EMC looks to be leading the pack. They were first out of the gate with SSD in their DMX systems, they are articulating the value proposition of “SSD-inside” better than anyone else right now, and they are already embarking on phase two to stay ahead of the pack. Other vendors are following – with basic support of SSD like HP, to large investments. SSD vendors are happy, coming up with new innovations (like Texas Memory) and looking to tie up as many OEM deals they can in this feeding frenzy. Sun is also investing heavily, putting SSDs everywhere they can. But the winners are going to be the ones that can provide true solutions to problems – not just cool technology…

Also See:

• Tweek N Storage 3-13-09
• Taylor’s Take on Delicious
• The Storage Buzz:

In: SSD | 5 Minutes Ago: Flash | Out: Memory

This Week’s Blog:

Boiling Tape, Screaming Disk & Windows on Steroids
The smartest move I have seen any marketing professional make is walk right into their local IT manager’s office and ask them what would get them excited about whatever technology their company is hocking…

Storage News:

Stephen Foskett’s Blog: Ten-Year Trend: Mobility
Dave Hitz at NetApp simulated some brain cells with his post asking what ten-year trend the industry is building to – in the 80’s it was getting a computer on every desk; and the 90’s brought networking all those computers together. Mr. Hitz throws out three trends: Clouds, Virtualization, and SSD. I like Stephen Foskett’s response – he pins the new trend as “information mobility” and I wholeheartedly agree. Our information no longer lives on a single device or in an application – it lives on an ever-growing and changing network of information and services. Clouds, Virtualization, and even SSDs are enablers to this macro trend….

Chuck’s Blog: EMC 2009 Strategic Forum
A great recap from Chuck on the main points of Joe Tucci’s keynote at EMC 2009 Strategic Forum. Some points that peaked my interest: In Q4, EMC did over $90M+ in dedupe products; Chuck’s analogy that SSD is “I/O dedupe”; EMC completely sold out of EFDs (enterprise flash drives) for DMX and CX in recent quarters; DMX-4 w/ SSD has 60% more IOPs and is 17% lower in cost than DMX-4 w/o SSD.

EMC CEO drops storage product hints at investors’ forum
Doesn’t look like Tucci spilled the beans on too many futures – most of it we already know: SSD, virtualization (VMware NOT for sale), Dedup, etc. A couple points – Data Domain is clearly in Tucci’s (and EMC’s) crosshairs. And the next SSD step for EMC looks to be array controllers that provide automated data migration to SSDs. Archive/compliance search and eDiscovery across multiple storage repositories continues to be a focus as well. (I am wondering where the EMC Cloud stuff is going however…)

Texas Memory brings out PCIe-based solid state
This type of SSD implementation is pretty cool because it leverages the small form factor of SSD by attached the high I/O and dense storage medium to a computer expansion card. Texas Memory has rolled out the RamSan-20, its first SSD-based PCIe card – It has a 450GB drive that delivers 120,000 IOPS. Pricing starts at $18,000 ($40/GB), which opens a whole new market opp for them – they are looking for OEMs and the SSD PCIe card will be targeted to apps that need large/fast buffer areas – DBs, financial modeling, scientific computing, video editing.

Sun flashes new NAND module
Sun is putting SSD everywhere – packed in storage appliances managed by ZFS as well as Flash-enabling their servers. Today they launched a module for holding NAND chips (Open Flash Module) which consists of 24GB attached to a small board with the same footprint as a SO-DIMM module. They also added support for small form factor (SFF) Intel SSDs.

Pillar adds solid-state disks to Axiom arrays
Pillar jumps on the SSD bandwagon with an SSD “brick” for its Axiom system. Pillar’s Axiom arrays are built with capacity nodes it calls “bricks” and compute nodes it calls “slammers”. Customers must purchase 12 SSDs in a brick; primarily b/c Axiom has up to 96GB of cache. Oracle-backed Pillar focuses on high-performing transactional storage systems.

HP puts solid state in EVA storage arrays
HP follows EMC, HDS, IBM, Sun with support for SSDs from STEC, their new EVAs will support six to eight 72GB FC SSD drives.

Isilon expands with transactional and archive systems
Isilon, best known for its clustered NAS systems, is looking to break into adjacent markets by coming out with two new NAS platforms: The S-Series that will target the primary/transactional market with quad-core x86 processors, 16GB of memory per node, and 15,000 rpm SAS disks. And the NL-Series node that will target the archive market with 36TB of SATA disk per 4U node.

• For more Industry News see Taylor’s Take on Delicious…

• Tweek N Storage 2-27-09
• Taylor’s Take on Delicious
• The Storage Buzz:

In: “The Current Environment” | 5 Minutes Ago: “These Economic Times” | Out: “The Recession”

This Week’s Blog:

SRM Tools – an Extreme Cash Cow?
I have personally seen raised frustrations around SRM tools from end-users ever since the “Single-Pane-of-Glass” glory days – pitched by every storage vendor under the sun…

Storage News:

VMware makes world takeover bid
VMware Infrastructure 4 will now be called “vSphere.” VMware CEO Paul Maritz at VMworld related vSphere to a “giant software mainframe” with management at the service level. This is exciting, in my StorageTek days I helped open-source StorageTek’s first an only open source initiative – OpenTMS. The thought was to embed data management services in the OS-layer, similar to Mainframe’s DFSMS offerings. At Sun, I became an Open Storage advocate with the agenda of seeing DFSMS-like functionality embedded in OpenSolaris. But with Mr. Maritz’s latest keynote, I now see that VMware “gets it” and may just have the technology, resource, and momentum to actually pull it off…

Chuck’s Blog: It’s Happening Again
Chuck sees a new trend happening that looks like an old one – the Golden Age of UNIX was in the mid-1980’s. Will the new Golden Age of the 2000’s be VMware???

Will the SAN Market become a Feature?
A bright engineer at StorageTek used to say, “Never put a product where a feature should be.” He was talking about tape encryption, when we put an encryption chip right next to the compression chip on the STK T10000. This was a better approach than a separate appliance. My friend, Mr. John McArthur, asks a similar question. And it looks like StorMagic is trying to turn a SAN into a feature…

Products of the Year 2008
And the winners are….VMware Site Recovery Manager takes Gold for Backup & DR software; Data Domain DD690 wins Gold for Backup hardware; BlueArc Titan 3200 takes Gold for Disk systems; Riverbed Optimization System (RiOS) takes Gold for Networking; and VMware VMotion brings home Gold for Storage management tools.

EMC beefs up Celerra NAS
The Celerra NS-120, NS-480, and NS-960 models pull in hashing codes from Avamar for file-level dedupe, but no block-level dedupe yet. Additionally, code from the Kashya file-system crawler was pulled into Celerra to locate inactive files for dedup and compression. On the hardware side, larger disk systems were added from Clariion CX4 (NS-960 has up to 960 drives & 8 blades) – and the new NS series will support Flash drives. Also see Chuck’s blog, NAS Evolved.

HP Joins Solaris Community (Live Free or Die)
Sun just inked a deal with HP’s ProLiant server business. Now you can get Solaris on HP, IBM, and Dell servers. Good for Sun’s Solaris business (and a testament to Solaris’ strength as an OS). Good for customers. Good for HP because they can now access customers that won’t move off of Solaris. But I suspect difficult for Sun’s server business – if you want Solaris, but are happy with your HP hardware, no need to change. On the other hand, if you are not happy with your HP hardware and like Solaris, you may look at Sun’s now.

Latest Sun/NetApp clash: SPEC SFS
Yet another benchmark debate. I managed the Sun Storage benchmark team for a short stint, and in that time I learned a lot about benchmarks, SPEC, and SPC. Without a lengthy post, I can make two general observations: 1. There is a LOT of science that goes behind these benchmarks and a lot off good people that try to make them fair. 2. If a vendor’s product performs well, then there is little complaint. But if it does not, that vendor will always discredit the benchmark and/or try to change the “criteria” so that vendor’s product performs better.

Iron Mountain opens file archiving service
Iron Mountain Digital rolled out a new cloud storage offering this week with a service called Virtual File Store (VFS).

The conversation led me to look back on some of my past analysis around de-dup. I ended up looking 5 years into the past.

Global Compression at StorageTek

At StorageTek there used to be an engineering research and IP department called Advanced Technology Research or “AdTek.” My current business partner and boss, Randy Chalfant, used to run it. A brilliant engineer by the name of Chuck Milligan ran the group after Randy – Chuck is the one who hired me at StorageTek. I eventually ended up heading the department.

I was looking at an old list of Research Probes we were recommending to STK execs for productization – there were 11 cases we presented in 2003 (Grid Storage, Flash/SSD, Encryption, etc.) On the list was “Global Compression.” In our pitch to management, we stated that this yielded extremely high compression ratios and had the potential to disrupt tape. We recommended adding it as a feature to the backup disk products STK was looking to bring to market – we even recommended some companies to evaluate for investment. (Unfortunately, some other probes were picked for further research that year!)

Fast forward some years and my strategy team and I found ourselves briefing Sun executives (after the STK acquisition) on the future of de-duplication as it has come to be known. I remember saying two things:

1. De-duplication has officially moved from cutting edge to a must have for disk backup, VTL, and secondary storage

2. Dedup will move from secondary storage to primary storage in the future (we backed up our claims with an excellent 451 Group report on the subject)

Dedup in Primary vs. Secondary Storage

Now we have dedup in primary storage. However, some think primary storage is not always the best place for dedup. The thinking is that de-dup works where there is a lot of…duplication. Primary storage tends to hold more transactional data, while secondary storage has more duplicate data. While this is true, there is more duplicate data on primary storage than users know.

I have moved from simply recommending storage strategies to actually implementing them in my new venture (which is much more fun!) Dedup is one of the steps we use with clients to get to a more efficient and optimized storage infrastructure.

We help storage users identify all of the inert data sitting on their primary storage – data that has not been referenced in more than 6 months. Users are almost always surprised about how much we find – around 40% on average.

The next question is what to do with this data – it needs to be cleaned up or moved in order to return that 40% to free pool capacity.

One clean up step is dedup – and in some instances a significant amount can be deduplicated. What are duplicates doing on primary storage? A lot of data management practices (or lack thereof) lead to this.

One example: In many cases application engineers will be testing new applications or updates. They need to run tests on real data – but obviously can’t run them on live, production data. So, they make a snap copy of the production data and run the tests against this data set. If they want to run another test, they’ll make another copy and so on. Do they remember to go back into the system and clean up their copies? Most often the answer is no – and this simple process (which is one of many) robs a primary disk system of its precious capacity.

So, deduplication can have a significant impact on primary storage in addition to secondary storage. But like any storage technology, the way in which it is implemented is the critical part of the equation.