Welcome to the Fall 2010 edition of the Server and StorageIO Group (StorageIO) newsletter. This follows the August 2010 edition building on the great feedback received from recipients.
You can access this news letter via various social media venues (some are shown below) in addition to StorageIO web sites and subscriptions. Click on the following links to view the Fall 2010 edition as an HTML or PDF or, to go to the newsletter page to view previous editions.
A few months ago IBM bought a Data Footprint Reduction (DFR) technology company called Storwize (read more about DFR and Storwize Real time Compression here, here, here, here and here).
A couple of weeks ago IBM renamed the Storwize real time compression technology to surprise surprise, IBM real time compression (wow, wonder how lively that market focus research group study discussion was).
Subsequently IBM recycled the Storwize name in time to be used for the V7000 launch.
Now to be clear right up front, currently the V7000 does not include real time compression capabilities, however I would look for that and other forms of DFR techniques to appear on an increasing basis in IBM products in the future.
IBM has a diverse storage portfolio with good products some with longer legs than others to compete in the market. By long legs, that means both technology and marketability for enabling their direct as well as partners including distributors or vars to effectively compete with other vendors offerings.
The enablement capability of the V7000 will be to give IBM and their business partners a product that they will want go tell and sell to customers competing with Cisco, Dell, EMC, Fujitsu, HDS, HP, NEC, NetApp and Oracle among others.
What about XIV?
For those interested in XIV regardless of if you are a fan, nay sayer or simply an observer, here, here and here are some related posts to view if you like (as well as comment on).
Back to the V7000
A couple of common themes about the IBM V7000 are:
It appears to be a good product based on the SVC platform with many enhancements
Branding the storwize acquisition as real-time compression as part of their DFR portfolio
Confusion about using the Storwize name for a storage virtualization solution
Lack of Data Footprint Reduction (DFR) particularly real-time compression (aka Storwize)
Yet another IBM storage product adding to confusion around product positioning
Common questions that Im being asked about the IBM V7000 include among others:
Is the V7000 based on LSI, NetApp or other third party OEM technology?
No, it is based on the IBM SVC code base along with an XIV like GUI and features from other IBM products.
Is the V7000 based on XIV?
No, as mentioned above, the V7000 is based on the IBM SVC code base along with an XIV like GUI and features from other IBM products.
Does the V7000 have DFR such as dedupe or compression?
No, not at this time other than what was previously available with the SVC.
Does this mean there will be a change or defocusing on or of other IBM storage products?
IMHO I do not think so other than perhaps around XIV. If anything, I would expect IBM to start pushing the V7000 as well as the entire storage product portfolio more aggressively. Now there could be some defocusing on XIV or put a different way, putting all products on the same equal footing and let the customer determine what they want based on effective solution selling from IBM and their business partners.
What does this mean for XIV is that product no longer the featured or marquee product?
IMHO XIV remains relevant for the time being. However, I also expect to be put on equal footprint with other IBM products or, if you prefer, other IBM products particularly the V7000 to be unleashed to compete with other external vendors solutions such as those from Cisco, Dell, EMC, Fujitsu, HDS, HP, NEC, NetApp and Oracle among others. Read more here, here and here about XIV remaining relevant.
Why would I not just buy an SVC and add storage to it?
That is an option and strength of SVC to sit in front of different IBM storage products as well as those of third party competitors. However with the V7000 customers now have a turnkey storage solution to sell instead of a virtualization appliance.
Is this a reaction to EMC VPLEX, HDS VSP, HP SVSP or 3PAR, Oracle/Sun 7000?
Perhaps it is, perhaps it is a reaction to XIV, and perhaps it is a realization that IBM has a lot of IP that could be combined into a solution to respond to a market need among many other scenarios. However, IBM has had a virtualization platform with a decent installed base in the form of SVC which happens to be at the heart of the V7000.
Does this mean IBM is jumping on the using off the shelf server instead of purpose built hardware for storage systems bandwagon like Oracle, HP and others are doing?
If you are new to storage or IBM, it might appear that way, however, IBM has been shipping storage systems that are based on general purpose servers for a couple for a couple of decades now. Granted, some of those products are based on IBM Power PC (e.g. power platform) also used in their pSeries formerly known as the RS6000s. For example, the DS8000 series similar to its predecessors the ESS (aka Shark) and VSS before that have been based on the Power platform. Likewise, SVC has been based on general purpose processors since its inception.
Likewise, while only generally deployed in two node pairs, the DS8000 is architected to scale into many more nodes that what has been shipped meaning that IBM has had clustered storage for some time, granted, some of their competitors will dispute that.
How does the V7000 stack up from a performance standpoint?
Interestingly, IBM has traditionally been very good if not out front running public benchmarks and workload simulations ranging from SPC to TPC to SPEC to Microsoft ESRP among others for all of their storage systems except one (e.g. XIV). However true to traditional IBM systems and storage practices, just a couple of weeks after the V7000 launch, IBM has released the first wave of performance comparisons including SPC for the V7000 which can be seen here to compare with others.
What do I think of the V7000?
Like other products both in the IBM storage portfolio or from other vendors, the V7000 has its place and in that place which needs to be further articulated by IBM, it has a bright future. I think that the V7000 for many environments particularly those that were looking at XIV will be a good IBM based solution as well as competitor to other solutions from Dell, EMC, HDS, HP, NetApp, Oracle as well as some smaller startups providers.
Comments, thoughts and perspectives:
IBM is part of a growing industry trend realizing that data footprint reduction (DFR) focus should expand the scope beyond backup and dedupe to span an entire organization using many different tools, techniques and best practices. These include archiving of databases, email, file systems for both compliance and non compliance purposes, backup/restore modernization or redesign, compression (real-time for online and post processing). In addition, DFR includes consolidation of storage capacity and performance (e.g. fast 15K SAS, caching or SSD), data management (including some data deletion where practical), data dedupe, space saving snapshots such as copy on write or redirect on write, thin provisioning as well as virtualization for both consolidation and enabling agility.
IBM has some great products, however too often with such a diverse product portfolio better navigation and messaging of what to use when, where and why is needed not to mention the confusion over the current product dejur.
As has been the case for the past couple of years, lets see how this all plays out in a year or so from now. Meanwhile cast your vote or see the results of others as to if XIV remains relevant. Likewise, join in on the new poll below as to if the V7000 is now relevant or not.
Note: As with the ongoing is XIV relevant polling (above), for the new is the V7000 relevant polling (below) you are free to vote early, vote often, vote for those who cannot or that care not to vote.
Here are some links to read more about this and related topics:
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
Over the past couple of years I routinely get asked what I think of XIV by fans as well as foes in addition to many curious or neutral onlookers including XIV competitors, other analysts, media, bloggers, consultants as well as IBM customers, prospects, vars and business partners. Consequently I have done some blog posts about my thoughts and perspectives.
Its time again for what has turned out to be the third annual perspective or thoughts around IBM XIV and if it is still relevant as a result of the recent IBM V7000 (excuse me, I meant to say IBM Storwize V7000) storage system launch.
In a nut shell, the V7000 is a new storage system with built in storage virtualization or virtual storage if you prefer that leverages IBM developed software from its San Volume Controller (SVC), DS8000 enterprise system and others.
Unlike the SVC which is a gateway or appliance head that virtualizes various IBM and third party storage systems providing data movement, migration, copy, replication, snapshot and other agility or abstraction capabilities, the V7000 is a turnkey integrated solution.
By being a turnkey solution, the V7000 combines the functionality of the SVC as a basis for adding other IBM technologies including a GUI management tool similar to that found on XIV along with dedicated attached storage (e.g. SAS disk drives including fast, high capacity as well as SSD).
In other words, for those customer or prospects who liked XIV because of its management GUI interface, you may like the V7000.
For those who liked the functionality capabilities of the SVC however needed it to be a turnkey solution, you might like the V7000.
For those of you who did not like or competed with the SVC in the past, well, you know what to do.
BTW, for those who knew of Storwize the Data Footprint Reduction (DFR) vendor with real time compression that IBM recently acquired and renamed IBM Real time Compression, the V7000 does not contain any real time compression (yet).
What are my thoughts and perspectives?
In addition to the comments in the companion post found here, right now Im of the mind set that XIV does not fade away quietly into the sunset or take a timeout at the IBM technology rest and recuperation resort located on the beautiful someday isle.
The reason I think XIV will remain somewhat relevant for some time, (time to be determined of course) is that IBM has expended over the past two and half years significant resources to promote it. Those resources have included marketing time, messaging space and in some instances perhaps inadvertinly at the expense of other IBM storage solutions. Simiarly, a lot of time, money and effort have gone into business partner outreach to establish and keep XIV relevant with those commuities who in turn have gone to their customers to tell and sell the XIV story to some customers who have bought it.
Consequently or as a result of all of that investment, I would be surprised if IBM were simply to walk away from XIV at least near term.
What I do see as happening including some early indicators is that the V7000 (along with other IBM products) now will be getting equal billing, resources and promotional support. Weather this means the XIV division finally being assimilated into the mainstream IBM fold and on equal footing with other IBM products, or, that other IBM products being brought up to an elevated position of XIV is subject to interpretation and your own perception.
I expect to continue to see IBM teams and subsequently their distributors, vars and other business partners get more excited talking about the V7000 along with other IBM solutions. For example, SONAS for bulk, clustered and scale out NAS, DS8000 for high end, GMAS and Information Archive platforms as well as N and DS3K/DS4K/DS5K not to mentiuon the TS/TL backup and archive target platforms along with associated Tivoli software. Also, lets not forget about SVC among other IBM solutions including of course, XIV.
I would also not be surprised if some of the diehard XIV loyalist (e.g. sales and marketing reps that were faithful members of Moshe Yani army who appears to be MIA at IBM) pack up their bags and leave the IBM storage SANdbox in virtual protest. That is, refusing to be assimilated into the general IBM storage pool and thus leaving for Greener IT pastures elsewhere. Some will stick around discovering the opportunities associated with selling a broader more diverse product portfolio into their target accounts where they have spent time and resources to establish relationships or getting thier proverbial foot in the door.
Consequently, I think XIV remains somewhat relevant for now given all of the resources that IBM poured into it and relationships that their partner ecosystem also spent on establishing with the installed customer base.
However, I do think that the V7000 despite some confusion (here and here) around its recycled Storwize name that is built around the field proven SVC and other IBM technology has some legs. Those legs of the V7000 are both from a technology standpoint as well as a means to get the entire IBM systems and storage group energized to go out and compete with their primary nemesis (e.g. Dell, EMC, HP, HDS, NetApp and Oracle among others).
As has been the case for the past couple of years, lets see how this all plays out in a year or so from now. Meanwhile cast your vote or see the results of others as to if XIV remains relevant. Likewise, join in on the new poll below as to if the V7000 is now relevant or not.
Note: As with the ongoing is XIV relevant polling (above), for the new is the V7000 relevant polling (below) you are free to vote early, vote often, vote for those who cannot or that care not to vote.
Here are some links to read more about this and related topics:
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
Have you heard or read the reports and speculation that VTLs (Virtual Tape Libraries) are dead?
It seems that in IT the all to popular trend is to declare something dead so that your new product or technology can have a chance of making it in to the market or perhaps seen in a better light.
Sometimes this approach works to temporary freeze the market until common sense and clarity returns to the market or until something else fun to talk about comes along and in other cases, the messages can fall on deft ears.
The approach of declaring something dead tends to play well for those who like shiny new toys (SNT) or new shiny toys (NST) and being on the popular, cool trendy bandwagon.
Not surprisingly, while some actual IT customers can fall into the SNT or NST syndrome, its often the broader industry including media, bloggers, analysts, consultants and other self proclaimed or anointed pundits as well as vendors who latch on to the declare it dead movement. After all, who wants to talk about something that is old, boring and already being sold to paying customers who are using it. Now this is not a bad thing as we need a balance of up and coming challengers to keep the status quo challenged, likewise we need a balance of the new to avoid death grips on the old and what is working.
Likewise, many IT customers particularly larger ones tend to be very risk averse and conservative with their budgets protecting their investments thus they may only go leading bleeding edge if there is a dual redundant blood bank with a backup on hot standby (thats some HA humor BTW).
Another reason that declaring items dead in support of SNT and NST is that while many of the commonly declared dead items are on the proverbial plateau of productivity for IT customers, that also can mean that they are on the plateau of profitability for the vendors.
However, not all good things last and at sometime, there is the need to transition from the old to the new and this is where things like virtualization including virtual tape libraries or virtual disk libraries or virtual storage library or what ever you want to call a VxL (more on what a VxL is in a moment) can come into play.
I realize that for some, particularly those who like to grasp on to SNT, NST and ride the dead pool bandwagons this will probably appear as snarky or cynical which is fine, after all, for some, you should be laughing to the bank and if not, you may in fact be missing out on an opportunity for playing in the dead pool marketing game.
Now back to VxL.
In the case of VTLs, for some it is the T word that bothers them, you know T as in Tape which is not a SNT or NST in an age where SSD has supposedly killed the disk drive which allegedly terminated tape (yeah right). Sure tape is not being used as much for backup as it has in the past with its role shifting to that of longer term retention, something that it is well suited for.
For tape fans (or cynics) you can read more here, here and here. However there is still a large amount of backup/restore along with other data protection or preservation (e.g. archiving) processing (software tools, processes, procedures, skill sets, management tools) that still expects to see tape.
Hence this is where VTLs or VxLs come into play leveraging virtualization in an Life Beyond Consolidation (and here) scenario providing abstraction, transparency, agility and emulation and IMHO are still very much alive and evolving.
Ok, for those who do not like or believe in or of its continued existence and evolving role, substitute the T (tape) with X and you get a VxL. That is, plug in what ever X word that makes you happy or marketable or a Shiny New TLA. For example Virtual Disk Library, Virtual Storage Library, Virtual Backup Library, Virtual Compression Library, Virtual Dedupe Library, Virtual ILM Library, Virtual Archive Library, Virtual Cloud Library and so forth. Granted some VxLs only emulate tape and hence are VTLs while others support NAS and other protocols (or personalities) not to mention functionality ranging from replication, DFR as well as automated policy management.
However, keep in mind that if your preference is VTL, VxL or what ever other buzzword bingo name that you want to use or come up with, look at how virtualization in the form of abstraction, transparency and emulation can bridge the gap between the new (disk based data protection) combined with DFR (Data Footprint Reduction) and the old (existing backup/restore, archive or other management tools and processes.
Here are some additional links pertaining to VTLs (excuse me, VxLs):
Virtual tape libraries: Old backup technology holdover or gateway to the future?
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
This is part of an ongoing series of short industry trends and perspectives (ITP) blog posts briefs based on what I am seeing and hearing in my conversations with IT professionals on a global basis.
These short posts compliment other longer posts along with traditional industry trends and perspective white papers, research reports, videos, podcasts, webcasts as well as solution brief content found a www.storageioblog.com/reports and www.storageio.com/articles.
If you recall from previous posts including here, here or here among others, Data Footprint Reduction (DFR) is a collection of tools, technologies and best practices for addressing growing data storage management and cost impacts.
DFR encompasses many different tools, techniques and technologies across various applications ranging from active or primary storage to secondary and inactive along with backup and archive.
Some of the technologies techniques and technologies include archiving, backup modernization, compression, data management, dedupe, space saving snapshots and thin provisioning among others.
Following are some links to various articles and commentary pertaining to DFR:
Using DFR including dedupe and compression to defry storage and management costs
Deduplicate, compress and defray costs of data storage management
Virtual tape libraries: Old backup technology holdover or gateway to the future?
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 de-dupe vendors like to debate details of their solutions, ranging from compression or de-dupe ratios, to hashing and caching algorithms, to processor vs. disk vs. memory, to in-band vs. out-of-band, pre or post processing among other items. At times the dedupe debates can get more lively than a political debate or even the legendary storage virtualization debates of yester year.
However one item that an IT professional recently mentioned that is not being addressed or talked about during the de-dupe debates is how IT customers will get around vendor lock-in. Never mind the usual lock-in debates of whose back-end storage or disk drives, whose server a de-dupe appliance software runs and so forth.
The real concern is how data in the future will be recoverable from a de-dupe solution similar to how data can be recovered from tape today. Granted this is an apple to oranges comparison at best. The only real similarity is that a backup or archive solution sends a data stream in a tar-ball or backup or archive save set or perhaps in a file format to the tape or de-dupe appliance. Then, the VTL or de-dupe appliance software puts the data into yet another format.
Granted not all tape media can be interchanged between different tape drives given format, generations and of course using the proper backup or archive application to un-pack the data for use. Probably a more applicable apple to oranges comparison would be how will IT personal get data back from a VTL (non de-duping) disk based storage system compared to getting data back from a VTL or de-dupe appliance.
Today and for the foreseeable future the answer is simple, if your pain point is severe and you need the benefits of de-dupe, then the de-dupe software and appliance is your point of vendor lock-in. If vendor lock-in is a main concern, take your time, do your homework and due diligence for solutions that reduce lock-in or at least give a reasonable strategy for data access in the future.
Welcome to the world of virtualized data and virtualized data protection. Here?s the golden rule for de-dupe and that is like virtualization, who ever controls the software and management meta data controls the vendor lock-in, good, bad or in-different, that?s the harsh reality.
For the record, I like de-dupe technology in general as part of an overall data footprint reduction strategy combined with archiving and real-time compression for on-line and off-line data. I see a very bright future for it moving forward. I also see many of the heavy thinking and heavy lifting issues to support large-scale deployments and processing getting addressed over time allowing de-dupe to move from mid markets to large-scale mainstream adoption.
Now, back to your regularly scheduled de-dupe debate drama!
