So what will happen to Sun?
The new Silicon Valley parlour game
Comment Silicon Valley has a new parlour game: what's going to happen to Sun after the cuts? Rumours suggest it will merge with EMC, that HP or IBM will take it over, that Fujitsu will buy its hardware business, or even that the StorageTek storage business unit will be spun off. Do Sun's leaders want to be redeemed or to retire?
The company has bit the downsizing bullet and announced up to 6000 job losses following on from a $1.7bn quarterly loss.
Its made its big open storage announcement and there are server announcements coming too. But investors have seemingly discounted these moves as the company's share price is at $3.17 with its market capitalisation at $2.34bn, about the same as its cash pile and so effectively rendering the company worthless. This is lower than the $3.62 stock price before the cuts were announced, and before a raft of technology and product announcements like the open storage one.
Investors have seen these announcements and reckoned that nothing substantial has changed in the company's fortunes. The company, led by CEO Jonathan Schwartz (right), has already downsized, is downsizing some more and is still following its strategy of promoting open source system software products and commodity HW-based server and storage sales alongside its higher-priced and proprietary SPARC server business.
It bought StorageTek (high-end and mid-range tape and disk storage products) for around $4bn a few years ago and MySQL (open source database software) for a billion earlier this year. So far neither acquisition has prevented Sun's sales revenue slump. Nor has its open source system software strategy, aimed at developers with consequent hardware and service sales dragged along in their wake. It's a classic product transition problem with revenue from new and lower-priced products not rising fast enough to offset declines in older products.
It's not helped by the indirect way Sun is hoping for new product sales to follow in the wake of developer take-up of its open source products. There is no good indication of how many developers and how much time is needed for such sales, no rule of thumb such as 100,000 developers over two years equals $10,000 of product sales and 200,000 over the same period equals $20,000. Sun simply doesn't know, and like some Las Vegas fruit machine addict keeps on going back to the one-arm bandit with a fresh bag of coins hoping for the jackpot.
It hasn't come yet and investors and analysts are asking what happens if it takes another couple of years or, worse, the sales level now is as good as its going to get and there is no more to come.
Next page: Decline and fall
Matt Bryant is coming...?
Reminds me of the old Spitting Image skit of David Steel and David Owen, where they are wating for the Liberal Wave to Rise and sweep them into power, and David Steel's puppet keeps ecstaticly wailing; "It's coming, David, the wave is coming!"
Of course, the wave never did come.
Just for the Itty Bitty Machiners with very short and selective memory, T1, T2, T2+ were released ahead of time and performance on-par or better than promised. Sun had assured us all it was "revolutionary" and would be better than all the competing chips, etc, etc.
For the better part of a couple of years, application performance was best in class in 1, 2, and 4 socket machines.
/Laugh, point, yawn, laugh some more.
To Anon Corward - "Oracle on a 12 core chip... "
An Anonymous Coward says, "Oracle does not recognize LDOMS for sub capacity pricing so Sun customers are forced to try to use zones"
"Hard partitioning physically segments a server, by taking a single large server and separating it into distinct smaller systems. Each separated system acts as a physically independent, self-contained server, typically with its own CPUs, operating system, separate boot area, memory, input/output subsystem and network resources. "
"Examples of such partitioning type include:... This is not a comprehensive list of all the different types of technologies or resource allocation devices/programs that would fall into the category of Hard partitioning."
If capped zones are acceptable, LDOM is obviously acceptable, since CPU capacity is added a thread of a core at a time, has it's own OS, separate boot area, memory, separate I/O subsystem, and network resources.
All the requirements are clearly met, by the letter of the Oracle licensing law!
"Oracle on a 12 core chip... "
Oracle on a 16 micro-core chip requires 12 Oracle licenses.
That is $688K in the first year with maintenance.
Multiply that by the 8 chips in the largest Rock system is $5.5M.
Oracle does not recognize LDOMS for sub capacity pricing so Sun customers are forced to try to use zones but $344K for half of a chips performance is still insane.
All this is mute anyways since Sun has already canceled Rock.