Tag: SVC

Posted on

IBMs Storwize or wise Storage, the V7000 and DFR

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
  • Expanding the industry scope and focus awareness around Data Footprint Reduction (DFR)
  • 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:

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

Posted on

HP Storage Virtualization Services Platform (SVSP)

Storage I/O trends

HP recently announced announced their new SAN Virtualization Services Platform (SVSP) which is an appliance with software (oh, excuse me, I mean platform) for enabling various (e.g. replication, snapshots, pooling, consolidation, migration, etc) storage virtualization capabilities across different HP (e.g. MSA, EVA and in "theory" XP) or in "theory" as well, 3rd party (e.g. EMC, Dell, HDS, IBM, NetApp, Sun, etc) storage.

Sure HP has had a similar capability via their XP series which HP OEMs from Hitachi Ltd. (who also supplies the similar/same product to HDS which HP competes with), however what?s different from the XP based solution and the SVSP is that one (SVSP) is via software running on an appliance and the other implemented via software/firmware on dedicated Hitachi based hardware (e.g. the XP). One requires an investment in the XP which for larger organizations may be practical while the other enables smaller organizations to achieve the benefits of virtualization capabilties to enable efficient IT not to mention help transition from different generations of HP MSA, EVAs to newer versions of MSAs and EVAs or even to XPs .Other benefits of solutions like the HP SVSP which also include the IBM SAN Volume Controller (SVC) include cross storage system, or cross storage vendor based replication, snapshots, dynamic (e.g. thin) provisioning among other capabilities for block based storage access.

While there will be comparisons of HP SVSP to the XP, those in many ways will be apples to oranges, the more applicable apples to apples comparison would be IBM SVC to HP SVSP, or, perhaps HP SVSP to EMC Invista, Fujitsu VS900, Incipient, Falconstor or ?Datacore based solutions.

With the HP SVSP announcement, I’m suspecting that we will see the re-emergence of the storage virtualization in-band vs. out-of-band including fast-path control-path aka split path approaches being adopted by HP with the SVSP not to mention hardware vs. software and appliance based approaches as was the case a few years ago.

This time around as the storage virtualization discussions heat up again, we should see and hear the usual points, counter points and continued talk around consolidation and driving up utilization to save money and avoid costs. However, as part of enabling and transforming into an efficient IT organization (e.g. a ?Green and Virtual Data Center?) that embodies efficient, productivity in an economical and environmental friendly manner, virtualization discussions will also re-focus on using management transparency to enable data movement or migration for load-balancing, maintenance, upgrades and technology replacement, BC/DR and other common functions to enable more work to be done in the same or less anoint of time while supporting more data and storage processing and retention needs.

Thus similar to servers where not all servers have been, will be or can be consolidated, however most can be virtualized for management transparency for BC/DR and migration, the same holds true for storage, that is, not all storage can be consolidated for different quality of service reasons, however, most storage can be virtualized to assist with and facilatate common management functions.

Here are some additional resources to learn more about the many faces of Storage Virtualizaiton and related topics and trends:

Storage Virtualization: Myths, Realities and Other Considerations
Storage virtualization: How to deploy it
The Semantics of Storage Virtualization
Storage Virtualization: It’s More Common Than You Think
Choosing a storage virtualization approach
Switch-level storage virtualization: Special report
Resilient Storage Networks (Elsevier)
The Green and Virtual Data Center (Auerbach)

Cheers – gs

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