Hewlett-Packard held its 3Q FY2007 Server Quarterly Business Update for IT Analysts on 9/6 to provide the “story behind the numbers” and answer analysts’ irritating questions.  We were assured that HP is the most efficient supplier of storage and servers…

Had a briefing from a company who has an interesting approach to making virtualization more efficient and less resource hungry. FastScale is a new (founded 1/06) Sunnyvale company that has developed a virtualization provisioning package that cuts down the size of virtualized guest operating systems and applications by as much as 99%. In a RHEL4/Apache example, the standard load of application, libraries, drivers, etc., totals 3GB. With FastScale, the same software, with the same functionality only needs to load 30MB of data. Their secret sauce is their software that analyzes the application software from a needs standpoint, and then only loads as much of the operating system (and application) as is absolutely needed for the environment. Unnecessary drivers don’t load; libraries that aren’t needed don’t go on the system, even parts of the application that aren’t applicable to the particular installation are jettisoned.

I wish I weren’t just coming off a full day of airline hell…then I might have an easier time finding the words to savage the thinking behind Sun Microsystems move from their SUNW ticker to the JAVA symbol. Lots of folks have already weighed in, with reactions ranging from bemusement (most outsiders) to anger (as I’ve heard from Sun insiders). The justification from Jonathan is that this is all about brand equity and that OpenOffice and Java are two of the best known brands on the internet. He goes on to say…

Some of you visitors may have made your way here through a link on The Register. I was a recent guest on an Ashlee Vance Semi-Coherent Computing Meatcast where we discussed the x86 server market, x86 virtualization, and a few…

Science (a really important scientific journal, maybe the only one you need – which is why they can get away with calling themselves “Science”) is set to publish papers by IBM researchers this week on the possibility of atomic-level computing….

Kind of a strange situation on the press/analyst call after the joint Sun/IBM press conference (see separate post for details)a reporter (or analyst, I’m not saying which or using any names) asked a question. In the background, we could clearly hear a busy street scene and distant sirens. As he (or she) asked his (or her) question (yeah, I’ll knock the him/her stuff off now), we could hear stress in the voice and the sirens growing constantly closer. After the question was finished, we could hear the sirens come alarmingly close even more street sounds.Then the person on the phone said “oh sh*t”and dropped off the line.

Sun and IBM held a joint press conference today to announce that IBM will extend support for Solaris x86 to most of Big Blue’s x86 server offerings. IBM will distribute Solaris x86 and basically support it like any other x86 operating system. Sun will provide service and maintenance for the operating system, and both companies will spend money to qualify and test systems to ensure full compatibility and performance. You can find the joint press release here, and some pretty good analysis from The Register here (yeah, I’m linking to them because they quoted me.) So now that the “official” details are stipulated, let’s into discussion

I did my scheduled NGDC (Next Generation Data Center) virtualization tutorial session yesterday morning. It went the full three hours, five minutes over in fact, but I scheduled two breaks to keep it from becoming a total PowerPoint death march. We covered a lot of ground, beginning with current data center problems (server sprawl, complexity, power/cooling/floor space challenges, etc.) From there we discussed how virtualization, particularly in an x86 server context, can go a long way towards solving the problems or at least relieving some of the pain. We looked at benefits real customers are getting from x86 consolidation talked through a few case studies, and then took a relaxing break. We then covered the various methods to virtualize x86 boxes (hypervisor, O/S virtualization, non-native virtualization, etc.) and wrapped up with the GCG vision for data center peace, harmony, and efficiency.

Sun Microsystems publicly detailed their new Niagara II processor yesterday. Sun announced the processor with an intro presentation titled “ULTRASPARC T2: The Highest Performing, Most Energy Efficient Processor”. Typical understatement from Sun; when will these guys get develop some self esteem? Niagara II is an 8-core, 64-thread cpu that shows considerable improvement over their Niagara I processor. Each core now has its own floating point unit, which bumps FP performance by 10x, according to Sun. They also state that the 1.4GHz Niagara II provides double the throughput of Niagara I, at the same clock speed. In addition, Sun highlighted Niagara II’s meager energy requirements, benchmark performance, and integrated I/O. All the details are here.

Sun’s overarching theme (and value proposition) is that Niagara II offers industry leading power per core

I received a press release today that was different from the usual stuff that relentlessly flows through my inbox. IBM was touting the fact that their POWER chips are playing a key role in the upcoming (tomorrow) launch of NASA’s newest Mars mission. The goal is to fly the spacecraft 423 million miles, safely land a rover on the surface, and then direct it towards the North Pole region where it will collect and analyze samples to see if there is (or was) life in the red rock of Mars. It will also give us a chance to see if the Soviets have claimed the Martian North Pole as their property.