perspective Archives

October 22, 2014March 7, 2022

VMware Cisco EMC VCE Zen and now server storage I/O convergence

Storage I/O trends

VMware Cisco EMC VCE Zen and now server storage I/O convergence

In case you have not heard, the joint initiative (JV) founded in the fall of 2009 between Intel VMware Cisco and EMC called VCE had a change of ownership today.

Well, kind of…

Who is VCE and what’s this Zen stuff?

For those not familiar or who need a recap, VCE was created to create converged server, storage I/O networking hardware and software solutions combing technologies from its investors resulting in solutions called vBlocks.

The major investors were Cisco who provides the converged servers and I/O networking along with associated management tools as well as EMC who provides the storage systems along with their associated management tools. Minority investors include VMware (who is majority owned by EMC) who provides the server virtualization aka software defined data center management tools and Intel whose’s processor chip technologies are used in the vBlocks. What has changed from Zen (e.g. yesterday or in the past) and now is that Cisco has sold the majority (they are retaining about 10%) of its investment ownership in VCE to EMC. Learn more about VCE, their solutions and valueware in this post here (VCE revisited, now and Zen).

Activist activating activity?

EMC pulling VCE in-house which should prop up its own internal sales figures by perhaps a few billion USDs within a year or so (if not sooner) is not as appealing to activists investors who want results now such as selling off parts of the company (e.g. EMC, VMware or other assets) or the entire company.

However EMC has been under pressure from activist shareholder Elliot Management to divest or sell-off portions of this business such as VMware so that the investors (including the activist) can make more money. For example there have been the recent stories about EMC looking to sell or merge with the likes of HP (who is now buying back shares and splitting up its own business) among others which certainly must make the activist investors happy.

However to the activist investors who want to see things sold to make money they are not happy with EMC off buying or investing it appears.

Via Bloomberg

“The last thing on investors’ minds is the future of VCE,” Daniel Ives, an analyst with FBR Capital Markets, wrote in a note today. “EMC has a fire in its house right now and the company appears focused on painting its bedroom (e.g. VCE), while the Street wants a resolution on the strategic ownership situation sooner rather than later.”

Read more at Bloomberg

Whats this EMC Federation stuff?

Note that EMC has organized itself into a federation that consists of EMC Information Infrastructure (EMCII) or what you might know a traditional EMC based storage and related software solutions, VMware, Pivotal and RSA. Also note that each of those federated companies have their own CEO as well as have holdings or ownership of other companies. However all report to a common federated leadership aka EMC. Thus when you hear EMC that could mean depending on the context the federation mother ship which controls the individual companies, or it could also be used to refer to EMCII aka the traditional EMC. Click here to learn more about the EMC federation.

Converging Markets and Opportunities

Looking beyond near-term or quick gains, EMC could be simply doing something others do to take ownership and control over certain things while reducing complexities associated with joint initiatives. For example with EMC and Cisco in a close partnership with VCE, both parties have been free to explore and take part in other joint initiatives such as Cisco with EMC competitors NetApp, HDS among others. Otoh EMC partners with Arista for networking, not to mention via VMware acquired virtual network or software defined network Nicira now called NSX.

server and storage I/O road map to convergence

EMC is also in a partnership with Lenovo for developing servers to be used by EMC for various platforms to support storage, data and information services while shifting the lower-end SMB storage offerings such as Iomega to the Lenovo channel.

Note that Lenovo is in the process of absorbing the IBM xSeries (e.g. x86 based) business unit that started closing earlier in October (will take several months to completely close in all countries around the world). For its part Cisco is also partnering with hyper-converged solution provider Simplivity while EMC has announced its statement of direction to bring to market its own hyper-converged platform by end of the year. For those not familiar, Hyper-converged solutions are simply the next evolution of converged or pre-bundled turnkey systems (some of you might have just had a Dejavu moment) that today tend to be targeted for SMBs and ROBOs however used for targeted applications such as VDI in larger environments.

Storage I/O trends

What does this have to do with VCE?

IF EMC is about to release as it has made statement of direction statements of a hyper-converged solution by year-end to compete head-on with those from Nutanix, Simplivity and Tintri as well as perhaps to a lesser extent VMwares EVO:Rail, by having more control over VCE means reducing if not eliminating complexity around vBlocks which are Cisco based with EMC storage vs. what ever EMC brings to market for hyper-converged. In the past under the VCE initiatives storage was limited to EMC and servers along with networking from Cisco, hypervisors from VMware, however what happens in the future remains to be seen.

Does this mean EMC is moving even more into servers than just virtual servers?

Tough to say as EMC can not afford to have its sales force lose focus on its traditional core products while ramping up other business, however, the EMC direct and partner teams want and need to keep up account control which means gaining market share and footprint in those accounts. This also means EMC needs to find ways to take cost out of the sales and marketing process where possible to streamline which perhaps brining VCE will help do.

Will this perhaps give the EMC direct and partner sales teams a new carrot or incentive to promote converged and hyper-converged at the cost of other competitors or incumbents? Perhaps, lets see what happens in the coming weeks.

What does this all mean?

In a nut shell, IMHO EMC is doing a couple of things here one of which is cleaning up some ownership in JVs to give it self more control, as well as options for doing other business transactions (mergers and acquisitions (M&A), sales or divestiture’s, new joint initiatives, etc). Then there is streamline its business from decision-making to quickly respond to new opportunities as well as routes to markets and other activities (e.g. removing complexity and cost vs. simply cutting cost).

Does this signal the prelude to something else? Perhaps, we know that EMC has made a statement of direction about hyper-converged which with VCE now more under EMC control, perhaps we will see more options from under the VCE umbrella both for lower-end and entry SMB as well as SME and large enterprise organizations.

What about the activist investors?

They are going to make noise as long as they can continue to make more money or get what they want. Publicly I would be shocked if the activist investors were not making statements that EMC should be selling assets not buying or investing.

On the other hand, any smart investor, financial or other analyst should see though the fog of what this relatively simple transaction means in terms of EMC getting further control of its future.

Of course the question will stay does EMC remain in control of its current federation of EMC, VMware, Pivotal, RSA along each of their respective holdings, does EMC doe a block buster merger, divestiture or acquisition?

server and storage I/O road ahead

Take a step back, look at the big picture!

Some things to keep an eye on:

Will this move help streamline decision-making enabling new solutions to be brought to market and customers quicker?
While there is a VMware focus, don’t forget about the long-running decades old relationship with Microsoft and how that plays into the equation
Watch for what EMC releases with their hyper-converged solution as well as where it is focused, not to mention how sold
Also watch the EMC and Lenovo join initiative, both for the Iomega storage activity as well as what EMC and Lenovo do with and for servers
Speaking of Lenovo, unless I missed something as of the time of writing this, have you noticed that Lenovo is not yet part of the VMware EVO:Rail initiative?

Ok, nuff said (for now)

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

September 21, 2014December 31, 2022

Seagate has shipped over 10 Million storage HHDD’s, is that a lot?

Recently Seagate made an announcement that they have shipped over 10 million Hybrid Hard Disk Drives (HHDD) also known as Solid State Hybrid Drives (SSHD) over that past few years. Disclosure Seagate has been a StorageIO client.

I know where some of those desktop class HHDD’s including Momentus XTs ended up as I bought some of the 500GB and 750GB models via Amazon and have them in various systems. Likewise I have installed in VMware servers the newer generation of enterprise class SSHD’s which Seagate now refers to as Turbo models as companions to my older HHDD’s

What is a HHDD or SSHD?

The HHDD’s continue to evolve from initially accelerating reads to now being capable of speeding up write operations across different families (desktop/mobile, workstation and enterprise). What makes a HHDD or SSHD is that as their name implies, they are a hybrid combing a traditional spinning magnetic Hard Disk Drive (HDD) along with flash SSD storage. The flash persistent memory is in addition to the DRAM or non-persistent memory typically found on HDDs used as a cache buffer. These HHDDs or SSHDs are self-contained in that the flash are built-in to the actual drive as part of its internal electronics circuit board (controller). This means that the drives should be transparent to the operating systems or hypervisors on servers or storage controllers without need for special adapters, controller cards or drivers. In addition, there is no extra software needed to automated tiering or movement between the flash on the HHDD or SSHD and its internal HDD, its all self-contained managed by the drives firmware (e.g. software).

Some SSHD and HHDD industry perspectives

Jim Handy over at Objective Analysis has this interesting post discussing Hybrid Drives Not Catching On. The following is an excerpt from Jim’s post.

Why were our expectations higher?

There were a few reasons: The hybrid drive can be viewed as an evolution of the DRAM cache already incorporated into nearly all HDDs today.

Replacing or augmenting an expensive DRAM cache with a slower, cheaper NAND cache makes a lot of sense.
An SSHD performs much better than a standard HDD at a lower price than an SSD. In fact, an SSD of the same capacity as today’s average HDD would cost about an order of magnitude more than the HDD. The beauty of an SSHD is that it provides near-SSD performance at a near-HDD price. This could have been a very compelling sales proposition had it been promoted in a way that was understood and embraced by end users.
Some expected for Seagate to include this technology into all HDDs and not to try to continue using it as a differentiator between different Seagate product lines. The company could have taken either of two approaches: To use hybrid technology to break apart two product lines – standard HDDs and higher-margin hybrid HDDs, or to merge hybrid technology into all Seagate HDDs to differentiate Seagate HDDs from competitors’ products, allowing Seagate to take slightly higher margins on all HDDs. Seagate chose the first path.

The net result is shipments of 10 million units since its 2010 introduction, for an average of 2.5 million per year, out of a total annual HDD shipments of around 500 million units, or one half of one percent.

Continue reading more of Jim’s post here.

In his post, Jim raises some good points including that HHDD’s and SSHD’s are still a fraction of the overall HDD’s shipped on an annual basis. However IMHO the annual growth rate has not been a flat average of 2.5 million, rather starting at a lower rate and then increasing year over year. For example Seagate issued a press release back in summer 2011 that they had shipped a million HHDD’s a year after their release. Also keep in mind that those HHDD’s were focused on desktop workstations and in particular, at Gamers among others.

The early HHDD’s such as the Momentus XTs that I was using starting in June 2010 only had read acceleration which was better than HDD’s, however did not help out on writes. Over the past couple of years there have been enhancements to the HHDD’s including the newer generation also known as SSHD’s or Turbo drives as Seagate now calls them. These newer drives include write acceleration as well as with models for mobile/laptop, workstation and enterprise class including higher-performance and high-capacity versions. Thus my estimates or analysis has the growth on an accelerating curve vs. linear growth rate (e.g. average of 2.5 million units per year).

	Units shipped per year	Running total units shipped
2010-2011	1.0 Million	1.0 Million
2011-2012	1.25 Million (est.)	2.25 Million (est.)
2012-2013	2.75 Million (est.)	5.0 Million (est.)
2013-2014	5.0 Million (est)	10.0 Million

StorageIO estimates on HHDD/SSHD units shipped based on Seagate announcements

estimated hhdd and sshd shipments

However IMHO there is more to the story beyond numbers of HHDD/SSHD shipped or if they are accelerating in deployment or growing at an average rate. Some of those perspectives are in my comments over on Jim Handy’s site with an excerpt below.

In talking with IT professionals (e.g. what the vendors/industry calls users/customers) they are generally not aware that these devices exist, or if they are aware of them, they are only aware of what was available in the past (e.g. the consumer class read optimized versions). I do talk with some who are aware of the newer generation devices however their comments are usually tied to lack of system integrator (SI) or vendor/OEM support, or sole source. Also there was a focus on promoting the HHDD’s to “gamers” or other power users as opposed to broader marketing efforts. Also most of these IT people are not aware of the newer generation of SSHD or what Seagate is now calling “Turbo” drives.

When talking with VAR’s, there is a similar reaction which is discussion about lack of support for HHDD’s or SSHD’s from the SI/vendor OEMs, or single source supply concerns. Also a common reaction is lack of awareness around current generation of SSHD’s (e.g. those that do write optimization, as well as enterprise class versions).

When talking with vendors/OEMs, there is a general lack of awareness of the newer enterprise class SSHD’s/HHDD’s that do write acceleration, sometimes there is concern of how this would disrupt their “hybrid” SSD + HDD or tiering marketing stories/strategies, as well as comments about single source suppliers. Have also heard comments to the effect of concerns about how long or committed are the drive manufactures going to be focused on SSHD/HHDD, or is this just a gap filler for now.

Not surprisingly when I talk with industry pundits, influencers, amplifiers (e.g. analyst, media, consultants, blogalysts) there is a reflection of all the above which is lack of awareness of what is available (not to mention lack of experience) vs. repeating what has been heard or read about in the past.

IMHO while there are some technology hurdles, the biggest issue and challenge is that of some basic marketing and business development to generate awareness with the industry (e.g. pundits), vendors/OEMs, VAR’s, and IT customers, that is of course assuming SSHD/HHDD are here to stay and not just a passing fad…

What about SSHD and HHDD performance on reads and writes?

What about the performance of today’s HHDD’s and SSHD’s, particular those that can accelerate writes as well as reads?

SSHD and HHDD read / write performance exchange
Enterprise Turbo SSHD read and write performance (Exchange Email)

What about the performance of today’s HHDD’s and SSHD’s, particular those that can accelerate writes as well as reads?

SSHD and HHDD performance TPC-B
Enterprise Turbo SSHD read and write performance (TPC-B database)

SSHD and HHDD performance TPC-E
Enterprise Turbo SSHD read and write performance (TPC-E database)

Additional details and information about HHDD/SSHD or as Seagate now refers to them Turbo drives can be found in two StorageIO Industry Trends Perspective White Papers (located here and another here).

Where to learn more

Refer to the following links to learn more about HHDD and SSHD devices.
StorageIO Momentus Hybrid Hard Disk Drive (HHDD) Moments
Enterprise SSHD and Flash SSD
Part of an Enterprise Tiered Storage Strategy
Part II: How many IOPS can a HDD, HHDD or SSD do with VMware?
2011 Summer momentus hybrid hard disk drive (HHDD) moment
More Storage IO momentus HHDD and SSD moments part I
More Storage IO momentus HHDD and SSD moments part II
New Seagate Momentus XT Hybrid drive (SSD and HDD)
Another StorageIO Hybrid Momentus Moment
SSD past, present and future with Jim Handy
Part II: How many IOPS can a HDD, HHDD or SSD do with VMware?

Closing comments and perspectives

I continue to be bullish on hybrid storage solutions from cloud, to storage systems as well as hybrid-storage devices. However like many technology just because something makes sense or is interesting does not mean its a near-term or long-term winner. My main concern with SSHD and HHDD is if the manufactures such as Seagate and WD are serious about making them a standard feature in all drives, or simply as a near-term stop-gap solution.

What’s your take or experience with using HHDD and/or SSHDs?

Ok, nuff said (for now)

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

September 21, 2014June 13, 2021

Docker for Smarties (e.g. non-dummies) from VMworld 2014

In this Industry Trends Perspectives video pod cast episode (On YouTube) I had a chance to visit with Nathan LeClaire of docker.com at the recent VMworld 2014 in San Francisco for a quick overview of docker and containers are about, what you need to know and where to find more information. Check out this StorageIO Industry Trends Perspective episode "Docker for Smarties" aka not for dummies via YouTube by clicking here or on the image below.

For those not familiar with docker.

Server storage I/O docker for non-dummies
Docker overview

What to know about docker
Three things to know about docker

key points and where to learn more about docker

Checkout the Docker for non-dummies video here.

What’s your take, is docker in your future or are you already using it?

Ok, nuff said (for now)

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

August 31, 2014November 26, 2023

August 2014 Server and StorageIO Update newsletter

Welcome to the August 2014 edition of the StorageIO Update (newsletter) containing trends perspectives on cloud, virtualization, software defined and data infrastructure topics. This past week I along with around 22,000 others attended VMworld 2014 in San Francisco. For those of you in Europe, VMworld Barcelona is October 14-16 2014 with registration and more information found here. Watch for more post VMworld coverage in upcoming newsletters, articles, posts along with other industry trend topics. Enjoy this edition of the StorageIO Update newsletter and look forward to catching up with you live or online while out and about this fall.

Greg Schulz @StorageIO

August 2014 Industry trend and perspectives

StorageIO Industry Trends and Perspectives

The following is a synopsis of some StorageIOblog posts, articles and comments in different venues on various industry trends, perspectives and related themes about clouds, virtualization, data and storage infrastructure topics among related themes.

StorageIO comments and perspectives in the news

StorageIO in the news

Virtual Desktop Infrastructures (VDI) remains a popular industry and IT customer topic, not to mention being one of the favorite themes of Solid State Device (SSD) vendors. SSD component and system solution vendors along with their supporters love VDI as the by-product of aggregation (e.g. consolidation) which applies to VDI is aggravation. Aggravation is the result of increased storage I/O performance (IOP’s, bandwidth, response time) from consolidating the various desktops. It should not be a surprise that some of the biggest fans encouraging organizations to adopt VDI are the SSD vendors. Read some of my comments and perspectives on VDI here at FedTech Magazine.

Speaking of virtualizing the data center, software defined data centers (SDDC) along with software defined networking (SDN) and software defined storage (SDS) remain popular including some software defined marketing (SDM). Here are some of my comments and perspectives moving beyond the hype of SDDC.

FCIA Fibre Channel Industry Association

Recently the Fibre Channel Industry Association (FCIA) who works with the T11 standards body of both legacy or classic Fibre Channel (FC) as well as newer FC over Ethernet (FCoE) made some announcements. These announcements including enhancements such as Fibre Channel Back Bone version 6 (FC-BB-6) among others. Both FC and FCoE are alive and doing well, granted one has been around longer (FC) and can be seen at its plateau while the other (FCoE) continues to evolve and grow in adoption. In some ways, FCoE is in a similar role today to where FC was in the late 90s and early 2000s ironically facing some common fud. You can read my comments here as part of a quote in support of the announcement , along with my more industry trend perspectives in this blog post here.

Buyers guides are popular with both vendors, VAR’s as well as IT organizations (e.g. customers) following are some of my comments and industry trend perspectives appearing in Enterprise Storage Forum. Here are perspectives on buyers guides for Enterprise File Sync and Share (EFSS), Unified Data Storage and Object Storage. EMC has come under pressure as mentioned in earlier StorageIO update newsletters to increase its shareholder benefit including spin-off of VMware. Here are some of my comments and perspectives that appeared in CruxialCIO. Read more industry trends perspectives comments on the StorageIO news page.

StorageIO video and audio pod casts

StorageIOblog post
StorageIO audio podcasts are also available via
and at StorageIO.tv

StorageIOblog posts and perspectives

StorageIOblog post

Despite being declared dead, traditional or classic Fibre Channel (FC) along with FC over Ethernet (FCoE) continues to evolve with FC-BB-6, read more here.

VMworld 2014 took place this past week and included announcements about EVO:Rack and Rail (more on this in a future edition). You can get started learning about EVO:Rack and RAIL at Duncan Epping (aka @DuncanYB) Yellow Bricks site. VMware Virtual SAN (VSAN) is at the heart of EVO which you can read an overview here in this earlier StorageIO update newsletter (March 2014).

VMware VSAN example

Also watch for some extra content that I’m working on including some video podcasts articles and blog posts from my trip to VMworld 2014. However one of the themes in the background of VMworld 2014 is the current beta of VMware vSphere V6 along with Virtual Volumes aka VVOL’s. The following are a couple of my recent posts including primer overview of VVOL’s along with a poll you can cast your vote. Check out Are VMware VVOL’s in your virtual server and storage I/O future? and VMware VVOL’s and storage I/O fundamentals (Part 1) along with (Part 2).

StorageIO events and activities

Server and StorageIO seminars, conferences, web cats, events, activities

The StorageIO calendar continues to evolve including several new events being added for September and well into the fall with more in the works including upcoming Dutch European sessions the week of October 6th in Nijkerk Holland (learn more here). The following are some upcoming September events. These include live in-person seminars, conferences, keynote and speaking activities as well as on-line webinars, twitter chats, Google+ hangouts among others.

Sep 25 2014	MSP CMG	Server and StorageIO SSD industry trends perspectives and tips	TBA 9:30AM CT
Sep 18 2014	InfoWorld	Hybrid Storage In Government	Webinar 2:30PM ET
Sep 18 2014		Converged Storage and Storage Convergence	Webinar 9AM PT
Sep 17 2014		Data Center Convergence	Webinar 1PM PT
Sep 16 2014		Critical Infrastructure and Disaster Recovery	Webinar Noon PT
Sep 16 2014	Starwind Software	Software Defined Storage and Virtual SAN for Microsoft environments	Webinar 1PM CT
Sep 16 2014	Dell BackupU	Exploring the Data Protection Toolbox – Data and Application Replication	Google+ 9AM PT
Sep 2 2014	Dell BackupU	Exploring the Data Protection Toolbox – Data and Application Replication	Online Webinar 11AM PT

Note: Dates, times, venues and subject contents subject to change, refer to events page for current status

Click here to view other upcoming along with earlier event activities. Watch for more 2014 events to be added soon to the StorageIO events calendar page. Topics include data protection modernization (backup/restore, HA, BC, DR, archive), data footprint reduction (archive, compression, dedupe), storage optimization, SSD, object storage, server and storage virtualization, software defined, big data, little data, cloud and object storage, performance and management trends among others.

Vendors, VAR’s and event organizers, give us a call or send an email to discuss having us involved in your upcoming pod cast, web cast, virtual seminar, conference or other events.

Server and StorageIO Technology Tips and Tools

Server and StorageIO seminars, conferences, web cats, events, activities

In addition to the industry trends and perspectives comments in the news mentioned above, along with the StorageIO blog posts, the following are some of my recent articles and tips that have appeared in various industry venues.

Storage Acceleration

Over at the new Storage Acceleration site I have a couple of pieces, the first is What, When, Why & How to Accelerate Storage and the other is Tips for Measuring Your Storage Acceleration.
Meanwhile over at Search Storage I have a piece covering What is the difference between a storage snapshot and a clone? and at Search Cloud Storage some tips about What’s most important to know about my cloud privacy policy?. Also with Software Defined in the news and a popular industry topic, I have a piece over at Enterprise Storage Forum looking at Has Software Defined Jumped the Shark? Check out these and others on the StorageIO tips and articles page.

StorageIO Update Newsletter Archives

Click here to view earlier StorageIO Update newsletters (HTML and PDF versions) at www.storageio.com/newsletter. Subscribe to this newsletter (and pass it along) by clicking here (Via Secure Campaigner site). View archives of past StorageIO update news letters as well as download PDF versions at: www.storageio.com/newsletter

Ok, nuff said (for now)

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

August 24, 2014June 13, 2021

VMware VVOLs and storage I/O fundementals (Part 2)

VMware VVOL’s and storage I/O fundamentals (Part II)

Note that this is a three part series with the first piece here (e.g. Are VMware VVOL’s in your virtual server and storage I/O future?), the second piece here (e.g.VMware VVOL’s and storage I/O fundamentals Part 1) and the third piece here (e.g. VMware VVOL’s and storage I/O fundamentals Part 2).

Picking up from where we left off in the first part of the VMware VVOL’s and storage I/O fundamentals, lets take a closer look at VVOL’s.

First however lets be clear that while VMware uses terms including object and object storage in the context of VVOL’s, its not the same as some other object storage solutions. Learn more about object storage here at www.objectstoragecenter.com

Are VVOL’s accessed like other object storage (e.g. S3)?

No, VVOL’s are accessed via the VMware software and associated API’s that are supported by various storage providers. VVOL’s are not LUN’s like regular block (e.g. DAS or SAN) storage that use SAS, iSCSI, FC, FCoE, IBA/SRP, nor are they NAS volumes like NFS mount points. Likewise VVOL’s are not accessed using any of the various object storage access methods mentioned above (e.g. AWS S3, Rest, CDMI, etc) instead they are an application specific implementation. For some of you this approach of an applications specific or unique storage access method may be new, perhaps revolutionary, otoh, some of you might be having a DejaVu moment right about now.

VVOL is not a LUN in the context of what you may know and like (or hate, even if you have never worked with them), likewise it is not a NAS volume like you know (or have heard of), neither are they objects in the context of what you might have seen or heard such as S3 among others.

Keep in mind that what makes up a VMware virtual machine are the VMK, VMDK and some other files (shown in the figure below), and if enough information is known about where those blocks of data are or can be found, they can be worked upon. Also keep in mind that at least near-term, block is the lowest common denominator that all file systems and object repositories get built-up.

VMware ESXi basic storage I/O
VMware ESXi storage I/O, IOPS and data store basics

Here is the thing, while VVOL’s will be accessible via a block interface such as iSCSI, FC or FCoE or for that matter, over Ethernet based IP using NFS. Think of these storage interfaces and access mechanisms as the general transport for how vSphere ESXi will communicate with the storage system (e.g. their data path) under vCenter management.

What is happening inside the storage system that will be presented back to ESXi will be different than a normal SCSI LUN contents and only understood by VMware hypervisor. ESXi will still tell the storage system what it wants to do including moving blocks of data. The storage system however will have more insight and awareness into the context of what those blocks of data mean. This is how the storage systems will be able to more closely integrate snapshots, replication, cloning and other functions by having awareness into which data to move, as opposed to moving or working with an entire LUN where a VMDK may live. Keep in mind that the storage system will still function as it normally would, just think of VVOL as another or new personality and access mechanism used for VMware to communicate and manage storage.

VMware VVOL basics
VMware VVOL concepts (in general) with VMDK being pushed down into the storage system

Think in terms of the iSCSI (or FC or something else) for block or NFS for NAS as being the addressing mechanism to communicate between ESXi and the storage array, except instead of traditional SCSI LUN access and mapping, more work and insight is pushed down into the array. Also keep in mind that with a LUN, it is simply an address from what to use Logical Block Numbers or Logical Block Addresses. In the case of a storage array, it in turn manages placement of data on SSD or HDDs in turn using blocks aka LBA/LBN’s In other words, a host that does not speak VVOL would get an error if trying to use a LUN or target on a storage system that is a VVOL, that’s assuming it is not masked or hidden ;).

What’s the Storage Provider (SP)

The Storage Provider aka SP is created by the, well, the provider of the storage system or appliance leveraging a VMware API (hint, sign up for the beta and there is an SDK). Simply put, the SP is a two-way communication mechanism leveraging VASA for reporting information, configuration and other insight up to VMware ESXi hypervisor, vCenter and other management tools. In addition the storage provider receives VASA configuration information from VMware about how to configure the storage system (e.g. storage containers). Keep in mind that the SP is the out of band management interface between the storage system supporting and presenting VVOL’s and VMware hypervisors.

What’s the Storage Container (SC)

This is a storage pool created on the storage array or appliance (e.g. VMware vCenter works with array and storage provider (SP) to create) in place of using a normal LUN. With a SP and PE, the storage container becomes visible to ESXi hosts, VVOL’s can be created in the storage container until it runs out of space. Also note that the storage container takes on the storage profile assigned to it which are inherited by the VVOLs in it. This is in place of presenting LUN’s to ESXi that you can then create VMFS data stores (or use as raw) and then carve storage to VMs.

Protocol endpoint (PE)

The PE provides visibility for the VMware hypervisor to see and access VMDK’s and other objects (e.g. .vmx, swap, etc) stored in VVOL’s. The protocol endpoint (PE) manages or directs I/O received from the VM enabling scaling across many virtual volumes leveraging multipathing of the PE (inherited by the VVOL’s.). Note that for storage I/O operations, the PE is simply a pass thru mechanism and does not store the VMDK or other contents. If using iSCSI, FC, FCoE or other SAN interface, then the PE works on a LUN basis (again not actually storing data), and if using NAS NFS, then with a mount point. Key point is that the PE gets out-of-the-way.

VVOL Poll

What are you VVOL plans, view results and cast your vote here

Wrap up (for now)

There certainly are many more details to VVOL’s. that you can get a preview of in the beta, a well as via various demos, webinars, VMworld sessions as more becomes public. However for now, hope you found this quick overview on VVOL’s. of use, since VVOL’s. at the time of this writing are not yet released, you will need to wait for more detailed info, or join the beta or poke around the web (for now). Also if you have not seen the first part overview to this piece, check it out here as I give some more links to get you started to learn more about VVOL’s.

Keep an eye on and learn more about VVOL’s. at VMworld 2014 as well as in various other venues.

IMHO VVOL’s. are or will be in your future, however the question will be is there going to be a back to the future moment for some of you with VVOL’s.?

What VVOL questions, comments and concerns are in your future and on your mind?

Ok, nuff said (for now)

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

August 24, 2014March 8, 2022

VMware VVOLs storage I/O fundementals (Part 1)

VMware VVOL’s storage I/O fundamentals (Part I)

Some of you may already be participating in the VMware beta of VVOL involving one of the initial storage vendors also in the beta program.

Ok, now let’s go a bit deeper, however if you want some good music to listen to while reading this, check out @BruceRave GoDeepMusic.Net and shows here.

Taking a step back, digging deeper into Storage I/O and VVOL’s fundamentals

Instead of a VM host accessing its virtual disk (aka VMDK) which is stored in a VMFS formatted data store (part of ESXi hypervisor) built on top of a SCSI LUN (e.g. SAS, SATA, iSCSI, Fibre Channel aka FC, FCoE aka FC over Ethernet, IBA/SRP, etc) or an NFS file system presented by a storage system (or appliance), VVOL’s push more functionality and visibility down into the storage system. VVOL’s shift more intelligence and work from the hypervisor down into the storage system. Instead of a storage system simply presenting a SCSI LUN or NFS mount point and having limited (coarse) to no visibility into how the underlying storage bits, bytes as well as blocks are being used, storage systems gain more awareness.

Keep in mind that even files and objects still get ultimately mapped to pages and blocks aka sectors even on nand flash-based SSD’s. However also keep an eye on some new technology such as the Seagate Kinetic drive that instead of responding to SCSI block based commands, leverage object API’s and associated software on servers. Read more about these emerging trends here and here at objectstoragecenter.com.

With a normal SCSI LUN the underlying storage system has no knowledge of how the upper level operating system, hypervisor, file system or application such as a database (doing raw IO) is allocating the pages or blocks of memory aka storage. It is up to the upper level storage and data management tools to map from objects and files to the corresponding extents, pages and logical block address (LBA) understood by the storage system. In the case of a NAS solution, there is a layer of abstractions placed over the underlying block storage handling file management and the associated file to LBA mapping activity.

Storage I/O basics
Storage I/O and IOP basics and addressing: LBA’s and LBN’s

Getting back to VVOL, instead of simply presenting a LUN which is essentially a linear range of LBA’s (think of a big table or array) that the hypervisor then manages data placement and access, the storage system now gains insight into what LBA’s correspond to various entities such as a VMDK or VMX, log, clone, swap or other VMware objects. With this more insight, storage systems can now do native and more granular functions such as clone, replication, snapshot among others as opposed to simply working on a coarse LUN basis. The similar concepts extend over to NAS NFS based access. Granted, there are more to VVOL’s including ability to get the underlying storage system more closely integrated with the virtual machine, hypervisor and associated management including supported service manage and classes or categories of service across performance, availability, capacity, economics.

What about VVOL, VAAI and VASA?

VVOL’s are building from earlier VMware initiatives including VAAI and VASA. With VAAI, VMware hypervisor’s can off-load common functions to storage systems that support features such as copy, clone, zero copy among others like how a computer can off-load graphics processing to a graphics card if present.

VASA however provides a means for visibility, insight and awareness between the hypervisor and its associated management (e.g. vCenter etc) as well as the storage system. This includes storage systems being able to communicate and publish to VMware its capabilities for storage space capacity, availability, performance and configuration among other things.

With VVOL’s VASA gets leveraged for unidirectional (e.g. two-way) communication where VMware hypervisor and management tools can tell the storage system of things, configuration, activities to do among others. Hence why VASA is important to have in your VMware CASA.

What’s this object storage stuff?

VVOL’s are a form of object storage access in that they differ from traditional block (LUN’s) and files (NAS volumes/mount points). However, keep in mind that not all object storage are the same as there are object storage access and architectures.

Object Storage basics, generalities and block file relationships

Avoid making the mistake of when you hear object storage that means ANSI T10 (the folks that manage the SCSI command specifications) Object Storage Device (OSD) or something else. There are many different types of underlying object storage architectures some with block and file as well as object access front ends. Likewise there are many different types of object access that sit on top of object architectures as well as traditional storage system.

Object storage I/O
An example of how some object storage gets accessed (not VMware specific)

Also keep in mind that there are many different types of object access mechanism including HTTP Rest based, S3 (e.g. a common industry defacto standard based on Amazon Simple Storage Service), SNIA CDMI, SOAP, Torrent, XAM, JSON, XML, DICOM, IL7 just to name a few, not to mention various programmatic bindings or application specific implementations and API’s. Read more about object storage architectures, access and related topics, themes and trends at www.objecstoragecenter.com

Lets take a break here and when you are ready, click here to read the third piece in this series VMware VVOL’s and storage I/O fundamentals Part 2.

Ok, nuff said (for now)

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

August 24, 2014June 13, 2021

Are VMware VVOLs in your virtual server and storage I/O future?

Are VMware VVOL’s in your virtual server and storage I/O future?

Note that this is a three part series with the first piece here (e.g. Are VMware VVOL’s in your virtual server and storage I/O future?), the second piece here (e.g. VMware VVOL’s and storage I/O fundamentals Part 1) and the third piece here (e.g. VMware VVOL’s and storage I/O fundamentals Part 2).

With VMworld 2014 just around the corner, for some of you the question is not if Virtual Volumes (VVOL’s) are in your future, rather when, where, how and with what.

What this means is that for some hands on beta testing is already occurring or will be soon, while for others that might be around the corner or down the road.

Some of you may already be participating in the VMware beta of VVOL involving one of the first storage vendors also in the beta program.

On the other hand, some of you may not be in VMware centric environments and thus VVOL’s may not yet be in your vocabulary.

How do you know if VVOL are in your future if you don’t know what they are?

First, to be clear, as of the time this was written VMware VVOL’s are not released and only in beta as well as having been covered in earlier VMworld’s. Consequently what you are going to read here is based on what VVOL material has already been made public in various venues including earlier VMworld’s and VMware blogs among other places.

The quick synopsis of VMware VVOL’s overview:

Higher level of abstraction of storage vs. traditional SCSI LUN’s or NAS NFS mount points

Tighter level of integration and awareness between VMware hypervisors and storage systems

Simplified management for storage and virtualization administrators

Removing complexity to support increased scaling

Enable automation and service managed storage aka software defined storage management

VVOL considerations and your future

As mentioned, as of this writing, VVOL’s are still a future item granted they exist in beta.

For those of you in VMware environments, now is the time to add VVOL to your vocabulary which might mean simply taking the time to read a piece like this, or digging deeper into the theories of operations, configuration, usage, hints and tips, tutorials along with vendor specific implementations.

Explore your options, and ask yourself, do you want VVOL or do you need it

What support does your current vendor(s) have for VVOL or what is their statement of direction (SOD) which you might have to get from them under NDA.

This means that there will be some first vendors with some of their products supporting VVOL’s with more vendors and products following (hence watch for many statements of direction announcements).

Speaking of vendors, watch for a growing list of vendors to announce their current or plans for supporting VVOL’s, not to mention watch some of them jump up and down like Donkey in Shrek saying "oh oh pick me pick me".

When you ask a vendor if they support VVOL’s, move beyond the simple yes or no, ask which of their specific products, it is a block (e.g. iSCSI) or NAS file (e.g. NFS) based and other caveats or configuration options.

Watch for more information about VVOL’s in the weeks and months to come both from VMware along with from their storage provider partners.

How will VVOL impact your organizations best practices, policies, workflow’s including who does what, along with associated responsibilities.