Around the Storage Block

Definitive agreement to acquire IBRIX

CalvinZ — Fri, 17 Jul 2009 11:46:00 GMT

By Calvin Zito

Today, HP announced a definitive agreement to acquire IBRIX. IBRIX is a privately held company in Billerica, MA. The company's flagship product is called IBRIX Fusion. It's a software-based parallel file system. You can read more about it on the IBRIX web site but a few highlights are:

Scalability - 1000's of nodes in single namespace
Read-only caching nodes
Data Protection with replication and snapshots
Data Movement/Content Handling
Data Efficiency via storage tiering

These capabilities combined with HP infrastructure help remove complexity and bottlenecks from traditional siloed architectures and drive down costs through the use of common components. And just as HP LeftHand P4000 storage solutions deliver a scale-out block storage solution, IBRIX provides scale-out file services.

Before anyone asks what did HP pay or what is IBRIX revenue, I won't disclose either. The acquisition is expected to close in 30 days.

I think this will be a great fit for HP and our customers. IBRIX has been an HP partner for three years and we have joint customers. The IBRIX software works with our HP StorageWorks SANs, x86 HP ProLiant rack-mount and blade servers as well as HP ProCurve Ethernet switches.

Here's a link to the press release.

This should be interesting!

Tweet this!

Why NetApp Gets Blogged

CalvinZ — Thu, 16 Jul 2009 21:46:00 GMT

By Jim Haberkorn

Before I begin, I don't know how other readers react to it, but whenever I see someone get frustrated and lose their temper on a blog, it's usually because deep inside they know they are losing. Maybe that's not how it is portrayed in movies and books, but in real life, that's how it works.

For those who have come in late to this discussion, (see the discussion on our previous post titled "Are NetApp performance claims logical") this entire exchange I am having with Alex from NetApp actually started last November when I analyzed a NetApp white paper attacking the HP StorageWorks EVA, and pointed out its inconsistencies and highly questionable tactics. At the same time, an HP engineer, initiated a blog in which he discussed performance testing he'd completed on a NetApp filer vs. an EVA. I'm pointing everyone now to the last of the four blogs our engineer posted titled "Making sense of WAFL Part 4" as this one more specifically addresses the performance issue Alex raised in his blog comments I referenced above. I have made the comment several times that HP won that discussion. I stand by that, but in the end, it's up to every reader to decide for themselves.

Now, Alex asked if I would explain why NetApp's having a file system optimized for writes has any bearing on NetApp storage performance. Here is the answer: The NetApp file system - WAFL - is optimized for writes. Basically, WAFL will write to the nearest available free space to where the disk head is. I believe Alex conceded that. The rest of the arrays that we have tested in our lab take a different tack; they optimize for reads by updating blocks in place. And why? Because in block environments most applications are read intensive as opposed to write, and you want to keep the blocks for databases as contiguous as possible so they can be read faster with a minimum of disk head movement. Oracle, for example, depends heavily on locality of reference for its performance. This NetApp write-optimization was designed into the NetApp file system many years before they ever contemplated going into block storage, and the trade-off is that their read performance is impacted relative to the competition. Now, I don't consider this single point to be the final word on NetApp filer performance - all storage systems have their peculiarities - but coupled with some of NetApp's other design decisions and some of the testing we've presented, I think we are building a pretty good case in regards their block performance behavior.

So, forget for a second the tests that each vendor runs and publishes on their own product, forget that all of us are paid to ensure our company's success in the market, forget that we all like to win debates; the point I keep hammering home in my blog posts through various arguments, some technical and some logical, is that the block performance, usable capacity, and cost of ownership claims NetApp makes about its technology do not add up. They don't add up in our lab when we test them, and they don't add up logically when we analyze their technology. Oh, every vendor puts its best foot forward - we all expect that, but, in my opinion, some of NetApp's claims deserve special attention.

Finally, there are two things that NetApp has done over the past several years that, in my opinion, have seriously hurt their credibility among people who know storage. One was the capacity guarantee program that I have previously blogged about, and the second was their Wyman/Mercer cost of ownership white paper where they attacked the HP EVA, and which I also blogged.

If any reader wants to understand why I question some of NetApp's claims about itself, those two blogs would be a good place to start.

Best regards,

Jim

Tweet this!

The latest on HP Storage Essentials

CalvinZ — Thu, 16 Jul 2009 04:23:00 GMT

By Nimish Shelat, Product Manager

We recently released a new product - HP Storage Essentials Performance Edition (SEPE) software. It's got some great new capabilities in it that I think you'll like, so I'd like to point you to a few different things around our hp.com web.

Look for information about the HP Storage Essentials Storage Resource Management (SE) software on the hp.com product page. And new stuff on the recently launched SEPE software can be found on it's hp.com page.

Beyond what you find at the respective product pages, you will find additional information in the product data sheets.

Immerse yourself and increase your knowledge around Storage Essentials with a set of white papers.

Now that you know what SE has to offer, take a look at how other customers have applied it to their advantage via the following case studies

And finally get more on SE at www.hp.com/go/getSE

More Case studies
Product functionality Demonstration
ROI Analysis paper
On Demand "Capacity Management" webinar
On Demand "Manage Physical and Virtual Storage " webinar

Tweet this!

Are NetApp performance claims logical?

CalvinZ — Tue, 14 Jul 2009 16:31:00 GMT

By Jim Haberkorn

We at HP like to test competitor arrays and see if we can match their published results. In our internal testing, only the NetApp results are so out of whack that we are left scratching our heads over what the heck they did to achieve them. So for NetApp, we have published our results and challenged them on it. And in fact, the NetApp folks at first put up a vigorous defense which included a fair number of attacks on the integrity of our engineer who did the testing, but then as the discussion progressed, the NetApp enthusiasts went quiet. See the blog post titled Making sense of WAFL.

So, we've argued against NetApp performance with numbers and the argument got very technical, and we won. But recently, NetApp, on one of its blogs, waited till the discussion had died down and then, to our surprise, acted as if they had won the discussion and that the issue now was totally resolved and that they had once again defeated the forces of evil. So, now NetApp has left us no choice but to try a new tactic: Logic.

The NetApp counter-arguments on the subject of their performance are becoming more and more like the man who admits it is raining, admits he is standing outside, admits he doesn't have an umbrella, but then denies he is getting wet. If you ask a NetApp engineer these performance related questions you will get the answer 'yes' to all of them.

Do you build your LUNs on top of a file system?
Does your file system write only to free block space rather than updating the old blocks?
Do you ship a de-fragmentation tool on every NetApp filer?
Do you use software RAID?
Does your file system spread the metadata over the entire disk system?
Does WAFL require you to build secondary inode trees if the file is bigger than 64KB?
Can IOs to a particular file be serviced by only a single controller in a NetApp cluster?
Do NetApp snaps reside in the same disk group as the primary volume?
Is only a quarter of your NVRAM usable?
Is the processing power of your largest filer, rated by NetApp to handle 1176 disks, based on a maximum 8 x 2.6 GHz AMD dual core Opteron processors - about the same processing power as a Proliant DL785?
Is your file system optimized for writes?

But, if you then ask a NetApp blogger, if taken together, do these features negatively impact NetApp performance, you'll get an answer to the effect, "What are you crazy? How did you ever come up with that conclusion?"

Now, I am sure that every one of those eleven engineering decisions was made by NetApp for a logical reason from their perspective. But I am also sure that every one of them has a negative impact on NetApp performance, and the cumulative effect is pretty significant in most real-world environments. And those features put NetApp at a huge performance disadvantage in a storage world dominated by vendors who don't require the extra overhead of having to build LUNs on top of file systems, or don't need to ship a de-fragmentation tool with their array, or don't use software RAID.

Conclusion: Is every NetApp NAS customer unhappy with NetApp performance? Answer: No, of course not. But, of the storage arrays we've tested, is NetApp block performance the worst by a pretty wide margin? Yeah, looks that way to us.

Best regards,

Jim

Tweet this!

New 6Gb SAS, vote for our blog, and Connect Community!

CalvinZ — Mon, 13 Jul 2009 18:07:00 GMT

By Calvin Zito

I don't usually cover multiple topics in one post but I'm afraid if I don't do that today, it may take all week to talk about these three topics. So here they are:

New 6Gb SAS

Today, HP is announcing new 6Gbit per second SAS. My colleague Sonia Mathur on the HP ProLiant team has a blog post talking about it. You can find her post by clicking here. Here's also a link to an hp.com page that has more information including a mention of a new 6Gb/s SAS enclosure that we'll have in a few months.

Vote for our "Around the Storage Block" blog

StorageMonkeys.com is a storage community. On their home page, they describe themselves as a place to:

Connect and expand your network
View profiles and add new friends
Share your photos and videos
Create your own group or join others

There are lots of storage people on the site and they have over 500 members. On the bottom of their page, they list their top 10 blogs and top 10 vendor blogs. They are going to update their vendor blog list and are taking votes to determine which 10 vendor blogs to list. If you've enjoyed our blog and have found it useful, please take a few minutes and vote for us. Here's a link to their poll where you can vote.

HP community with Connect

And speaking of communities, I wanted to mention Connect. Connect is an independent users group of HP users. From their website, they describe the reasons for joining as: "The Connect Community is where you can connect with other HP business professionals and maximize the return on investment attainable from HP products and technologies. Use our online resources, training and webcasts, or participate in our online community discussions, blogs and groups - all while building a network of professional contacts and friends. Strengthen your voice to HP by joining today."

Before heading off to HP Technology Forum, I was poking around Connect's community site and noticed that they had groups for lots of HP technologies (e.g. OpenVMS, HP-UX, BladeSystem, NonStop, and others) but nothing for storage. I asked the question of a few people and before I knew it, I was promoted to be the manager of the new HP StorageWorks group on Connect's site. At HP Tech Forum, I was able to meet a number of people from Connect. Nina Buik is the President of Connect and is one of the most energetic people I've ever met. Meeting her face to face for the first time was a funny situation - I was sitting in the front row at HP Tech Forum twittering during the opening keynotes while she was reading the tweets one row behind me, not knowing I was right in front of her. Brad Harwell who sits on the Connect board and works for HP pointed out that we were right there and we had a good laugh about it.

Speaking of Tech Forum, there were a few videos that SDRNews.com did with at Tech Forum that you might find interesting:

Interview with Nina Buik, giving a great overview of Connect
Interview with Chris Koppe, currently VP of Connect and will become president in January
Awards at HP Tech Forum Luau, volunteer of the year and the HP recognition award

All of that said, I want to recommend that if you aren't already part of the 50,000 Connect members and you are an HP user, that you consider joining today.

Tweet this!

Box score for NetApp capacity calculator

CalvinZ — Tue, 07 Jul 2009 21:34:00 GMT

By Calvin Zito

So let me catch you up on what's happened here. We posted a blog recently talking about our HP Virtualization Bundles - bundles that include servers, storage, virtualization software, networking - essentially to make it very easy for midsize customers who are implementing virtual server environments to reduce the complexity of bringing their infrastructure up. Alex McDonald, whose role at NetApp is competitive analysis, dropped a comment pointing to a blog post he had trying to cast HP LeftHand solutions as having poor capacity utilization.

I can only assume that NetApp is seeing increased competition from HP LeftHand which I would totally expect now that the worldwide reach of HP is behind this great iSCSI-based solution. There were a lot of comments on his blog on the topic and we also posted something here by Jasen Baker, one of our field storage architects.

So, get out your scorecards and let me try to step you though the box score.

NetApp bats first

Alex got to bat first and we're the home team, so we'll bat last. Alex started it off by questioning a few things that Chris McCall had said in a video interview from HP Tech Forum. He first questioned why Chris worked for our Unified Storage Division since our HP LeftHand solution is an iSCSI SAN based system (SAN only, no NAS). I'm just wondering why Alex cares so much about our internal organization but I'm sorry to say we'll just have to keep Alex hanging on this one.

Next Alex questioned comments Chris made about the HP LeftHand solution being "green". Alex thought he had something here (though as I'll discuss in a moment, pretty much ignored everything Chris said about thin provisioning) and developed his LeftHand Capacity Calculator. Here's a look at it:

That's it - that's the calculator. Alex said all you have to do is stick in your total disk space and you always know your usable capacity with HP LeftHand. NetApp looks like they have a big lead but now the home team gets to step up to the plate.

HP's turn at bat

Alex demonstrated his lack of understanding of HP LeftHand and here's where he goes wrong:

Alex stated that his little calculator always worked. Jasen Baker wrote a nice post pointing out the faulting logic Alex used. The first issue is that our HP LeftHand solution can use either RAID 5, 6, or 10. So for example, on our HP LeftHand P4300 Storage System, RAID 5 utilization is 87.5% meaning it's a 7+1 configuration. In fact, I'm looking at a sizing tool and with a 6 TB system using RAID 5 with no Network RAID, all things considered, capacity utilization is over 78%. Isn't that a balk on our scorecard? Alex's "always" right calculator appears to be broken but there's more.
The big point Alex missed and continues to be confused about is Network RAID. This is a pretty cool and unique capability of the HP LeftHand solutions. As Jason said, "Network RAID is a unique feature of the HP LeftHand SAN that allows you to CHOOSE on a per volume basis how many replicated copies of your LUN / VOLUME are distributed across the SAN." It's an optional feature and Jasen went on to say, "Network RAID is dynamic, because you as the customer choose to turn it on or off depending on the application protection needs. With that choice, you select the use of additional capacity to protect your data in a manner superior to standard hardware RAID." Let me summarize what this means - Network RAID isn't always used and can be turned on when it's needed. Do customers use it? Of course! Do customers use it with all of their data? Probably not! Score that as an error and a run cored. Seems like the calculator's keys are broken.
And I noticed something else that just has me shaking my head; George Wagner is an HP LeftHand expert. On Alex's blog post, he pointed out that Network RAID "provides HA [high availability] for the volumes that require it". What was Alex's response to this? "Sorry, George it's got zero to do with HA". Wow - Alex thinks he knows more about HP LeftHand than HP does. Sorry Alex, the whole reason for Network RAID is to improve HA. John Spiers, a founder of LeftHand and former CTO said this, "When using Network RAID 2 it protects you from multiple disk faults, complete array faults and site faults with auto failover and failback.". Network RAID is a choice point - a great, low cost way to build HA into your HP LeftHand SAN. What's the cost? Unlike NetApp who will charge you for equivalent functionality and also lower your utilization, the only cost with HP LeftHand is the disk space used. And again, we give you control of this at a volume level and let you turn it off as you determine. If you want to compare capacity utilization of the two solutions then it has to be an apples to apples configuration. Alex is doing that and the comparison is bogus. I'd also suggest that the cost of the solution should be part of the comparison and I'm sure Alex nor NetApp want you to know the cost difference between the solutions. The umpire just discovered that Alex was using an illegal bat so his at bat suddenly isn't looking so good.
The other major flaw in Alex's calculator is how we use thin provisioning. Thin provisioning on our solution is leveraged across all of the storage objections: volumes, snapshots, clones, and remote copies. What does this mean? HP LeftHand uses something called "allocate on write" - no storage capacity is reserved up front for any storage object, be it a volume, snapshot, etc. Why does this matter? Because other vendors, NetApp included, have to set a reserve for each of those things. I don't know what their reserve - NetApp will have to answer that. And if you don't use the reserve, guess what - it's wasted space that can't easily be reclaimed. Whoa - it's a whole different game now, isn't it?

If you watch Chris' video, you'll notice that Alex didn't raise any questions about the great fit LeftHand has with HP. Chris talked about a day when we'll have HP LeftHand running inside our HP BladeSystem for a comprehensive solution - networking with Virtual Connect, storage, servers - all in an efficient infrastructure. Alex didn't raise this point because it's a competitive disadvantage. And of course he completely ignored that we have our virtualization bundle today... and I think you get the point why he ignored.

The last thing I'll mention is the overall value of the two solutions. Let's keep this high-level as I want to wrap on this:

Value add software like asynchronous replication, synchronous replication, clustering, and performance monitoring can cost upwards of $120,000 in licensing fees with NetApp. How much does the value add software cost with HP LeftHand? $0. Plug that number into your calculator and the value is clear. So while NetApp continues to argue capacity utilization (which they have wrong), they won't tell you about how much extra you'll have to pay to get what is included for free with HP LeftHand.
The HP LeftHand SAN pricing model is pay-as-you-grow. You buy capacity or performance when you need it rather than ahead of time as is the case with the NetApp architecture. You buy only what you need and scale your capacity and performance non-disruptively online with HP LeftHand SANs.
With NetApp, you'll have to oversize your controller today to accommodate future growth, buy more capacity than you need and as you fill your NetApp array and see your performance drop, you'll have to buy additional capacity to address the drop in performance. That point about performance tanking as they fill up their array may be something you hadn't heard of before but here's a chart from NetApp that shows that: Phew... Alex's calculator seems to have run out of batteries!
With HP LeftHand, thin provisioning is leveraged throughout the architecture - with NetApp, its limited and space is committed when you create objects. Remember, HP LeftHand uses allocate on write - making the most of the storage capacity. With our thin provisioning, the capacity is always available to you when you need it without any pre-commit of space.

Well, I think we've clearly demonstrated that the NetApp calculator is missing a few keys, out of batteries, and generally on the fritz. There have been several folks engaged in this discussion and Alex doesn't seem to want to admit anything he's stated is wrong. I also think that customers Alex has focused on a very narrow focus (capacity utilization) when what you really care about is the cost - which capacity utilization impacts. Every decision you make has a cost tradeoff - when decided on Fibre Channel or iSCSI, cost as at the core of that decision. So I'd challenge Alex that if you want to keep the discussion going, let's raise it to the level that customers will care - and get a new calculator.

Tweet this!

Blog wars and cat fights - do you care?

CalvinZ — Thu, 02 Jul 2009 18:07:00 GMT

By Calvin Zito

Alex McDonald, who I think is a competitive analyst over at NetApp, has been trying his best to make our HP LeftHand solutions look bad compared to his products. It's gone back and forth with lots of comments and posts on both this blog and Alex's. This has me thinking about the value of these public cat fights and whether or not they are helping our customers to better sort fact from fiction. I'm watching my metrics on "page views" on our blog and clearly, a lot of you like to read these type of blog posts.

Every storage vendor (and really, every product team) makes engineering choices that results in strengths and weaknesses in what they offer. Let me give a simplified theoretical example to help bring what I'm saying to life. Let's say that Company A's product costs 10% more than Company B's, but Company A's widget has a total cost of ownership that is 1/3 of Company B's even with the higher purchase price. Would you as a customer care about a 10% price difference knowing that the TCO is so much better? You certainly would want to know but I don't think you make that a deciding factor (unless the extra 10% means you go over budget). So to bring it back to something concrete, is it helpful for you when to hear these discussions about a specific product detail without the broader context of the benefits? In the current case with NetApp, I tried to bring the discussion back to that broader context on Alex's blog but he and his colleagues were singularly focused on nothing other than capacity utilization and ignored my raising the benefits of our virtualization bundles (and I guess I shouldn't be surprised about that since NetApp only has storage - no servers, networking, virtualization software, etc.).

I'm not sure I can answer whether or not customers find value in these types of squabbles yet but I'm sure it's something I'll talk about in a future blog post. I'm interested in what you think - is it helping you better understand the products, creating more confusion, or is it just fun to watch a vendor debate in the blogosphere? My intent really is to make our blog a place where customers can learn more about storage, HP StorageWorks, and infrastructure convergence. Feel free to drop me an email by clicking on the "Contact" link on the right-hand navigation of this blog or click on this text.

In my next post, I'll summarize where the specific discussion with NetApp has gone over the last several days - that is unless I get an overwhelming response that you don't see any value in these debates.

Tweet this!

HP LeftHand capacity

CalvinZ — Tue, 30 Jun 2009 21:37:00 GMT

By Jasen Baker, Storage Architect

I once heard that in communicating your opinion or differences, you should not use personal phrases, such as "you always", "you never", "every time", etc. These make broad, sweeping assumptions which seldom reflect the truth, especially when communicating differences in products. Attention to detail, such as quoting someone's name when providing a source of argument, or consolidating many options into a single unified calculation over simplify and often times mislead readers who are looking for educated facts instead of uninformed guesses.

As an example, take a look at online value calculators. There are calculators for mortgages, calculators for the national debt, ROI calculators, and even storage capacity calculators. They do their best to point you in a certain direction, to narrow down the scope of what you will be working with, but don't truly take in all the factors, hence why the infamous asterisk * exists!

In responding to a recent blog post referencing "LeftHand Capacity Calculator" crafted to demonstrate useable percentages of available capacity, it's supposed to ALWAYS, come out this way.

To quote the blog, "That's because, regardless of how small or how large your LHN SAN, it's always:"

Image "courtesy" of NetApp

There's that word again, always.

In storage, there are useable capacities that always occur. That always, is the space you lose as a result of hardware RAID, well, unless it's hardware RAID 0.

First, the HP LeftHand storage nodes can be configured in RAID 5, 6, or RAID 10, all with various useable capacities. This calculator only has RAID 5. Why choose? The reasons are many, but most common are performance, protection and capacity. You choose, it's no different with us or any other vendor solution.

Second, "Disk rightsizing", a term used to explain why that 1TB hard drive you bought only shows ~932GB useable. Why? Well, that's because the hard drive vendors view 1MB as 1000 kbytes while your Operating system views 1MB as 1024 kbytes. That extra 24 bytes adds up which is why you truly don't get the actual hard size useable (this is before formatting it with your favorite file system as well). Again, nothing specific to use or any other vendor solution.

Third, Network RAID. What is Network RAID? Network RAID is a unique feature of the HP LeftHand SAN that allows you to CHOOSE on a per volume basis how many replicated copies of your LUN / VOLUME are distributed across the SAN. What is unique about this is it's DYNAMIC. You get to choose which volumes have it and which do not. What it offers you is the ability to survive entire node failures; if your nodes are physically separated and you lose an entire physical sites, your data remains online and available.

Hardware RAID is usually a set it and forget it configuration, and it's seldom changed. Network RAID is dynamic, because you as the customer choose to turn it on or off depending on the application protection needs. With that choice, you select the use of additional capacity to protect your data in a manner superior to standard hardware RAID. They key point here is choice. You have the choice, and if you change your mind, the system is dynamic and allows you to change the level of data protection on a per volume basis as often as desired. Unfortunately, a calculator without options isn't very reflective of real life. In essence, the above calculator was missing the infamous *Your mileage may vary...

To quote our previous blog poster "Unlike NetApp's space efficiency calculator, the LHN Duplication Calculator I've designed doesn't have any input fields or buttons..."

The HP Centralized Management interface WE designed, does have buttons, and even drop-downs, allowing you to choose how your capacity is used, ALWAYS.

Tweet this!

Video interview from Dave Roberson, Sr VP and GM of StorageWorks

CalvinZ — Wed, 24 Jun 2009 06:17:00 GMT

By Calvin Zito

Last week at HP Technology Forum, I arranged to have our Senior VP and General Manager of HP StorageWorks interviewed by SDR News and Shane Pitman from Neowin.net. Dave was a very busy guy at the event and we had to reschedule the interview for Thursday but I was really glad that we were able to make this happen. The interview covered a lot of ground and is worth a look. Click here to see the video.

Tweet this!

Making virtualization easy

CalvinZ — Mon, 22 Jun 2009 15:24:00 GMT

By John Spiers (Former CTO and a founder of LeftHand Networks, now working for HP StorageWorks)

If you haven't taken a look at the new HP virtualization bundles, you definitely should. The virtualization bundles provide an end-to-end solution that delivers application high availability without external storage. Sounds like a contradiction? Read on!

It has been characterized as a "mini-Matrix system", offering server, virtualization, storage and networking products configured and tested to reach the full potential of server virtualization. These bundles include ProLiant G6 servers, VMware's vSphere 4 virtualization software, ProCurve networking Switches, HP LeftHand P4000 and HP's Insight Control Suite (ICE) for management.

My colleague recently wrote about the virtualization bundles and it got me thinking about how unique these bundles are for SMBs and other companies looking to improve application availability and cost savings through virtualization.

Allow me to elaborate...

HP positions these easy-to-buy bundles as solutions that reduce the complexity and uncertainty of virtualization. You have rack or tower servers, highly available shared storage and networking with simple, centralized management.

Looking at the value of the bundles, Illuminata recently stated, "A major contributor to the value of what HP offers in these bundles is the fact that the requirement for acquiring, integrating and testing external SAN storage can be avoided."

We address one of the main hurdles on the way to server virtualization: the need for shared storage. Without shared, highly available storage VMotion, VMware HA or VMware FT cannot happen automatically, virtual machines cannot be moved and application users cannot be shielded from the outage of a physical server. If all you do is consolidate many virtual machines onto one physical server, you have basically placed all bets in one basket (traditionally knows as all eggs in one basket). Some workloads and business requirements can tolerate this scenario, yet many cannot. With HP LeftHand Virtual SAN Appliance, the internal server disks (and directly attached disks) can be pooled in a VMware environment and act like a pool of storage, like a virtual SAN. The IT administrator ends us using a SAN without ever having bought a SAN, a physical SAN that is!

The majority of these Virtualization Bundles include physical SAN nodes. And another secret is that servers and the SAN can not only failover, but automatically failback and incrementally re-sync the data on the primary SAN without manual intervention and with complete application data consistency using VMware's vSphere Fault Tolerance capability. Not to mention that these meaty bundles include software for snapshots, cloning, remote replication, thin provisioning, multi-site synchronous replication and advanced performance monitoring - at no additional charge.

With this new technology combination, HP is clearly establishing a new paradigm in server and storage virtualization. This is what customers have been asking for, for years and they can finally get it. I don't know of a single vendor server and SAN solution in the market today that is comparable.

Tweet this!

Day 3 (Wednesday) Videos from HP Tech Forum

CalvinZ — Thu, 18 Jun 2009 04:44:00 GMT

By Calvin Zito

Today at HP Technology Forum we had a couple of our HP StorageWorks exec interviewed by Shane Pitman Editor in Chief from Neowin.net with some help from Andy McCaskey from SDR News.

The first one was with Brian Ignomirello, who I talked about in a my Day 2 Summary post, and is our CTO of the Americas HP StorageWorks Division. I can't embed the video on the blog but here's a link where you watch the interview with Brian: http://bit.ly/4hF1Ju. Brian gives a brief overview of StorageWorks, talks about storage technology trends, and some of his priorities as CTO.

The next interview was with Chris McCall. Chris manages a team of product marketing managers in our Unified Storage Division and recent came to HP via our acquisition of LeftHand Networks. Here again is a link to his interview: http://bit.ly/SgPmy.

One other note - I'll post a more complete Day 3 summary in the next couple of days as I am traveling back home tomorrow to celebrate my son's 10th Birthday.

Tweet this!

Day 2 Summary from HP Tech Forum

CalvinZ — Wed, 17 Jun 2009 13:40:00 GMT

By Calvin Zito

Day 2 kicked off with a opening track sessions - the storage track was at 8 AM with several others at that time. After the TweetUp on Monday night, I was wishing that it was a bit later in the morning. But who I really felt sorry for was the band. We had the same band playing in the storage track opening session that played at the keynotes on Monday night. They are a good band but how many bands to you know that have gigs at 8 AM?

The session kicked off with Chris Riley, VP of Americas sales giving an overview of the last year. I was impressed to see that in the Americas, HP StorageWorks was the only vendor to grow faster than the market in Q4 and Q1. The results since last year's Tech Forum for StorageWorks are solid. Chris and the Americas team have a lot to be proud of.

Chris then switched gears and talked about where StorageWorks is going. He talked to a slide that a couple colleagues of mine had shared with a couple of weeks ago. The theme you'll be hearing about from us is convergence. Convergence of servers, storage, and the network(s) to collapse the physical environment, collapse the management (i.e simplify and lower cost of storage management), minimize the footprint, and minimize time to production. Chris gave a few examples of how we're starting to do this today with the ExDS9100, the EVA family, HP LeftHand, and our BladeSystem Matrix. (Note: the links point to blog posts on these topics).

From their Chris brought out a panel that include our CTO of ProLiant Servers Greg Huff, CTO for the Americas StorageWorks Brian Ignomirello, the head of HP LeftHand Sales in the Americas, and Dave Roberson, the head of HP StorageWorks. They discussed the future of storage tackling issues like storage for the cloud, convergence, and many others. I'm actually met with Brian, our CTO of StorageWorks in the Americas, to get him to post on our blog in the near future so watch for that. We'll also have a video summary of the panel discussion available soon. Here's a picture I got of the panel:

The session concluded with Chet Jacobs doing a quick fly-by of our portfolio. Chet is a funny guy and is aways one of the most popular speakers at StorageWorks events. I was really glad to see Chet present because I know that he had fallen the day prior and was taken to the hospital. He had an interesting factoid about the National Weather Service. He said that they are sending 1 PB of data from satellites per month - and they save all of it. That's a real data explosion. Here's Chet all comfy in his chair:

I attended several sessions during the day including the XP update where many of the new software features were talked about. I've asked the XP team to prepare a blog post talking about that and I'll share that as soon as we have it. One of the new features they talked about in the session is a recent blog post we did on HP System Copy Software for SAP.

I also attended a very good HP LeftHand session. We've had a few blog posts here on our HP LeftHand solutions in the past and we'll have more conversations in the future.

My evening ended by attending the Connect Luau. I'll have much more to say about Connect in a future blog post. Nina Buik who runs Connect (as a volunteer and also has a blog on hp.com) is about the most energetic person I've ever met. It was good to see her again. She presented Deb Nelson, Sr VP of TSG Marketing, with an award recognizing her support of Connect.

Lastly, we also heard that our #HPTF hashtag for all of our Twitters cracked the top 100. Thank you to everyone who was Tweeting and Retweeting on Monday night and Tuesday. I was really shocked to learn that we were in the top 100. You can see what has been talked about by going to this link: http://search.twitter.com/search?q=%23HPTF. If you want to see what I've talked about (focused of course on StorageWorks), you can go to http://twitter.com/HPstorageGuy.

Since Day 3 at HP Tech Forum is nearly half over, I better get this posted and start working on the next post!

Tweet this!

Day 1 summary from HP Tech Forum

CalvinZ — Tue, 16 Jun 2009 13:22:00 GMT

By Calvin Zito

There was great energy at HP Technology Forum on Monday night as it officially got underway. I was able to sit in the front row of the opening sessions with a number of the "new media" folks that are here. I'm not going to give a detailed review of the keynotes because I did that yesterday via Twitter as I and others gave blow by blow tweets of the keynotes. (NOTE: even if you don't use Twitter, you can go to my Twitter page and see the tweets from me). One of the new media guys streamed the keynotes as well and I believe you can watch it from his website: http://sdrnews.com.

With today's sessions starting soon, I'll be brief with this update. As I listened to the keynotes from Ann Livermore (you can see bios of all the keynote speakers here: https://www.hptechnologyforum.com/keynotes.html), Paul Miller, and Prith Banerjee, storage was a large part of each of their keynotes. One of the themes talked about frequently was convergence. This will be the theme of today's storage keynote and since it starts in around an hour - and the walk from my room here at Mandalay Bay to the conference center is a long one - I'll save talking about it for my next post.

At the end of the opening keynotes, I thought back to several years ago when it was a bit envious of the attention storage was getting from a few storage only-vendors. Obviously, HP has a deep portfolio of products that is much more than storage and as a result, I used to wonder what it would be like to work for a company that was "all storage, all the time". Well, I don't think about that any more. I actually am wondering now whether those types of companies will survive on their own as the infrastructure around us converges.

The keynotes on Monday helped really energize me and made me proud to work for HP and HP StorageWorks. I'll give a Day 2 update either later tonight or tomorrow morning.

Extreme storage for media and entertainment

CalvinZ — Mon, 15 Jun 2009 21:42:00 GMT

By Pete Brey, HP StorageWorks ExDS9100 Product Marketing Manager

As I'm sitting enjoying a cappuccino at the HQ of the 2009 HP Technology Forum in Las Vegas, I'm reflecting on how many changes have occurred since HPTF 2008. In that time, we started shipping the 9100 Extreme Data Storage System, one of the industry's most scalable, manageable, and affordable storage systems. We also introduced numerous innovations in our BladeSystem and StorageWorks portfolio to deliver greater simplicity and better TCO. And just last week, we introduced our HP Extreme Scale-out portfolio.

If you follow the Media and Entertainment (M&E) industry, you already know that they face some of the most serious challenges when it comes to dealing with explosive content. In "The Digital Dilemma" report from the Academy of Motion Picture Arts and Sciences, you get a clear glimpse into the long-term issues the industry is facing. While you might think Hollywood's biggest challenge is building systems big enough to support their archiving needs, "The Digital Dilemma" lays out a myriad of other issues which in many ways are much more concerning. A great read...I strongly suggest it. http://www.oscars.org/science-technology/council/projects/digitaldilemma/

Through HP's work with DreamWorks (see the press release here) and other M&E customers, we are collaborating to develop leading end-to-end solutions to address these challenges. And because HP's storage systems are open-ended leveraging industry-standard technology, these customers can sleep at night knowing they will have long-term access to innovative technology without worrying about being locked into a specific vendor's technology.

(Editor's note: You can stop by the Extreme Data Storage demo at HP Tech Forum to see it for yourself as well as attend session 4026 with Pete and DreamWorks co-presenting).

Tweet this!

HP Tech Forum is here!

CalvinZ — Mon, 15 Jun 2009 15:57:00 GMT

By Calvin Zito

In our last post, we talked about some of the goings-on at HP Technology Forum (HPTF). If you're coming to HPTF, be sure to take a look at the post and be sure to join us for our Tweetup tonight. It starts at 8 PM PDT and you can register here: http://twtvite.com/w73n7f

I'm happy to report that I've arrivied in Las Vegas withoug any travel issues and am excited to get things going. Things have already kicked off with some deep dive technical training sessions today but the core event will get going later today with the opening keynote at 4:30 PM PT. Some time later today, we'll bring up our event webpage that will point to blog posts, have multiple Twitter feeds, images, and videos from the event. I'll also have highlights here so check back for more updates.