NetApp Archives

IBM recently took a flash step announcing it wants and needs more SSD capabilities in different packaging and functionality capabilities to meet the demands and opportunities of customers, business partners and prospects by acquiring Texas Memory Systems (TMS).

IBM buys SSD flash vendor TMS

Unlike most of the current generation of SSD vendors besides those actually making the dies (chips or semiconductors) or SSD drives that are startups or relatively new, TMS is the industry veteran. Where most of the current SSD vendors experiences (as companies) is measured in months or at best years, TMS has seen several generations and SSD adoption cycles during its multi-decade existence.

What this means is that TMS has been around during past dynamic random access memory (DRAM) based SSD cycles or eras, as well as being an early adopter and player in the current nand flash SSD era or cycle.

Granted, some in the industry do not consider the previous DRAM based generation of products as being SSD, and vice versa, some DRAM era SSD aficionados do not consider nand flash as being real SSD. Needless to say that there are many faces or facets to SSD ranging in media (DRAM, and nand flash among others) along with packaging for different use cases and functionality.

IBM along with some other vendors recognize that the best type of IO is the one that you do not have to do. However reality is that some type of Input Output (IO) operations need to be done with computer systems. Hence the second best type of IO is the one that can be done with the least impact to applications in a cost-effective way to meet specific service level objectives (SLO) requirements. This includes leveraging main memory or DRAM as cache or buffers along with server-based PCIe SSD flash cards as cache or target devices, along with internal SSD drives, as well as external SSD drives and SSD drives and flash cards in traditional storage systems or appliances as well as purpose-built SSD storage systems.

While TMS does not build the real nand flash single level cell (SLC) or multi-level cell (MLC) SSD drives (like those built by Intel, Micron, Samsung, SANdisk, Seagate, STEC and Western Digital (WD) among others), TMS does incorporate nand flash chips or components that are also used by others who also make nand flash PCIe cards and storage systems.

IMHO this is a good move for both TMS and IBM, both of whom have been StorageIO clients in the past (here, here and here) that was a disclosure btw ;) as it gives TMS, their partners and customers a clear path and large organization able to invest in the technologies and solutions on a go forward basis. In other words, TMS who had looked to be bought gets certainty about their future as do they clients.

IBM who has used SSD based components such as PCIe flash SSD cards and SSD based drives from various suppliers gets a PCIe SSD card of their own, along with purpose-built mature SSD storage systems that have lineages to both DRAM and nand flash-based experiences. Thus IBM controls some of their own SSD intellectual property (e.g. IP) for PCIe cards that can go in theory into their servers, as well as storage systems and appliances that use Intel based (e.g. xSeries from IBM) and IBM Power processor based servers as a platform such. For example DS8000 (Power processor), and Intel based XIV, SONAS, V7000, SVC, ProtecTier and Pursystems (some are Power based).

In addition IBM also gets a field proven purpose-built all SSD storage system to compete with those from startups (Kaminario, Purestorage, Solidfire, Violin and Whiptail among others), as well as those being announced from competitors such as EMC (e.g. project X and project thunder) in addition to SSD drives that can go into servers and storage systems.

The question should not be if SSD is in your future, rather where will you be using it, in the server or a storage system, as a cache or a target, as a PCIe target or cache card or as a drive or as a storage system. This also means the question of how much SSD do you need along with what type (flash or DRAM), for what applications and how configured among other topics.

What this means is that there are many locations and places where SSD fits, one type of product or model does not fit or meet all requirements and thus IBM with their acquisition of TMS, along with presumed partnership with other SSD based components will be able to offer a diverse SSD portfolio.

The industry trend is for vendors such as Cisco, Dell, EMC, IBM, HP, NetApp, Oracle and others all of whom are either physical server and storage vendors, or in the case of EMC, virtual servers partnered with Cisco (vBlock and VCE) and Lenovo for physical servers.

Thus it only makes sense for those vendors to offer diverse SSD product and solution offerings to meet different customer and application needs vs. having a single solution that users adapt to. In other words, if all you have is a hammer, everything needs to look like a nail, however if you have a tool box of various technologies, then it comes down to being able to leverage including articulating what to use when, where, why and how for different situations.

I think this is a good move for both IBM and TMS. Now lets watch how IBM and TMS can go beyond the press release, slide decks and webex briefings covering why it is a good move to justify their acquisition and plans, moving forward and to see the results of what is actually accomplished near and long-term.

Read added industry trends and perspective commentary about IBM buying TMS here and here, as well as check out these related posts and content:

How much SSD do you need vs. want?
What is the best kind of IO? The one you do not have to do
Is SSD dead? No, however some vendors might be
Has SSD put Hard Disk Drives (HDDs) On Endangered Species List?
Why SSD based arrays and storage appliances can be a good idea (Part I)
EMC VFCache respinning SSD and intelligent caching (Part I)
SSD options for Virtual (and Physical) Environments: Part I Spinning up to speed on SSD
Speaking of speeding up business with SSD storage
Is SSD dead? No, however some vendors might be
Part I: PureSystems, something old, something new, something from big blue
The Many Faces of Solid State Devices/Disks (SSD)
SSD and Green IT moving beyond green washing

Meanwhile, congratulations to both IBM and TMS, ok, nuff said (for now).

Cheers Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

June 7, 2012November 26, 2023

NetApp on rough ground, or a diamond in the rough?

Storage I/O Industry Trends and Perspectives

In case you missed it, NetApp announced their most recent quarterly earnings a few weeks ago which in themselves were not bad. However what some of their competition jumping up and down for joy while others are scratching their heads is the forward-looking guidance given by NetApp.

NetApp can be seen as being on rough ground given their forward-looking guidance over the next year which could be seen as either very conservative, or an admission that they are not growing as fast as some of their competitors are challenging them.

Reading between the lines, looking at various financial and other resources in addition to factoring in technology items, there is more to NetApp then meets the eye and current stock price or product portfolio.

For example, NetApp is sitting on over $4 Billion USD cash that they could use for an acquisition, buying back stock, launching a major sales and marketing initiative to expand into new or adjacent markets or other activities. Speaking of acquisitions, NetApp has done some in the past including Spinnaker, which is now integrated with Ontap (e.g. clustering), Topio, Decru (security encryption) and Onaro (DCIM and IRM management software tools). More recently, NetApp has acquired Bycast (archiving and policy storage management software), Akorri (capacity management and DCIM and IRM software) and Engenio. NetApp is also maintaining good margins via both direct, channel and OEM activities while launching new products such as the channel and SMB focused FAS 2220.

Its arguable depending upon your point of view (or who you for or are a fan of) if NetApp has all the right product pieces now, in the works, or on their radar for acquisitions. Assuming that NetApp has the pieces, they also need to move beyond selling simply what is on the truck or what is safe and comfortable or perhaps easy to sell. This is not to say that NetApp is not being effective in selling what they have and pushing the envelope, however keeping in mind who their main competitor is, the old sales saying of being able to sell ice to an Eskimo comes to mind.

In the case of NetApp, when the competition makes an issue about scalibility or performance of their flagship storage systems FAS and Ontap storage software, change the playing field leveraging all the tools in their portfolio. NetApp like EMC before them is figuring out how to sell via different channels or venues their complete portfolio with a mix of direct, channel and OEM. After all, it seems like only yesterday that EMC was trying to figure out where and when to sell CLARiiON (e.g. now VNX) as opposed to avoiding competing with the Symmetrix (aka now the VMAX) not to mention expanding from a direct to channel and OEM model. Perhaps NetApp can continue to figure out how to leverage more effectively the Engenio E series for big bandwidth beyond their current OEMs. NetApp can also leverage their existing partners who have embraced Bycast (aka StorageGrid) while finding new ones.

The reality is that NetApp is being challenged by EMC who is moving down market into some of NetApp’s traditional accounts along with in the scale-out NAS and big data sectors. This is where NetApp can leverage their technical capabilities including people combined with some effective sales and marketing execution to change the playing field vs. responding to EMC and others.

NetApp has many of the pieces, parts, products, people, programs and partners so now how can they leverage those to expand both their revenues, as well as support margin to grow the business, unless they are looking to be acquired.

I still subscribe that NetApp and EMC are two similar companies on parallel tracks offset by time, by about a decade or decade and a half.

Storage I/O Industry Trends and Perspectives

Thus, IMHO NetApp is a diamond in the rough, granted I am guessing EMC and some others do not see it that way. However, there was a time when EMC was seen as a diamond in the rough while others discounted that notion, particularly an Itty Bitty Manufacturing company from New York who is now focusing on services among other things.

Keep in mind however, diamonds can also be lost or taken as well as there can be fake gems.

Here are some related links:
Unified storage systems showdown: NetApp FAS vs. EMC VNX
Two companies on parallel tracks moving like trains offset by time: EMC and NetApp
NetApp buying LSI’s Engenio Storage Business Unit

Ok, nuff said for now

Cheers Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

May 17, 2012November 26, 2023

Are large storage arrays dead at the hands of SSD?

Storage I/O trends

An industry trends and perspective.

Are large storage arrays dead at the hands of SSD? Short answer NO not yet.
There is still a place for traditional storage arrays or appliances particular those with extensive features, functionality and reliability availability serviceability (RAS). In other words, there is still a place for large (and small) storage arrays or appliances including those with SSDs.

Is there a place for newer flash SSD storage systems, appliances and architectures? Yes
Similar to how there is a place for traditional midrange storage arrays or appliances have found their roles vs. traditional higher end so-called enterprise arrays. Think as an example EMC CLARiiON/VNX or HP EVA/P6000 or HDS AMS/HUS or NetApp FAS or IBM DS5000 or IBM V7000 among others vs. EMC Symmetrix/DMX/VMAX or HP P10000/3Par or HDS VSP/USP or IBM DS8000. In addition to traditional enterprise or high-end storage systems and midrange also known as modular, there are also specialized appliances or targets such as for backup/restore and archiving. Also do not forget the IO performance SSD appliances like those from TMS among others that have been around for a while.

Is the role of large storage systems changing or evolving? Yes
Given their scale and ability to do large amounts of work in a dense footprint, for some the role of these systems is still mission critical tier 1 application and data support. For other environments, their role continues to evolve being used for high-density tier 2 bulk or even near-line storage for on-line access at scale.

Storage I/O trends

Does this mean there is completion between the old and new systems? Yes
In some circumstances as we have seen already with SSD solutions. Some will place as competing or replacements while others as complementing. For example in the PCIe flash SSD card segment EMC VFCache is positioned is complementing Dell, EMC, HDS, HP, IBM, NetApp, Oracle or others storage vs. FusionIO who positions as a replacement for the above and others. Another scenario is how some SSD vendors have and continue to position their all-flash SSD arrays using either drives or PCIe cards to complement and coexist with other storage systems in an environment (e.g. data center level tiering) vs. as a replacement. Also keep in mind SSD solutions that also support a mix of flash devices and traditional HDDs for capacity and cost savings or cloud access in the same solution.

Does this mean that the industry has adopted all SSD appliances as the state of art?
Avoid confusing industry adoption or talk with industry and customer deployment. They are similar, however one is focused on what the industry talks about or discusses as state of art or the future while the other is what customers are doing. Certainly some of the new flash SSD appliance and storage startups such as Solidfire, Nexgen, Violin, Whiptail or veteran TMS among others have promising futures, some of which may actually be in play with the current SSD market shakeout and consolidation.

Does that mean everybody is going SSD?
SSD customer adoption and deployment continues to grow, however so too does the deployment of high-capacity HDDs.

Storage I/O trends

Do SSDs need HDDs, do HDDs need SSDs? Yes
Granted there are environments where needs can be addressed by all of one or the other. However at least near term, there is a very strong market for tiering and mix of SSD, some fast HDDs and lots of high-capacity HDDs to meet various needs including performance, availability, capacity, energy and economics. After all, there is no such thing, as a data or information recession yet budgets are tight or being reduced. Likewise, people and data are living longer.

What does this mean?
If there, were no such thing as a data recession and budgets a non-issue, perhaps everything could move to all flash SSD storage systems. However, we also know that people and data are living longer along with changing data life-cycle patterns. There is also the need for performance to close the traditional data center IO performance to space capacity gap and bottlenecks as well as store and keep data longer.

There will continue to be a need for a mix of high-capacity and high performance. More IO will continue to gravitate towards the IO appliances, however more data will settle in for longer-term retention and continued access as data life-cycle continue to evolve. Watch for more SSD and cache in the large systems, along with higher density SAS-NL (SAS Near Line e.g. high capacity) type drives appearing in those systems.

If you like new shiny new toys or technology (SNTs) to buy, sell or talk about, there will be plenty of those to continue industry adoption while for those who are focused on industry deployment, there will be a mix of new, and continued evolution for implementation.

Ok, nuff said for now

Cheers Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

April 12, 2012November 26, 2023

Part IV: PureSystems, something old, something new, something from big blue

This is the fourth in a five-part series around the recent IBM PureSystems announcements. You can view the earlier post here, and the next post here.

So what does this mean for IBM Business Partners (BPs) and ISVs?
What could very well differentiate IBM PureSystems from those of other competitors is to take what their partner NetApp has done with FlexPods combing third-party applications from Microsoft and SAP among others and take it to the next level. Similar to what helped make EMC Centera a success (or at least sell a lot of them) was inclusion and leveraging third-party ISVs and BPs to add value. Compared to other vendors with object based or content accessible storage (CAS) or online archive platforms that focused on the technology feature, function speeds and feeds, EMC realized the key was getting ISVs to support so that BPs and their own direct sales force could sell the solution.

With PureSystems, IBM is revisiting what they have done in the past which if offer bundled solutions providing incentives for ISVs to support and BPs to sell the IBM brand solution. EMC took an early step with including VMware with their Vblock combing server, storage, networking and software with NetApp taking the next step adding SAP, Microsoft and other applications. Dell, HP, Oracle and others are following suit so it only makes sense that IBM returns to its roots leveraging its DNA to reach out and get their ISVs who are now, have been in the past, or are new opportunities to be on board.

IBM is throwing its resources including their innovation centers for training around the world where business partners can get the knowledge and technical support they need. In other words, workshops or seminars on how to sell deploy and setting up of these systems, application and customer testing or proof of concepts and things one would expect out of IBM for such an initiative. In addition to technology and sales training along with marketing support, IBM is making their financing capabilities available to help customers as well as offer incentives to their business partners to simplify acquisitions.

So what buzzword bingo topics and themes did IBM address with this announcement:
IBM did a fantastic job in terms of knocking the ball out of the park with this announcement pertaining buzzword bingo and deserves an atta boy or atta girl!

So what about how this will affect sales of Bladecenters or other systems?
If all IBM and their BPs do are, encroach on existing systems sales to circle the wagons and protect the installed base, which would be one thing. However if IBM and their BPs can use the new packaging and model approach to reestablish customers and partnerships, or open and expand into new adjacent markets, then the net differences should be more Bladecenters (excuse me, PureFlex) being sold.

So what will this cost?
IBM is citing entry PureSystems Express models starting at around $100,000 USD for base systems with others starting at around $200,000 and $300,000 expandable into larger configurations and budgets. Note that like airlines that advertise a low airfare and then you get to pay extra for peanuts, drinks, extra bag space, changes to reservations and so forth, look at these and related systems not just for the first starting price, also for expansion costs over different time periods. Contact IBM, your BP or ISV to find out what one of these systems will do for and cost you.

So what about VARs and IBM business partners (BPs)?
This could be a boon for those BPs and ISVs that had previously sold their software solutions bundled with IBM hardware platforms who were being challenged by other converged solution stacks or were being forced to unbundled. This will also allow those business partners to compete on par with other converged solutions or continue selling the pieces of what they are familiar with however under a new umbrellas. Of course, pricing will be a focus and concern for some who will want to see what added value exists vs. acquiring the various components. This also means that IBM will have to make incentives available for their partners to make a living while also allowing their customers to afford solutions and maximize their return on innovation (the new ROI) and enablement.

Click here to view the next post in this series, ok nuff said for now.

Here are some links to learn more:
Various IBM Redbooks and related content
The blame game: Does cloud storage result in data loss?
What do you need when its time to buy a new server?
2012 industry trends perspectives and commentary (predictions)
Convergence: People, Processes, Policies and Products
Buzzword Bingo and Acronym Update V2.011
The function of XaaS(X) Pick a letter
Hard product vs. soft product
Buzzword Bingo and Acronym Update V2.011
Part I: PureSystems, something old, something new, something from big blue
Part II: PureSystems, something old, something new, something from big blue
Part III: PureSystems, something old, something new, something from big blue
Part IV: PureSystems, something old, something new, something from big blue
Part V: PureSystems, something old, something new, something from big blue
Cloud and Virtual Data Storage Networking

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

April 12, 2012October 18, 2024

Part V: PureSystems, something old, something new, something from big blue

This is the fifth in a five-part series around the recent IBM PureSystems announcements. You can view the earlier post here.

So what about vendor or technology lock in?
So who is responsible for vendor or technology lock in? When I was working in IT organizations, (e.g. what vendors call the customer) the thinking was vendors are responsible for lock in. Later when I worked for different vendors (manufactures and VARs) the thinking was lock in is what was caused by the competition. More recently I’m of the mind set that vendor lock in is a shared responsibility issue and topic. I’m sure some marketing wiz or sales type will be happy to explain the subtle differences of how their solution does not cause lock in.

Vendor lock in can be a shared responsibility. Generally speaking, lock in, stickiness and account control are essentially the same, or at least strive to get similar results. For example, vendor lock in too some has a negative stigma. However vendor stickiness may be a new term, perhaps even sounding cool thus it is not a concern. Remember the Mary Poppins song a spoon full of sugar makes the medicine go down? In other words, sometimes changing and using a different term such as sticky vs. vendor lock in helps make the situation taste better.

So what should you do?
Take a closer look if you are considering converged infrastructures, cloud or data centers in a box, turnkey application or information services deployment platforms. Likewise, if you are looking at specific technologies such as those from Cisco UCS, Dell vStart, EMC Vblock (or via VCE), HP, NetApp FlexPod or Oracle (ExaLogic, ExaData, etc) among others, also check out the IBM PureSystems (Flex and PureApplication). Compare and contrast these converged solutions with your traditional procurement and deployment modes including cost of acquiring hardware, software, ongoing maintenance or service fees along with value or benefit of bundled tools. There may be a higher cost for converged systems in some scenarios, however compare on the value and benefit derived vs. doing the integration yourself.

Compare and contrast how converged solutions enable, however also consider what constraints exists in terms of flexibility to reconfigure in the future or make other changes. For example as part of integration, does a solution take a lowest common denominator approach to software and firmware revisions for compatibility that may lag behind what you can apply to standalone components. Also, compare and contrast various reference architectures with different solution bundles or packages.

Most importantly compare and evaluate the solutions on their ability to meet and exceed your base requirements while adding value and enabling return on innovation while also being cost-effective. Do not be scared of these bundled solutions; however do your homework to make informed decisions including overcoming any concerns of lock in or future costs and fees. While these types of solutions are cool or interesting from a technology perspective and can streamline acquisition and deployment, make sure that there is a business benefit that can be addressed as well as enablement of new capabilities.

So what does this all mean?
Congratulations to IBM with their PureSystems for leveraging their DNA and roots bundling what had been unbundled before cloud and stacks were popular and trendy. IBM has done a good job of talking vision and strategy along lines of converged and dynamic, elastic and smart, clouds and other themes for past couple of years while selling the pieces as parts of solutions or ala carte or packaged by their ISVs and business partners.

What will be interesting to see is if bladecenter customers shift to buying PureFlex, which should be an immediate boost to give proof points of adoption, while essentially up selling what was previously available. However, more interesting will be to see if net overall new customers and footprints are sold as opposed to simply selling a newer and enhanced version of previous components.

In other words will IBM be able to keep up their focus and execution where they have sold the previous available components, while also holding onto current ISV and BP footprint sales and perhaps enabling those partners to recapture some hardware and solution sales that had been unbundled (e.g. ISV software sold separate of IBM platforms) and move into new adjacent markets.

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

Here are some links to learn more:
Various IBM Redbooks and related content
The blame game: Does cloud storage result in data loss?
What do you need when its time to buy a new server?
2012 industry trends perspectives and commentary (predictions)
Convergence: People, Processes, Policies and Products
Buzzword Bingo and Acronym Update V2.011
The function of XaaS(X) – Pick a letter
Hard product vs. soft product
Buzzword Bingo and Acronym Update V2.011
Part I: PureSystems, something old, something new, something from big blue
Part II: PureSystems, something old, something new, something from big blue
Part III: PureSystems, something old, something new, something from big blue
Part IV: PureSystems, something old, something new, something from big blue
Part V: PureSystems, something old, something new, something from big blue
Cloud and Virtual Data Storage Networking

Ok, so what is next, lets see how this unfolds for IBM and their partners.

Nuff said for now.

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

April 12, 2012November 26, 2023

Part III: PureSystems, something old, something new, something from big blue

This is the third in a five-part series around the recent IBM PureSystems announcements. You can view the earlier post here, and the next post here.

So what about the IBM Virtual Appliance Factory?
Where PureFlex and PureApplication (PureSystems) are the platforms or vehicles for enabling your journey to efficient and effective information services delivery, and PureSystem centre (or center for those of you in the US) is the portal or information center, the IBM Virtual Appliance Factory (VAF) is a collection of tools, technologies, processes and methodologies. The VAF helps developers or ISVs to prepackage applications or solutions for deployment into Kernel Virtual Machine (KVM) on Intel and IBM PowerVM virtualized environments that are also supported by PureFlex and PureApplication systems.

VAF technologies include Distributed Management Task Force (DMTF) Open Virtual Alliance (OVA) Open Virtualization Format (OVF) along with other tools for combing operating systems (OS), middleware and solution software into a delivery package or a virtual appliance that can be deployed into cloud and virtualized environments. Benefits include reducing complexity of working logical partions (LPAR) and VM configuration, abstraction and portability for deployment or movement from private to public environments. Net result should be less complexity lowering costs while reducing mean time to install and deploy. Here is a link to learn more about VAF and its capabilities and how to get started.

So what does cloud ready mean?
IBM is touting cloud ready capability in the context of rapid out of the box, ease of deployment and use as well as easy to acquire. This is in line with what others are doing with converged server, storage, networking, hardware, software and hypervisor solutions. IBM is also touting that they are using the same public available products as what they use in their own public services SmartCloud offerings.

So what is scale in vs. scale up, scale out or scale within?
Traditional thinking is that scaling refers to increasing capacity. Scaling also means increasing performance, availability, functionality with stability. Scaling with stability means that as performance, availability, capacity or other features are increased problems are not introduced or complexity is not increased. For example, scaling with stability for performance should not result in loss of availability or capacity, capacity increase should not be at the cost of performance or availability, should not cost performance or capacity and management tools should work for you, instead of you working for them.

Scaling up and scaling out have been used to describe scaling performance, availability, capacity and other attributes beyond the limits of a single system, box or cabinet. For example clustered, cloud, grid and other approaches refer to scaling out or horizontally across different physical resources. Scaling up or scaling vertically means scaling within in a system using faster, denser technologies doing more in the same footprint. HDS announced a while back what they refer to 3D scaling which embraces the above notions of scaling up, out and within across different dimensions. IBM is building on that by emphasizing scaling leveraging faster, denser components such as Power7 and Intel processors to scale within the box or system or node, which can also be scaled out using enhanced networking from IBM and their partners.

So what about backup/restore, BC, DR and general data protection?
I would expect IBM to step up and talk about how they can leverage their data protection and associated management toolsets, technologies and products. IBM has the components (hardware, software) already for backup/restore, BC, DR, data protection and security along with associated service offerings. One would expect IBM to not only come out with a backup, restore, BC, DR and archiving solution or version, as well as ones for archiving or data preservation, compliance appliance variants as well as related themes. We know that IBM has the pieces, people, process and practices, let us see if IBM has learned from their competitors who may have missed data protection messaging opportunities. Sometimes what is assumed to be understood does not get discussed, however often what is assumed and is not understood should be discussed, hence, let us see if IBM does more than say oh yes, we have those capabilities and products too.

So what do these have compared to others who are doing similar things?
Different vendors have taken various approaches for bringing converged products or solutions to the market place. Not surprising, storage centric vendors EMC and NetApp have partnered with Cisco for servers (compute). Where Cisco was known for networking having more recently moved into compute servers, EMC and NetApp are known for storage and moving into converged space with servers. Since EMC and NetApp often compete with storage solutions offerings from traditional server vendors Dell, HP, IBM and Oracle among others, and now Cisco is also competing with those same server vendors it has previously partnered with for networking thus it makes sense for Cisco, EMC and NetApp to partner.

While EMC owns a large share of VMware, they do also support Microsoft and other partners including Citrix. NetApp followed EMC into the converged space partnering with Cisco for compute and networking adding their own storage along with supporting hypervisors from Citrix, Microsoft and VMware along with third-party ISVs including Microsoft and SAP among others. Dell has evolved from reference architectures to products called vStart that leverage their own technologies along with those of partners.

A challenge for Dell however is that vStart sounds more like a service offering as opposed to a product that they or their VARs and business partners can sell and add value around. HP is also in the converged game as is Oracle among others. With PureSystems IBM is building on what their competitors and in some cases partners are doing by adding and messaging more around the many ISVs and applications that are part of the PureSystems initiative. Rest assured, there is more to PureSystems than simply some new marketing, press releases, videos and talking about partners and ISVs. The following table provides a basic high level comparison of what different vendors are doing or working towards and is not intended to be a comprehensive review.

Who	What	Server	Storage	Network	Software	Other comments
Cisco	UCS	Cisco	Partner	Cisco	Cisco and Partners	Various hypervisors and OS
Dell	vStart	Dell	Dell	Dell and Partners	Dell and partners	Various hypervisors, OS and bundles
EMC VCE	Vblock VSPEX	Cisco	EMC	Cisco and partners	EMC, Cisco and partners	Various hypervisors, OS and bundles, VSPEX adds more partner solution bundles
HP	Converged	HP	HP	HP and partners	HP and partners	Various hypervisors, OS and bundles
IBM	PureFlex	IBM	IBM	IBM and partners	IBM and partners	Various hypervisors, OS and bundles adding more ISV partners
NetApp	FlexPod	Cisco	NetApp	Cisco and partners	NetApp, Cisco and partners	Various hypervisors, OS and bundles for SAP, Microsoft among others
Oracle	ExaLogic (Exadata database)	Oracle	Oracle	Partners	Oracle and partners	Various Oracle software tools and technologies

So what took IBM so long compared to others?
Good question, what is the saying? Rome was not built-in a day!

Click here to view the next post in this series, ok, nuff said for now.

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

April 12, 2012January 18, 2021

Part II: PureSystems, something old, something new, something from big blue

This is the second in a five-part series around the recent IBM PureSystems announcements. You can view the earlier post here, and the next post here.

So what are the speeds and feeds of a PureFlex system?
The components that make up the PureFlex line include:

IBM management node (server with management software tools).
10Gb Ethernet (LAN) switch, adapters and associated cabling.
IBM V7000 virtual storage (also see here and here).
Dual 8GFC (8Gb Fibre Channel) SAN switches and adapters.
Servers with either x86 xSeries using for example Intel Sandy Bridge EP 2.6 GHz 8 core processors, or IBMs Power7 based pSeries for AIX. Note that IBM with their blade center systems (now rebadged as part of being PureSystems) support various IO and networking interfaces include SAS, Ethernet, Fibre Channel (FC), Fibre Channel over Ethernet (FCoE), and InfiniBand using adapters and switches from various partners.
Virtual machine (VM) hypervisors such as Microsoft Hyper V and VMware vSphere/ESX among others. In addition to x86 based hypervisors or kernel virtual machines (KVM), IBM also supports its own virtual technology found in Power7 based systems. Check IBM support matrix for specific configurations and current offerings.
Optional middleware such as IBM WebSphere.

Read more speeds and feeds at the various IBM sites including on Tony Pearson’s blog site.

So what is IBM PureApplication System?
This builds off and on PureFlex systems as a foundation for deploying various software stacks to deliver traditional IT applications or cloud Platform as a Service (PaaS) or Software as a Service (SaaS) and Application as a Service (AaaS) models. For example cloud or web stacks, java, database, analytics or other applications with buzzwords of elastic, scalable, repeatable, self-service, rapid provisioning, resilient, multi tenant and secure among others. Note that if are playing or into Buzzword bingo, go ahead and say Bingo when you are ready as IBM has a winner in this category.

So what is the difference between PureFlex and PureApplication systems?
PureApplication systems leverage PureFlex technologies adding extra tools and functionality for cloud like application functionality delivery.

So what is IBM PureSystems Centre?
It is a portal or central place where IBM and their business partner solutions pertaining to PureApplication and PureFlex systems can be accessed for including information for first installation support along with maintenance and upgrades. At launch, IBM is touting more than 150 solutions or applications that are available or qualified for deployment on PureApplication and PureFlex systems. In addition, IBM Patterns (aka templates) can also be accessed via this venue. Examples of application or independent software vendor (ISV) developed solutions for banking, education, financial, government, healthcare and insurance can be found at the PureSystems Centre portal (here, here and here).

So what part of this is a service and what is a product?
Other than the PureSystem center, which is a web portal for accessing information and technologies, PureFlex and PureApplication along with Virtual Appliance Factory are products or solutions that can be bought from IBM or their business partners. In addition, IBM business partners or third parties can also use these solutions housed in their own, a customer, or third-party facility for delivering managed service provided (MSP) capabilities, along with other PaaS and SaaS or AaaS type functionalities. In other words, these solutions can be bought or leased by IT and other organizations for their own use in a traditional IT deployment model, private, hybrid or public cloud model.

Another option is for service providers to acquire these solutions for use in developing and delivering their own public and private or hybrid services. IBM is providing the hard product (hardware and software) that enables your return on innovation (the new ROI) to create and deliver your own soft product (services and experiences) consumed by those who use those capabilities. In addition to traditional financial quantitative return on investment (traditional ROI) and total cost of ownership (TCO), the new ROI complements those by adding a qualitative aspect. Your return on innovation will be dependent on what you are capable of doing that enables your customers or clients to be productive or creative. For example enabling your customers or clients to boost productivity, remove complexity and cost while maintaining or enhancing Quality of Service (QoS), service level objectives (SLOs) and service level agreements (SLAs) in addition to supporting growth by using a given set of hard products. Thus, your soft product is a function of your return on innovation and vise versa.

Note that in this context, not to be confused with hardware and software, hard product are those technologies including hardware, software and services that are obtained and deployed as a soft product. A soft product in this context does not refer to software, rather the combination of hard products plus your own developed or separately obtained software and tools along with best practices and usage models. Thus, two organizations can use the same hard products and deliver separate soft products with different attributes and characteristics including cost, flexibility and customer experience.

So what is a Pattern of Expertise?
Combines operational know how experience and knowledge about common infrastructure resource management (IRM), data center infrastructure management (DCIM) and other commonly repeatable related process, practices and workflows including provisioning. Common patterns of activity and expertise for routine or other time-consuming tasks, which some might refer to as templates or workflows enable policy driven based automation. For example, IBM cites recurring time-consuming tasks that lend themselves to being automated such as provisioning, configuration, and upgrades and associated IRM, DCIM and data protection, storage and application management activities. Automation software tools are included as part of the PureSystems with patterns being downloadable as packages for common tasks and applications found at the IBM PureSystem center.

At announcement, there are three types or categories of patterns:

IBM patterns: Factory created and supplied with the systems based on experiences IBM has derived from various managers, engineers and technologist for automating common tasks including configuration, deployment and application upgrades and maintenance. The aim is to cut the amount of time and intervention for deployment of applications and other common functions enabling IT staff to be more productive and address other needs.
ISV patterns: These leverage experience and knowledge from ISVs partnered with IBM, which at time of launch numbers over 125 vendors offering certified PureSystems Ready applications. The benefit and objective are to cut the time and complexity associated with procuring (e.g. purchasing), deploying and managing third-party ISV software. Downloadable patterns packages can be found at the IBM PureSystem center.
Customer patterns: Enables customers to collect and package their own knowledge, processes, rules, policies and best practices into patterns for automation. In addition to collecting knowledge for acquisition, configuration, day to day management and troubleshooting, these patterns can facility automation of tasks to ease on boarding of new staff employees or contractors. In addition, these patterns or templates capture workflows for automation enabling shorter deployment times of systems and applications into locations where skill sets do not exist.

Here is a link to some additional information about patterns on the IBM developerWorks site.

Click here to view the next post in this series, ok, nuff said for now.

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

April 12, 2012May 24, 2020

Part I: PureSystems, something old, something new, something from big blue

This is the first in a five-part series around the recent IBM PureSystems announcements. You can view the next post here.

For a certain generation of IBM faithful or followers the recently announced PureFlex and PureApplication systems might give a sense of DejaVu perhaps even causing some to wonder if they just woke up from a long Rip Van Winkle type nap.

Yet for another generation who may not yet be future IBM followers, fans, partners or customers, there could be a sense of something new and revolutionary with the PureFlex and PureApplication systems (twitter @ibmpuresystems).

In between those two groups, exist others who are either scratching their heads or reinvigorated with enthusiasm to get out and be able to discuss opportunities around little data (traditional and transactional) and big data, servers, virtualized, converged infrastructure, dynamic data centers, private clouds, ITaaS, SaaS and AaaS, PaaS, IaaS and other related themes or buzzword bingo topics.

Let us dig a little deeper and look at some So What types of questions and industry trends perspectives comments around what IBM has announced.

So what did IBM announce?
IBM announced PureSystems including:

PureFlex systems, products and technologies
PureApplication systems
PureSystems Centre

You can think of IBM PureSystems and Flex Systems Products and technology as a:

Private cloud or turnkey solution bundle solution
Platform deploying public or hybrid clouds
Data center in a box or converged and dynamic system
ITaaS or SaaS/AaaS or PaaS or IaaS or Cloud in a box
Rackem stack and package them type solution

So what is an IBM PureFlex System and what is IBM using?
It is a factory integrated data and compute infrastructure in a cabinet combing cloud, virtualization, servers, data and storage networking capabilities. The IBM PureFlex system is comprised of various IBM and products and technologies (hardware, software and services) optimized with management across physical and virtual resources (servers, storage (V7000), networking, operating systems, hypervisors and tools).

PureFlex includes automation and optimization technologies along with what IBM is referring to as patterns of expertise or what you might relate to as templates. Support for various hypervisors and management integration along with application and operating system support by leveraging IBM xSeries (x86 such as Intel) and pSeries (Power7) based processors for compute. Storage is the IBM V7000 (here and here) with networking and connectivity via IBM and their partners. The solution is capable of supporting traditional, virtual and cloud deployment models as well as platform for deploying Infrastructure as a Service (IaaS) on a public, managed service provider (MSP), hosting or private basis.

Click here to view the next post in this series, ok nuff said for now.

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

February 6, 2012October 18, 2024

EMC VFCache respinning SSD and intelligent caching (Part II)

This is the second of a two part series pertaining to EMC VFCache, you can read the first part here.

In this part of the series, lets look at some common questions along with comments and perspectives.

Common questions, answers, comments and perspectives:

Why would EMC not just go into the same market space and mode as FusionIO, a model that many other vendors seam eager to follow? IMHO many vendors are following or chasing FusionIO thus most are selling in the same way perhaps to the same customers. Some of those vendors can very easily if they were not already also make a quick change to their playbook adding some new moves to reach broader audience.

Another smart move here is that by taking a companion or complimentary approach is that EMC can continue selling existing storage systems to customers, keep those investments while also supporting competitors products. In addition, for those customers who are slow to adopt the SSD based techniques, this is a relatively easy and low risk way to gain confidence. Granted the disk drive was declared dead several years (and yes also several decades) ago, however it is and will stay alive for many years due to SSD helping to close the IO storage and performance gap.

Data center and storage IO performance capacity gap (Courtesy of Cloud and Virtual Data Storage Networking (CRC Press))

Has this been done before? There have been other vendors who have done LUN caching appliances in the past going back over a decade. Likewise there are PCIe RAID cards that support flash SSD as well as DRAM based caching. Even NetApp has had similar products and functionality with their PAM cards.

Does VFCache work with other PCIe SSD cards such as FusionIO? No, VFCache is a combination of software IO intercept and intelligent cache driver along with a PCIe SSD flash card (which could be supplied as EMC has indicated from different manufactures). Thus VFCache to be VFCache requires the EMC IO intercept and intelligent cache software driver.

Does VFCache work with other vendors storage? Yes, Refer to the EMC support matrix, however the product has been architected and designed to install and coexist into a customers existing environment which means supporting different EMC block storage systems as well as those from other vendors. Keep in mind that a main theme of VFCache is to compliment, coexist, enhance and protect customers investments in storage systems to improve their effectiveness and productivity as opposed to replacing them.

Does VFCache introduce a new point of vendor lockin or stickiness? Some will see or place this as a new form of vendor lockin, others assuming that EMC supports different vendors storage systems downstream as well as offer options for different PCIe flash cards and keeps the solution affordable will assert it is no more lockin that other solutions. In fact by supporting third party storage systems as opposed to replacing them, smart sales people and marketeers will place VFCache as being more open and interoperable than some other PCIe flash card vendors approach. Keep in mind that avoiding vendor lockin is a shared responsibility (read more here).

Does VFCache work with NAS? VFCache does not work with NAS (NFS or CIFS) attached storage.

Does VFCache work with databases? Yes, VFCache is well suited for little data (e.g. database) and traditional OLTP or general business application process that may not be covered or supported by other so called big data focused or optimized solutions. Refer to this EMC document (and this document here) for more information.

Does VFCache only work with little data? While VFCache is well suited for little data (e.g. databases, share point, file and web servers, traditional business systems) it also able to work with other forms of unstructured data.

Does VFCache need VMware? No, While VFCache works with VMware vSphere including a vCenter plug in, however it does not need a hypervisor and is practical in a physical machine (PM) as it is in a virtual machine (VM).

Does VFCache work with Microsoft Windows? Yes, Refer to the EMC support matrix for specific server operating systems and hypervisor version support.

Does VFCache work with other unix platforms? Refer to the EMC support matrix for specific server operating systems and hypervisor version support.

How are reads handled with VFCache? The VFCache software (driver if you prefer) intercepts IO requests to LUNs that are being cached performing a quick lookup to see if there is a valid cache entry in the physical VFCache PCIe card. If there is a cache hit the IO is resolved from the closer or local PCIe card cache making for a lower latency or faster response time IO. In the case of a cache miss, the VFCache driver simply passes the IO request onto the normal SCSI or block (e.g. iSCSI, SAS, FC, FCoE) stack for processing by the downstream storage system (or appliance). Note that when the requested data is retrieved from the storage system, the VFCache driver will based on caching algorithms determinations place a copy of the data in the PCIe read cache. Thus the real power of the VFCache is the software implementing the cache lookup and cache management functions to leverage the PCIe card that complements the underlying block storage systems.

How are writes handled with VFCache? Unless put into a write cache mode which is not the default, VFCache software simply passes the IO operation onto the IO stack for downstream processing by the storage system or appliance attached via a block interface (e.g. iSCSI, SAS, FC, FCoE). Note that as part of the caching algorithms, the VFCache software will make determinations of what to keep in cache based on IO activity requests similar to how cache management results in better cache effectiveness in a storage system. Given EMCs long history of working with intelligent cache algorithms, one would expect some of that DNA exists or will be leveraged further in future versions of the software. Ironically this is where other vendors with long cache effectiveness histories such as IBM, HDS and NetApp among others should also be scratching their collective heads saying wow, we can or should be doing that as well (or better).

Can VFCache be used as a write cache? Yes, while its default mode is to be used as a persistent read cache to compliment server and application buffers in DRAM along with enhance effectiveness of downstream storage system (or appliances) caches, VFCache can also be configured as a persistent write cache.

Does VFCache include FAST automated tiering between different storage systems? The first version is only a caching tool, however think about it a bit, where the software sits, what storage systems it can work with, ability to learn and understand IO paths and patterns and you can get an idea of where EMC could evolve it to, similar to what they have done with recoverpoint among other tools.

Evolving data access patterns and life cycles (more retention and reads)

Does VFCache mean all or nothing approach with EMC? While the complete VFCache solution comes from EMC (e.g. PCIe card and software), the solution will work with other block attached storage as well as existing EMC storage systems for investment protection.

Does VFCache support NAS based storage systems? The first release of VFCache only supports block based access, however the server that VFCache is installed in could certainly be functioning as a general purpose NAS (NFS or CIFS) server (see supported operating systems in EMC interoperability notes) in addition to being a database or other other application server.

Does VFCache require that all LUNs be cached? No, you can select which LUNs are cached and which ones are not.

Does VFCache run in an active / active mode? In the first release it is active passive, refer to EMC release notes for details.

Can VFCache be installed in multiple physical servers accessing the same shared storage system? Yes, however refer to EMC release notes on details about active / active vs. active / passive configuration rules for ensuring data integrity.

Who else is doing things like this? There are caching appliance vendors as well as others such as NetApp and IBM who have used SSD flash caching cards in their storage systems or virtualization appliances. However keep in mind that VFCache is placing the caching function closer to the application that is accessing it there by improving on the locality of reference (e.g. storage and IO effectiveness).

Does VFCache work with SSD drives installed in EMC or other storage systems? Check the EMC product support matrix for specific tested and certified solutions, however in general if the SSD drive is installed in a storage system that is supported as a block LUN (e.g. iSCSI, SAS, FC, FCoE) in theory it should be possible to work with VFCache. Emphasis, visit the EMC support matrix.
What type of flash is being used?

What type of nand flash SSD memory is EMC using in the PCIe card? The first release of VFCache is leveraging enterprise class SLC (Single Level Cell) nand flash which has been used in other EMC products for its endurance, long duty cycle to minnimize or eliminate concerns of wear and tear while meeting read and write performance. EMC has indicated that they will also as part of an industry trend leverage MLC along with Enterprise MLC (EMLC) technologies on a go forward basis.

Doesnt nand ssd flash cache wear out? While nand flash SSD can wear out over time due to extensive write use, the VFCache approach mitigates this by being primarily a read cache reducing the number or program / erase cycles (P/E cycles) that occur with write operations as well as initially leveraging longer duty cycle SLC flash. EMC also has several years experience from implementing wear leveling algorithms into the storage systems controllers to increase duty cycle and reduce wear on SLC flash which will play forward as MLC or Enterprise MLC (EMLC) techniques are leveraged. This differs from vendors who are positioning their SLC or MLC based flash PCIe SSD cards for mainly write operations which will cause more P/E cycles to occur at a faster rate reducing the duty or useful life of the device.

How much capacity does the VFCache PCIe card contain? The first release supports a 300GB card and EMC has indicated that added capacity and configuration options are in their plans.

Does this mean disks are dead? Contrary to popular industry folk lore (or wish) the hard disk drive (HDD) has plenty of life left part of which has been increased by being complimented by VFCache.

Various SSD locations, types, packaging and usage scenario options

Can VFCache work in blade servers? The VFCache software is transparent to blade, rack mount, tower or other types of servers. The hardware part of VFCache is a PCIe card which means that the blade server or system will need to be able to accommodate a PCIe card to compliment the PCIe based mezzaine IO card (e.g. iSCSI, SAS, FC, FCOE) used for accessing storage. What this means is that for blade systems or server vendors such as IBM who have a PCIe expansion module for their H series blade systems (it consumes a slot normally used by a server blade), PCIe cache cards like those being initially released by IBM could work, however check with the EMC interoperability matrix, as well as your specific blade server vendor for PCIe expansion capabilities. Given that EMC leverages Cisco UCS for their vBlocks, one would assume that those systems will also see VFCache modules in those systems. NetApp partners with Cisco using UCS in their FlexPods so you see where that could go as well along with potential other server vendors support including Dell, HP, IBM and Oracle among others.

What about benchmarks? EMC has released some technical documents that show performance improvements in Oracle environments such as this here. Hopefully we will see EMC also release other workloads for different applications including Microsoft Exchange Solutions Proven (ESRP) along with SPC similar to what IBM recently did with their systems among others.

How do the first EMC supplied workload simulations compare vs. other PCIe cards? This is tough to gauge as many SSD solutions and in particular PCIe cards are doing apples to oranges comparisons. For example to generate a high IOPs rating for marketing purposes, most SSD solutions are stress performance tested at 512 bytes or 1/2 of a KByte or at least 1/8 of a small 4Kbyte IO. Note that operating systems such as Windows are moving to 4Kbyte page allocation size to align with growing IO sizes with databases moving from the old average of 4Kbytes to 8Kbytes and larger. What is important to consider is what is the average IO size and activity profile (e.g. reads vs. writes, random vs. sequential) for your applications. If your application is doing ultra small 1/2 Kbyte IOs, or even smaller 64 byte IOs (which should be handled by better application or file system caching in DRAM), then the smaller IO size and record setting examples will apply. However if your applications are more mainstream or larger, then those smaller IO size tests should be taken with a grain of salt. Also keep latency in mind that many target or oppourtunity applications for VFCache are response time sensitive or can benefit by the improved productivity they enable.

What is locality of reference? Locality of reference refers to how close data is to where it is being requested or accessed from. The closer the data to the application requesting the faster the response time or quick the work gets done. For example in the figure below L1/L2/L3 on board processor caches are the fastest, yet smallest while closest to the application running on the server. At the other extreme further down the stack, storage becomes large capacity, lower cost, however lower performing.

Locality of reference data and storage memory

What does cache effectiveness vs. cache utilization mean? Cache utilization is an indicator of how much the available cache capacity is being used however it does not give an indicator of if the cache is being well used or not. For example, cache could be 100 percent used, however there could be a low hit rate. Thus cache effectiveness is a gauge of how well the available cache is being used to improve performance in terms of more work being done (IOPS or bandwidth) or lower of latency and response time.

Isnt more cache better? More cache is not better, it is how the cache is being used, this is a message that I would be disappointed in HDS if they were not to bring up as a point of messaging (or rebuttal) given their history of emphasis cache effectiveness vs. size or quantity (Hu, that is a hint btw ;).

What is the performance impact of VFCache on the host server? EMC is saying greatest of 5 percent or less CPU consumption which they claim is several times less than the competitions worst scenario, as well as claiming 512MB to 1GB of DRM on the server vs. several times that of their competitors. The difference could be expected to be via more off load functioning including flash translation layer (FTL), wear leveling and other optimization being handled by the PCIe card vs. being handled in the servers memory and using host server CPU cycles.

How does this compare to what NetApp or IBM does? NetApp, IBM and others have done caching with SSD in their storage systems, or leveraging third party PCIe SSD cards from different vendors to be installed in servers to be used as a storage target. Some vendors such as LSI have done caching on the PCIe cards (e.g. CacheCaid which in theory has a similar software caching concept to VFCache) to improve performance and effectiveness across JBOD and SAS devices.

What about stale (old or invalid) reads, how does VFCache handle or protect against those? Stale reads are handled via the VFCache management software tool or driver which leverages caching algorithms to decide what is valid or invalid data.

How much does VFCache cost? Refer to EMC announcement pricing, however EMC has indicated that they will be competitive with the market (supply and demand).

If a server shutdowns or reboots, what happens to the data in the VFCache? Being that the data is in non volatile SLC nand flash memory, information is not lost when the server reboots or loses power in the case of a shutdown, thus it is persistent. While exact details are not know as of this time, it is expected that the VFCache driver and software do some form of cache coherency and validity check to guard against stale reads or discard any other invalid cache entries.

Industry trends and perspectives

What will EMC do with VFCache in the future and on a larger scale such as an appliance? EMC via its own internal development and via acquisitions has demonstrated ability to use various clustered techniques such as RapidIO for VMAX nodes, InfiniBand for connecting Isilon nodes. Given an industry trend with several startups using PCIe flash cards installed in a server that then functions as a IO storage system, it seems likely given EMCs history and experience with different storage systems, caching, and interconnects that they could do something interesting. Perhaps Oracle Exadata III (Exadata I was HP, Exadata II was Sun/Oracle) could be an EMC based appliance (That is pure speculation btw)?

EMC has already shown how it can use SSD drives as a cache extension in VNX and CLARiiON servers ( FAST CACHE ) in addition to as a target or storage tier combined with Fast for tiering. Given their history with caching algorithms, it would not be surprising to see other instantiations of the technology deployed in complimentary ways.

Finally, EMC is showing that it can use nand flash SSD in different ways, various packaging forms to apply to diverse applications or customer environments. The companion or complimentary approach EMC is currently taking contrasts with some other vendors who are taking an all or nothing, its all SSD as disk is dead approach. Given the large installed base of disk based systems EMC as well as other vendors have in place, not to mention the investment by those customers, it makes sense to allow those customers the option of when, where and how they can leverage SSD technologies to coexist and complement their environments. Thus with VFCache, EMC is using SSD as a cache enabler to discuss the decades old and growing storage IO to capacity performance gap in a force multiplier model that spreads the cost over more TBytes, PBytes or EBytes while increasing the overall benefit, in other words effectiveness and productivity.

Ok, nuff said for now, I think I see some storm clouds rolling in…

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

February 6, 2012December 24, 2020

EMC VFCache respinning SSD and intelligent caching (Part I)

This is the first part of a two part series covering EMC VFCache, you can read the second part here.

EMC formerly announced VFCache (aka Project Lightning) an IO accelerator product that comprises a PCIe nand flash card (aka Solid State Device or SSD) and intelligent cache management software. In addition EMC is also talking about the next phase of the flash business unit and project Thunder. The approach EMC is taking with vFCache should not be a surprise given their history of starting out with memory and SSD evolving it into an intelligent cache optimized storage solution.

Data center and storage IO performance capacity gap (Courtesy of Cloud and Virtual Data Storage Networking (CRC Press))

Could we see the future of where EMC will take VFCache along with other possible solutions already being hinted at by the EMC flash business unit by looking where they have been already?

Likewise by looking at the past can we see the future or how VFCache and sibling product solutions could evolve?

After all, EMC is no stranger to caching with both nand flash SSD (e.g. FLASH CACHE, FAST and SSD drives) along with DRAM based across their product portfolio not too mention being a core part of their company founding products that evolved into HDDs and more recent nand flash SSDs among others.

Industry trends and perspectives

Unlike others who also offer PCIe SSD cards such as FusionIO with a focus on eliminating SANs or other storage (read their marketing), EMC not surprisingly is marching to a different beat. The beat EMC is marching too or perhaps leading by example for others to follow is that of going mainstream and using PCIe SSD cards as a cache to compliment theirs as well as other vendors storage systems vs. replacing them. This is similar to what EMC and other mainstream storage vendors have done in the past such as with SSD drives being used as flash cache extension on CLARiiON or VNX based systems as well as target or storage tier.

Various SSD locations, types, packaging and usage scenario options

Other vendors including IBM, NetApp and Oracle among others have also leveraged various packaging options of Single Level Cell (SLC) or Multi Level Cell (MLC) flash as caches in the past. A different example of SSD being used as a cache is the Seagate Momentus XT which is a desktop, workstation consumer type device. Seagate has shipped over a million of the Momentus XT which use SLC flash as a cache to compliment and enhance the integrated HDD performance (a 750GB with 8GB SLC memory is in the laptop Im using to type this with).

One of the premises of solutions such as those mentioned above for caching is to discuss changing data access patterns and life cycles shown in the figure below.

Evolving data access patterns and life cycles (more retention and reads)

Put a different way, instead of focusing on just big data or corner case (granted some of those are quite large) or ultra large cloud scale out solutions, EMC with VFCache is also addressing their core business which includes little data. What will be interesting to watch and listen too is how some vendors will start to jump up and down saying that they have done or enabling what EMC is announcing for some time. In some cases those vendors will be rightfully doing and making noise on something that they should have made noise about before.

EMC is bringing the SSD message to the mainstream business and storage marketplace showing how it is a compliment to, vs. a replacement of existing storage systems. By doing so, they will show how to spread the cost of SSD out across a larger storage capacity footprint boosting the effectiveness and productive of those systems. This means that customers who install the VFCache product can accelerate the performance of both their existing EMC as well as storage systems from other vendors preserving their technology along with people skills investment.

Key points of VFCache

Combines PCIe SLC nand flash card (300GB) with intelligent caching management software driver for use in virtualized and traditional servers
Making SSD complimentary to existing installed block based disk (and or SSD) storage systems to increase their effectiveness
Providing investment protection while boosting productivity of existing EMC and third party storage in customer sites
Brings caching closer to the application where the data is accessed while leverage larger scale direct attached and SAN block storage
Focusing message for SSD back on to little data as well as big data for mainstream broad customer adoption scenarios
Leveraging benefit and strength of SSD as a read cache and scalable of underlying downstream disk for data storage
Reducing concerns around SSD endurance or duty cycle wear and tear by using as a read cache
Off loads underlying storage systems from some read requests enabling them to do more work for other servers

Ok, nuff said for now, I think I see some storm clouds rolling in…

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

October 25, 2011November 25, 2019

Congratulations to IBM for releasing XIV SPC results

Over the past several years I have done an annual post about IBM and their XIV storage system and this is the fourth in what has become a series. You can read the first one here, the second one here, and last years here and here after the announcement of the IBM V7000.

IBM XIV Gen3
IBM recently announced the generation 3 or Gen3 version of XIV along with releasing for the first time public performance comparison benchmarks using storage performance council (SPC) throughout SPC2 workload.

The XIV Gen3 is positioned by IBM as having up to four (4) times the performance of earlier generations of the storage system. In terms of speeds and feeds, the Gen3 XIV supports up to 180 2TB SAS hard disk drives (HDD) that provides up to 161TB of usable storage space capacity. For connectivity, the Gen3 XIV supports up to 24 8Gb Fibre Channel (8GFC) or for iSCSI 22 1Gb Ethernet (1 GbE) ports with a total of up to 360GBytes of system cache. In addition to the large cache to boost performance, other enhancements include leveraging multi core processors along with an internal InfiniBand network to connect nodes replacing the former 1 GbE interconnect. Note, InfiniBand is only used to interconnect the various nodes in the XIV cluster and is not used for attachment to applications servers which is handled via iSCSI and Fibre Channel.

IBM and SPC storage performance history
IBM has a strong history if not leading the industry with benchmarking and workload simulation of their storage systems including Storage Performance Council (SPC) among others. The exception for IBM over the past couple of years has been the lack of SPC benchmarks for XIV. Last year when IBM released their new V7000 storage system benchmarks include SPC were available close to if not at the product launch. I have in the past commented about IBMs lack of SPC benchmarks for XIV to confirm their marketing claims given their history of publishing results for all of their other storage systems. Now that IBM has recently released SPC2 results for the XIV it is only fitting then that I compliment them for doing so.

Benchmark brouhaha
Performance workload simulation results can often lead to applies and oranges comparisons or benchmark brouhaha battles or storage performance games. For example a few years back NetApp submitted a SPC performance result on behalf of their competitor EMC. Now to be clear on something, Im not saying that SPC is the best or definitive benchmark or comparison tool for storage or other purpose as it is not. However it is representative and most storage vendors have released some SPC results for their storage systems in addition to TPC and Microsoft ESRP among others. SPC2 is focused on streaming such as video, backup or other throughput centric applications where SPC1 is centered around IOPS or transactional activity. The metrics for SPC2 are Megabytes per second (MBps) for large file processing (LFP), large database query (LDQ) and video on demand delivery (VOD) for a given price and protection level.

What is the best benchmark?
Simple, your own application in as close to as actual workload activity as possible. If that is not possible, then some simulation or workload simulation that closets resembles your needs.

Does this mean that XIV is still relevant?
Yes

Does this mean that XIV G3 should be used for every environment?
Generally speaking no. However its performance enhancements should allow it to be considered for more applications than in the past. Plus with the public comparisons now available, that should help to silence questions (including those from me) about what the systems can really do vs. marketing claims.

How does XIV compare to some other IBM storage systems using SPC2 comparisons?

System	SPC2 MBps	Cost per SPC2	Storage GBytes	Price tested	Discount	Protection
DS5300	5,634.17	$74.13	16,383	417,648	0%	R5
V7000	3,132.87	$71.32	29,914	$223,422	38-39%	R5
XIV G3	7,467.99	$152.34	154,619	1,137,641	63-64%	Mirror
DS8800	9,705.74	$270.38	71,537	2,624,257	40-50%	R5

In the above comparisons, the DS5300 (NetApp/Engenio based) is a dual controller (4GB of cache per controller) with 128 x 146.8GB 15K HDDs configured as RAID 5 with no discount applied to the price submitted. The V7000 system which is based on the IBM SVC along with other enhancements consists of dual controllers each with 8GB of cache and 120 x 10K 300GB HDDs configured as RAID 5 with just under a 40% discount off list price for system tested. For the XIV Gen3 system tested, discount off list price for the submission is about 63% with 15 nodes and a total of 360GB of cache and 180 2TB 7.2K SAS HDDs configured as mirrors. The DS8800 system with dual controllers has a 256GB of cache, 768 x 146GB 15K HDDs configured in RAID5 with a discount between 40 to 50% off of list.

What the various metrics do not show is the benefit of various features and functionality which should be considered to your particular needs. Likewise, if your applications are not centered around bandwidth or throughput, then the above performance comparisons would not be relevant. Also note that the systems above have various discount prices as submitted which can be a hint to a smart shopper where to begin negotiations at. You can also do some analysis of the various systems based on their performance, configuration, physical footprint, functionality and cost plus the links below take you to the complete reports with more information.

DS8800 SPC2 executive summary and full disclosure report

XIV SPC2 executive summary and full disclosure report

DS5300 SPC2 executive summary and full disclosure report

V7000 SPC2 executive summary and full disclosure report

Bottom line, benchmarks and performance comparisons are just that, a comparison that may or may not be relevant to your particular needs. Consequently they should be used as a tool combined with other information to see how a particular solution might be a fit for your specific needs. The best benchmark however is your own application running as close to possible realistic workload to get a representative perspective of a systems capabilities.

Ok, nuff said
Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

October 18, 2011November 26, 2023

Commentary on Clouds, Storage, Networking, Green IT and other topics

Rather than doing a bunch of separate posts, here is a collection of different perspectives and commentary on various IT and data storage industry activity.

Various comments and perspectives

In this link are comments and perspectives regarding thin provisioning including how it works as well as when to use it for optimizing storage space capacity. Speaking of server and storage capacity, here in this link are comments on what server and storage would be needed to support an SMB office of 50 people (or more, or less) along with how to back it up.

For those interested or in need of managing data and other records in this link are comments on preparing yourself for regulatory scrutiny.

Storage networking interface or protocol debates (battles) can be interesting, in this link, see the role of iSCSI SANs for data storage environments. Lets not forget about Fibre Channel over Ethernet (FCoE) which is discussed in this link and here in this link. Here in this link are comments about how integrated rackem, stackem and package bundles stack up. To support increased continued demand for managed service providers (MSP), cloud and hosted services providers are continuing to invest in their infrastructures, so read some comments here. While technology plays a role particular as it matures, there is another barrier to leveraging converged solutions and that is organizational, read some perspectives and thoughts here.

Storage optimization including data footprint reduction (DFR) can be used to cut costs as well as support growth. In this link see tips on reducing storage costs and additional perspectives in this link to do more with what you have. Here in this link are some wit and wisdom comments on the world of disaster recovery solutions. Meanwhile in this link are perspectives for choosing the right business continuity (BC) and disaster recovery (DR) consultant. In this link are comments on BC and DR including planning for virtualization and life beyond consolidation. Are disk based dedupe and virtual tape summit resources libraries a hold over for old backup, or a gateway to the future, see some perspectives on those topics and technologies in this link.

Here are some more comments on DR and BC leveraging the cloud while perspectives on various size organizations looking at clouds for backup in this piece here. What is the right local, cloud or hybrid backup for SMBs, check out some commentary here while viewing some perspectives on cloud disaster recovery here. Not to be forgotten, laptop data protection can also be a major headache however there are also many cures discussed in this piece here.

The Storage Networking Industry Association (SNIA) Green Storage Initiative (GSI) debut their Emerald power efficiency measurement specification recently, read some perspectives and comments in this link here. While we are on the topic of data center efficiency and effectiveness, here in this link are perspectives on micro servers or mini blade systems. Solution bundles also known as data center in a box or SAN in a CAN have been popular with solutions from EMC (vBlocks) and NetApp (FlexPods) among others, read perspectives on them in this link.

What would a conversation involving data storage and IT (particularly buzzword bingo) be without comments about Big Data and Big Bandwidth which you can read here.

Want to watch some videos, from Spring 2011 SNW, check out starting around the 15:00 to 55:00 time scale in this video from the Cube where various topics are discussed. Interested in how to scale data storage with clustered or scale up and out solutions, check out this video here or if you want to see some perspectives on data de duplication watch this clip.

Various comments and perspectives

Here is a video discussing SMBs as the current sweet spot for server virtualization with comments on the SMB virtualization dark side also discussed here. Meanwhile here are comments regarding EMC Flashy announcements from earlier this year on the Cube. Check out this video where I was a guest of Cali Lewis and John MacArthur on the Cube from the Dell Storage Forum discussing a range of topics as well as having some fun. Check out these videos and perspectives from VMworld 2011.

Whats your take on choosing the best SMB NAS? Here are some of my perspectives on choosing a SMB NAS storage system. Meanwhile here are some perspectives on enterprise class storage features finding their way into SMB NAS storage systems.

Meanwhile industry leaders EMC and NetApp have been busy enhancing their NAS storage solutions that you can read comments here.

Are you familiar with the Open Virtualization Alliance (OVA)? Here are some comments about OVA and other server virtualization topics.

Whats your take on Thunderbolt the new interconnect Apple is using in place of USB, here are my thoughts. Meanwhile various other tips and Ask the Expert (AtE) and discussion can be found here.

Check out the above links, as well view more perspectives, comments and news here, here, here, here and here.

Ok, nuff said for now

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

September 8, 2011November 25, 2019

HDS buys BlueArc, any surprises here?

Technically here in the northern hemisphere it is still summer, so there is another summer wedding to announce.

The other day Hitachi Data Systems (aka HDS) announced that they finally tied the knot buying their Network Attached Storage (NAS) partner BlueArc whom they have been in a OEM premarital arrangement for the last five years or so (wow, was that a long engagement or what?). HDS being a subsidiary of Hitachi Ltd. a Japanese company it should be no surprise that they operate in a cool, calculated conservative manner with products that have over the past several decades been known for delivering resiliency, functionality, performance and value.

To those in the IT and specifically data storage industry, the only surprise about HDS buying BlueArc should be what took them so long to do so myself included. With unstructured data, big data, high performance computing, high productivity computing (aka HPC), and big bandwidth needs expanding, it only makes sense that HDS finally ties the knot formally acquiring BlueArc signaling what I hope are a few things for their collective future together.

Things that I hope HDS can accomplish with their acquisition of BlueArc include among others:

Leverage the BlueArc hardware and performance combine with the HDS software suite to expand further upstream (and downstream) as well as into different adjacent markets leveraging their success over the long courtship where both parties got to know each other more.
Signal to the industry that they are truly committed to a long term NAS product solution strategy. HDS has been doing a good job of sticking with BlueArc for the past five or so years having had several previous NAS partner relationships including with NetApp, NSS and others besides their own internal projects.
Expand their focus to lead with NAS pulling storage with it in addition to using NAS to accessorize (or bling aka Mr. T starter kit to go with Mr. T storage videos) storage systems which means of course, going more direct toe to toe with the likes of former partner NetApp, EMC, HP (with IBRIX), IBM and Dell among many others. Ironically former HDS partner NetApp acquired the Engenio storage group from LSI whose products competed with HDS in some spaces, while BlueArc was a Engenio partner.
Continue to develop both the hardware and software feature functionality around the BlueArc products in addition to further integration across the joint product lines for both traditional, as well as clustered, scale out, bulk, big data, big bandwidth and HPC environments.
Sharpen their NAS message and solution offerings including providing the support, tools and programs to enable both their joint direct sales forces as well as their partner value added reseller (VAR) and channel networks.

Check out (here) some additional comments and perspectives by Ray Lucchesi (aka twitter @raylucchesi) over on his blog pertaining to HDS buying BlueArc.

Congratulations to both HDS and BlueArc along with best wishes, this is a deal that is good for both, now, or once the honeymoon is over, lets see how this is executed upon building on their prior joint success to expand into new market opportunities on a global basis. HDS has tools and people to move into and leverage these new as well as existing opportunities, lets see how they can execute on those hopefully not spending too much time or money on the honeymoon while their competitors are out being busy in some of those same accounts in this last month of an important sales quarter (all quarters are important when it comes to sales).

Disclosure for those interested and FWIW: BlueArc had been a client of StorageIO a few years ago, however not currently. HDS is not nor have they been a client of StorageIO, however in prior life I was a customer of theirs in addition to being a partner and supplier when I was on the vendor side of the table.

Ok, nuff said for now.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio