I would rather show off my quad headed westmere
wasted CPU cycles are not cool.
having four 24inch monitors hooked up to my PC is way cool
37 posts • joined Wednesday 1st April 2009 01:59 GMT
So I watched the video and as much as Oracle tries to hide that is is re-badged Sun x86 it still is with no innovation in the hardware.
The only value is the "pay as your grow" or what some people call sub capacity pricing. Just because they refuse to offer sub-capacity pricing on vmware does not make me want to switch to oracle linux and oracle VM on sun hardware.
Go back to zero and start over. Strangely enough we are "SMB" size and priced out the cost of x86 HP with Intel and decided to go with IBM's Power7 instead. The software cost savings justified the higher hardware price not to mention the reliability saved us from the expense of doing RAC.
Cheers
I am available for any CEO position of a major IT company.
I resided over the acquisition of a top open source database.
I am techy
I am a leader in communications with my blogs
I am located in the valley
I know hardware
I know enterprise hardware
Larry Ellison doesn't hate me
I doubled the value of my last companies stock through a successful acquisition.
Meg will be out in a year....call me
Kebob is going to make the reg feedback columns worthless with all his cut and paste of the same 8 year old garbage. He should get a life.
wasted CPU cycles are not cool.
having four 24inch monitors hooked up to my PC is way cool
HP is in total disarray, and the only thing they can do is be reactionary to Oracle. The Exadata 1 dump and new enemy status has them scrambling for ideas. Violin is their desperate attempt to have an offering, but no one is going to put Oracle on Itanium for a new BI project. As far as proliant they only have it on the DL980 which is a poor attempt at an 8 socket box. Look at the processor to I/O card architecture and you'll see that a processor has to go thru two glue chips and another processor to get to the violin. Sure the benchmark will put the violin on the processor that is directly attached but in real life processors are not pinned so easily. The QPI architecture sucks on the DL980
just ask Pepsi they moved to DB2/Power for SAP from Oracle/SAP/Superdome..... they told Larry to piss off
I can't believe no one has talked about why Oracle knows so much...and why they say HP is hiding the truth.
Kebabbert.......you obviously do not understand computer architecture.
The notion that all that matters is the cpu is myopic. The mainframe is the perfect example of a system of CPU chips / cache chips / I/O subsystem chips / service processor chips / etc.....it is not about a single chip.
As far as the T goes...yes it is good for WebLogic but sucks for the rest of Oracle's "data intensive" products.
The SPARC64 is dead and Oracle has to do something to keep those Sun customers paying thru the nose for SPARC maintenance. And who cares about poor core performance as long as all the profit is based on core licensing.
They cannot clock chips to 5GHz without major problems. The chips are made in China then shipped to Mexico and have a huge dead on arrival percentage. Unfortunately for Oracle they are still paying for the mistakes Sun make during the last 10 years. KKR forced mfg to Mexico and TI refused to keep up on the fab technology because DLP does not benefit from lower nm's .
Only time will tell if this 4 year old core baked on the Chinese fab then assembled in Mexico with an aggressive clock speed will bring us back to the SPARCIII eCache memory reliability again.
Keep stressing how the T chip saved Sun an they are the leaders though. We just got two PS3's another xbox for kinect....so two more cell chips and another power chip at the house this Christmas. I hear my BMW has a bunch of Power chips also, but that is just rumor. Maybe Larry's next project could be going to Mars, since IBM has 100% market share there with Power chips.
dump Oracle, end the ELA abuse...never do a ULA.....and if you can't dump Oracle quickly at least put your licenses on IBM Power so you get the most for your money. From a performance stand point and a utilization/virtualization of the technology
Here is the official SPARC64 roadmap.
Clearly SPARC64 is DEAD
http://www.fujitsu.com/global/services/computing/server/sparcenterprise/technology/protection/roadmap.html
www.tpc.org
Larry has been spending millions on ads talking about the TPC-C benchmark from last October.
Check out how Power7 compares
4 Systems vs. 12 systems
10.36M transactions vs. 7.65M transactions
$1.38/transaction vs. $2.36/transaction
224 flash drives vs. 4,800 flash drives
$11.5M Full DB2 license vs. $7.85M 3 year only license (like anyone buys 3 year...IBM should create one of those BS 3 year term things as the $/trans would be even lower)
I wonder what the next ad will be from Oracle.
35% less transactions
71% more expensive
Oracle SPANC is not dead...please keep paying our maintenance fees.....Larry needs a new America's cup yacht.
Oracle bought Sun to control (almost kill) MySQL. They also got Java which they can use against SAP and they are trying to protect the billions they make from old sun hardware with Oracle licenses.
Which brings the point of Java vs. Google. They hire the same lawyer who got rich off SCO and burned it to the ground.
All I can say is F oracle and Larry can take his gondala (yes he has one) to hell.
I don't see any future SPARC64 chips in the market after the lame 65bm 3GHz. Power7 is 8 times more powerful and Nehalem is 4X, nothing Fujitsu can do will solve the technology gap.
Even if Oracle changes the pricing so Fujitsu SPARC64 is on par with x86 it will do nothing for hardware sales and will only hurt Oracle's maintenance stream. Power7 is 4X more powerful per core than SPARC64 and is only 33% more expensive. A .5 multiplier for SPARC64 will not change the game. They would only do it to try and stave off the migrations as they trick customers into ULA's which cement the maintenance stream.
Larry is not a patient person and hardware is in the tank.
This is another indication that Oracle is getting out of the hardware business except for Exadata which they will soon OEM the x86 systems from Dell just like Teradata and netezza does from IBM.
Software, Hardware Complete....but we never said we would be making the hardware.
The mainframe is the most respected system in most data centers. The discipline and management is why it is the mission critical and strategic system of choice. This sounds like it will help with the nightmare most customers have with "distributed" systems. I for one have always had the most respect for centralized systems. Larry has customers over a barrel and is becoming the new Computer Associates in the industry. IBM is fair, has the best technology and is not trying to lash together technology to charge customers millions in RAC software.
It was fun while it lasted, but dont trust Larry.....your company should not be paying for the Americas cup.
We use VMWare for small applications and infrastructure clutter.
We use PowerVM for all the database workloads and larger applications
Lessons:
VMWare
- is easy for easy workloads
- is very expensive
- is not architected for heavy I/O
- cannot have a virtual machine larger than 8 threads
PowerVM
- easy but you need to use AIX versions of software
- makes Power systems cheap compared to x86+VMWare
- Can handle the highest transaction rates we have had on black Friday
- can scale from one thread to I heard over a thousand in the new boxes.
Its a matter of picking the right platforms for the right work vs. how to try to get VMWare to do something it was not made to do
"The result was not the fastest recorded; far from it, a Sun SPARC box recorded 7.65 million TPC-Cs last year. "
That was 12 yes 12 Sun SPARC boxes in a cluster. If you use perpetual licenses and regular maintenance then the price is $20 MILLION for 3 years.
IBM was able to do 1.2M with two chips in a p780 which can scale to 8 chips....aka sockets.
SPARCCMT is dead as the previous poster compared the performance per core is unbelievable yet it is.
Compare the SAP 2-tier p780 to the Oracle/Sun/Fujitsu M9000 and you see their is a 8X performance advantage.
SPARC64 is dead and Oracle is not even bothering to sell it as all they care about is trying to make Exadata V2 successful as V1 was a disaster.
Randy Dandy Sandy
Oracle only cares about Exadata and that is only because it drives software revenue.
Every client rep had to have a proposal on the customers desk by end of December or they don't get any commission dollars.
Every client has to have a proof of concept or a customer workload benchmark or they cannot go to the sales club event.
Every Sun sales rep (the few that are left) have to sell at least one Exadata by end of May or their job and certainly their territory will be in jeopardy.
The m-class systems are of no interest to Oracle and will go the same way as the Hitachi storage very soon.
Everyone with innovation skills left / customers saw the disaster / IBM and HP pillaged
Stockholders lost billions / IBM quickly became disinterested at any price / Oracle went to the dollar store and got a bargain
Spent $4B on STK and $1B on MySQL / Could not integrate them / MySQL costs billions more as acquisition took 10 months
Solaris 10 success / Open Source blinders / Solaris 11 disaster in the making as it is based on OpenSolaris not Solaris 10
Great career / ruined Sun / career Hara-kiri
The database can be on Itanium just like any other Oracle database but the application servers will never be supported on Itanium. You are forced into a linux/x86 and HP-UX/Itanium
Why do they have to call it a "Itanium 9500"?
Oracle only charges .5 for Itanium 91xx and earlier chips.
The new pricing says Itanium 9500 will be 1 license per core as it now falls under
"All Other Multicore chips"
So the price of Oracle and Weblogic is going to be 2X per core and the core performance is not even going to increase.
http://www.oracle.com/corporate/contracts/library/processor-core-factor-table.pdf
I need to hear about this Power7 stuff.
"IBM has nothing at the low-end, which I'm sure you have some need for."
IBM has 4 socket p6 blades. The largest supercomputer in Europe I believe is build on p6 blades.
gotta go check the top500 list for T boxes...
Cheers from the UK
If the T2+ is that good then why does Sun still try to sell us M-class boxes with Fujitsu chips for any DB or I/O workload?
I would ask if those T3 threads are simultaneous or if they are round robin KISS ass treads.
SPARC and Itanium are dead. Squeezed out between Nehalem and Power.
As I recall Pony tail boy claimed the T2 was 9.6GHz because he tried to multiply 1.2 * 8 cores.
Pot/Kettle/Black....join us or die ugly
Cheers from the UK
Sun has manufacturing plants
http://www.thestreet.com/story/10452796/sun-microsystems-to-shut-scotland-plant.html
They do outsource a lot of things, but they do have mfg plants. Even the M-class systems which are fujitsu technology are made at Sun mfg sites.
bozo
...the exec's got their payola and said screw the shareholders.....
maybe Solaris will survive but SPARC is surely dead. Larry don't give no shits about saving SPARC chips...especially since they are now fujitsu technology
...lady gaga
You forgot to mention how little Sun makes on software vs. hardware. IBM made the transition to software and services while Sun could only give software away for free.
Safra Catz, Oracle's other co-president, said that Oracle would be using a mix of cash and debt to acquire Sun, and that the company believed that the Sun unit could deliver $1.5bn in non-GAAP operating income per year,
Run for the Hills.....RIF day is is coming...and maintenance costs will be doubled.
Expect a lot of things to die with this deal. Oracle has no patience for low margin hardware unless it sells lots of software licenses.
HP is the real loser as they are the only ones without a software stack which is were the real profit is. (but they still have ink)
McNealy's life work is for nothing buy Larry's chopping block.
No thank you
And you want $33M each for the loser CEO and the Joker chairman?
Your software does not make money let alone profit.
The only money to be made is in maintenance fees for hardware..that will make customers happy with the acquiring company
STK, MySQL....where did all the good people go?
You spend $3B on stock buy backs and the stock is in shambles?
Next layoff day all the people who get RIF'd should stand out front and way white flags
Sam makes $1.8M in base salary.....and you wonder why IBM would not pay Pony Tail $33M
The company needs either a new coach or needs to merge with a new team.
Think of this like a basket ball team where you have a coach more interested in talking to press and the fans vs. helping the team on the court. The team is tired, fed up and is looking to be acquired even if it means they will lose their job. Everything is in complete disarray.
It's 9pm and the sky is red.
they really should put this story in the news section
www.itaniumsolutionsalliance.com
First Unisys now SGI. The Tukwila 12month delay will cause others to dump it. The volumes just not support having an Itanium system unless you are HP.
Looks like Itanium will be nothing more than an HP-UX PA-RISC replacement.
Rick Beluzzo...why did you force SGI to move to Itanium? If you look at the critical decision that sunk SGI it was hiring the HP Itanium fanboy.
Announce 6,000 layoffs which affect 20% of the company....than tell people the number is too high this time. Hello....everyone is still extremely worried now......how stupid.
oh btw....ROCK was killed today. It was being kept alive because Fujitsu might be interested but now that they are out and IBM has no interested in another sparc 8 socket at most box....its dead.
Hopefully NiagaraIII will survive.....ironic that the sales force layoffs were on the same day as Nehalem announce.
Ironic that our last glimmer of technology the T2+ will be killed by Nehalem and we are helping the demise with Solaris support.
someone please buy us and put us our of our misery....I need a golden parachute
but then again Linux looks like the right answer....crazy that we sell more windows and linux on our x86 boxes than solaris
Sun did not want to sell m-class, it was a by-product of the sparcV cancel
I am sure IBM will continue to sell against it and tell customers they are stupid to buy a system with partitioning....get with the program and use virtualization
Nehalem is the real reason Tukwila will be 12 months late. Tukwila will not be out until November, conveniently after HP's fiscal year end..
Nehalem is 4.1X for fp_rate_2006, 5.5X for Specjbb_2005, 4.7X Spec_int_rate_2006, and 4.7X for SAP-SD over Itanium
What idiot would buy Itanium unless they want to pay for 5X the processors and 100X the cost..
cheers!