Mission Critical Computing Blog
Your source for the latest insights on HP Integrity, mission critical computing, and other relevant server and technology topics from the BCS team.

Server Power, Cooling, and Density, Tukwila, and more...

 


Last week, we had a training event for some of our internal as well as partner reps out here in California. One of the topics that I got to present multiple times was Greener UNIX.


 


I have asked the question, multiple times, about which has a higher importance: increasing server density, or allowing systems to take up more physical room but consuming less power. While I often get a mixed response, with the economy starting to recover, the answer was almost anonymous "help me get more stuff in my datacenter."


 


Most customers seem to like higher density - but hate the idea that while they might get much more performance, they might only deploy half full racks (preferably with blanking panels in them) since they can only power or cool at a certain density. You get more performance, smaller footprint, and a  much better price/performance, performance/watt, and performance/space. Hopefully the half full racks become less of an issue.


 


I also learned a few things, and got reminders about others:



  • Each watt saved on components has a significant multiplier - often >2.5x - by the time you get to the overall power and cooling draw.

  • High Efficiency power supplies, such as those used by HP BladeSystem and other HP servers, are great - but may save a few percent of system power usage. Turning on CPU power management, such as Green Active processors in HP-UX, has a much bigger impact on the total power usage than a more efficient power supply.

  • At least some of the people who work with customers mentioned that their customers are aware of the power savings features in HP-UX and on HP Integrity servers - even if they haven't implemented them yet. Implementation would be better, but at least people are talking about it.


 


Needless to say, there was talk around the Intel Itanium 9300 (aka Tukwila) announcement. I've seen some comments on the blog that people want to know about which servers will include these processors. The one comment, from the Intel press release, is "OEM systems are expected to ship within 90 days."


 


And on a personal note, I'm definitely enjoying the Olympics. However, having been born and raised in Canada, I'm happy to see the Canadian men's hockey team starting to have more success. The games against the Swiss and Team USA, my current home, were stressful to me as a fan. However, after dispatching the Russian team yesterday, I'm hoping to see a Canada and USA rematch - in the gold medal game.


 


Jacob

Performance Improvements that make a difference






With the
announcement earlier this week of the Intel Itanium 9300 processor, as well as
the IBM Power 7 processor, there was a lot of talk in the press and blogs about
system performance. Performance improvements are a good thing. They help you
process the ever increasing amount of information you need to handle, but with
smaller, more efficient, lower cost servers. Let's face it, a whole lot of the
tech industry is built upon the pursuit of Moore's law - doubling the number of
transistors every 18 months. Granted, despite the coverage this week, performance is usually not the only, or even most, important consideration when purchasing a server. There are a lot of other factors such as management, availability, virtualization, automation, and software stacks that play into the decision. However, since the talk this week is often around performance, let's go with that topic.


 


Performance is often, at least in the press, described by benchmarks. Having said
that, many people realize that even when it comes to performance,  it isn't performance benchmarks that matter,
it is the real-world performance of your application, in your datacenter, that
matters. So, in this week when performance seems to be the hot topic, here are
a couple of things you may have missed over the previous few months.


 


First, last fall, HP
rolled out a number of papers and webcasts around the 2009 Gabriel UNIX
research. Gabriel Consulting surveyed UNIX users from all three major vendors.
But despite what the benchmarks may suggest, it turned out that HP Integrity
and HP-UX users had the highest ratings for
real-world, observed performance
. While benchmarks are interesting, they
don't tell the whole story, as everyone knows.


 


The second thing
around performance that you may have missed was some
updates to HP-UX 11i v3
in September and November of 2009. In September
2009 there were updates to LVM, and in November 2009, there were updates to
VxFS and OnlineJFS. Direct I/O and Concurrent I/O are now supported, and they
drastically increase the speed of the file system. How much? Performance now
comes in around 96% to 99% of raw disks, but with the manageability of a file
system. One manufacturing customer who shared their results with us found that
their 6 hour batch job dropped to 2 hours after they implemented Concurrent I/O
around the New Year. Concurrent I/O definitely helps with workloads that have
both reads and writes.


 


This type of
performance upgrade absolutely helps with observed, real-world performance.
However, it often isn't reflected in benchmark results, which are often run on
systems tuned for peak performance, and not real-world, managed environments.  If you are running HP-UX 11i v3, you just
need to update. If you are running HP-UX 11i v1 or v2, this gives you another
incentive to upgrade to HP-UX 11i v3.


 


The best part? For
HP-UX 11i customers with support contracts, you can get this performance
improvement at no additional charge. No extra software license fees. No new
hardware. No migration costs. Now that is a performance improvement that really
pays off!


 


Jacob


 

Search
Showing results for 
Search instead for 
Do you mean 
Follow Us
Featured


About the Author(s)
  • I work as a Master Architect in HP Servers R & D group. I work with teams spread across the lab and outside to build solutions which are highly available on HP-UX, OpenVMS and Mission Critical Linux platforms. In particular I contribute to develop HP Serviceguard clusters, HP-UX Security and Middleware products. I have been with HP for last 17 years and have exposure to HA/DR field from both R & D and customer perspectives.
  • Kirk Bresniker is the Vice President/Chief Technologist for HP Business Critical Systems where he has technical responsibility for all things Mission Critical, including HP-UX, NonStop and scalable x86 platforms. He joined HP in 1989 after graduating from Santa Clara University and has been an HP Fellow since 2008.
  • I’m the worldwide marketing manager for HP NonStop. I’ll be blogging and tweeting out news as it relates to NonStop solutions – you can find me here and on twitter at @CarolynatHP
  • Cynthia is part of the HP ExpertOne team. ExpertOne offers professional IT training and certifications from infrastructure refresh to areas that span across the datacenter like Cloud and Converged Infrastructure.
  • Hi, I work on the HP Servers team as HP-UX worldwide product marketing manager. I´m interested in how customers use our technology and will be blogging about their stories and on how our products evolve to help their businesses be always on.
  • I have worked with NonStop systems since 1982. I am a Master Technologist for HP and am part of the IT SWAT organization, the Cloud SWAT and work with HP Labs. I report into the Enterprise Solutions and Architecture organization.
  • Joe Androlowicz is a Technical Communications and Marketing manager in HP’s NonStop Product Division. Joe is a 25 year journeyman in information systems design, instructional technologies and multimedia development. He left Apple Computer for Tandem Computers to help launch G03 and hasn’t looked back yet. He previously managed the program management team for the NonStop Education and Training Center and drove the development and growth of the NonStop Certification programs.
  • Hello! I am a social media manager for servers, so my posts will be geared towards HP server-related news & info.
  • HP Servers, Converged Infrastructure, Converged Systems and ExpertOne
  • Luke Oda is a member of the HP's BCS Marketing team. With a primary focus on marketing programs that support HP's BCS portfolio. His interests include all things mission-critical and the continuing innovation that HP demonstrates across the globe.
  • I am the Superdome 2 Product Manager. My interest is to learn how mission critical platform helps customers and would also like to share my thoughts on how Superdome has been helping customers and will continue to do so.
  • I work in the HP Servers marketing group, managing a marketing team responsible for marketing solutions for enterprise customers who run mission-critical workloads and depend on HP to keep their business continuously running.
  • Mohan Parthasarathy is a Technical Architect in the HP-UX lab. His primary focus currently is in the core kernel, platform enablement and virtualization areas of HP-UX. Mohan has worked on various modules of HP-UX, including networking protocol stacks, drivers, core kernel and virtualization
  • I’ll be blogging about the latest news and enhancements as it relates to HP Moonshot.
  • Greetings! I am on the HP Enterprise Group marketing team. Topics I am interested in include Converged Infrastructure, Converged Systems and Management, and HP BladeSystem.
  • As a Managing Consultant for HP’s Enterprise Solution & Architecture group, I collaborate with client business and IT senior management to understand, prioritize and architect advanced use of data and information, drawing insights required to make informed business decisions. My current focus leverages event-driven business intelligence design techniques and technologies to identify patterns, anticipate outcomes and proactively optimize business response creating a differentiated position in the marketplace for the client.
  • Wendy Bartlett is a Distinguished Technologist in HP’s NonStop Enterprise Division, and focuses on dependability – security and availability - for the NonStop server line. She joined Tandem in 1978. Her other main area of interest is system architecture evolution. She has an M.S. degree in computer science from Stanford University.
  • I am part of the integrated marketing team focused on HP Moonshot System and HP Scale-up x86 and Mission-critical solutions.
Labels
The opinions expressed above are the personal opinions of the authors, not of HP. By using this site, you accept the Terms of Use and Rules of Participation.