Slashdot Mirror
Sun Releases New Servers, Blades & More
desau writes "This Yahoo article gives some tidbits on Sun's new toys that are being released today. Looks like they're aiming their guns at intel based systems with many new blade offerings and several small to midrange servers. The article also points out that they're lowering their prices on other servers." Probably a lot more information will come out from the web view - that starts @ 12:30 PM EST - but I think it'll take more than blade servers to make a difference in the future.Removed the first part of the link - the DoubleClick part was my copying link location, and not checking it - it should be correct now.
What's with the DoubleClick link? Are we not even bothering to have the illusion that the stories are really ads in disguise?
Somebody needs to combine the high-density, inexpensive technology of blade servers with a scalable single-system-image design. I'd like to be able to take a single rack chassis, four units high or something, and put one CPU in it, or two, or fourteen, or whatever, but not have to dick around with clustering or load-balancing or something.
SGI kind of went that direction with their Origin series (2000 and 3000, and now Altix), but they're overbuilt. It costs a fortune to buy an empty system, and a fortune to put processors and slots in it.
Maybe somebody has done this already. I don't really keep up with the whole blade server thing very much. Anybody know?
I write in my journal
I would love to have a Sun box, and each new offering from Sun looks better and better.
But they continue to shrink in marketshare, and the non-hardware related news items coming from Sun make them look, well, stupid.
Are the engineers and PHBs even talking to each other any more?
So rise up, all ye lost ones, as one, we'll claw the clouds.
a brand new Sun Workstation is nothing special...
:)
I really don't think that there servers are that much special either. When I saw the headline, I thought that Sun was going to announce some competative hardware (faster CPUs and higher memory bandwidth), but this was about blade servers (that you can get just about anywhere) and a 12 processor box (how many people need one of these?).
I coadmin a Sun cluster (I think its like the biggest in the northern hemisphere), and admin an Alpha cluster. And although the hardware is excellent in terms of reliability and overall craftmanship, but they are too damn slow. At least for scientific computing. I've done some benchmarks on brand new 280s with the 900MHz processors (retail about 20k), and they perform as well or worse than an 800$ low end Dell (about 8 months old). Take a look at the Itanium2's performance. These guys are awsome. Memory bandwidth out the yazoo! 64bit addressing, nice machines. We're getting 3 of em soon
I loved this line from the article: Sun's been criticized heavily for sticking to its own Sparc processors and Solaris operating system.
Umm, so if they don't do this, then what do they do? Become an integrator or a reseller? One thing I will give Sun, is Solaris is pretty damn nice.
I will give one thing to Sun's boxes/Solaris. They might not be fast, but then again they never really slow down. I've seen Sun boxes that are almost completely out of memory and have a load of like 10 or 20 (maybe higher, don't remember on a 1 cpu box), and they are completely usable! Compared to my dual Alpha's running Linux, if they are paging hard and the load is about 4-6 it can take a couple of minutes just to log into one of em.
All in all I like Suns, but they look like they are setting themselves up to be an orphaned division of some other company.
There are darn few things which Sun is cost effective for anymore. Running a big DB, etc... But the word is Intel for file and print servers and smaller app servers as well. Choose a Linux box with commodity hardware and you could have that entry level blade for about $1,000. If you are worried about the reliability of commodity hardware, get a back up. You still saved half your money.
Exactly right, and this is why I think they are doing themselves serious harm by still pretending like there is profit to be made in their vertical strategy. Linux hasn't hurt Sun that badly in the computer room, but it is eating its lunch in the network room and on the desktop. Who in their right mind would shell out twice or thrice the bucks for a Sun desktop box when they can get functional equivalence or better with a Linux/Intel one?
Seems like I keep beating this horse...Sun is not going to be able to compete any more on the user end unless they join the commoditization parade. Period. They don't want to recognize this but they really need to. The no-alternative days that saw any corporation needing Unix run to one of the big vendors and forking over millions for end-to-end installations are long over. SGI has been down this path already; Sun won't be able to subsidize their desktop hardware with server revenue for much longer.
You also mention another reason I hate Solaris -- the dearth of what have become common tools and features for an OS. Yes, I know that kickback from Veritas is nice, but volume management support is about six months away from becoming a throw-in. Oh yes, it makes perfect business sense to maintain an entire separate toolchain for things like 'ls' and 'grep'. Etc.
And I really wish Sun would stop calling their shitty workstations "Blades", since that term has become accepted to mean something else entirely.
Yea, and the world is full of people and software capable enough to build and support x86 failover clusters that have 24/7 operation ... right.
... once you get past the technojocks who think networking 4 x86 systems with linux is clustering.
... guess what? You've just gone to 4 independants and paid more for what you could have got just by going to somebody like SUN for a one vendor solution.
... Where are your consultants going to be around long? Or are they just a traveling snake oil salesman?
... you'll find is just as expensive as going to a top notch vendor like Sun.
Oh, I guess not
The fact of the matter is, once you've hired the right people to do this alternative, then invested in the premium hardware (What? Not buying cheap clones for your companies critical apps?), then arrange for Software and software support
On top of that
Linux is cool, no doubt. Intel platforms are inexpensive, no doubt. Linux programmers, Linux support and intel System engineering all combined together for building, deploying and maintaining mission critical apps is not. So the time you took and the money you spent and the money you are going to spend on support
As for Windows? Pftttt, Windows is a toy. Look how much effort Microsoft is putting into the home entertainment market. They see their future quite clearly.
Here's an interesting thought I've been having for the last 20 minutes:
Why doesn't Sun pull something like Apple did? Make a high-end workstation, running Solaris with some much, much better UI over top of it - something akin to Aqua.. Could call it Solarix, heh, or Solaris X or something. Possibly dump X11 in favour of a proprietary display engine, similar to Apple/QNX/NeXT/etc, but keep X11 compatibility availble in the system. Start getting stuff like Photoshop and the big 3d apps, Maya, Lightwave, Softimage|XSI, ported over. It'd probably take a serious expenditure of capital to bribe the companies into supporting the OS/architecture.. but it could be done. The SPARC processor would likely stay, of course, but they'd have to get better 3rd-party video hardware support going to really get this to play nicely. DDR memory would be necessary, too, maybe even AGP graphics. Almost a complete reworking of existing SPARC motherboards, I'd think.
Then you get high-end SPARC servers, and midrange, class workstations equivalent to Apple's best, and, if they design the OS properly, usable by new users as easily as OS X is now.
Pipe dream, maybe. Could be worthwhile for Sun to look in to this sort of thing.
What do you guys think?