When you are the volume leader in the x64 server racket, as Hewlett-Packard is, you have customers who have all kinds of different needs, and when Intel launches a new processor for the workhorse two-socket portion of the server market, you go broad and you go deep to protect the HP server biz. So it comes as no surprise that HP …
If HP is so great...
...and Sun sucks, why do they get kicked in the butt in this benchmark?
Maybe Dell and Cisco should take a better look at Sun... Maybe they miss an opportunity here...
Same Location for power supplies?
"...With the ProLiant G6 rack servers, HP is also moving to a standard set of power supplies, which are all located in the same location within the servers to make it easier for admins...."
Wow, well done HP. Only 3 generations late, behind Dell.
they are bringing back Turbo, wonder if there is going to be button for it...
Wow.. that brings me back
Capping power - capping performance
It would be better if HP could build servers which don't gobble power and spew out heat in the first place. Try using low-power components rather than trying to sell us hot ones which we are then expected to turn down a bit.
a better look at Sun...
> Maybe Dell and Cisco should take a better look at Sun... Maybe they miss an opportunity here...
yes, please look. Sun reached a performance of 123k SAPS using 128 cores. Intel has 25k SAPS using 8 cores. So take a look again. Sun has 5 times the performance with 16 times the cores.... it's a shame!
RE: If HP is so great... & a better look at Sun..., & RE: Same Location for power supplies?
RE: RE: If HP is so great... & RE: a better look at Sun...
Or is that the same desperate Sunshiner? Just quit with the SAP bench figures, comparing latest Sun kit to four-year-old hp kit is just making yourself look stupid, we've been through a thorough debunking of that Sun sales FUD in several posts to these forums. In fact, it is even more embarrassing to you as the SAP figures just show up what a poor performer SPARC in any form is, let alone the Sun Galaxy boxes. Face it, Sun is dead, no-one with a clue will be buying kit with no future. What will you guys do when the Sun has set, sell 419 scams?
Personally, I find the sheer number of hp servers in the lower end of the ProLiant range a tad confusing, surely it would be better to just make one 1U rack chassis and one 2U rack chassis for the low- to mid-range Wintel/Lintel market, and then just offer the customers the ability to configure them up as they want? Mind you, hp don't make new lines without checking the numbers, so I assume they have their reasons. Can't really argue with the number one x64 server vedor!
RE: Same Location for power supplies?
And I'd like it if they copied the Dell cable arms, the Dell ones have a nice black coating which makes them not just less of an eyesore but also mean they don't have the sharp edges the ProLiant ones do.
@a better look at Sun..
The question is neither cores or sockets.
The question is, can any Intel setup serve 40k users at the same time (highest value in the benchmark), while providing all the needed RAS features?
I guess not...
Complete this sentence: "HP's quad-core "Shanghai" Opterons,"
And, to the power supply and energy complainers, please get a clue. HP has much, much more sophisticated energy management in their blade servers than Dell, and has had it for years. The blade power supplies are also modular, easy to hot plug, and you only need install as many of them as power requirements and redundancy dictates.
@@a better look at Sun..
Others (IBM Power, IBM z10 and Itanium2) can do that easily with the fraction of Sun Sparc cores and fraction of licensing costs.
RE: @@a better look at Sun..
Others (IBM Power, IBM z10 and Itanium2) can do that easily with the fraction of Fujitsu Sparc64 cores and fraction of licensing costs.
There, straigtened that out for you! I mean, who on Earth would be using Sun SPARC for SAP? ;)
@Matt "Loser" Bryant
What do you mean by 4 year old HP kit?
The benchmark was a direct comparison of Xeon Processor X5570 Systems.
And your beloved H-P did loose that benchmark by 12.5% !
OK, so we have articles on Nehalem's release, new IBM, hp and Dell servers, so where's the Sun Nehalem Kit? I thought they were dying to tell all at the 30th March event, or is The Reg so persona non grata now that Ashley's left that they didn't get an invite to the Hospital Club? ;)
Actually, I can't work out which is more ironic - the fact that Sun chose a venue dedicated to serving the "creative industries" (well, I suppose vapourware is covered, then), or that they chose a club with a name so appropriate to their critical condition!
RE: @Matt "Loser" Bryant
Lol, you guys are so bitter! Just accept the inevitable - Sun is dead because it made poor products with low appeal. But, if you want to continue your idiotic defence and provide us more humour, please reply with the SAP benchmark session number for whatever figures you want to discuss so we can all have another good laugh at you. Oh, and please let us know - when IBM has butchered up Sun and thrown most of it on the scrap heap, will you still be here muttering on about old SAP benchmarks? How long will it be before you just dry up and blow away?
RE: @Matt "Loser" Bryant
Re-posted in antcipation of a non-reply from our SAP-bench-waving Sunshiners (and with due deference to Jake for pointting out that it should be "hoist", not "hoisted"):
.....Now for the hoisting! Seeing as you seem so eager to throw Opteron SAP benchmark figures around, shall we look at benchmark session 2008062? Yes, the benchmark session that haunts Sunshiners everywhere! In November 2008 the poor ickle M3000 with the latest SPARCVII chip stumbled to a derisory 4180 SAPS. Care to look at bench session 2005024? Yes, that's the old hp BL25p Opteron blade from 2005 hitting 4880 SAPS. Mind you, it could have been worse, seeing as the BL25p also bested the later Niagara-based T2000 (4780 SAPS, December 2005, bench 2005047) and the Sunfire X4200 (4180 SAPS, December 2006, bench 2006087). Indeed, the BL25p G2 model totally creamed them when it posted 5250 SAPS (August 2006, bench 2006064). So it looks like SPARC is completly irrellevant whan compared to Opteron, they just can't even compete with the older versions!
But for real fun let's look at some more recent Opteron-based hp bench sessions. How about last December's 2008064, where the hp ProLiant DL785 G5 8-socket posted 35400 SAPS, compared to the October 2008 bench session 2008061, where the similar Sun Fire X4600M2 8-socket only managed 29670 SAPS. Yes, I know the Sunshiners will start whining about how the hp server had the 2.7GHz 8384 4-core Opterons, whereas Sun's server had to make do with the 2.5GHz 8360 4-core Opterons, but it's strange that 8% jump in CPU clock gave a 20% jump in performance. Oh, hold on a sec, I see the differentiator - the Sun box was struggling with Slowaris 10, whereas the DL was humming along with SuSE Linux. Looks like SPARC isn't just shown up by the SAP benchmarks, Slowaris on x64 is also exposed as the complete shadow of a real Linux.
And to close, may fave de-Sunshiner! Bench 2006089, from December 2006, where a 64-core Superdome using those old 1.6GHz 9050 dual-core Itaniums still posted 152530 SAPS, compared to the latest Sun M9000 with 64 Fujitsu dual-core 2.4GHz SPARCVIIs, which only managed 129420 SAPS in November 2008! Even with the latest M9000 being stacked with double the RAM of the old model Superdome, the latest Sun kit couldn't compete. Core for core, the latest SPARCVII got thrashed by a three-year-old Itanium. No wonder the Sunshiners are FUDing Tukzilla so hard.
Looks like their desperation to FUD stretches to Nehalem too, which is ironic seeing as it seems the only bit of the Sun server range with a future! Any salesbod or BOFH wanting to beat up Sun or a Sunshiner please feel free to use the above gratis, it's only fair to share the fun!
Re: MB the Liar
"And to close, may fave de-Sunshiner! Bench 2006089, from December 2006, where a 64-core Superdome using those old 1.6GHz 9050 dual-core Itaniums still posted 152530 SAPS, compared to the latest Sun M9000 with 64 Fujitsu dual-core 2.4GHz SPARCVIIs, which only managed 129420 SAPS in November 2008! Even with the latest M9000 being stacked with double..."
I can't allow your FUD (lying) to go un-rebuked any longer. You are lying.
- The 129,420 SAP's for the M9000 was with the Dual-Core SPARC64 VI, not the SPARC64 VII as you claim.
- The record for SAP's is the M9000 with SPARC64 VII's at 196,564 SAPS.
So, seeing how Matt continues to lie, I can't believe that he even believes himself any more. Go home Matt. No ones buying your bull.
Also, other than licensing cost, which is not everything, who cares about cores to cores comparisons? It's about system to system and HP is in sad shape, and with IBM+Sun, and Intel likely to leave the lagging Itanium market, prepare for HP to abandon the highend for the midrange and low end where Nehalem will take them.