What could be more appropriate?
HP’s lackluster showing in The Info Pro’s survey – see yesterday’s post – reminded me that I’d written about HP shortly after after I’d started blogging (see HP’s Storage Grid-lock: panic-stricken execs promise fix in four years).
Here’s a quote from the September 2004 post:
HP’s storage shortfall this past quarter has Carly pulling out the stops to save one of HP’s few high-margin non-printer businesses. Firing executives, check. Inspirational speech to resellers, check. Roll out ambitious product roadmap for delivery in 2008, check.
2008!?! Why not just put out a press release titled †HP execs panic over storage shortfall, have no clue how to fix business in less than four years� Then, at least, they could start facing up to their real problems.
Issuing long-range roadmaps is always a move of pure desperation, so the HP storage business must be considerably weaker than they have let on.
So what were they going to deliver this year?
Get this wacky idea: a storage grid. As an HP whitepaper described it:
The HP StorageWorks Grid will be built from intelligent building blocks called smart cells. These elements will incorporate commodity hardware. In addition to the expected control and storage hardware, smart cells will incorporate a flexible operating environment that allows storage functions to be downloaded as needed—and allows smart cells to be repurposed if necessary.
While the 4 year timeline was laughable the actual proposal was smart and forward-looking. The technology was there. But the paper didn’t address the business dynamics that would enable HP to bring the project to fruition. In other words, the marketing problem.
Clearly no one else did either.
The StorageMojo take
Today clustered storage is the obvious successor to big-iron arrays. When HP wrote the paper it wasn’t. If they’d followed through they’d be the thought leaders in the industry and well-positioned to take commercial leadership as well.
As I noted then,
But HP’s roots as a device company have always made the systems approach [. . .] difficult to execute. Even though HP bought a strong storage business with Compaq (which won it when they bought DEC) and the StorageWorks line, the feckless storage mavens in Palo Alto (best idea ever: “Let’s introduce EMC into all our top corporate accounts! It’s cheap, easy and with no engineering its all profit!â€) have managed to run it into the ground.
HP should take a leaf from Sun’s storage strategy: move storage software from tin-wrapped boxes into the OS group where commodity servers and networks can provide cost-effective infrastructure.
HP had a great idea 4 years ago. Now it’s time to deliver.
Comments welcome, of course.
HP Storage has their share of issues to wrestle with today as they did four years ago. Although I do not see their failing to deliver on Grid Storage as a large issue. Such initiatives are far more likely to fail than succeed in large corporation.
Taking a page from Sun’s storage strategy would be a bad idea IMHO. Let’s not forget that after failed acquisitions of MaxStrat (late 90’s), Pirus (sold off to HDS), and spending $4B on StorageTek they are now pushing toward software. A circuitous route to selling commodity hardware with open source software.
To their credit Sun is changing the storage game and I applaud Jonathan for making the moves he has. In the chess game of corporate strategy he has so far come out on top of NetApp in the latest contest. At least from a PR perspective. The end game will be interesting.
Sounds a lot like storage virtualization – big ideas, a little ahead of their time, overmarketed, but then ultimately the right solution. It’s not just perserverence, it’s timing, too. EMC realized that when it scooped up VMWare.
I was an architect on that project. I left in disgust after a year.
It’s fair to place some of the blame on marketing, for sending mixed and contradictory signals, and for their inability to decide on the target customer. But engineering deserves a hell of a lot of the blame, too, for letting the folks lead with the worst track record on delivering product, but the best on hot air.
At the start of the project, HP Labs essentially handed engineering a working prototype. Management decided to throw the entire weight of the storage division behind the project, which involved putting 20 architects and 80 engineers to work.
After a year, the group had identified 85 (!) different papers to be written and reviewed. They’d successfully reviewed seven. Exactly twenty lines of code had been added to the prototype.
Paralyzed by specmanship, Geneva was doomed from the start.
The fact is, “Storage Grid” is marketing hype simply like “Cloud Computing” you hear these days. There are tons of computer science papers on storage cluster/grid technologies with lofty goals….and you can implement any “technique” (albeit non-proven but wonderful for engineers to “try out”)…which is why John got 85 papers…
In the end, it is very difficult to create dynamic, scalable storage, simply because mass storage use physical heads/media to store data. Dynamically moving tons of data around every time new storage is added is a _show stopper_ simply because you’re copying and re-calculating parity on terabytes of data at meager throughput.
What’s interesting is that Isilon changed the rules of the game and implemented RAID within the filesystem…a novel technique that gives them a lot of benefits…