If a broad server product line guaranteed sales, then the server business of Sun Microsystems would be as large as that of IBM and Hewlett-Packard - and considerably larger than that of rival Dell. But breadth and depth of product, while necessary, is not sufficient for a healthy and growing server biz. You need a good sales …
SAS or SATA
Nice work on the T2+ dual socket blade, but Sun really should support SATA drives in all servers by now. Many people prefer the higher capacity of SATA. Reliability isn't such a big deal if you're running RAID or ZFS. Sometimes "what's best" is "what people want" - and this philosophical difference might explain Sun's preannounced Q1FY09 losses? I guess we'll find out next Thursday when Jon Schwartz and Mike Lehman talk to analysts from an alternate reality where sales and adoption are growing nicely, especially in BRIC. Back in the real world Sun's shareholders are taking it on the chin and wishing Sun's leaders would go take a course called "How to sell open source like Red Hat" (e.g. by offering credit card subscriptions via the web site). Man, it's not rocket science. Hmmph.
More "me too" than innovative.
Apart from the T2+ blades, the rest is just following where other blade vendors have already gone. It does make the Sun offering a more rounded proposition, but still lags behind what HP and IBM can offer, and I can't see it leading to more market share against either. It may bulk up existing Sun accounts as a defensive measure though, especially those already bitten with the Niagara bug, which I suppose is a good thing for Sun. Still don't think it will make enough money to compensate for the decline in the core SPARC bizz though, which leads to the question of how long will it be before more Sun layoffs.
To Matt and Kevin
Hey Matt, who cares who had what first? Get over yourself, and your Sun bashing. It gets old fast. The fact is that Sun made a design error by not including internal drives (a low end requirement in my opinion!), so they added a drive blade.
The real story is the T2+ blade which HP nor IBM have anything even close. Look at the new benchmarks being won with the T2+. It's pretty impressive. Especially versus HP. HP is quickly falling off the performance curve. It doesn't look like Intel has much interest in remedying this either. HP really only has the management tools... Those are sorely missing on Sun's gear.
I like your comment about Niagara users being "bitten by the Niagara bug" though. It is extremely contagious. We use them to extremely high utilization using containers/zones, of which HP can only approximate with resource management tools of which Sun has as well, but the containers are much more usable. In HPUX a badly behaving application can take down the other applications. With Solaris Containers the bad application is contained within its own container, causing no issues to the other containers. This is especially important for testing new applications and processes. I can build a container in minutes, test what I need to test, and then tear down the container again in mere minutes.
Hey Kevin, I agree with you. Since, in my opinion, internal drives are a low end requirement you should provide a low end solution. I bet their stance is SATA is not reliable and that SATA is too slow. Of course, as you state, if customers want 'em, give it to 'em.
Innovation questioned? Shall we question Matt's favourite vendor?
Matt, good to see life is regular, your still trolling every Sun post with amazing regularity but if your questioning innovation lets think for a second shall we.....
Erm, Sun, first company to tread the "many cores" instead of "mhz" route and seemingly doing very well with it compared to your beloved HP who's Itaniums were the last to go dual core. Looks like HP are playing catch up and the rest of the vendors are indeed catching up.
Fujitsu & Sun coming up with a Sparc based processor thats now doing Instruction execution retry, a feature not seen outside of the mainframe in reality. Hang on, lets think about your dearly beloved HP products again, ah, yes, Itanium is not quite up to Instruction retry yet is it, hmm....
Which vendor should we really accuse of lack of innovation, Mr HP Sales bod?
Sun is going the wrong way
Sun doesn't get it. They need less types of systems. This is why their manufacturing costs are sky high. Unless they cut half of the different types of systems they sell and cancel ROCK they will never be profitable.
...for once I'm going to have to help Matt 'Sun is pants' Bryant...
Sadly for AC, the IBM Power6 does instruction retry.
Happily though, the P6 is being spanked by the T2+ on Siebel and Spec2006 benchmarks!
"sunshiners/hp/lulz/bwhahaha/Scwhartz/IBM/Sunshiners/linuxandwindows/shareprice/lol/sunshiners etc etc etc...."
RE: Anonymous Sunshiner / Marketeering Droid / ignoramus
Where to start, just so much male bovine manure to cover!
"Hey Matt, who cares who had what first?..." The market cares. You see, they like tried and tested solutions, and HP, IBM and Dell have built up customer belief in their x86 products over time, which is why they have been successful when moving into blades as they could play on that trust already there from their x86 racked servers. Sun has never had that, and now they have to forge new relationships with people outside the traditional SPARC arena. From the market data it looks like that isn't going well and the Sun x86 and Niagara are just cannibalising existing Sun bizz rather than gaining market share. This does not bode well for Sun, especially as the resellers they will look to sell the x86 servers (and hence all those blade chassis the Niagara blades will need to plug into) will be experienced IBM, HP and Dell resellers, all unlikely to go to the trouble of switching accounts from HP, IBM and Dell x86 products.
"....The real story is the T2+ blade which HP nor IBM have anything even close...." This is true. All the HP and IBM blades, whether Xeon-, Opteron-, Power- or Itanium-based can actually run heavy threads and therefore offer the ability to consolidate real enterprise apps such as Oracle and SAP off old RISC servers into shared blade chassis farms. HP, IBM and Dell wouldn't think to produce a limited non-product like the T2+ blades, so you are quite right there. Niagara can only do consolidation for the thinnest of old SPARC apps, but is very good for light webserving. It's just such a shame that webserving is a market already dominated by Lintel/Wintel, from HP, IBM and Dell, where those vendors have the established relationships and reseller backing, and Sun has SFA....
"....Look at the new benchmarks being won with the T2+. It's pretty impressive. Especially versus HP. HP is quickly falling off the performance curve...." Really? So where are the SAP, Siebel, Oracle or MS SQL figures for T2+ and how do they compare to a Superdome? Oh, I forgot, T2+ is a memory-crippled T2 which barely scales to two sockets, and even then can't handle real enterprise apps. Maybe we should compare it to a Xeon ProLiant? Then again, maybe not, seeing as I can't find any enterprise application benchmarks for T2+ using respected test tools such as TPC-C or TPC-H which customers use to compare systems. SPEC has an even funnier story - Sun has submitted test results for the rate versions which test the whole system, where they can make the most of the high core count, but have zero results entered for the individual thread tests (gee, I wonder why....).
"....In HPUX a badly behaving application can take down the other applications. With Solaris Containers the bad application is contained within its own container, causing no issues to the other containers..." You obviously have zero knowledge of hp-ux's partitioning technology. Even going back to the old PA-RISC servers I had software partitioning, where each partition had a completely separate OS image, though hardware could be shared, which is better than containers can offer now. And I also had hardware partitioning on the cell-based PA-RISC servers, which meant I had a share-nothing solution with real isolation. With containers, if the underlying OS goes down then all the containers go down, period. Add on top of this that hp-ux had resource-based partitioning (PRM) and SLA-based management (WLM) tools in the OS which could stop a misbehaving app hoggign resources even before Slowaris got containers and you will plainly see HP where years ahead of Sun on UNIX virtualisation. Oh, sorry, I mean you will see after you loosen up the Sunshiner Blindfold (TM) which is probably also restricting the flow of blood to your brain.
"....Fujitsu & Sun coming up with a Sparc based processor thats now doing Instruction execution retry, a feature not seen outside of the mainframe in reality. Hang on, lets think about your dearly beloved HP products again, ah, yes, Itanium is not quite up to Instruction retry yet is it, hmm...." Latest Sun feature sell? Simple way to beat it, just like all the previous Sun feature sells - go to a shoot-out, run real data to mimic the real environment, including deliberate errors, and see how the respective systems stand up. So far, I've happilly defeated all Sunshiner attempts to uproot our Superdomes by this simple method, and usually because Sun drag their feet over going to a shoout-out they know they'll lose. My most entertaining bit of Sun humiliation was running an Oracle-linked billing app faster on hp-ux on Itanium than Slowaris 10 on SPARC64, then booting the partition into Red Hat Linux with Transitive QuickTransit and running the old Slowaris 9 binaries faster than the SPARC solution on Red Hat on Itanium! I will admit we did later look at replacing the Xeon blade web front-end to the app with T2 kit, but in the end we decided the added cost, separate support contract and admin burden didn't warrant the minor gain in performance, even before we looked at the shakey roadmap for Sun.
"....Erm, Sun, first company to tread the "many cores" instead of "mhz" route...." Ignoring AMD's Opteron? And you went dual-core with Ultra-SPANKED, and your business died because single-core CPUs in HP and IBM servers outperformed it at a lower price and with far better RAS features. Like many Sunshiners, you have still failed to grasp the fact that the company that makes what is closest to what the market requires will win. Making "wowie-zowie" but low-performance, expensive products with limited market appeal has become a Sun speciality. Even Dell are better at the market prediction bit than Sun, whom have happilly wasted time on numerous dead-end projects before limping after the other vendors which have left Sun far behind. Suns storage portfolio is late and thin compared to HP and IBM, their blades are even later and just as limited, and their "Java" thin-client answer to Windows on the desktop is so low in penetration it lags Novell and Apple in marketshare! Sun is the least diversified of the commercial UNIX vendors, which is why the decline in the UNIX market has hurt it worst. You act all snobby about HP printers, but the truth is HP will be making a profit off printers long after Sun has been broken up and sold off.
Re: RE: Anonymous Sunshiner / Marketeering Droid / ignoramus
hee hee hee... Matt's so easy...
I only really read part of your post, 'cuz it's always the same. Matt trying to justify why picking a bland non-engineering company like HP is the right choice... OK Matt! we get it... the same thing every time.
So, Matt, you want real data center apps huh? Well, according to Oracle, the T5440 is the fastest Siebel server in the world:
Since we all know that Oracle hates Sun, this can't be fluff, right?
How about SAP, which you must admit is Data Center caliber... This little 4U 4 processor server outperforms a 4 processor Itanium server (from guess who... oh yeah, the only one really using Itanium... HP), by 4 times!
Get real, Matt, HP is losing it... They should stick to competing with DELL. They have a lot in common.
More Matt BS
"I can't find any enterprise application benchmarks for T2+ using respected test tools such as TPC-C or TPC-H which customers use to compare systems."
Why only point at T2+? The comment was that HP is losing the performance battle with the poor choice of Itanic... Let's look at the SAP benchmark, where the Sun M9000 had 39100 users compared to HP SuperDomes 30000 users. The M9000 had 196570 SAPS, while the SuperDome only had 152530.
How about SPECfp2006 where Sun demonstrated a score of 28.8 SPECfp2006 (25.5base)... HP can't even beat Sun's base number...
There are too many records to enumerate here. You can find them yourself. TPC-C is a joke, and TPC-H is only slightly less so. Even HP doesn't use TPC-C anymore (though IBM keeps chugging along on this joke of a benchmark). However, let's look at those TPC-C numbers, shall we? Sun's 1000GB result is 118,573 qphh, which HP's result is only 69,999. Quite a difference...
Hasn't Intel abandoned Itanic yet? Wasn't Tukwila supposed to ship in 2007, then 2008, and now 2009? What ever happened to Whitefield by the way? The rumor is that Tukwila will be canceled and they will just wait for Poulson... Where are the ROADMAPS HP and INTEL past 2010???? Man, I would have a hard time running on HPUX since it does not run on x64/x86 right now... Just think about all the pain that you HPUX users will have to go through, not just going to a whole other architecture, but to a whole other OS... What a joke. What are you going to do until 2010 when the first systems are "supposed" to be released with Tukwila chips?
RE: Re: RE: Anonymous Sunshiner / Marketeering Droid / ignoramus
"....bland non-engineering company like HP...." How can designing and manufacturing products in at least ten times more markets than Sun make it less of en engineering company? Let's take a simple example, the HDS Lightening arrays. Hp are involved in teh design cycle, they write the firmware with HDS and write their own software to go on top. All Sun do is spray paint the outside and slap a sticker on. Another simple example? HP built up their number one position in blades through internal engineering - Sun went out and bought a poor design from an ex-Sun employee, got nowhere with it, tried again and failed, and are now on their third and still limited blade offering. Face it, Sun is a minor engineering company compared to HP.
"....So, Matt, you want real data center apps huh? Well, according to Oracle, the T5440 is the fastest Siebel server in the world...." Actually that test was run by Sun and is not endorsed by Oracle. This is shown by the Oracle statement in the footer on page 2: "Oracle does not warrant or guarantee that customers will obtain the same or similar results, even if they use the same or similar equipment and/or software applications. Oracle does not warrant, endorse, or guarantee any performance of any products, any results desired or achieved, or any statements made within this document. " So much for Oracle saying anything, this is just another dodgy Sun benchmarking exercise which will be easily shown up in real shoot-outs.
"....How about SAP, which you must admit is Data Center caliber... This little 4U 4 processor server outperforms a 4 processor Itanium server (from guess who... oh yeah, the only one really using Itanium... HP), by 4 times!...." <Yawn> We run SAP on Integrity, and we routinely test against other platforms at CTO's request. So far, neither Sun nor IBM have been able to match HP on performance, though IBM ran it a damn sight closer than Sun did. Whatever fun little Sun benchmark you want to quote, the reality is that real world implementations will show T2+ is more expensive, doesn't scale and has poor performance compared to ProLiant, let alone Integrity. Dream on!
".....HP is losing it... They should stick to competing with DELL. They have a lot in common...." Would that be profits, popular products and bouyant stock prices, things Sun hasn't got a hope of producing? Don't worry, Sun's pain can't last forever, either Fujitsu will absorb them soon or the market will put them out of their misery for good.
Matt "Show me the benchmarks, but not those benchmarks" Bryant
Matt, you contradict yourself. First you say "where are the benchmarks?" When the benchmarks are shown you say "yeah, but in the real world..." Come on Matt!!! Stick to the same story. You actually mention TPC-C and TPC-H as important, but when real world benchmarks are shown such as SAP and Siebel you question their validity.
I agree that benchmarks are generally garbage, but you can't say to look at the benchmarks from one side of your mouth and then say they don't matter on the other side.
How come you don't comment on Intels dedication to Itanic? Huh? A little worried that your favorite chip will not be there in a couple of years? Are you kidding me? What will you do when HP makes everyone change platforms ONCE AGAIN! You think they'll move HPUX to X64? Yeah right.
Matt the Troll
Hey Matt, if you're not a HP sales slug, then why do you spend all of your time trolling for Sun articles? I haven't read a Sun HW article yet that you haven't given your opinion on. If HP is doing anything interesting in regard to engineering then why haven't we seen any articles on HPUX or SuperDome? Would you comment on those articles as well? Are you jealous that Sun gets more attention on here than HP? What's your deal? Really...
RE: ACs, or just the one AC, or whatever!
Strange that you only post as AC, but moan that anyone would dare criticise Sun. For you, only the employee of a rival could post anything that might not be nice about your beloved Sun. To be honest, you display all the signs of a cult-like narcissism, but then I have come to expect that from Sunshiners. You're worse than the Mac fanbois, at least they actually have popular products! It really amuses me that you guys have such a hard time accepting that not everyone shares your views, and after years of suffering you Sunshiners continually bleating on falsely about Sun's superiority and invincibility, I'm amazed you don't expect other people to take glee in Sun's decline.
If you bothered to look at other than Sun articles (gee, do I detect a one track mind there!), you might have noted I comment on a wide range of articles on politics, different computing technologies and death-tech. There are plenty of articles on HP and other vendors, I suggest a little wider reading would broaden your very limited horizons. And yes I do comment on many of the Sun articles, especially those that simply requote Sun press releases unquestioningly.
As for benchmarks, let's do a little testing to show how simple it is to twist any benchmarking session. I will use an old Casio calculator (amazing what you find when you finally get round to clearing the loft), you can have any member of the current Sun server range. To start, we'll do a power up test - what do you know, my Casio comes on almost instantly, whilst your Sun box is still booting! Obviously, my Casio must be a superior enterprise computing product because it is faster to boot. Test two - simple addition; I type in 1+1= and get the answer 2, the whole process being completed as fast as I type (well, it is a calculator), but you have to go run up a program, or write a bit of code, all of which is slower. Test two therefore proves my old Casio is also superior as a integer computational tool. And that's even before we get round to looking at the fact my old Casio runs off a solar panel whilst your Sun box requires nasty electrical points - my Casio is greener too! So my old Casio calculator is faster booting, has better integer performance, and is greener than any Sun server available! After all, my benchmark just proved it.... ;)
And Tukwilla (I still prefer Tukzilla, as suggested by another Reg poster) would seem to have a healthier future than Rock. For a start, Intel actually has the money to make it, whereas Sun seem to be throwing cash away on questionable acquisitions (and by questionable I mean ones where leading market analysts go "WTF?"). If Sun does decide to buy up their own shares to avoid delisting then that will leave them strapped for cash for continued development. Secondly, Tukwilla will use the new high-speed interconnect with Xeon, another case of sharing of technologies between Intel lines that Sun chips just can't match, which means Intel is making more efficient investment of its technologies than Sun and making it easier for their partners to make Itanium servers. Thirdly, HP has a bouyant share price Sunshiners can only look at with envy, the Integrity product line is growing in marketshare because it can be used with hp-ux, VMS, Linux and Windows with HP support, and can weather a recession due to a wide range of products giving it depth, whilst Sun will die as Rock and Niagara will die with the decline of SPARC Slowaris.
But, it's obviously causing you a great deal of stress that I should not bow down and pray at the alter to the great Sun, so here's a simple way to solve your problem. Simply ignore my comments, just don't read them, and time will tell if you are right or wrong. According to you Sunshiners, Sun will somehow dominate all areas of computing with Niagara and Rock sharing out all the processing tasks anyone would ever want to do; Intel, HP, Dell and IBM will wither and die; and Microsoft and Linux will fall to the wayside. If you feel happy with that belief then you can take comfort in it and just smugly smile at the obvious stupidity of anyone that could think otherwise, resist the temptation to hammer your keyboard in another outpouring of frustration, in fact you can just give up wasting time on us idiots here at the Reg. Go forth calmly, secure in the knowledge of the inevitability of the Great IT Revolution of The Sunshiners.
/now where is that pointing-and-laughing icon? XD
So tell me Matt, how can the same person say:
"I can't find any enterprise application benchmarks for T2+ using respected test tools such as TPC-C or TPC-H which customers use to compare systems."
"As for benchmarks, let's do a little testing to show how simple it is to twist any benchmarking session."
You constantly deride Sun on benchmarks, and then when the benchmarks come out against you, you say benchmarks don't say anything. There a plenty of happy users out there that absolutely love Sun gear, and you deride them for daring to think differently than you. No one is saying you're stupid for using HP gear, yet you insist on taking every opportunity to deride anyone using Sun gear. There must be some ulterior motive, other than your HP gear runs so great that you want to spread your happiness to the rest of the world. You obviously have some deep angst against anything and everything Sun. Did Scott McNeally dump your mom? Did a Sun Sales Rep run over your cat? What is it?
I think you need a hug... There there little Matty.
RE: Still AC
"....You constantly deride Sun on benchmarks, and then when the benchmarks come out against you, you say benchmarks don't say anything...." No, I merely pointed out Sun are only posting benchmarks where they can ensure they get a good result for T2+, they are avoiding industry standards like TPC-H beacuse they know the result will be bad. Sun were happy to quote TPC-C figures for SPARC for years until they simply fell off the bottom of the chart. The fact Sun are so selective in Niagara benchmarks just goes to show how careful they are to keep it away from a real comparison.
"...There a plenty of happy users out there that absolutely love Sun gear..." They "love" it? They don't just like the technology, or find it easy to administer, they "love" it? My, they do sound like a balanced bunch of individuals, or rather you don't! IT guys I know will express a preference for certain vendor's tech, they will talk up one product over another, but they don't express to "love" it, that sounds more like extreme Sunshiner blind faith to me. Even the Sunshiners I know would draw the line at saying they "loved" a piece of Sun kit. You really need to get out more.
"....You obviously have some deep angst against anything and everything Sun...." More like you seem to have a deep rooted problem with anyone that disagrees with your personal assessment that the sun shines out of Sun's nether regions. In life, people will disagree with you - get over it.
"....Did Scott McNeally dump your mom?..." Scott wishes! Mind you, I suspect you'd be willing to offer up your own mother to the alter of the great Sunshine.
"....Did a Sun Sales Rep run over your cat? What is it?...." You just can't accept that anyone wouldn't "love" Sun. In order for you to balance the idea that someone wouldn't want Sun kit you have to invent some highly dramatic grievance or family feud. I'll spell it out for you - my technical appraisal of Sun's current technology, it's market position, and it strategy, are that Sun is in steep downward spiral and nothing short of drastic change will save it.
You really are an ultimate example of the blind Sunshiner cultist, for you it's like McNeally speaks The Truth and all speak against him must be shouted down. I suggest you find a new "religion" soon, Sun is long past its sell-by date.
You've written close to two and a half thousand words in the comments section of this entry alone. Go ahead, count em.
I think it's pretty apparent that apart from being incredibly full of hot air, it's clear you also have a (paid?) agenda of some sort against Sun, and plenty of time on your hands to carry out your little one-man crusade on El Reg's comments board.
I'll give you a tip though, make your trolling brief at least - folk tend to switch off when presented with a diatribe two times the length of a first-year university essay on a tech forum.
"You've written close to two and a half thousand words in the comments section of this entry alone..." Ah, once again I see you fall back on that razor sharp technical analysis. Oh, hold on a sec, no you didn't. In fact, you rarely try any sort of technical argument you just get all huffy. Is it your period?
"....it's clear you also have a (paid?) agenda of some sort against Sun...." Once again, more of the disbelief that anyone could actually not like Sun kit without some despicable motive. I shall repeat - I don't work for HP nor for an HP reseller, it's just my opinion that Sun suck. No nefarious conspiracy theories neccessary (are you one of them lame Troofers? Is Sun employing Scientologists?), I just don't share your myopic love for all things Sun because I have real industry experience and the ability to think for myself.
"....your little one-man crusade on El Reg's comments board...." And though you obviously don't like to admit it, I'm not the only posting that Sun haven't got clue.
"....folk tend to switch off when presented with a diatribe two times the length of a first-year university essay on a tech forum." Ah, is more than five words at a time a challenge for you? All I can say is you must have gone to a pretty down-market Uni then, my first year had much higher targets. That's assuming you even got past kindergarten.
Matt, .... if Sun is in troubles the HP Integrity line is not in any better shape with Itanic (despite how you are picturing nicely a well known dieing processor). Sure Intel has tons of money but, if you notice, they are putting all of them on Xeon not on the big (dieing) brother.
Intel (and HP) are fully committed to Xeon/Proliant ..... they are still doing Itanic/Integrity simply because they can't quite that market w/o loosing their face... but it's clear they are both disinvesting in that space.
Move onto the next religious war.