to create storage that balances perfor-mance, capacity and cost. Because the majority of the data will ultimately be stored on slower HDD instead of flash memory, the trick is to achieve consistently high perfor-mance without 100% flash. The secret sauce the hybrid storage array providers bring to the table is a combination of storage architecture, hardware, and software features.

The Business Value of a Hybrid Storage Array

Time is money, and old storage architectures take too much time. They are too hard to manage and can't keep up with customer needs or the random I/O demands of the virtualized data center. Desired business results are often hampered by inadequate storage system performance.

Hybrid storage arrays promise to deliver the dramatic perfor-mance benefits of an all flash array at a lower cost than an all flash array. In addition, by combining flash memory and high-capacity HDD in a single system, hybrid storage arrays accelerate access for a broader set of applications than can be housed on a smaller capacity all flash array. Unifying more storage under one modern management umbrella adds to the benefits a business realizes from the storage investment, while subtracting from the overall storage management cost.

Now is the Time

Storage industry veterans from a number of companies recognized the opportunity to combine a new generation of

server hardware, flash memory and HDD into a system that could enable IT to deliver the performance businesses seek at a lower cost than either all flash or traditional arrays.

How a Hybrid Storage Array Differs From an All-Flash Memory Storage Array

A hybrid storage array uses flash memory—generally in the form of either PCIe cards or Solid State Disks (SSDs)—in combination with hard disk drives to create server-address-able storage pools. Because not all storage in the hybrid storage array is flash, it is necessary to implement intelligent caching/tiering algorithms to place "hot" data in flash memory and warm/cold data on hard disk drives. The key concept is dynamic data placement in a hybrid storage pool that

combines flash memory and traditional hard disk drives.

How a Hybrid Storage Array Differs From a Traditional Array

Many traditional arrays can incorporate flash memory as a cache or as a high performance storage tier. A hybrid storage array is architected for flash memory, and gener-ally adopts a "flash first" approach to storage. In a hybrid storage array, caching/tiering algorithms are often combined with in-line deduplication and data compression—along with cache hardware and specialized software algorithms—to maximize the amount of storage I/O that is satisfied from high speed cache and flash memory.

Because of the "flash first" design, many of the hybrid stor-age arrays contain only flash memory and high capacity multi-terabyte 7.2K RPM SAS or SATA hard disk drives. In that regard, hybrid storage array providers are bypassing expensive and lower capacity Tier 1 15K SAS/FC and Tier 2 10K SAS/FC hard disk drives, thus minimizing complexity and capital expenses.

Hybrid storage arrays leverage the latest generation of commodity server hardware with multi-core CPUs and higher RAM capacities. This high-performance hardware makes it possible to implement data optimizations such as in-line dedu-plication and compression without impeding the flow of data.

Features Important in Selecting a Hybrid Storage Array

1. Caching/tiering capabilities

2. Consistent application performance



3. VMware integration

4. Performance monitoring

5. Included software

Caching/Tiering Capabilities

Design and implementation of caching/tiering capabilities is the most significant differentiator between hybrid storage arrays and all-flash or traditional arrays. Providers want to ensure that I/O requests are always satisfied from higher performing cache via tiering, particularly those associated with business critical applications systems.

Providers employ several strategies to achieve optimum caching/tiering results:

• More DRAM cache than in traditional storage arrays

• In-line deduplication and/or compression of data in the cache and on disk

• Highest performance media for write cache (e.g. NVRAM, SLC, mirrored SSDs)

• Metadata stored separately from file data on high performance media

• Quality of Service (QoS) policies per VM/LUN/Volume that determine how read and write queues are serviced

• Separate and dedicated read & write caches

• Multiple physical or logical write caches

Consistent Application Performance

Some providers are focused on making their storage smart about application data. In that regard, users can simply rely on the system to do the performance management for them. Conversely, competing providers allow users to specify, measure, and enforce QoS metrics on a per VM/LUN/Volume basis in order to run critical application workloads simultaneously.

VMware Integration

Rethinking storage architecture is driven by virtualization. That rethinking is done based on the largest installed base provider for hypervisors—VMware. In that regard, VMware provides application programming interfaces (API) for provisioning, management, and reporting. It is those APIs that make a difference in how servers and storage work together. hybrid storage arrays must take advantage of those VMware APIs.

Performance Monitoring

Visibility into the performance of the storage system is important for troubleshooting application performance problems when they arise. For example, some providers will implement VMware monitoring that reveals performance at the virtual machine level.

Included Software

Some providers sell their arrays with all software features already licensed. This creates one standard hybrid storage array package and reduces the number of decision points in the purchasing process. This simplified approach to licensing also increases the agility of an IT department in responding to changing business requirements compared to the traditional a-la-carte licensing model, and it is yet another aspect of driving administrative overhead out of the storage management process. This Buyer's Guide acknowledges the business value of included licenses by awarding a more points to products that ship with soft-ware features already licensed.

Crossing the Chasm by Disrupting the Market

Although the traditional storage providers have been slow to address this opportunity, most are now coming to market with hybrid solutions. Quite a number of startup compa-nies were founded with the express purpose of delivering hybrid storage arrays that are engineered from the ground up to address the need of businesses for high performing, high capacity storage for virtualized infrastructures. These companies include Avere, Nexgen (now part of Fusion-IO), Nexsan (now part of Imation), Nimble, Starboard, Tegile, Tintri and X-IO.

DCIG believes that hybrid storage arrays are ready to not only supplement, but to begin displacing traditional storage arrays in many data centers. Any business contemplating the purchase of a storage array should take a close look at these new alternatives to traditional arrays.

Performance and Pricing

Two factors that strongly influence buying decisions are performance and cost. So it may come as a surprise to those who look at this DCIG 2014 Hybrid Storage Array Buyer’s

Guide to see no performance benchmarks as to how any of the arrays performed and only high-level pricing information. There are two core reasons why performance or detailed pric-ing information are not included in this Buyer’s Guide.



Performance will vary according to data center environment, the data being stored, and implementation decisions. So to introduce any type of performance metric would only result in the analysis and evaluations of the arrays included in this Buyer’s Guide becoming more subjective, not less.

The intent of this Buyer’s Guide is to provide a near real time snapshot of the hybrid storage arrays currently available in the marketplace. If DCIG had tried to test and establish perfor-mance benchmarks for all of these arrays, the next genera-tion of arrays from all of these storage providers could well be available before the testing was completed, making this Buyer’s Guide obsolete before it ever saw the light of day.

As for pricing, each data sheet provides only a starting list price for that array. These list prices had no bearing in the weighting of any array and are provided for reference purposes only.

DCIG recognizes that features like price and performance are relevant and even key considerations when buying a hybrid storage array. However, it is also almost impossible for a third party like DCIG to objectively measure these features on a large scale. Therefore, evaluating these factors is a part of the buying process that is still best left to end users.

DCIG Observations & Recommendations

Best-in-Class Ranking

Observations

The Tegile Zebi HA2800 earned the Best-in-Class ranking among hybrid storage arrays evaluated in this Buyer’s Guide. In comparison to its counterparts, this array stood out in the following ways:

• The best balance of strengths across all scoring categories.

• Recommended or Excellent in all scoring categories.

Recommendation

The Tegile Zebi HA2800 is the latest array from Tegile, and the first to support FlashVols. Tegile defines FlashVols as volumes that are pinned in flash memory so applications run at maximum performance without the potential for delay due to caching algorithms or tiering policies. The Zebi HA2800 can function either as an all-flash array or as a hybrid array with the addition of one or more expansion chassis.

Tegile combines a Redirect on Write (ROW) file system with a proprietary Metadata Accelerated Storage System (MASS) technology that separates metadata from the primary data path and stores the metadata on high-speed memory devices with optimized retrieval paths. This opti-mizes functions such as deduplication, compression, RAID and snapshot pointers, while simultaneously accelerating all I/O.

Tegile claims their existing clients experience a real world 3x-5x effective capacity from deduplication and compres-sion. In that regard, deduplication and compression occur in front of the cache, they also boost the effective capacity of the already impressive 192 GB of cache.

The Zebi HA2800 includes excellent data protection features that support per-LUN automated snapshot policies comple-mented by replication.

The Zebi product line’s web-based management interface speeds deployment by making it relatively simple to define a particular LUN as backup target, virtualization store, database store or file server store with a single click.

Accelerating storage administration in hybrid storage arrays is support of VMware VAAI integration. The Zebi HA2800 proved Excellent in this category—supporting all VMware vSphere VAAI features evaluated by DCIG.

The Zebi HA2800 provides unified storage through concurrent support for both SAN and NAS protocols. DCIG confirms this aligns Tegile’s goal, “to deliver a new generation of storage arrays that address all of the demands of the modern data center, backed by expert customer support.”

Tegile Company Profile: The Tegile management team has a track record of working together to build successful companies and products. The CEO and CTO worked together in similar roles at Perfigo. The management team also has experience at HP/3PAR, Pillar Data Systems, Cisco and Cobalt Networks. Tegile was founded in 2010, and is privately funded.

Recommended Ranking

Observations

Tegile Zebi HA2400, HA2100EP and HA2100 and the EMC VNX7500, VNX5500, VNX5700 and VNX5300 round out the Recommended category. The Tegile Zebi arrays outscored all other arrays in Management and Software. As expected, EMC arrays captures the highest VMware integration



scores among all the arrays in this buyer’s guide. These Recommended arrays distinguished themselves by:

• Complete feature set across the board, achieving Best-in-Class, Recommended or Excellent scores across all scoring categories

• All offer concurrent SAN and NAS, as well as concurrent FC and iSCSI connections

Recommendations

The Recommended Tegile Zebi arrays all share the same Zebi Technology architecture and software as their Best-in-

Class counterpart. These arrays are distinguished from one another by hardware capacities in terms of cache, CPU, flash memory storage and HDD storage. These Zebi-based arrays are distinguished from the EMC arrays by their in-line deduplication and compression of all four data stores—DRAM cache, NVRAM cache, SSD and HDD.

As with the Tegile arrays, the EMC VNX7500, VNX5500, and VNX5300 arrays are also distinguished from one another in terms of hardware capacities. The VNX arrays include comprehensive quality of service (QoS) and hypervisor/operating system support as required to fit into nearly any data center.

Excellent Ranking

Observations

The hybrid storage arrays that achieved an Excellent ranking include the Oracle Sun ZFS Storage 7420, 7320 and 7120 Appliances along with the NetApp FAS3250, Starboard Storage AC4500, AC4000 and AC2000, and the Hitachi Data Systems HUS VM. These arrays were distinguished by:

• Recommended or Excellent scores in at least two scoring categories. Support thin provisioning and eager-zeroed-thick provisioning, with the licensing for these features included in the base package.

• Like the Recommended arrays, offer concurrent SAN and NAS, as well as concurrent FC and iSCSI connections.

Recommendations

The Oracle Sun ZFS Storage 7420, 7320 and 7120 Appliances surprised us with their high scores. Oracle clearly is targeting these arrays—and optimizing them—

especially for Oracle database and virtualization envi-ronments. The lack of VMware integration hurt Oracle in this report, though in October 2013, Oracle formally announced that it had licensed the VMware vSphere Storage APIs so we would expect to see support for vSphere soon.

The Starboard Storage AC2000, AC4000 and AC4500 actually scored Excellent or Good across all categories; indicating that this hybrid-only startup has managed to bring a well-balanced set of capabilities to market.

The NetApp FAS3250 and the HDS HUS VM are distin-guished from the other Excellent arrays by their strong VMware integration, including support for all VAAI API’s.

Good Ranking

Observations

The arrays that achieved a ranking of Good mix startups and industry stalwarts. These include the Fusion-io NexGen n5-50, n5-100, n5-150 Storage Systems, the HP 3PAR StorServ 7400 and 7200, the EMC VNX5100, the IBM Storwize V7000 Unified, the Imation Nexsan NST5530, NST5330, NST5130 Unified Hybrid Storage Systems, and the Dell EqualLogic PS6510ES.

The Good arrays were distinguished from higher and lower ranking arrays by:

• Every array achieved at least an Excellent ranking in one of the scoring categories

• Less complete features overall, with most earning just a Basic ranking in one category

• All except the Fusion-io NexGen n5’s offer multiprotocol, unified SAN and NAS storage

Recommendation

NexGen was acquired by Fusion-io during the develop-ment of this Buyer’s Guide. NexGen was a customer of Fusion-io, using Fusion-io’s PCIe modules to provide the flash memory for the NexGen n5 Series of hybrid stor-age arrays. The NexGen n5 arrays scored well across all categories except for VMware integration, achieving a Recommended score in Management and Software



features that beat out all but the Tegile Zebi arrays. The NexGen arrays are iSCSI-only, SAN-only arrays.

Basic Ranking

Observations

The arrays achieving only a Basic ranking include the arrays from Nimble Storage’s CS200 and CS400 series, Tintri’s VMstore T540, Dot Hill’s AssuredSAN Pro 5000, and the Avere FXT4500 and the Dell EqualLogic PS6510ES.

These arrays were distinguished from higher scoring arrays by:

• One protocol—either SAN or NAS. Not unified storage.

• Maximum capacity of less than 400 TB

• No deduplication or workload prioritization (Qos), except for Tintri

• Limited VAAI v5 API support, except for Tintri

Recommendation

The Tintri VMstore T540 ended up with a Basic ranking, in large part because it represents a significant departure from the norm—it does not fit neatly into our normal scor-ing metrics. Tintri has come to market with a very different approach that they call “Zero Management Storage” for virtualization. The VMstore T540 is a NAS-only VM-aware storage system that is managed from within the VMware vCenter console. There are no LUNs to manage. The Tintri hybrid storage arrays are VM-centric, with all management including provisioning, replication and monitoring being on a per-VM basis. The Tintri VMstore T540 is also the only array in this group to offer both in-line block-level deduplication and compression.

The Nimble Storage arrays led the Basic category by achieving a Good ranking in both Management & Software and VMware integration; and by among the lowest scores in the Hardware category.

While achieving only a Basic ranking, any of these Basic arrays may nevertheless be a very good fit for a particular business.



HYBRID STORAGE ARRAY SCORES AND RANKINGSThe scores and rankings for the hybrid storage arrays contain the following information:

• A chart that includes the scores and rankings for all of the products

• The mean and the standard deviation that were used to establish how each hybrid storage array was ranked

• A summary of the primary findings



Vendor Support for Servers and Virtual Platforms

HYBRID STORAGE ARRAYS SCORE RANKING

1. Tegile Zebi HA2800 92.15 BEST-IN-CLASS

2. Tegile Zebi HA2400 91.14 Recommended

3. Tegile Zebi HA2100EP 90.67 Recommended

4. Tegile Zebi HA2100 90.54 Recommended

5. EMC VNX7500 90.51 Recommended




9. Oracle Sun ZFS Storage 7420 Appliance 83.62 Excellent

10. Netapp FAS3250 78.39 Excellent


12. Starboard Storage AC4500 75.31 Excellent


14. Hitachi Data Systems HUS VM 74.11 Excellent



17. Fusion-io NexGen n5-100 Storage System 72.34 Good



20. Imation Nexsan NST5530 Unified Hybrid Storage System 65.90 Good

21. HP 3PAR StoreServ 7400 60.92 Good

22. EMC VNX5100 60.67 Good

23. IBM Storwize V7000 Unified 60.46 Good

24. HP 3PAR StoreServ 7200 60.20 Good

25. Imation Nexsan NST5330 Unified Hybrid Storage 59.85 Good

26. Imation Nexsan NST5130 Unified Hybrid Storage 57.20 Good

27. Dell Dell EqualLogic PS6510ES 55.01 Good

28. Nimble Storage CS240 48.44 Basic



continued on next page

OVERALL SCORES AND RANKINGS



OVERALL SCORES AND RANKINGS (CONTINUED)

HYBRID STORAGE ARRAYS SCORE RANKING



33. Nimble Storage CS420-X4 48.30 Basic

34. Nimble Storage CS420-X2 48.00 Basic


36. Dot Hill AssuredSAN Pro 5000 45.00 Basic

37. Tintri VMstore T540 43.90 Basic

38. Avere FXT 4500 41.90 Basic

39. DDN SFA7700 31.57 Basic

40. Avere FXT 4200 30.45 Basic

41. X-IO Hyper ISE 730 29.13 Basic

Total Number of Products 41

Highest Score 92.15 Lowest Score 29.13 Average (Mean) 64.09 Standard Deviation 18.49

Recommended 87.20 – 92.15 Excellent 73.34 – 87.19 Good 54.84 – 73.33 Basic 29.13 – 54.83

Rankings



HYBRID STORAGE ARRAY MODELS

DCIG Scores and Rankings

17

Supported Unsupported

©2013 DCIG, LLC. All rights reserved. All other brands or products are trademarks or registered trademarks of their respective holders and should be treated as such. The information, product recommendations and opinions made by DCIG, LLC are based upon public information and from sources that DCIG, LLC believes to be accurate and reliable.

* The DCIG Interactive Buyers Guide contains additional data elements for this category that are reflected in the scores assigned to each array, but which were not able to be included in this one-page data sheet.

OVERALL SCORE

Management & Software* VMware* Hardware* Support

30.45 14.25 2.50 11.05 2.65BASIC BASIC BASIC BASIC BASIC

SCALABILITY & SUPPORT

Hardware Warranty 1 Year

Contract Support Availability 24×7×365

Contract Support (Total #) 3

Non-Contract Support

HARDWARE*

Concurrent SAN & NAS

FC

iSCSI

Concurrent FC & iSCSI

Controller Config Active-Active

Scale-out (Max controllers)

Cores (Max) 1

Cache (Max RAM/Max) / 3.2 GB

Raw Storage Capacity (Max SSD/Max) 1.6 TB /

Storage Networking Ports (Max)

8

1/10/40 Gb Ethernet Ports (Max) 6 / 2 /

8/16 Gb FC Ports (Max) /

Information Dispersal Algorithms

RAID Options JBOD

Global Hot Spares (SSD/HDD) /

Redundancy (Total #) 4

HDD/SSD Interface SAS 6 Gb, SATA

SSD Optimizations (Total #)

Managed UPS/Battery Backup

RoHS Compliant

VMware INTEGRATION*

vSphere Plug-in for Array Management

vSphere Snapshots

Ingest Protocols

Full Copy

Hardware Assisted Locking

Block Zeroing

Thin Provisioning Dead Space Reclamation (SCSI UNMAP)

Full File Clone

Out-of-Space Conditions

Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /

VASRM / Storage DRS /

MANAGEMENT & SOFTWARE* (CONTINUED)

Workload Prioritization (QoS) (Total #)

Performance Monitoring

Provisioning: Automation & Policies (Total #)

Hypervisor/Operating System (Total #)

Backup Techniques

Data Migration to Cloud Storage Providers (Total #)

1

Network File Systems NFS, CIFS/SMB

Multiple Virtual NAS

Avere FXT 4200Approximate Starting List Price: $99,500

MANAGEMENT & SOFTWARE*

Snapshot Methods (Total #)

Asynch Replication Continuous

Synch Replication

Thin Provisioning/Eager-Zeroed-Thick /

Automated Storage Reclamation (Native)

Symantec Zero Reclamation API

Feature Software Licenses Included

Snapshot

Replication

Thin Provisioning

Deduplication and Compression

Forms of Deduplication (Block or File)

Deduplication (In-line or Post-process)

Block Level Compression

Data Stores

Deduplication Management Level

Automated Real Time Tiering/Caching

Preset System Policies/Algorithms

User-Defined Policies

User-Defined Performance Targets

Tiering/Caching Management Level

Forms of Flash-based Caching (Total #)

4


18




OVERALL SCORE


41.90 24.75 2.50 12.00 2.65BASIC BASIC BASIC BASIC BASIC






HARDWARE*


FC

iSCSI



Scale-out (Max controllers) 25

Cores (Max) 1

Cache (Max RAM/Max) / 6,000 GB

Raw Storage Capacity (Max SSD/Max)

3 TB / 6 TB


8




RAID Options JBOD




SSD Optimizations (Total #) 2


RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




Performance Monitoring System, VM



Backup Techniques


1



Avere FXT 4500Approximate Starting List Price: $159,000



Asynch Replication Continuous

Synch Replication





Snapshot

Replication

Thin Provisioning





Data Stores







System


4


19




OVERALL SCORE


31.56 8.88 - 18.99 3.70BASIC BASIC BASIC GOOD BASIC


Hardware Warranty 90 Days




HARDWARE*


FC

iSCSI




Cores (Max) 6

Cache (Max RAM/Max) 64 GB / 6,400 GB


634 TB / 1,584 TB


8

1/10/40 Gb Ethernet Ports (Max)

8 / 8 / 8

8/16 Gb FC Ports (Max) 8 / 4


RAID Options 1, 5, 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




1

Performance Monitoring System, LUN


3


Backup Techniques


1



DDN SFA7700Approximate Starting List Price: $50,00–$100,000



Asynch Replication

Synch Replication





Snapshot

Replication

Thin Provisioning





Data Stores







System, LUN


2


20




OVERALL SCORE


55.01 25.98 9.75 14.09 5.20GOOD BASIC EXCELLENT BASIC GOOD


Hardware Warranty 3 Years




HARDWARE*


FC

iSCSI


Controller Config Dual-Active


Cores (Max) 1

Cache (Max RAM/Max) 8 GB / 8 GB


2.8 TB / 48 TB


4










RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols iSCSI

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




Performance Monitoring System


2


12

Backup Techniques NDMP




Dell EqualLogic PS6510ESApproximate Starting List Price: $159,000


Snapshot Methods (Total #) 2

Asynch Replication Periodic

Synch Replication





Snapshot

Replication

Thin Provisioning





Data Stores







LUN



21




OVERALL SCORE


45.00 19.38 5.00 14.92 5.70BASIC BASIC GOOD GOOD GOOD






HARDWARE*


FC

iSCSI




Cores (Max) 1



32 TB / 360 TB


8

1/10/40 Gb Ethernet Ports (Max) / 8 /

8/16 Gb FC Ports (Max) 8 /


RAID Options 6, 10



HDD/SSD Interface SAS 6 Gb



RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols FC, iSCSI

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






3


9

Backup Techniques


1

Network File Systems


Dot Hill AssuredSAN Pro 5000Approximate Starting List Price: $50,000–$100,000




Synch Replication





Snapshot

Replication

Thin Provisioning





Data Stores








2


22




OVERALL SCORE


60.67 25.90 12.75 15.32 6.70GOOD BASIC RECOMMENDED GOOD RECOMMENDED






HARDWARE*


FC

iSCSI


Controller Config Active-Standby, Dual-Active


Cores (Max) 4



142 TB / 225 TB


8

1/10/40 Gb Ethernet Ports (Max) / /



RAID Options 0, 1, 5, 6, 10






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols FC

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




12



2


14

Backup Techniques




EMC VNX5100Approximate Starting List Price: Under $50,000



Asynch Replication Continuous, Periodic

Synch Replication





Snapshot

Replication

Thin Provisioning





Data Stores







LUN


3


23




OVERALL SCORE


87.96 43.20 13.75 24.46 6.55RECOMMENDED EXCELLENT BEST-IN-CLASS EXCELLENT EXCELLENT






HARDWARE*


FC

iSCSI




Cores (Max) 4



242 TB / 375 TB


40










RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols FC, iSCSI, NAS (NFS)

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




12



2


15



5



EMC VNX5300Approximate Starting List Price: Under $50,000




Synch Replication





Snapshot

Replication

Thin Provisioning



File


Post-process


Data Stores SSD, HDD


System, Filesystem, Volume, VM






System, VM, LUN


4


24




OVERALL SCORE


89.21 44.45 13.25 24.96 6.55RECOMMENDED EXCELLENT RECOMMENDED EXCELLENT EXCELLENT






HARDWARE*


FC

iSCSI




Cores (Max) 4



492 TB / 750 TB


60










RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




12



2


15



5



EMC VNX5500Approximate Starting List Price: $50,000–100,000




Synch Replication





Snapshot

Replication

Thin Provisioning



File


Post-process










System, VM, LUN


4


25




OVERALL SCORE


88.26 43.70 13.25 24.76 6.55RECOMMENDED EXCELLENT RECOMMENDED EXCELLENT EXCELLENT






HARDWARE*


FC

iSCSI




Cores (Max) 4



992 TB / 1,500 TB


72










RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




12



2


15



5



EMC VNX5700Approximate Starting List Price: $50,000–100,000




Synch Replication





Snapshot

Replication

Thin Provisioning



File


Post-process










System, VM, LUN


4


26




OVERALL SCORE


90.51 44.45 13.25 26.26 6.55RECOMMENDED EXCELLENT RECOMMENDED RECOMMENDED EXCELLENT






HARDWARE*


FC

iSCSI




Cores (Max) 6



1,992 TB / 3,000 TB


160










RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




12



2


15



5



EMC VNX7500Approximate Starting List Price: $50,000–$100,000




Synch Replication





Snapshot

Replication

Thin Provisioning



File


Post-process










System, VM, LUN


4


27




OVERALL SCORE


67.32 44.75 1.50 16.72 4.35GOOD EXCELLENT BASIC GOOD BASIC






HARDWARE*


FC

iSCSI




Cores (Max) 24



1.46 TB / 160 TB


16




RAID Options 6



HDD/SSD Interface PCI-e, SAS 6 Gb



RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




8

Performance Monitoring System, VM, LUN


6


2

Backup Techniques Embedded




Fusion–io NexGen n5-50 Storage SystemApproximate Starting List Price: $55,000




Synch Replication





Snapshot

Replication

Thin Provisioning



Block


In-line


Data Stores DRAM cache, NVRAM cache, SSD, HDD


System, LUN, Volume, VM






System, VM, LUN


3


28




OVERALL SCORE


72.34 49.25 1.50 17.24 4.35GOOD RECOMMENDED BASIC GOOD BASIC






HARDWARE*


FC

iSCSI




Cores (Max) 24



3.14 TB / 176 TB


16




RAID Options 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




8



6


2









Synch Replication





Snapshot

Replication

Thin Provisioning



Block


In-line










System, VM, LUN


3


29




OVERALL SCORE


67.76 44.75 1.50 17.16 4.35GOOD EXCELLENT BASIC GOOD BASIC






HARDWARE*


FC

iSCSI




Cores (Max) 24



4.8 TB / 192 TB


16




RAID Options 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




8



6


2









Synch Replication





Snapshot

Replication

Thin Provisioning



Block


In-line










System, VM, LUN


3


30




OVERALL SCORE


74.11 33.60 12.25 22.76 5.50EXCELLENT GOOD EXCELLENT EXCELLENT GOOD






HARDWARE*


FC

iSCSI




Cores (Max) 16



154 TB / 4,608 TB


56










RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




2



2


12





Hitachi Data Systems HUS VMApproximate Starting List Price: $150,000–$250,000




Synch Replication





Snapshot

Replication

Thin Provisioning



Block


In-line




System






System


1


31




OVERALL SCORE


60.20 23.10 13.50 16.75 6.85GOOD BASIC RECOMMENDED GOOD BEST-IN-CLASS






HARDWARE*


FC

iSCSI




Cores (Max) 16



24 GB / 400 GB


24




RAID Options 0, 1, 5, 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




3



7


12

Backup Techniques


1



HP 3PAR StoreServ 7200Approximate Starting List Price: Under $50,000




Synch Replication





Snapshot

Replication

Thin Provisioning



Block


Post-process




Volume






Volume


3


32




OVERALL SCORE


60.92 23.10 13.50 17.47 6.85GOOD BASIC RECOMMENDED GOOD BEST-IN-CLASS






HARDWARE*


FC

iSCSI




Cores (Max) 24



48 GB / 1,100 GB


24




RAID Options 0, 1, 5, 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




3



7


12

Backup Techniques


1



HP 3PAR StoreServ 7400Approximate Starting List Price: Under $50,000




Synch Replication





Snapshot

Replication

Thin Provisioning



Block


Post-process




Volume






Volume


3


33




OVERALL SCORE


60.46 27.75 10.00 18.31 4.40GOOD BASIC EXCELLENT GOOD BASIC






HARDWARE*


FC

iSCSI




Cores (Max) 4

Cache (Max RAM/Max) 16 GB / # GB


768 TB / 1,920 TB


64







HDD/SSD Interface FC-SW, SAS 6 Gb



RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




2



6


14

Backup Techniques Embedded, NDMP




IBM Storwize V7000 UnifiedApproximate Starting List Price: Under $50,000




Synch Replication





Snapshot

Replication

Thin Provisioning












LUN



34




OVERALL SCORE


57.20 25.08 5.25 22.23 4.65GOOD BASIC GOOD EXCELLENT GOOD






HARDWARE*


FC

iSCSI




Cores (Max) 8



4 TB / 124 TB


18







HDD/SSD Interface FC-AL, SAS 6 Gb



RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols iSCSI, NAS (NFS)

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






1


11





Imation Nexsan NST5130 Unified Hybrid Storage SystemApproximate Starting List Price: Under $50,000




Synch Replication





Snapshot

Replication

Thin Provisioning





Data Stores







System, LUN


5


35




OVERALL SCORE


59.85 25.08 5.25 24.37 5.15GOOD BASIC GOOD EXCELLENT GOOD






HARDWARE*


FC

iSCSI




Cores (Max) 16



8.8 TB / 1,440 TB


18










RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






1


11





Imation Nexsan NST5330 Unified Hybrid Storage SystemApproximate Starting List Price: Under $50,000




Synch Replication





Snapshot

Replication

Thin Provisioning





Data Stores







System, LUN


5


36




OVERALL SCORE


65.90 26.73 6.50 27.17 5.50GOOD BASIC GOOD RECOMMENDED GOOD






HARDWARE*


FC

iSCSI




Cores (Max) 24



8.8 TB / 5,040 TB


18










RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






1


11





Imation Nexsan NST5530 Unified Hybrid Storage SystemApproximate Starting List Price: $50,000– $100,000




Synch Replication





Snapshot

Replication

Thin Provisioning





Data Stores







System, LUN


5


37




OVERALL SCORE


78.38 37.90 12.25 22.69 5.55EXCELLENT GOOD EXCELLENT EXCELLENT GOOD






HARDWARE*


FC

iSCSI




Cores (Max) 16



2 TB / 2,880 TB


52




RAID Options 4, 6



HDD/SSD Interface PCI-e, SAS 6 Gb, SATA



RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






1


13



2



NetApp FAS3250Approximate Starting List Price: $50,000– $100,000




Synch Replication





Snapshot

Replication

Thin Provisioning



Block


Post-process


Data Stores HDD


Volume






System


2


38




OVERALL SCORE


47.97 29.73 5.25 9.39 3.60BASIC GOOD GOOD BASIC BASIC









Synch Replication





Snapshot

Replication

Thin Provisioning





Data Stores DRAM, NVRAM, SSD, HDD







LUN


1

HARDWARE*


FC

iSCSI


Controller Config Active-Standby


Cores (Max) 12



2.4 TB / 143 TB


6




RAID Options 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






5


7





Nimble Storage CS210Approximate Starting List Price: $38,000


39




OVERALL SCORE











Synch Replication





Snapshot

Replication

Thin Provisioning












LUN


1

HARDWARE*


FC

iSCSI




Cores (Max) 12



2.4 TB / 147 TB


6




RAID Options 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






5


7





Nimble Storage CS220Approximate Starting List Price: Not Listed


40




OVERALL SCORE











Synch Replication





Snapshot

Replication

Thin Provisioning












LUN


1

HARDWARE*


FC

iSCSI




Cores (Max) 12



2.4 TB / 159 TB


6




RAID Options 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






5


7







41




OVERALL SCORE











Synch Replication





Snapshot

Replication

Thin Provisioning












LUN


1

HARDWARE*


FC

iSCSI




Cores (Max) 12



2.4 TB / 171 TB


6




RAID Options 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






5


7







42




OVERALL SCORE











Synch Replication





Snapshot

Replication

Thin Provisioning












LUN


1

HARDWARE*


FC

iSCSI




Cores (Max) 12



2.4 TB / 147 TB


6




RAID Options 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






5


7





Nimble Storage CS420-X2Approximate Starting List Price: $


43




OVERALL SCORE











Synch Replication





Snapshot

Replication

Thin Provisioning












LUN


1

HARDWARE*


FC

iSCSI




Cores (Max) 12



2.4 TB / 147 TB


6




RAID Options 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






5


7





Nimble Storage CS420-X4Approximate Starting List Price: $


44




OVERALL SCORE











Synch Replication





Snapshot

Replication

Thin Provisioning












LUN


1

HARDWARE*


FC

iSCSI




Cores (Max) 12



2.4 TB / 159 TB


6




RAID Options 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






5


7





Nimble Storage CS440Approximate Starting List Price: $


45




OVERALL SCORE











Synch Replication





Snapshot

Replication

Thin Provisioning












LUN


1

HARDWARE*


FC

iSCSI




Cores (Max) 12



2.4 TB / 171 TB


6




RAID Options 6






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /






5


7





Nimble Storage CS460Approximate Starting List Price: $


46




OVERALL SCORE


73.70 47.40 2.50 18.30 5.50EXCELLENT EXCELLENT BASIC GOOD GOOD

Oracle Sun ZFS Storage 7120 ApplianceApproximate Starting List Price: Under $50,000






HARDWARE*


FC

iSCSI


Controller Config Single


Cores (Max) 4


Raw Storage Capacity (Max SSD/Max) /177 TB


12


12 / 4 / 4



RAID Options 0, 1, 5, 6, 10, Proprietary






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




1



2


14



2

Network File Systems NFS, CIFS/SMB, WebDAV





Synch Replication





Snapshot

Replication

Thin Provisioning



Block


In-line


Data Stores DRAM cache, SSD, HDD


System, LUN, Filesystem, Volume, VM






System, VM, LUN


3


47




OVERALL SCORE


78.03 47.40 2.50 22.63 5.50EXCELLENT EXCELLENT BASIC EXCELLENT GOOD







HARDWARE*


FC

iSCSI




Cores (Max) 8


Raw Storage Capacity (Max SSD/Max) /432 TB


12


12 / 4 / 4









RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




1



2


14



2






Synch Replication





Snapshot

Replication

Thin Provisioning



Block


In-line










System, VM, LUN


4


48




OVERALL SCORE


83.62 47.40 2.50 27.77 5.95EXCELLENT EXCELLENT BASIC BEST-IN-CLASS EXCELLENT







HARDWARE*


FC

iSCSI




Cores (Max) 40

Cache (Max RAM/Max) 2,000 GB / 14,608 GB

Raw Storage Capacity (Max SSD/Max) / 3,456 TB


56


40 / 24 / 8

8/16 Gb FC Ports (Max) 16 / 16








RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




1



2


14



2






Synch Replication





Snapshot

Replication

Thin Provisioning



Block


In-line










System, VM, LUN


4


49




OVERALL SCORE


74.01 39.35 8.00 20.41 6.25EXCELLENT GOOD GOOD GOOD EXCELLENT

Starboard Storage AC2000Approximate Starting List Price: $30,000






HARDWARE*


FC

iSCSI




Cores (Max) 8



1.1 TB / 171 TB


10




RAID Options 10, Proprietary






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




1




10

Backup Techniques







Synch Replication





Snapshot

Replication

Thin Provisioning





Data Stores DRAM cache, SSD







System, LUN


5


50




OVERALL SCORE


74.26 38.98 8.00 21.09 6.20EXCELLENT GOOD GOOD EXCELLENT EXCELLENT

Starboard Storage AC4000Approximate Starting List Price: Under $50,000






HARDWARE*


FC

iSCSI




Cores (Max) 8



3 TB / 576 TB


10




RAID Options 5, 10, Proprietary






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




1




10

Backup Techniques







Synch Replication





Snapshot

Replication

Thin Provisioning












System, LUN


5


51




OVERALL SCORE


75.31 39.03 8.00 22.03 6.25EXCELLENT GOOD GOOD EXCELLENT EXCELLENT

Starboard Storage AC4500Approximate Starting List Price: $50,000–$100,000






HARDWARE*


FC

iSCSI




Cores (Max) 8



6.8 TB / 576 TB


10




RAID Options 5, 10, Proprietary






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




1




11

Backup Techniques







Synch Replication





Snapshot

Replication

Thin Provisioning












System, LUN


5


52




OVERALL SCORE


90.54 50.73 10.50 23.37 5.95RECOMMENDED BEST-IN-CLASS EXCELLENT EXCELLENT EXCELLENT


Hardware Warranty 90 days







Synch Replication





Snapshot

Replication

Thin Provisioning



Block


In-line




LUN, Filesystem, Volume, VM






System, VM, LUN


4

HARDWARE*


FC

iSCSI


Controller Config Active-Active, Active-Standby


Cores (Max) 8



0.6 TB / 94 TB


20




RAID Options 0,1 ,5 ,6 ,10 ,60






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




2



2


7





Tegile Zebi HA2100Approximate Starting List Price: $60,000


53




OVERALL SCORE


90.67 50.48 10.00 24.24 5.95RECOMMENDED RECOMMENDED EXCELLENT EXCELLENT EXCELLENT









Synch Replication





Snapshot

Replication

Thin Provisioning



Block


In-line










System, VM, LUN


4

HARDWARE*


FC

iSCSI




Cores (Max) 16



1.2 TB / 94 TB


20




RAID Options 0, 1, 5, 6, 10, 60






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




1



2


7





Tegile Zebi HA2100EPApproximate Starting List Price: $100,000


54




OVERALL SCORE


91.14 50.73 10.50 23.96 5.95RECOMMENDED BEST-IN-CLASS EXCELLENT EXCELLENT EXCELLENT

Tegile Zebi HA2400Approximate Starting List Price: $100,000–$150,000









Synch Replication





Snapshot

Replication

Thin Provisioning



Block


In-line










System, VM, LUN


5

HARDWARE*


FC

iSCSI




Cores (Max) 16



2.2 TB / 65 TB


20




RAID Options 0, 1, 5, 6, 10, 60






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




2



2


7






55




OVERALL SCORE


92.15 50.73 10.50 24.98 5.95BEST-IN-CLASS BEST-IN-CLASS EXCELLENT EXCELLENT EXCELLENT









Synch Replication





Snapshot

Replication

Thin Provisioning



Block


In-line










System, VM, LUN


5

HARDWARE*


FC

iSCSI




Cores (Max) 16



4.4 TB / 148.4 TB


20




RAID Options 0, 1, 5, 6, 10, 60






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots


Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




2



2


7





Tegile Zebi HA2800Approximate Starting List Price: $150,000–$250,000


56




OVERALL SCORE


43.89 33.17 1.75 5.22 3.75BASIC GOOD BASIC BASIC BASIC








Asynch Replication Periodic, VM-level

Synch Replication




N/A


Snapshot

Replication

Thin Provisioning



Block


In-line


Data Stores HDD


System






System, VM


1

HARDWARE*

Concurrent SAN & NAS N/A

FC N/A

iSCSI N/A

Concurrent FC & iSCSI N/A



Cores (Max) 12

Cache (Max RAM/Max) N/A (not disclosed)


2.4 TB / 26.4 TB


8




RAID Options 6



HDD/SSD Interface SAS 6Gb



RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols NAS (NFS)

Full Copy (NFS)

Hardware Assisted Locking N/A for NFS

Block Zeroing N/A for NFS


N/A for NFS

Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC N/A /

VADP / VASA N/A /




1

Performance Monitoring System,VM, vDisks


6


3



1

Network File Systems NFS


Tintri VMstore T540Approximate Starting List Price: $90,000 (HW only)


57




OVERALL SCORE


29.13 10.68 2.75 10.45 5.25BASIC BASIC BASIC BASIC GOOD








Asynch Replication

Synch Replication





Snapshot

Replication

Thin Provisioning





Data Stores







LUN


1

HARDWARE*


FC

iSCSI




Cores (Max) 4



2 TB / 27 TB


8

1/10/40 Gb Ethernet Ports (Max) / /



RAID Options 5, 10






RoHS Compliant

VMware INTEGRATION*


vSphere Snapshots

Ingest Protocols FC

Full Copy


Block Zeroing


Full File Clone


Reserve Space

Extended Statistics

AQDT / SIOC /

VADP / VASA /




1



5


12

Backup Techniques




X-IO Hyper ISE 730Approximate Starting List Price: $100,000–$150,000



Product Rankings Dashboard

OVERALL

SCORE

MANAG

EMEN

T & SO

FTWAR

E

MANAG

EMEN

T & SO

FTWAR

E

VMware

VMware

HARDWAR

E

HARDWAR

E

SUPP

ORT

SUPP

ORT

OVERALL

SCORE

Avere FXT 4200

Best-In-Class RecommendedExcellentGood Basic

EMC VNX5700

Avere FXT 4500


EMC VNX7500

DDN SFA7700


Dell EqualLogic PS6510ES


Fusion–io NexGen n5-50 Storage System


Dot Hill AssuredSAN Pro 5000



Hitachi Data Systems HUS VM

EMC VNX5100

Best-In-Class RecommendedExcellentGood

Basic

EMC VNX5300


EMC VNX5500



Product Rankings Dashboard (continued)

Nimble Storage CS210

HP 3PAR StoreServ 7200

Best-In-Class

RecommendedExcellentGood

Basic


HP 3PAR StoreServ 7400

Best-In-Class


Basic

IBM Storwize V7000 Unified

Best-In-Class


Basic



Imation Nexsan NST5130 Unified Hybrid Storage System


Basic

Nimble Storage CS420-X2



Basic

Nimble Storage CS420-X4




Basic

NetApp FAS3250Best-In-Class RecommendedExcellentGood

Basic

OVERALL

SCORE

MANAG

EMEN

T & SO

FTWAR

E

MANAG

EMEN

T & SO

FTWAR

E

VMware

VMware

HARDWAR

E

HARDWAR

E

SUPP

ORT

SUPP

ORT

OVERALL

SCORE



Product Rankings Dashboard (continued)

OVERALL

SCORE

MANAG

EMEN

T & SO

FTWAR

E

MANAG

EMEN

T & SO

FTWAR

E

VMware

VMware

HARDWAR

E

HARDWAR

E

SUPP

ORT

SUPP

ORT

OVERALL

SCORE

Tegile Zebi HA2100



Basic

Tegile Zebi HA2100EP

Oracle Sun ZFS Storage 7120 Appliance




Tegile Zebi HA2400

Tegile Zebi HA2800


Best-In-Class

RecommendedExcellentGood Basic

Tintri VMstore T540

Starboard Storage AC2000


X-IO Hyper ISE 730







Appendix B—Storage Provider Contact Information

APPENDICESAppendix A: Definitions, Explanations and Terminology

Appendix B: Storage Provider Contact Information

Appendix C: Author Contact Information

© 2013 DCIG, LLC. All rights reserved. A-1


Appendix A—Definitions, Explanations and Terminology

Management & SoftwareSnapshot Methods (Total #)

This score indicates if the array can do snapshots and how comprehensive the snapshot options for this array are. The number specifies the number of different supported elements available. The specific elements supported for each product are available by accessing the DCIG Interactive Buyer’s Guide (IBG).

Asynch ReplicationIndicates if the array can asynchronously replicate data to another hybrid storage array from the same storage provider. Asynchronous replication may be continuous or periodic.

Continuous: Every write I/O is copied, stored in a local disk cache and then replicated as soon as possible to a secondary midrange array.

Periodic: A snapshot of one or more volumes is periodi-cally taken with that snapshot and then replicated to a secondary midrange array.

Synch ReplicationThe array can synchronously replicate data to another array from the same storage provider. Write I/Os need to be received at the primary or source array and then copied and written to the secondary, or target array, with the write confirmed as complete by both before process-ing can continue.

Thin ProvisioningA storage optimization method where volume resources are allocated on the disk only when needed.

Eager-Zeroed-ThickA thin provisioning optimization method used primarily in virtualized environments where volume resources are pre-allocated on the disk and the space then filled with zeros. This is done to indicate the space is unused and may be reclaimed as well as a method to overwrite data on storage space that was previously used by another virtual machine.

Definitions, Explanations and TerminologyThis section contains brief definitions and/or explanations of the terms used and assumptions made when developing the data sheets found in the DCIG 2014 Hybrid Array Buyer’s Guide. These terms are in the same order as they appear on the individual data sheets.

Automated Storage Reclamation (Native)Automated Storage Reclamation returns de-provisioned storage to the pool of available capacity. A check indicates that this capability is supported natively by the array without the aid of 3rd party software.

Symantec Zero Reclamation APIIndicates support for Symantec’s Zero Reclamation API which allows reuse of areas of storage that have been filled with zeros in thin provisioning scenarios.

Feature Software Licenses IncludedA check mark indicates if the array includes a license for the Snapshot, Replication or Thin Provisioning features without an extra licensing fee.

Deduplication and CompressionData deduplication saves disk space by storing only one copy of data when identical data is already stored on the array. Compression is a feature that compresses data as it is written to storage systems. Like deduplication, data compression works in both SAN and NAS environments.

Forms of Deduplication Block: Deduplicates data on a per-block basis. Stores a pointer to an existing identical block of data rather than a second instance of the block.

File: File deduplication stores a pointer to an existing identical file on the array rather than storing a second instance of the file. Some vendors call this single instance store.

Deduplication (In-line vs. Post-process)In-line: Data is deduplicated before it is stored to disk.

Post-process: Data is first stored to disk in its native or raw format and subsequently deduplicated.

Block Level CompressionA data compression technique for improving space efficiency by replacing repetitive strings of data within a block with a shorter referent from a dictionary of such data strings.



Appendix A—Definitions, Explanations and Terminology (continued)

Data StoresA listing of the data stores that are deduplicated and/or compressed. See the DCIG Interactive Buyer’s Guide (IBG) for a list of supported options for any particular array. Data stores that may be deduplicated and/or compressed:

• DRAM cache

• NVRAM/flash memory cache

• SSDs/Flash memory modules

• HDDs (Hard Disk Drives)

Deduplication Management LevelIndicates if the array management software included on the model supports deduplication at the System, LUN, File System, Volume or the Virtual Machine level.

Automated Real-Time Tiering/CachingTiering/caching ensures the most critical data always reside on high performance media including DRAM, NVRAM, or Solid State Drives (SSDs), while less active data blocks are moved to the hard disk drive tiers.

Preset System Policies/AlgorithmsData is moved/placed dynamically (in real time) based on preset system policies/algorithms.

User-Defined PoliciesData is moved/placed dynamically (in real time) based on user-defined policies

User-Defined Performance TargetsData is moved/placed dynamically (in real time) based on user-defined performance targets

Tiering/Caching Management LevelIndicates if the array offers management of storage tiering/caching at the System, Virtual Machine or LUN level. Management at each level typically can be accomplished with system presets or user-defined policies.

Forms of flash-based caching (Total #)The ability to utilize flash memory as cache in front of permanent storage to improve system performance. A count of the flash-based caching options (Block IO acceleration, NAS acceleration, read caching, write caching, write journaling) that are supported by the array. See the DCIG Interactive Buyer’s Guide (IBG) for a list of supported options for any particular array.

Block I/O Acceleration: The use of caching specifically for block (SAN) performance beyond read/write operations such as metadata storage.

NAS Acceleration: The use of caching specifically for NAS performance beyond read/write operations such as metadata storage.

Read Caching: The caching of frequently or recently accessed data to improve read performance. May include predictive caching techniques.

Write Caching: The caching of data to flash media prior to writing permanent storage in order to improve write performance.

Write Journaling: The use of a circular journal to provide write caching and reliability assurance before writing to permanent storage.

Workload Prioritization (QoS) (Total #)A count of the workload prioritization methods supported by the array. The specific elements supported for each product are available by accessing the DCIG Interactive Buyer’s Guide (IBG). Workload prioritization options include:

• I/O automatically balanced across all VMs/LUNS/volumes.

• User-defined queue ratios (i.e. one VM/LUN/Volume gets 80%, another gets 20%)

• User-defined target IOPs for each VM/LUN/Volume

• User-defined target bandwidth for each VM/LUN/Volume

• User-defined target system response time for each VM/LUN/Volume

• User-defined guaranteed minimum IOPs for each VM/LUN/Volume

• User-defined guaranteed minimum bandwidth for each VM/LUN/Volume

• User-defined guaranteed minimum average system response time for each VM/LUN/Volume

• User-defined maximum IOPs for each VM/LUN/Volume

• User-defined maximum bandwidth for each VM/LUN/Volume

• User-defined maximum system response time for each VM/LUN/Volume




• User categorizes each VM/LUN/Volume into pre-defined service levels (i.e. Gold, Silver, Bronze)

• Sacrifice performance of lower priority workloads for higher priority ones during degraded state operation (disk drive rebuild, controller failure, etc…)

Performance MonitoringThe array provides an application that monitors and reports on how an array’s resources (disk drives, storage network-ing ports, cache, LUNs, VMs, etc.) are being utilized and how well they are performing. A check mark indicates this feature is supported. The specific elements supported for each product are available by accessing the DCIG Interactive Buyer’s Guide (IBG).

Provisioning: Automation & Policies (Total #)A count of the automation and storage provisioning options supported by the array. The specific elements supported for each product are available by accessing the DCIG Interactive Buyer’s Guide (IBG). Automation and provisioning options include:

• Policy-based storage selection

• Create storage templates to include SLA/QOS requirements

• Provisioning via server groups linked to storage templates

• Self-service portal for server and/or storage administrators

• Automated reclamation when virtual server is decommissioned

• Scheduling and notification of provisioning activities

• Exposes APIs for use by 3rd party storage automation tools

• Support integration with ITSM products (Remedy, Tivoli)

• SDK for integration with management software

Hypervisor/Operating System (Total #)Count of the number of supported hypervisors or operating systems. The specific elements supported for each product are available by accessing the DCIG Interactive Buyer’s Guide (IBG).

Backup TechniquesBackup techniques/technologies supported by the array

Options:

• NDMP (Network Data Management Protocol) is an open standard protocol for enterprise-wide backup of heterogeneous network-attached storage.

• Embedded backup software specific to the vendor or array.

Data Migration to Cloud Storage Providers (Total #)The ability to natively attach, integrate and/or migrate data to public or private cloud storage providers. The number specifies the number of cloud storage options supported. The specific elements supported for each product are available by accessing the DCIG Interactive Buyer’s Guide (IBG).

Network File Systems (NAS Only)A Network File System is a protocol that allows the “mounting” of devices or file systems on other systems over a network. Indicates what network file systems are supported by the array. Options include CIFS/SMB, NFS, and WebDAV.

CIFS/SMB: (Common Internet File System/Server Message Block) CIFS/SMB is the underlying protocol of Windows File Sharing. Due to the large installed base of Windows workstations and servers it has become nearly ubiquitous and is supported by all major desktop and server operating systems.

NFS: (Network File System) NFS is to the Unix world what CIFS is to the Windows world. It is a protocol that allows the “mounting” of devices/file systems on other systems over a network.

WebDAV: (Web Distributed Authoring and Versioning) WebDAV is a HTTP (web) based file system implementation intended to support author and version tracking.

Multiple Virtual NASThe ability of a storage array to make itself appear as multiple NAS devices.




SupportHardware Warranty

Indicates the length of standard warranty for the array.

Contract Support AvailabilitySpecifies the hours when support is available when under service contract. Examples include “business hours” (9am–5pm, weekdays), “24x7” (24 hours a day, seven days a week, but not holidays) and “24x7x365” (24 hours a day, seven days a week, including holidays).

Contract Support (Total #)A count of the methods of support offered by the vendor. Options include phone, email, web chat, remote monitor-ing, remote login/problem resolution, dispatch technician onsite, dispatch technician onsite with 4-hour GTD response, same day delivery of replacement parts, and pre-failure shipping of replacement parts. The number specifies the number of different supported elements available. The specific elements supported for each product are available by accessing the DCIG Interactive Buyer’s Guide (IBG).

Non-Contract SupportA checkmark here indicates the array vendor provides support for the model on a non-contract basis. Hours of availability and support methods may differ from those offered for on-contract arrays, and may require a fee.

VMware IntegrationvSphere Plug-in for array management

A check mark indicates the array has a vSphere plug-in to perform array based management functions.

vSphere SnapshotsSupport for full integration with vSphere’s snapshot capability; either natively, or through a plug-in provided by the storage array vendor.

Ingest ProtocolsIndicates whether the array supports the storing of data for later usage using Fibre Channel, iSCSI or NAS (NFS) protocols.

Full CopyUsed to copy data and/or create clones, avoiding the need to send data back and forth to a host.

Hardware Assisted LockingAllows vCenter to offload SCSI commands from the ESX server to the storage array so it can control the locking mechanism while the storage array does data updates.

Block ZeroingThe VMware vSphere ESXi host issues a command to the private cloud storage array that it recognizes. This command instructs the storage array to write zeros to the virtual VMDK or VMFS LUNs. This generally occurs when initializing the virtual disk for a new VM. Support for this feature indicates that the storage array recognizes this vSphere primitive and performs this zeroing activity. Enables the storage array to zero out a large number of data blocks to speed the provisioning of virtual machines (VMs) and reduce I/O.


Using the SCSI UNMAP command, an ESXi host can inform a storage array that space may be reclaimed that previously had been occupied by a VM that has been migrated to another datastore or deleted.

Full File CloneThis command is part of VAAI 5.0 and is a NAS hardware acceleration primitive. The VMware vSphere ESXi host issues a command to the private cloud storage array that it recognizes. This command instructs the storage array to clone a virtual disk. Support for this feature indicates that the storage array recognizes this vSphere primitive and performs this cloning activity.

Out-of-Space ConditionsThis command is part of VAAI 5.0 and was introduced to mitigate the impact on VMs when thin-provisioned datastores reach 100 percent of capacity. The private cloud storage arrays alerts the VMware vSphere ESXi host and/or vCenter when specified thresholds are reached. Should a datastore reach 100 percent of capacity, only those VMs requiring additional capacity are paused while VMs needing no additional capacity continue to run. Support for this feature indicates that the storage array recognizes this vSphere primitive and performs this out-of-space alerting.

Reserve SpaceThis command is part of VAAI 5.0 and is a NAS hardware acceleration primitive. The VMware vSphere ESXi host




issues a command to the private cloud storage array that it recognizes. This command instructs the storage array to create thick VMDK files on NAS datastores. Support for this feature indicates that the storage array recognizes this vSphere primitive and performs this file allocation activity.

Extended StatisticsExtended Statistics enables vSphere functionality to display actual space usage statistics on NAS datastores without the use of third-party tools. Before the introduction of Extended Statistics, it would have been necessary to use array-based tools to monitor the space being used on a thinly provisioned Virtual Disk Machine (VMDK) on a back-end datastore.

AQDTVMware ESX 3.5 Update 4 introduced an adaptive queue depth throttling (AQDT) algorithm that adjusts the LUN queue depth in the VMkernel I/O stack. This algorithm is activated when the storage array indicates LUN I/O congestion by returning a BUSY or QUEUE FULL status. When LUN congestion is detected, VMkernel throttles the LUN queue depth. The VMkernel attempts to gradually restore the LUN queue depth when LUN congestion conditions subside. AQDT prevents the array from being flooded with LUN I/O requests and enables the array to recover to a normal operational state. NOTE: This is not applicable for NFS mounted storage.

SIOCStorage I/O Control (SIOC) for VMware is a dynamic control mechanism for proportional allocation of shared storage resources to VMs running on multiple hosts.

VADPvStorage APIs for Data Protection (VADP) is a data protection framework introduced in vSphere 4.0. VADP enables centralized, off-host LAN free backup of vSphere virtual machines, reduces ESX host resources to do backup processing, and enables flexible backup windows.

VASAvSphere Storage APIs for Storage Awareness is a set of APIs that permit storage arrays to integrate with vCenter for management functionality. Storage Awareness collects configuration, capability and storage health information from storage arrays. This allows the administrator to build Storage Profiles based on capabilities.

VASRMvStorage APIs for Site Recover Manager (VASRM) offers remote replication features enabling a device to failover to a recovery site.

Storage DRSStorage Distributed Resource Scheduler (DRS) provides virtual machine placement and load balancing mechanisms based on I/O and space capacity.

HardwareConcurrent SAN & NAS

The ability for the storage array to communicate with applications using both block (SAN) and network file system (NAS) clients at the same time.

FCFibre Channel (FC) is used as a networking protocol to transmit data between computer devices, such as a server and a storage device.

iSCSIInternet Small Computer System Interface (iSCSI) is a block-based protocol for running SCSI commands over Internet Protocol (IP) on Ethernet to access storage resources.

Concurrent FC & iSCSIThe ability for the storage array to connect to hosts over Fibre Channel and iSCSI at the same time.

Controller ConfigActive-Active: Two controllers are configured with multi-pathing software and have concurrent access to the disk drives that are then presented as LUNs to attached hosts. In the event a controller fails or is taken offline, attached host(s) may detect little or no interruption in service as the other controller takes over for the failed unit though a drop in performance may occur. This is consid-ered an enterprise class feature.

Active-Standby: All LUNs are controlled and assigned to a single active controller through which all storage I/O traffic is routed. A secondary standby controller takes over the storage I/O traffic for the active controller should it fail or be taken offline. The secondary controller also assumes control of the array’s LUNs at any time.




Dual Active: Both controllers are active and have concurrent access to the drives that are presented as LUNs to the attached hosts. The difference from Active-Active is that half of the storage array’s LUNs are assigned to and controlled by one controller and the other half of the LUNs to the other so a LUN can only be accessed down one path through one controller at a time. If a controller should be taken offline or fail, the other controller assumes control for its LUNs.

Scale-out (Max controllers)The maximum number of controllers that the model can support in a single logical configuration. An “X” indicates that this array does not support a scale-out SAN configuration.

Cores (Max)The number listed indicates the maximum number of processor cores available in each of the array’s controllers.

Cache (Max RAM/Max)The maximum number of gigabytes (GBs) of cache that each array controller can support.

Max RAM: Specifies the maximum number of gigabytes (GBs) of DRAM cache.

Max: Cache may consist of any combination of DRAM, NVRAM and SSD.

Raw Storage Capacity (Max SSD/Max)The maximum amount of raw storage capacity in terabytes (TBs) that the array can have under its management. However, this number only includes the array’s footprint and not the storage capacity of other systems it may have virtualized.

Max SSD: Maximum flash memory raw capacity supported in this array.

Max: Maximum capacity using a best case scenario with any combination of SSDs and HDDs using the largest available disk drives certified for this model.

Storage Networking Ports (Max)The maximum number of ports available in any configura-tion to connect the array to hosts or to a dedicated storage network. Controllers that support both Ethernet and Fibre Channel may also support concurrent use of both technologies. See “Concurrent FC & iSCSI” for

additional clarification. Ports for managing the array or interconnecting multiple storage controllers are not included in this count.

1/10/40 Gb Ethernet Ports (Max)Indicates the maximum number of 1 Gb, 10 Gb and 40 Gb Ethernet storage networking ports supported by the array in any configuration.

8/16 Gb FC Ports (Max)Indicates the maximum number of 8 Gb and 16 Gb Fibre Channel storage networking ports supported by the array in any configuration.

Information Dispersal AlgorithmsInformation dispersal algorithms/erasure coding allows an array to store data across multiple locations as a way to enhance redundancy and protect against data loss. (Generally used as an alternative to RAID.)

RAID OptionsLists the standard RAID (Redundant Array of Independent Disks) levels supported by the device. Examples include RAID 0 (striping without mirroring or parity), RAID 1 (mirroring without stripting or parity), RAID 5 (block-level striping with distributed parity), etc.

Global Hot Spares (SSD/HDD)Indicates if the array permits an SSD or HDD disk drive to be designated as a global hot spare, and be used to automatically replace a matching failed drive in a RAID set.

Redundancy (Total #)The elements that make up the Redundancy score include redundant and hot swap power supplies, fans, and drives. The number specifies the number of different supported elements available. The specific elements supported for each product are available by accessing the DCIG Interactive Buyer’s Guide (IBG).

HDD/SSD InterfaceIndicates the interface(s) the controller uses to connect to the back-end HDDs and SSDs. Options that may be supported include FC-AL, FC-SW, SATA SAS 3Gb and SAS 6Gb.

SSD Optimizations (Total #)Indicates the extent to which specialized SSD techniques are supported by the array. Optimization techniques that




may be supported include: Wear leveling, Wear monitoring and alerting, Buffering and/or coalescing of writes to match erasure block size (EBS), Variable RAID stripe sizing to match erasure block size (EBS), Tuning of data aging timers for write buffering, Inline deduplication, Block level compression, and Hardware accelerated compression. The number specifies the number of different supported elements available. The specific elements supported for each product are available by accessing the DCIG Interactive Buyer’s Guide (IBG).

Managed UPS/Battery BackupIndicates if the array offers a battery backup (i.e. integrated UPS in the array) in case of power failure.

RoHS CompliantThe Restriction of Hazardous Substances (RoHS) is a movement intended to limit certain dangerous substances commonly used in electronic and electronic equipment. Compliant components are tested for substances such as lead or mercury.

© 2013 DCIG, LLC. All rights reserved. B-1


Appendix B—Storage Provider Contact Information

Avere Systems, Inc.5000 McKnight Rd., Ste. 404Pittsburgh, PA 15237 USA +1.412.635.7170http://www.averesystems.com/index.aspx

DDN9351 Deering Avenue Chatsworth, CA [email protected]+1.800.TERABYTE (1.800.837.2298)http://www.ddn.com/

Dell1 Dell WayRound Rock, TX 78682+1.800.671.3355http://www.dell.com

Dot Hill Systems Corporation1351 S Sunset St.Longmont, CO 80501-6533+1.303.845.3200http://dothill.com

EMC Corporation176 South StreetHopkinton, MA [email protected]+1.866.438.3622http://www.emc.com

Fusion-io2855 E. Cottonwood Parkway, Ste.100Salt Lake City, UT 84121+1.801.424.5500http://www.fusionio.com/

Hitachi Data Systems Corporation2845 Lafayette StreetSanta Clara, California 95050-2639+1.408.970.1000http://www.hds.com

Hewlett-Packard Corporation3000 Hanover StreetPalo Alto, CA 94304+1.866.625.0242http://www.hp.com

IBM Corporation1 New Orchard RdArmonk, NY [email protected]+1.800.426.4968http://www.ibm.com/storage

Imation Nexsan Solutions1445 Lawrence DriveThousand Oaks, CA 91320+1.866.463.9726http://www.nexsan.com/

NetApp495 East Java DriveSunnyvale, CA 94089+1.877.263.8277http://www.netapp.com

Nimble Storage, Inc.2740 Zanker RoadSan Jose, CA [email protected]+1.877.364.6253+1.408.432.9600http://www.nimblestorage.com/

Oracle Corporation500 Oracle ParkwayRedwood Shores, CA 94065+1.650.506.7000+1.800.392.2999http://www.oracle.com

Starboard Storage Systems12303 Airport Way, Suite 230Broomfield, CO 80021+1.855.790.9996http://www.starboardstorage.com/

Storage Provider Contact Information

Tegile Systems, Inc. 8000 Jarvis Ave. Newark, CA 94560 +1.510.791.7900http://www.tegile.com/

Tintri, Inc.201 Ravendale DriveMountain View, CA 94043 [email protected]+1 650-810-8200 http://www.tintri.com/

X-IO Storage9950 Federal Drive, Suite 100Colorado Springs, CO 80921+1.866.472.6764http://xiostorage.com/

http://www.averesystems.com/index.aspx

mailto:info%40ddn.com?subject=

http://www.ddn.com/

http://www.dell.com

http://dothill.com

mailto:info%40isilon.com?subject=

http://www.emc.com

http://www.fusionio.com/

http://www.hds.com

http://www.hp.com

mailto:callserv%40ca.ibm.com?subject=

http://www.ibm.com/storage

http://www.nexsan.com/

mailto:info%40nimblestorage.com?subject=

http://www.nimblestorage.com/

http://www.oracle.com

http://www.starboardstorage.com/

http://www.tegile.com/

mailto:info%40tintri.com?subject=

http://www.tintri.com/

http://xiostorage.com/

© 2013 DCIG, LLC. All rights reserved. C-1


Appendix C—Author Contact Information

DCIG, LLC7511 Madison StreetOmaha, NE 68127+1.402.884.9594

CONTACT

Ken [email protected]

WEBSITEwww.dcig.com

Author Contact Information

mailto:ken.clipperton%40dcig.com?subject=

www.dcig.com

HYBRID STORAGE ARRAY BUYER S GUIDE - White Papers · 20 Dell EqualLogic PS6510ES ... 31 HP 3PAR...

Documents

Transcript of HYBRID STORAGE ARRAY BUYER S GUIDE - White Papers · 20 Dell EqualLogic PS6510ES ... 31 HP 3PAR...