Server StorageIO Data Infrastructure Insights and Analysis
|
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
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
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…
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).
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 |
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.
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.
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.
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.
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.
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.
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?
Some things to keep an eye on:
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
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
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.
Docker overview
Three things to know 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
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
In case you missed it, the Storage Networking Industry Association (SNIA) recently released their version 1.1 of its Cloud Data Management Interface (CDMI) specification.
Highlights of CDMI version 1.1 include:
Check out the full specification here.
Speaking of SNIA and CDMI, check out this pod cast post of CDMI in a conversation with Wayne Adams and David Dale of SNIA.
Ok, nuff said
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
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
The CompTIA folks are looking for some comments and feedback from those who are involved with data storage in various ways as part of planning for their upcoming enhancements to the Storage+ certification testing.
As a point of disclosure, I am member of the CompTIA Storage+ certification advisory committee (CAC), however I don’t get paid or receive any other type of renumeration for contributing my time to give them feedback and guidance other than a thank, Atta boy for giving back and playing it forward to help others in the IT community similar to what my predecessors did.
I have been asked to pass this along to others (e.g. you or who ever forwards it on to you).
Please take a few moments and feel free to share with others this link here to the survey for CompTIA Storage+.
What they are looking for is to validate the exam blueprint generated from a recent Job Task Analysis (JTA) process.
In other words, does the certification exam show real-world relevance to what you and your associates may be doing involved with data storage.
This is opposed to being aligned with those whose’s job it is to create test questions and may not understand what it is you the IT pro involved with storage does or does not do.
If you have ever taken a certification exam test and scratched your head or wondered out why some questions that seem to lack real-world relevance were included, vs. ones of practical on-the-job experience were missing, here’s your chance to give feedback.
Note that you will not be rewarded with an Amex or Amazon gift card, Starbucks or Dunkin Donuts certificates, free software download or some other incentive to play and win, however if you take the survey let me know and will be sure to tweet you an Atta boy or Atta girl! However they are giving away a free T-Shirt to every 10 survey takers.
Btw, if you really need something for free, send me a note (I’m not that difficult to find) as I have some free copies of Resilient Storage Networking (RSN): Designing Flexible Scalable Data Infrastructures (Elsevier) you simply pay shopping and handling. RSN can be used to help prepare you for various storage testing as well as other day-to-day activities.
CompTIA is looking for survey takers who have some hands-on experience or involved with data storage (e.g. can you spell SAN, NAS, Disk or SSD and work with them hands-on then you are a candidate ;).
Welcome to the CompTIA Storage+ Certification Job Task Analysis (JTA) Survey Here is what (and whom) CompTIA is looking for feedback from: As a small token of CompTIA appreciation for your participation, they will provide an official CompTIA T-shirt to every tenth (1 of every 10) person who completes this survey. Go here for official rules. Click here to complete the CompTIA Storage+ survey Contact CompTIA with any survey issues, research@comptia.org |
What say you, take a few minutes like I did and give some feedback, you will not be on the hook for anything, and if you do get spammed by the CompTIA folks, let me know and I in turn will spam them back for spamming you as well as me.
Ok, nuff said
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
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
| ||||||||||||||||||||||||||||||||
August 2014 Industry trend 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
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.
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 posts and perspectives
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).
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 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.
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 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.
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. | ||||||||||||||||||||||||||||||||
StorageIO Update Newsletter ArchivesClick 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) All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved | ||||||||||||||||||||||||||||||||
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
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 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 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 ;).
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.
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.
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.
What are you VVOL plans, view results and cast your vote here
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
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
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).
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.
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 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.
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.
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.
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
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
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.
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:
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.
Check out the companion piece to this that takes a closer look at storage I/O and VMware VVOL fundamentals here and here.
Also check out this good VMware blog via Cormac Hogan (@CormacJHogan) that includes a video demo, granted its from 2012, however some of this stuff actually does take time and thus this is very timely. Speaking of VMware, Duncan Epping (aka @DuncanYB) at his Yellow-Bricks site has some good posts to check out as well with links to others including this here. Also check out the various VVOL related sessions at VMworld as well as the many existing, and soon to be many more blogs, articles and videos you can find via Google. And if you need a refresher, Why VASA is important to have in your VMware CASA.
Of course keep an eye here or whichever venue you happen to read this for future follow-up and companion posts, and if you have not done so, sign up for the beta here as there are lots of good material including SDKs, configuration guides and more.
What are you VVOL plans, view results and cast your vote here
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).
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?
Also what VVOL questions, comments and concerns are in your future and on your mind?
And remember to check out the second part to this series here.
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
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
Like many technologies that have been around for more than a decade or two, they often get declared dead when something new appears and Fibre Channel (FC) for networking with your servers and storage falls into that category. It seems like just yesterday when iSCSI was appearing on the storage networking scene in the early 2000s that FC was declared dead yet it remains and continues to evolve including moving over Ethernet with FC over Ethernet (FCoE).
Recently the Fibre Channel Industry Association (FCIA) made an announcement on the continued development and enhancements including FC-BB-6 that applies to both "classic" or "legacy" FC as well as the newer and emerging FCoE implementations. FCIA is not alone in the FCIA activity as they are as the name implies the industry consortium that works with the T11 standards folks. T11 is a Technical Committee of the International Committee on Information Technology Standards (INCITS, pronounced "insights").
Keep in mind that a couple of pieces to Fibre Channel which are the upper levels and lower level transports.
With FCoE, the upper level portions get mapped natively on Ethernet without having to map on top of IP as happens with distance extension using FCIP.
Likewise FCoE is more than simply mapping one of the FC upper level protocols (ULPs) such as the SCSI command set (aka SCSI_FCP) on IP (e.g. iSCSI). Think of ULPs almost in a way as a guest that gets transported or carried across the network, however lets also be careful not to play the software defined network (SDN) or virtual network, network virtualization or IO virtualization (IOV) card, or at least yet, we will leave that up to some creative marketers ;).
At the heart of the Fibre Channel beyond the cable and encoding scheme are a set of protocols, command sets and one in particular is FC Backbone now in its 6th version (read more here at the T11 site, or here at the SNIA site).
Some of the highlights of the FCIA announcement include:
VN2VN connectivity support enabling direct point to point virtual links (not to be confused with point to point physical cabling) between nodes in an FCoE network simplifying configurations for smaller SAN networks where zoning might not be needed (e.g. remove complexity and cost).
Support for Domain ID scalability including more efficient use by FCoE fabrics enabling large scalability of converged SANs. Also keep an eye on the emerging T11 FC-SW-6 distributed switch architecture for implementation over Ethernet in final stages of development.
Here are my perspectives on this announcement by the FCIA:
"Fibre Channel is a proven protocol for networked data center storage that just got better," said Greg Schulz, founder StorageIO. "The FC-BB-6 standard helps to unlock the full potential of the Fibre Channel protocol that can be implemented on traditional Fibre Channel as well as via Ethernet based networks. This means FC-BB-6 enabled Fibre Channel protocol based networks give flexibility, scalability and secure high-performance resilient storage networks to be implemented." |
Both "classic" or "legacy" Fibre Channel based cabling and networking are still alive with a road map that you can view here.
However FCoE also continues to mature and evolve and in some ways, FC-BB-6 and its associated technologies and capabilities can be seen as the bridge between the past and the future. Thus while the role of both FC and FCoE along with other ways of of networking with your servers and storage continue to evolve, so to does the technology. Also keep in mind that not everything is the same in the data center or information factory which is why we have different types of server, storage and I/O networks to address different needs, requirements and preferences.
Additional reading and viewing on FC, FCoE and storage networking::
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
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
Server and StorageIO Update newsletter – July 2014 | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Server and StorageIO Update newsletter – June 2014 | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Server and StorageIO Update newsletter – April and May 2014 | ||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||
The question to ask yourself is not if flash Solid State Device (SSD) technologies are in your future.
Instead the questions are when, where, using what, how to configure and related themes. SSD including traditional DRAM and NAND flash-based technologies are like real estate where location matters; however, there are different types of properties to meet various needs. This means leveraging different types of NAND flash SSD technologies in different locations in a complementary and cooperative aka hybrid way.
Solid State Hybrid Disks (SSHD) are the successors to previous generation Hybrid Hard Disk Drives (HHDD) that I have used for several years (you can read more about them here, and here).
While it would be nice to simply have SSD for everything, there are also economic budget realities to be dealt with. Keep in mind that a bit of nand flash SSD cache in the right location for a given purpose can go a long way which is the case with SSHDs. This is also why in many environments today there is a mix of SSD, HDD of various makes, types, speeds and capacities (e.g. different tiers) to support diverse application needs (e.g. not everything in the data center is the same).
However, If you have the need for speed and can afford or benefit from the increased productivity by all means go SSD!
Otoh if you have budget constraints and need more space capacity yet want some performance boost, then SSHDs are an option. The big difference however between today’s SSHDs that are available for both enterprise class storage systems and servers, as well as desktop environments is that they can accelerate both reads and writes. This is different from their predecessors that I have used for several years now that had basic read acceleration, however no write optimizations.
Better Together: Where SSHDs fit in an enterprise tiered storage environment with SSD and HDDs
As their names imply, they are a hybrid between a nand flash Solid State Device (SSD) and traditional Hard Disk Drive (HDD) meaning a best of situation. This means that the SSHD are based on a traditional spinning HDD (various models with different speeds, space capacity, interfaces) along with DRAM (which is found on most modern HDDs), along with nand flash for read cache, and some extra nonvolatile memory for persistent write cache combined with a bit of software defined storage performance optimization algorithms.
Btw, if you were paying attention to that last sentence you would have picked up on something about nonvolatile memory being used for persistent write cache which should prompt the question would that help with nand flash write endurance? Yup.
In the StorageIO Industry Trends Perspective thought leadership white paper I recently released compliments of Seagate Enterprise Turbo SSHD (that’s a disclosure btw ;) enterprise class Solid State Hybrid Drives (SSHD) were looked at and test driven in the StorageIO Labs with various application workloads. These activities include being in a virtual environment for common applications including database and email messaging using industry standard benchmark workloads (e.g. TPC-B and TPC-E for database, JetStress for Exchange).
Conventional storage system focused workloads using iometer, iorate and vdbench were also run in the StorageIO Labs to set up baseline reads, writes, random, sequential, small and large I/O size with IOPs, bandwidth and response time latency results. Some of those results can be found here (Part II: How many IOPS can a HDD, HHDD or SSD do with VMware?) with other ongoing workloads continuing in different configurations. The various test drive proof points were done in the comparing SSHD, SSD and different HDDs.
Data Protection (Archiving, Backup, BC, DR) | Staging cache buffer area for snapshots, replication or current copies before streaming to other storage tier using fast read/write capabilities. Meta data, index and catalogs benefit from fast reads and writes for faster protection. |
Big Data DSS | Support sequential read-ahead operations and “hot-band” data caching in a cost-effective way using SSHD vs. slower similar capacity size HDDs for Data warehouse, DSS and other analytic environments. |
Email, Text and Voice Messaging | Microsoft Exchange and other email journals, mailbox or object repositories can leverage faster read and write I/Os with more space capacity. |
OLTP, Database | Eliminate the need to short stroke HDDs to gain performance, offer more space capacity and IOP performance per device for tables, logs, journals, import/export and scratch, temporary ephemeral storage. Leverage random and sequential read acceleration to compliment server-side SSD-based read and write-thru caching. Utilize fast magnetic media for persistent data reducing wear and tear on more costly flash SSD storage devices. |
Server Virtualization | Fast disk storage for data stores and virtual disks supporting VMware vSphere/ESXi, Microsoft Hyper-V, KVM, Xen and others. Holding virtual machines such as VMware VMDKs, along with Hyper-V and other hypervisor virtual disks. Compliment virtual server read cache and I/O optimization using SSD as a cache with writes going to fast SSHD. For example VMware V5.5 Virtual SAN host disk groups use SSD as a read cache and can use SSHD as the magnetic disk for storing data while boosting performance without breaking the budget or adding complexity. Speaking of Virtual, as mentioned the various proof points were run using Windows systems that were VMware guests with the SSHD and other devices being Raw Device Mapped (RDM) SAS and SATA attached, read how to do that here. Hint: If you know about the VMware trick for making a HDD look like a SSD to vSphere/ESXi (refer to here and here) think outside the virtual box for a moment on some things you could do with SSHD in a VSAN environment among other things, for now, just sayin ;). |
Virtual Desktop Infrastructure (VDI) | SSHD can be used as high performance magnetic disk for storing linked clone images, applications and data. Leverage fast read to support read ahead or pre-fetch to compliment SSD based read cache solutions. Utilize fast writes to quickly store data enabling SSD-based read or write-thru cache solutions to be more effective. Reduce impact of boot, shutdown, and virus scan or maintenance storms while providing more space capacity. |
Table 1 Example application and workload scenarios benefiting from SSHDs
Various workloads were run using Seagate Enterprise Turbo SSHD in the StorageIO lab environment across different real world like application workload scenarios. These include general storage I/O performance characteristics profiling (e.g. reads, writes, random, sequential or various IOP size) to understand how these devices compare to other HDD, HHDD and SSD storage devices in terms of IOPS, bandwidth and response time (latency). In addition to basic storage I/O profiling, the Enterprise Turbo SSHD was also used with various SQL database workloads including Transaction Processing Council (TPC); along with VMware server virtualization among others use case scenarios.
Note that in the following workload proof points a single drive was used meaning that using more drives in a server or storage system should yield better performance. This also means scaling would be bound by the constraints of a given configuration, server or storage system. These were also conducted using 6Gbps SAS with PCIe Gen 2 based servers and ongoing testing is confirming even better results with 12Gbs SAS, faster servers with PCIe Gen 3.
Copy (read and write) 80GB and 220GB file copies (time to copy entire file)
SQLserver TPC-B batch database updates
Test configuration: 600GB 2.5” Enterprise Turbo SSHD (ST600MX) 6 Gbps SAS, 600GB 2.5” Enterprise Enhanced 15K V4 (15K RPM) HDD (ST600MP) with 6 Gbps SAS, 500GB 3.5” 7.2K RPM HDD 3 Gbps SATA, 1TB 3.5” 7.2K RPM HDD 3 Gbps SATA. Workload generator and virtual clients ran on Windows 7 Ultimate. Microsoft SQL Server 2012 Database was on Windows 7 Ultimate SP1 (64 bit) 14 GB DRAM, Dual CPU (Intel x3490 2.93 GHz)), with LSI 9211 6Gbps SAS adapters with TPC-B (www.tpc.org) workloads. VM resided on separate data store from devices being tested. All devices being tested with SQL MDF were Raw Device Mapped (RDM) independent persistent with database log file (LDF) on a separate SSD device also persistent (no delayed writes). Tests were performed in StorageIO Lab facilities by StorageIO personal.
SQLserver TPC-E transactional workload
Test configuration: 600GB 2.5” Enterprise Turbo SSHD (ST600MX) 6 Gbps SAS, 600GB 2.5” Enterprise Enhanced 15K V4 (15K RPM) HDD (ST600MP) with 6 Gbps SAS, 300GB 2.5” Savio 10K RPM HDD 6 Gbps SAS, 1TB 3.5” 7.2K RPM HDD 6 Gbps SATA. Workload generator and virtual clients Windows 7 Ultimate. Microsoft SQL Server 2012 database was on Windows 7 Ultimate SP1 (64 bit) 14 GB DRAM, Dual CPU (E8400 2.99GHz), with LSI 9211 6Gbps SAS adapters with TPC-E (www.tpc.org) workloads. VM resided on separate SSD based data store from devices being tested (e.g., where MDF resided). All devices being tested were Raw Device Mapped (RDM) independent persistent with database log file on a separate SSD device also persistent (no delayed writes). Tests were performed in StorageIO Lab facilities by StorageIO personal.
Microsoft Exchange workload
Test configuration: 2.5” Seagate 600 Pro 120GB (ST120FP0021 ) SSD 6 Gbps SATA, 600GB 2.5” Enterprise Turbo SSHD (ST600MX) 6 Gbps SAS, 600GB 2.5” Enterprise Enhanced 15K V4 (15K RPM) HDD (ST600MP) with 6 Gbps SAS, 2.5” Savio 146GB HDD 6 Gbps SAS, 3.5” Barracuda 500GB 7.2K RPM HDD 3 Gbps SATA. Email server hosted as guest on VMware vSphere/ESXi V5.5, Microsoft Small Business Server (SBS) 2011 Service Pack 1 64 bit, 8GB DRAM, One CPU (Intel X3490 2.93 GHz) LSI 9211 6 Gbps SAS adapter, JetStress 2010 (no other active workload during test intervals). All devices being tested were Raw Device Mapped (RDM) where EDB resided. VM on a SSD based separate data store than devices being tested. Log file IOPs were handled via a separate SSD device.
Read more about the above proof points along view data points and configuration information in the associated white paper found here (no registration required).
Similar to flash-based SSD technologies the question is not if, rather when, where, why and how to deploy hybrid solutions such as SSHDs. If your applications and data infrastructures environment have the need for storage I/O speed without loss of space capacity and breaking your budget, SSD enabled devices like the Seagate Enterprise Turbo 600GB SSHD are in your future. You can learn more about enterprise class SSHD such as those from Seagate by visiting this link here.
Watch for extra workload proof points being performed including with 12Gbps SAS and faster servers using PCIe Gen 3.
Ok, nuff said.
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
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
Greg Schulz on break
