Displaying articles for: August 2008
There's been a rash of coverage in the trade press recently about the role that lack of standards plays as an inhibitor to the blades market.
On the face of it, standards for blades are attractive, offering the ability for third parties to build a single version of things like switches, and offering the ability to source blades from multiple vendors, with the implication that you can select from the best new implementations while maintaining much more independence from vendor lock-in. And on this last point, some of the commentators are correct - commitment to a specific blade architecture implies a higher degree of commitment to a vendor than does a rack-mount server purchase, because of the fact that the infrastructure is unique. But then again, it's not hugely different than committing to a specific brand of rack mount server. The main difference is that the commitment is now modulo 8, 16 or 32, rather than one (and yes, there is some initial startup investment in training, etc).
But before we run away in the direction of standards, we need to answer a fundamental question - do we loose more than we gain by designing and building standard blade servers, and how different is the real data center environment today when considering vendor lock-in in an environment of standard servers?
Standards versus innovation, the balancing act
The vision of a standard blade is compelling, but there are real tradeoffs. The first, and most important over the long term, is innovation. A standard blade implies more than just a standard form factor and connector. It assumes similar behavior, which in turn implies similar resources, or at least a consistent logical presentation of resources (think of a HAL on steroids), which will be very difficult to implement if the underlying system architecture changes radically. And change is certain. Blade servers have gone through multiple generations of fundamental architectural change since their commercial introduction in approximately 2001, and can be expected to go through additional change over the next decade as architectures evolve. The evolution will involve fundamental refactoring f the architectures, particularly the I/O and networking infrastructure and power management. Industry analysts have pointed out future innovations in virtualized I/O architectures, for example, that will require some fundamental re-engineering of future systems. To attempt to force future architects to accommodate a standard blade when considering these fundamental changes is a major inhibitor of future customer value over the long term.
The issue of standardizing blades and their behavior goes deeper, since, as mentioned above, there will be some expectation of consistent behavior. This will in turn begin to infiltrate management architecture, and will potentially ripple through the entire software stack, forcing all vendors into a least common denominator management stack. Vendor management stacks are differentiated for a reason - both their designers and their customer believe they add value, and the future evolution of dynamic data centers with virtualized environments demands that users and vendors have room to innovate. The path to the next level of data center architecture will be a messy decade-long process, almost certainly marked by some spectacular successes as well as some embarrassing failures, but the handicap it now by attempting to freeze one of the most important centers of architectural innovation is premature and short-sighted.
Standards and Vendor Lock-in
The notion of a truly standardized blade that users can buy from multiple sources and plug into their enclosures from any vendor has a lot of attraction at first blush. But wait! We have been buying little rack mount servers for more than a decade, and they have about the most standardized interfaces possible - a few Ethernet ports, some SCSI connections, a power plug, and a rack format that has been with us since before World War II. Why don't users mix and match servers freely in their environments, and why haven't we been able to buy standard boards that can plug into our Dell, IBM and HP rack servers, which after all, should have been easier to standardize than the more complex blade system architectures? The truth is that even in something as supposedly standardized as a rack mount server, vendors continually innovate, and that there is considerable value in the entire management environment, as well as in the totality of the vendor relationship. These last two points are particularly critical when considering blade servers. With management costs increasingly dominating the operations picture, the value of a consistent management environment and a smooth vendor relationship probably eclipses any small theoretical advantage in cost that might be obtained from multiple sources of server boards.
Furthermore, the notion that independent standard vendors will lower prices significantly has potential flaws. The market for blade servers is already extremely competitive, and with Dell now entering with a competent product, will become more so. And our customers are not stupid - they understand that major new projects represent important junctures for vendor competition, and behave accordingly. Another hole in the competitive price scenario is the pattern of volume in the industry. Right now, HP and IBM account for over 80% of the market volume, and have developed accordingly efficient supply chains to support these volumes. It's hard to make a case that an ecosystem of multiple smaller sources could do much better.
Lets Go to Fry's and Buy a Blade
But suppose, for a moment, that everything I say is so totally wrong (my kids think that all the time) that within six months we have a standard for blades, and you are operating a data center with a nice set of enclosures, hopefully from HP, designed for these standard blades. Your sales rep convinced you that your initial installation should at least have the vendor's own branded blades. Everything works fine. Now its time to add some capacity and your boss gives you a shopping list and you head down to Fry's. In the blade aisle you have the branded blades from HP, and some really great bargains from the same people who sell you modems, ATX motherboards and chassis. Some of them are cheaper than others. But they are all standards-compliant, meeting the MBDB (Minimal Brain Dead Blade) industry standard. But hey, the standard never said anything about build quality, signal integrity above a certain minimum, and a host of other subtleties that go into making a true enterprise quality blade.
Take a couple back to your data center, along with maybe a couple of power supplies and a new switch, plug them in, and see what happens. Seems pretty OK to me. And when it fails, I'm sure all the multiple vendors as well as your own internal engineering groups and users will be quite understanding and more than willing to work together to solve your problem.
OK, so I'm engaging in a little reduction-ad-absurdum argumentation, but the germ of truth is there - third party blade suppliers will need to be qualified even more rigorously than the primary vendor's equipment, and support arrangements will need to be modified. Most organizations today do not want to cope with the support of mixed vendor environments except across fairly coarse project, application or infrastructure function boundaries. To do so within a single enclosure is an almost insurmountable burden. It is also an activity that adds nothing in fundamental business value while consuming resources that almost certainly would be better employed elsewhere.
Absent Standards, Where Do We Go From Here?
It's a very Dickensonian world we live in, as in "It was the best of times. It was the worst of times." Vendors will continue to innovate and compete. Successive waves of products will get better and will not be standardized for the foreseeable future. Users will continue to be forced to make major commitments to complex infrastructures, and will have to spend the time and resources to understand the new technologies. But the solutions they get will deliver real business value, and competition will keep vendors as honest and efficient as they can be. Not a bad situation for consumers of technology.
So in the final analysis, will standards really limit the growth of blades? All of the industry observers agree that blades will remain the fastest growing segment of the server market, and at HP, we are still seeing blade growth well in excess of the industry forecasts. Clearly something is working here, despite the lack of standards.
Yesterday I participated on a panel discussion sponsored by ComputerWorld. I was joined by Kurt Lender of Intel and Alex Yost of IBM. We had a friendly discussion on the importance of innovation and standards for blades.
I guess there were no surprises coming from any of us, but on reflection, I think there are some interesting points to be made.
First Kurt Lender of Intel is proposing the need for more standards around the form factors of blades and interconnects (primarily aimed at SMB markets). His view includes standardization down to the motherboard dimensions. However I was struck by his emphasis on the value this brings to the manufacturers of server and blade components. I guess his point is that such standards benefit those suppliers. But somewhat left out is what exactly is the benefit to customers. He did mention the opportunity for suppliers to innovate, but I don't recall exactly what sort of useful innovations he had in mind for customers.
Alex Yost gave his usual pitch for BladeCenter. His version of open standards was blade.org. I think this is telling of what IBM really has in mind when it comes to standards: If you go to http://www.blade.org/ it looks like this is an open forum to promote blades. Until you read the fine print buried in the bylaws that: "Blade Platform shall mean the IBM BladeCenter or the Intel Blade server platform based on the common IBM/Intel blade specification". It appears to me that Mr. Yost wants to make blade.org sound open, yet it really is exclusive to IBM's blade form factor.
During the discussion I tried to be very frank about HP's position on standards. We think they are great for enabling interoperability. The key for blades systems is that they interoperate with data center standards such as Ethernet, Fibre Channel and 19 inch racks. Our take is that standardizing form factors at the component or motherboard level will limit innovation. The fact of the matter is that the form factors in our industry that are the most standardized are also the places with the least innovation and the least growth. Innovation is good for customers and growth is good for vendors - everyone wins.
Now that is not to say that HP believes we can do it all ourselves. This is why we have the Solution Builder program with over 300 partners - so customers can get the complete solutions they want. We're just not going to pretend that Solution Builder is something it is not.
I'll post the link to the panel discussion once it is available.
With all the recent debate about the value of blade standardization vs. innovation, I kept thinking a lot about the nature and value of invention. That's when I remembered learning about the the Theory of Inventive Problem Solving; better known as TRIZ.
Did you know that someone actually studied over 200,000 patents, then categorized ALL of them into just 40 universal principles of innovation? His name was Genrich S. Altshuller.
But before I go any further about Genrich, you need to know a little bit about TRIZ. Read on if you have a minute, then come back tomorrow and I'll connect all the dots for you to blades. That's when we'll discuss how big (or small) of an innovation blades really are and give some examples of TRIZ principles put in action with the HP BladeSystem.
Here's a summary of TRIZ from http://www.mazur.net/triz/:
Genrich S. Altshuller was born in the former Soviet Union in 1926. His first invention, for scuba diving, was when he was only 14 years old. His hobby led him to pursue a career as a mechanical engineer. Serving in the Soviet Navy as a patent expert in the 1940s, his job was to help inventors apply for patents. He found, however, that often he was asked to assist in solving problems as well. His curiosity about problem solving led him to search for standard methods.
In the next few years, Altshuller screened over 200,000 patents looking for inventive problems and how they were solved. Of these, only 40,000 had somewhat inventive solutions; the rest were straight forward improvements. Altshuller more clearly defined an inventive problem as one in which the solution causes another problem to appear, such as increasing the strength of a metal plate causing its weight to get heavier. Usually, inventors must resort to a trade-off and compromise between the features and thus do not achieve an ideal solution. In his study of patents, Altshuller found that many described a solution that eliminated or resolved the contradiction and required no trade-off.
Altshuller categorized these patents in a novel way. Instead of classifying them by industry, such as automotive, aerospace, etc., he removed the subject matter to uncover the problem solving process. He found that often the same problems had been solved over and over again using one of only forty fundamental inventive principles. If only later inventors had knowledge of the work of earlier ones, solutions could have been discovered more quickly and efficiently.
He categorized the solutions into five levels.
- Level one: Routine design problems solved by methods well known within the specialty. No invention needed. About 32% of the solutions fell into this level.
- Level two: Minor improvements to an existing system, by methods known within the industry. Usually with some compromise. About 45% of the solutions fell into this level.
- Level three: Fundamental improvement to an existing system, by methods known outside the industry. Contradictions resolved. About 18% of the solutions fell into this category.
- Level four: A new generation that uses a new principle to perform the primary functions of the system. Solution found more in science than in technology. About 4% of the solutions fell into this category.
- Level five: A rare scientific discovery or pioneering invention of essentially a new system. About 1% of the solutions fell into this category.
What Altshuller tabulated was that over 90% of the problems engineers faced had been solved somewhere before. If engineers could follow a path to an ideal solution, starting with the lowest level, their personal knowledge and experience, and working their way to higher levels, most of the solutions could be derived from knowledge already present in the company, industry, or in another industry.
Altshuller distilled the problems, contradictions, and solutions in these patents into a theory of inventive problem solving which he named TRIZ.
Divide an object into independent parts.
- Replace mainframe computer by personal computers.
- Replace a large truck by a truck and trailer.
- Use a work breakdown structure for a large project.
Make an object easy to disassemble.
- Modular furniture
- Quick disconnect joints in plumbing
Increase the degree of fragmentation or segmentation.
- Replace solid shades with Venetian blinds.
- Use powdered welding metal instead of foil or rod to get better penetration of the joint.
Separate an interfering part or property from an object, or single out the only necessary part (or property) of an object.
- Locate a noisy compressor outside the building where compressed air is used.
- Use fiber optics or a light pipe to separate the hot light source from the location where light is needed.
- Use the sound of a barking dog, without the dog, as a burglar alarm.
3. Local quality
Change an object's structure from uniform to non-uniform, change an external environment (or external influence) from uniform to non-uniform.
- Use a temperature, density, or pressure gradient instead of constant temperature, density or pressure.
Make each part of an object function in conditions most suitable for its operation.
- Lunch box with special compartments for hot and cold solid foods and for liquids.
Make each part of an object fulfill a different and useful function.
- Pencil with eraser
- Hammer with nail puller
- Multi-function tool that scales fish, acts as a pliers, a wire stripper, a flat-blade screwdriver, a Phillips screwdriver, manicure set, etc.
Change the shape of an object from symmetrical to asymmetrical.
- Asymmetrical mixing vessels or asymmetrical vanes in symmetrical vessels improve mixing (cement trucks, cake mixers, blenders).
- Put a flat spot on a cylindrical shaft to attach a knob securely.
If an object is asymmetrical, increase its degree of asymmetry.
- Change from circular O-rings to oval cross-section to specialized shapes to improve sealing.
- Use astigmatic optics to merge colors. 5. Merging
Bring closer together (or merge) identical or similar objects, assemble identical or similar parts to perform parallel operations.
- Personal computers in a network
- Thousands of microprocessors in a parallel processor computer
- Vanes in a ventilation system
- Electronic chips mounted on both sides of a circuit board or subassembly
Make operations contiguous or parallel; bring them together in time.
- Link slats together in Venetian or vertical blinds.
- Medical diagnostic instruments that analyze multiple blood parameters simultaneously
- Mulching lawnmower 6. Universality
Make a part or object perform multiple functions; eliminate the need for other parts.
- Handle of a toothbrush contains toothpaste
- Child s car safety seat converts to a stroller
- Mulching lawnmower (Yes, it demonstrates both Principles 5 and 6, Merging and Universality.)
- Team leader acts as recorder and timekeeper.
- CCD (Charge coupled device) with micro-lenses formed on the surface 7. Nested doll
Place one object inside another; place each object, in turn, inside the other.
- Measuring cups or spoons
- Russian dolls
- Portable audio system (microphone fits inside transmitter, which fits inside amplifier case)
Make one part pass through a cavity in the other.
- Extending radio antenna
- Extending pointer
- Zoom lens
- Seat belt retraction mechanism
- Retractable aircraft landing gear stow inside the fuselage (also demonstrates Principle 15, Dynamism). 8. Anti-weight
To compensate for the weight of an object, merge it with other objects that provide lift.
- Inject foaming agent into a bundle of logs, to make it float better.
- Use helium balloon to support advertising signs.
To compensate for the weight of an object, make it interact with the environment (e.g. use aerodynamic, hydrodynamic, buoyancy and other forces).
- Aircraft wing shape reduces air density above the wing, increases density below wing, to create lift. (This also demonstrates Principle 4, Asymmetry.)
- Vortex strips improve lift of aircraft wings.
- Hydrofoils lift ship out of the water to reduce drag. 9. Preliminary anti-action
If it will be necessary to do an action with both harmful and useful effects, this action should be replaced with anti-actions to control harmful effects.
- Buffer a solution to prevent harm from extremes of pH.
Create beforehand stresses in an object that will oppose known undesirable working stresses later on.
- Pre-stress rebar before pouring concrete.
- Masking anything before harmful exposure: Use a lead apron on parts of the body not being exposed to X-rays. Use masking tape to protect the part of an object not being painted 10. Preliminary action
Perform, before it is needed, the required change of an object (either fully or partially).
- Pre-pasted wall paper
- Sterilize all instruments needed for a surgical procedure on a sealed tray.
Pre-arrange objects such that they can come into action from the most convenient place and without losing time for their delivery.
- Kanban arrangements in a Just-In-Time factory
- Flexible manufacturing cell 11. Beforehand cushioning
Prepare emergency means beforehand to compensate for the relatively low reliability of an object.
- Magnetic strip on photographic film that directs the developer to compensate for poor exposure
- Back-up parachute
- Alternate air system for aircraft instruments 12. Equipotentiality
In a potential field, limit position changes (e.g. change operating conditions to eliminate the need to raise or lower objects in a gravity field).
- Spring loaded parts delivery system in a factory
- Locks in a channel between 2 bodies of water (Panama Canal)
- Skillets in an automobile plant that bring all tools to the right position (also demonstrates Principle 10, Preliminary Action) 13. The other way round
Invert the action(s) used to solve the problem (e.g. instead of cooling an object, heat it).
- To loosen stuck parts, cool the inner part instead of heating the outer part.
- Bring the mountain to Mohammed, instead of bringing Mohammed to the mountain.
Make movable parts (or the external environment) fixed, and fixed parts movable.
- Rotate the part instead of the tool.
- Moving sidewalk with standing people.
- Treadmill (for walking or running in place.)
Turn the object (or process) 'upside down'.
- Turn an assembly upside down to insert fasteners (especially screws).
- Empty grain from containers (ship or railroad) by inverting them. 14. Spheroidality - Curvature
Instead of using rectilinear parts, surfaces, or forms, use curvilinear ones; move from flat surfaces to spherical ones; from parts shaped as a cube (parallelepiped) to ball-shaped structures.
- Use arches and domes for strength in architecture.
Use rollers, balls, spirals, domes.
- Spiral gear (Nautilus) produces continuous resistance for weight lifting.
- Ball point and roller point pens for smooth ink distribution
Go from linear to rotary motion, use centrifugal forces.
- Produce linear motion of the cursor on the computer screen using a mouse or a trackball.
- Replace wringing clothes to remove water with spinning clothes in a washing machine.
- Use spherical casters instead of cylindrical wheels to move furniture. 15. Dynamics
Allow (or design) the characteristics of an object, external environment, or process to change to be optimal or to find an optimal operating condition.
- Adjustable steering wheel (or seat, or back support, or mirror position...)
Divide an object into parts capable of movement relative to each other.
- The *butterfly* computer keyboard, (also demonstrates Principle 7, *Nested doll*.)
If an object (or process) is rigid or inflexible, make it movable or adaptive.
- The flexible boroscope for examining engines
- The flexible sigmoidoscope, for medical examination 16. Partial or excessive actions
If 100 percent of an object is hard to achieve using a given solution method then, by using 'slightly less' or 'slightly more' of the same method, the problem may be considerably easier to solve.
- Over spray when painting, then remove excess. (Or, use a stencil--this is an application of Principle 3, Local Quality and Principle 9, Preliminary anti-action).
- Fill, then *top off* when filling the gas tank of your car. 17. Another dimension
To move an object in two- or three-dimensional space.
- Infrared computer mouse moves in space, instead of on a surface, for presentations.
- Five-axis cutting tool can be positioned where needed.
Use a multi-story arrangement of objects instead of a single-story arrangement.
- Cassette with 6 CD s to increase music time and variety
- Electronic chips on both sides of a printed circuit board
- Employees *disappear* from the customers in a theme park, descend into a tunnel, and walk to their next assignment, where they return to the surface and magically reappear.
Tilt or re-orient the object, lay it on its side.
- Dump truck
Use 'another side' of a given area.
- Stack microelectronic hybrid circuits to improve density. 18. Mechanical vibration
Cause an object to oscillate or vibrate.
- Electric carving knife with vibrating blades
Increase its frequency (even up to the ultrasonic).
- Distribute powder with vibration.
Use an object's resonant frequency.
- Destroy gall stones or kidney stones using ultrasonic resonance.
Use piezoelectric vibrators instead of mechanical ones.
- Quartz crystal oscillations drive high accuracy clocks.
Use combined ultrasonic and electromagnetic field oscillations.
- Mixing alloys in an induction furnace 19. Periodic action
Instead of continuous action, use periodic or pulsating actions.
- Hitting something repeatedly with a hammer
- Replace a continuous siren with a pulsed sound.
If an action is already periodic, change the periodic magnitude or frequency.
- Use Frequency Modulation to convey information, instead of Morse code.
- Replace a continuous siren with sound that changes amplitude and frequency.
Use pauses between impulses to perform a different action.
- In cardio-pulmonary respiration (CPR) breathe after every 5 chest compressions. 20. Continuity of useful action
Carry on work continuously; make all prts of an object work at full load, all the time.
- Flywheel (or hydraulic system) stores energy when a vehicle stops, so the motor can keep running at optimum power.
- Run the bottleneck operations in a factory continuously, to reach the optimum pace. (From theory of constraints, or takt time operations)
Eliminate all idle or intermittent actions or work.
- Print during the return of a printer carriage--dot matrix printer, daisy wheel printers, inkjet printers. 21. Skipping
Conduct a process , or certain stages (e.g. destructible, harmful or hazardous operations) at high speed.
- Use a high speed dentist s drill to avoid heating tissue.
- Cut plastic faster than heat can propagate in the material, to avoid deforming the shape. 22. *Blessing in disguise* or *Turn Lemons into Lemonade*
Use harmful factors (particularly, harmful effects of the environment or surroundings) to achieve a positive effect.
- Use waste heat to generate electric power.
- Recycle waste (scrap) material from one process as raw materials for another.
Eliminate the primary harmful action by adding it to another harmful action to resolve the problem.
- Add a buffering material to a corrosive solution.
- Use a helium-oxygen mix for diving, to eliminate both nitrogen narcosis and oxygen poisoning from air and other nitrox mixes.
Amplify a harmful factor to such a degree that it is no longer harmful.
- Use a backfire to eliminate the fuel from a forest fire. 23. Feedback
Introduce feedback (referring back, cross-checking) to improve a process or action.
- Automatic volume control in audio circuits
- Signal from gyrocompass is used to control simple aircraft autopilots.
- Statistical Process Control (SPC) -- Measurements are used to decide when to modify a process. (Not all feedback systems are automated!)
- Budgets --Measurements are used to decide when to modify a process.
If feedback is already used, change its magnitude or influence.
- Change sensitivity of an autopilot when within 5 miles of an airport.
- Change sensitivity of a thermostat when cooling vs. heating, since it uses energy less efficiently when cooling.
- Change a management measure from budget variance to customer satisfaction. 24. 'Intermediary'
Use an intermediary carrier article or intermediary process.
- Carpenter s nailset, used between the hammer and the nail
Merge one object temporarily with another (which can be easily removed).
- Pot holder to carry hot dishes to the table 25. Self-service
Make an object serve itself by performing auxiliary helpful functions
- A soda fountain pump that runs on the pressure of the carbon dioxide that is used to *fizz* the drinks. This assures that drinks will not be flat, and eliminates the need for sensors.
- Halogen lamps regenerate the filament during use--evaporated material is redeposited.
- To weld steel to aluminum, create an interface from alternating thin strips of the 2 materials. Cold weld the surface into a single unit with steel on one face and copper on the other, then use normal welding techniques to attach the steel object to the interface, and the interface to the aluminum. (This concept also has elements of Principle 24, Intermediary, and Principle 4, Asymmetry.)
Use waste resources, energy, or substances.
- Use heat from a process to generate electricity: *Co-generation*.
- Use animal waste as fertilizer.
- Use food and lawn waste to create compost. 26. Copying
Instead of an unavailable, expensive, fragile object, use simpler and inexpensive copies.
- Virtual reality via computer instead of an expensive vacation
- Listen to an audio tape instead of attending a seminar.
Replace an object, or process with optical copies.
- Do surveying from space photographs instead of on the ground.
- Measure an object by measuring the photograph.
- Make sonograms to evaluate the health of a fetus, instead of risking damage by direct testing.
If visible optical copies are already used, move to infrared or ultraviolet copies.
- Make images in infrared to detect heat sources, such as diseases in crops, or intruders in a security system. 27. Cheap short-living objects
Replace an inexpensive object with a multiple of inexpensive objects, comprising certain qualities (such as service life, for instance).
- Use disposable paper objects to avoid the cost of cleaning and storing durable objects. Plastic cups in motels, disposable diapers, many kinds of medical supplies. 28 Mechanics substitution
Replace a mechanical means with a sensory (optical, acoustic, taste or smell) means.
- Replace a physical fence to confine a dog or cat with an acoustic *fence* (signal audible to the animal).
- Use a bad smelling compound in natural gas to alert users to leakage, instead of a mechanical or electrical sensor.
Use electric, magnetic and electromagnetic fields to interact with the object.
- To mix 2 powders, electrostatically charge one positive and the other negative. Either use fields to direct them, or mix them mechanically and let their acquired fields cause the grains of powder to pair up.
Change from static to movable fields, from unstructured fields to those having structure.
- Early communications used omnidirectional broadcasting. We now use antennas with very detailed structure of the pattern of radiation.
Use fields in conjunction with field-activated (e.g. ferromagnetic) particles.
- Heat a substance containing ferromagnetic material by using varying magnetic field. When the temperature exceeds the Curie point, the material becomes paramagnetic, and no longer absorbs heat. 29. Pneumatics and hydraulics
Use gas and liquid parts of an object instead of solid parts (e.g. inflatable, filled with liquids, air cushion, hydrostatic, hydro-reactive).
- Comfortable shoe sole inserts filled with gel
- Store energy from decelerating a vehicle in a hydraulic system, then use the stored energy to accelerate later. 30. Flexible shells and thin films
Use flexible shells and thin films instead of three dimensional structures
- Use inflatable (thin film) structures as winter covers on tennis courts.
Isolate the object from the external environment using flexible shells and thin films.
- Float a film of bipolar material (one end hydrophilic, one end hydrophobic) on a reservoir to limit evaporation. 31. Porous materials
Make an object porous or add porous elements (inserts, coatings, etc.).
- Drill holes in a structure to reduce the weight.
If an object is already porous, use the pores to introduce a useful substance or function.
- Use a porous metal mesh to wick excess solder away from a joint.
- Store hydrogen in the pores of a palladium sponge. (Fuel *tank* for the hydrogen car--much safer than storing hydrogen gas) 32. Color changes
Change the color of an object or its external environment.
- Use safe lights in a photographic darkroom.
Change the transparency of an object or its external environment.
- Use photolithography to change transparent material to a solid mask for semiconductor processing. Similarly, change mask material from transparent to opaque for silk screen processing. 33. Homogeneity
Make objects interacting with a given object of the same material (or material with identical properties).
- Make the container out of the same material as the contents, to reduce chemical reactions.
- Make a diamond cutting tool out of diamonds. 34. Discarding and recovering
Make portions of an object that have fulfilled their functions go away (discard by dissolving, evaporating, etc.) or modify these directly during operation.
- Use a dissolving capsule for medicine.
- Sprinkle water on cornstarch-based packaging and watch it reduce its volume by more than 1000X!
- Ice structures: use water ice or carbon dioxide (dry ice) to make a template for a rammed earth structure, such as a temporary dam. Fill with earth, then, let the ice melt or sublime to leave the final structure.
Conversely, restore consumable parts of an object directly in operation.
- Self-sharpening lawn mower blades
- Automobile engines that give themselves a *tune up* while running (the ones that say *100,000 miles between tune ups*) 35. Parameter changes
Change an object's physical state (e.g. to a gas, liquid, or solid.)
- Freeze the liquid centers of filled candies, then dip in melted chocolate, instead of handling the messy, gooey, hot liquid.
- Transport oxygen or nitrogen or petroleum gas as a liquid, instead of a gas, to reduce volume.
Change the concentration or consistency.
- Liquid hand soap is concentrated and more viscous than bar soap at the point of use, making it easier to dispense in the correct amount and more sanitary when shared by several people.
Change the degree of flexibility.
- Use adjustable dampers to reduce the noise of parts falling into a container by restricting the motion of the walls of the container.
- Vulcanize rubber to change its flexibility and durability.
Change the temperature.
- Raise the temperature above the Curie point to change a ferromagnetic substance to a paramagnetic substance.
- Raise the temperature of food to cook it. (Changes taste, aroma, texture, chemical properties, etc.)
- Lower the temperature of medical specimens to preserve them for later analysis. 36. Phase transitions
Use phenomena occurring during phase transitions (e.g. volume changes, loss or absorption of heat, etc.).
- Water expands when frozen, unlike most other liquids. Hannibal is reputed to have used this when marching on Rome a few thousand years ago. Large rocks blocked passages in the Alps. He poured water on them at night. The overnight cold froze the water, and the expansion split the rocks into small pieces which could be pushed aside.
- Heat pumps use the heat of vaporization and heat of condensation of a closed thermodynamic cycle to do useful work. 37. Thermal expansion
Use thermal expansion (or contraction) of materials.
- Fit a tight joint together by cooling the inner part to contract, heating the outer part to expand, putting the joint together, and returning to equilibrium.
If thermal expansion is being used, use multiple materials with different coefficients of thermal expansion.
- The basic leaf spring thermostat: (2 metals with different coefficients of expansion are linked so that it bends one way when warmer than nominal and the opposite way when cooler.) 38. Strong oxidants
Replace common air with oxygen-enriched air.
- Scuba diving with Nitrox or other non-air mixtures for extended endurance
Replace enriched air with pure oxygen.
- Cut at a higher temperature using an oxy-acetylene torch.
- Treat wounds in a high pressure oxygen environment to kill anaerobic bacteria and aid healing.
Expose air or oxygen to ionizing radiation.
- No specific example
Use ionized oxygen.
- Ionize air to trap pollutants in an air cleaner.
Replace ozonized (or ionized) oxygen with ozone.
- Speed up chemical reactions by ionizing the gas before use. 39. Inert atmosphere
Replace a normal environment with an inert one.
- Prevent degradation of a hot metal filament by using an argon atmosphere.
Add neutral parts, or inert additives to an object.
- Increase the volume of powdered detergent by adding inert ingredients. This makes it easier to measure with conventional tools. 40. Composite materials
Change from uniform to composite (multiple) materials.
- Composite epoxy resin/carbon fiber golf club shafts are lighter, stronger, and more flexible than metal. Same for airplane parts.
- Fiberglass surfboards are lighter and more controllable and easier to form into a variety of shapes than wooden ones.
Let's talk more tomorrow.
Dear HP VARs!
Tuesday, all of us at HP were honored to receive your votes at the 2008 VARBusiness Annual Report Card Awards for ARC Company of the Year in both the Midrange (High-End) Server and Volume Mainstream Business Server categories.
There are a lot of awards out there, but this one means a lot more to us because it was based on your votes and satisfaction with us. That real says something.
We really think it's you that should get the awards. The blade team would like to thank you for all your help over the years to make BladeSystems a success. See you next year!
The HP BladeSystem Team
PS: For those that may not know, here's how the winners were selected:
Winners were determined based on a weighted total of product innovation, support and partnership. Winners were selected by VARBusiness editorial based on the survey results of more than 5,000 systems integrators, IT consulting organizations, value-added resellers (VARs), solution providers and software developers.
The Annual Report Card winners can be found online at http://www.channelweb.com/ and will be included in the October 27, 2008 issue of VARBusiness.
Don't worry, we don't have big heads. We know it's a short trip from the penthouse to the outhouse. But it's always good to take a step back and let the team celebrate a job well done.
Across the board, from engineering to sales and finance, we have a bunch of bright, passionate people behind this business. See some pics of this great team below. Look out folks, becasue these guys and gals aren't slowing down at 50% share.
Here's a sample of some of today's HP earning news featuring blade results.
HP delivers strong third quarter fueled by blades, international, notebooks by ZDNet's Larry Dignan -- HP on Tuesday reported fiscal third quarter earnings of $2 billion, or 80 cents a share, on revenue of $28 billion, up 10 percent from a year ago. Excluding items, HP reported earnings of 86 cents a share, 3 cents ahead of Wall Street estimates. Revenue also topped Wall Street expectations of $27.4 billion, according to
HP Results Gain on Laptop, Blade Sales, By Stephen Lawson San Francisco | Wednesday, 20 August, 2008
Did you find an article? Share it below.
Big day in 2007 - Virtual Connect launch
I wasn't ready!!! (or maybe I was feeling the good Shorty vibe)
And who came up with this hokey pose anyway? BTW - 2007 Shorty Launch
My favorite - 2006 BladeSystem c7000 launch. Good looking group, huh?
This whole topic of 'blade incompatibility' really bugs Gary, Richard and me. If you want to know why, tune your web browser to the panel discussion with IBM's Doug Balog, Intel's Kurt Lender and the referee, er, moderator, Rob Mitchell from Computerworld.
You can also check back here in a few days where we'll share our thoughts in a new blog and then we'll give you a review of the discussion.
The event goes down on August, 26 from 2:00 to 2:45 Central Time. If you want to listen in, get the time and place here and sign up for a reminder.
The panel discussion is being billed as “Blade Servers: fast, growing, innovative - and incompatible” and it's part of the Data Center Directions virtual conference. It's kind of like a tradeshow, but online. I really got a kick out of the session description below. (I'm still trying to figure out the statement below. Who wrote this and isn't "IBM compatible-like" standard an oxymoron?)
growing, innovative - and incompatible
The compact size, cost, and efficiency of server blades has earned these systems a growing presence in data centers. But blade hardware, from vendor to vendor, is not interoperable. Are users risking vendor lock-in by deploying blade servers?
Today blades plug into a common backplane within a shared enclosure, or chassis. But unlike traditional servers, those backplanes are proprietary. Rather than an open, industry standard architecture such as PCI-Express, every vendor has its own private design. Meanwhile, an ecosystem of third party IO devices for storage and network switching have emerged that are blade system specific. A blade switch designed for one vendors' chassis won't work in another's.
Until now, vendors of enterprise-class blade servers have been uninterested in creating an "IBM compatible-like" hardware backplane for blades, claiming instead that this is an area where innovation still matters. Does innovation trump standardization? Or does the lack of hardware compatibility impose unnecessary costs on users?
And where will that innovation pay off? As blade server adoption grows, what new advances will we see in blade server technology that allow better support for virtualization, energy efficient data centers, and management?
These days, server power efficiency is top of mind for everyone. Five years ago, most customers had no idea how much power a server used. Now, everyone knows - it's a lot. In some cases, customers are making power consumption the primary criteria for vendor selection.
So why is it so dang hard to get a straight story on exactly what options are the most power efficient?
In our experiences with power measurements, we found lots of ways to the results get skewed; whether intentionally or accidentally. We honestly try to avoid them, but here are some of the dirty little secrets a lot of vendors don't want you to know about their power testing results. Consider these red flags next time someone spends lots of money in the Wall Street Journal to post a big claim with lots of fine print on power savings.
One easy way for vendors to skew power results is to cherry-pick low power components. Processors (even those in the same power grade) and memory DIMMs tend to consume significant power and can have wide variances in power consumed from one part to another.
We call units built by cherry-picking components "Lab Queens".
Generally, these do not represent what a customer might actually be able to purchase. Here's an example where we tried to avoid this scenario; the systems compared on this competitive power report on our website uses the exact same processors and DIMMs on all units tested, thereby eliminating differences due to component variances. It would have been easy to create a Lab Queen and bump the results higher, artificially.
Peak power efficiency for a given system always requires the "best" configuration. Memory power is mostly a function of DIMM count, and not capacity. Therefore, to achieve minimum power, the minimum number of DIMMs should be used to realize the desired memory capacity.
If you see a comparison where the DIMM count is different or not mentioned, you might notice the strong odor of dead fish.
On the infrastructure side of the equation, a blade system can be configured with varying numbers of fans and power supplies. Obviously some configurations will produce better power efficiency than others. For instance, 4 power supplies run more efficiently than 6, assuming that 2+2 power redundancy delivers adequate power for a given configuration. The most power efficient configurations though won't always be generated by a competitor when publishing a comparison. Honestly, there are such big differences here that an apple to apple comparison is tough. Only an HP BladeSystem dynamically throttles fan speeds based on demand across the different cooling zones in an enclosure.
The voltage level and room temperature can cause variances in the power supply efficiencies and the speed the system fans must run. Consequently it is important that when comparing servers to verify that these parameters are held constant. I once heard a story of an engineer setting up a box fan to blow air on his servers to try to reduce the fan power of the blades.
Obviously he wasn't planning on counting the power from the box fan!
Remarkably, there are published benchmarks that allow for external cooling to be deployed and not counted as a part of the system power.
Gaming the Benchmark
Any benchmark a vendor publishes is necessarily narrow in what it measures. When looking at a published benchmark, you should consider how close the benchmark mimics your applications. If the benchmark is similar to your applications, the results might be relevant to you. If not, then you might do best just to ignore them. Also, some benchmarks are very loose on configuration requirements, making it very easy to "game them" and making the results all but totally useless. One benchmark that is broadly published in the industry falls into this category.
Where to go from here?
At this point, you are probably thinking "Wow! This is much more complicated than I really thought!" And you are right. Benchmarking fairly is very tricky business, even if you are trying to be fair. The best results you can get are the ones you measure yourself. In my next blog post, I'll comment on some of the techniques and challenges with measuring power yourself.
We like to think so. In fact, we really hate the wiki definition (noun) of blade. Basically, a "smaller server flipped on its side".
Blades have expanded so far beyond the early days of 2000, the old definition just doesn't ring true to me any more.
You can blade just about anything to make it more efficient and convenient. A Data Warehouse, a workstation, storage, a PC desktop, a huge HPC cluster, a NonStop system, tape back-up and 10 more solutions I can think of off the top of my head. In fact, if you've met anyone on our team, you know we think you can blade just about anything. Why? To make it cost less, use less power, save more time and make change easier.
The definition has grown so wide, a blade is more a verb than a noun. 'Blade' has simply become a better way build an infrastructure and a better way to get things done. A better definition might be to make modular and consolidate; to make intgrated and interconnected; to simplify IT.
Oh yeah, you can blade your servers too.
So how do you define blade?
We're starting a new series on the blade blog called 'Blade Hacks'. More tips and tricks than true hacks (security is kind of important you know). I just like the name.
For our first post, I wanted to focus on the command line interface of the built-in, Onboard Administrator. A lot of people love its simplicity, but our real power users love the amount of control it puts at their fingertips via the CLI.
Recently, some of our top Blade Ambassadors shared some cool tips and tricks that can really save you tons time. A lot of them are captured in a free download of the Onboard Adminstrator Command Line Interface User Guide. This was just updated a few days ago with some cool new scripts and commands.
Do you have a favorite CLI script you want to share with the community? Post a comment below.
To find more Blade Hacks in the future, just check the tags to the right or request topics in the comments.
We hear questions all the time about the security issues of virtual servers. To summarize, "is it too many eggs in one basket?" Chris Whitener, HP's chief security strategist offered 5 steps to safer virtual servers in a recent article in CIO magazine.
1. Protect your host operating system by using server hardening tools and methodologies.
Additional OS features such as isolation capabilities and strong security between OS partitions makes it easier for you to decrease the "attack surface" of a host OS.
2. Ensure that your host OS is as secure as the guest operating system.
A virtual machine inherits all vulnerabilities of a host OS. Select a virtualization technology which provides strong security isolation (enforces distrust) between guest OS instances if needed. If organizations are concerned about malicious software in one guest OS attacking another OS, or don't have mutual trust among administrators of the different guest OSes, then the virtualization layer must be designed to enforce the idea of distrust.
3. Security policies in the host OS should reflect requirements of individual virtual machines.
Using the host OS to implement compliance requirements further enhances your assurance of compliance. It can be relied upon independently of trust in the administration of the guest OS.
4. Manage virtual processes more like you already manage your physical resources.
The host OS security lifecycle and virtual machine security lifecycle(s) must both be managed efficiently thought the data center. Ideally, the virtual infrastructure would be managed in the same way as physical resources. This includes software configuration, updates and patches, auditing and performance monitoring.
5. Stay vigilant about securely managing the physical infrastructure.
Deploying workloads on virtualized platforms make them more mobile, and provides flexibility and agility; this does not mean that the physical infrastructure can be ignored. The physical infrastructure has a critical role in supporting the good execution of those workloads, and the security of the virtualized infrastructure depends on the physical resource configuration and access control being managed securely across the data center.
I have to confess. One of my favorite campaigns going right now is by freecreditreport.com. That catchy little song about the guy stuck in a seafood restaurant in a pirate shirt - all because he didn't manage his credit. I sing it daily, badly.
It makes me want a blade jingle, but that is SO not-HP.
Since I have zero music writing ability, I propose to shameless cover the freecreditreport.com pirate song with my own lame blade lyrics. It goes like this (Sing along in your head to the tune of the freecreditreport.com pirate song)
Any musicians out there want to cut a version for us? Scott Anderson - is your band up for a little jam session?
There are a lot of materials available to customers and partners around the competitive strengths and weaknesses of the major players in the blade market. Lots of claims, lots of counter-claims, YouTube videos, podcasts, press releases, full-page ads, web banners, reports and the list goes on and on and on. If you listened to what Dell and IBM say about HP BladeSystem, you'd think we haven't sold one. In fact, I think they talk more about HP than their own solutions.
Taking a step back, do customers make their decision based on this kind of marketing?
It may get a mention or a thought during the evaluation process but there are usually 3 or 4 bigger factors that influence a sale: the relationship between the customer and an account manager, one who can listen to their needs and then deliver the right solution at the right price, supported by a proven service and support structure. These are just a few.
Wow, so all the competitive attacks in the world won’t change their minds? That's right, customers aren’t stupid. In fact, they are quite savvy with regard to competitive claims.
The numbers don’t lie.Blades Unit Market Share; IDC server tracker Q1 2008
The latest IDC report shows that HP is the clear market leader and sold twice as many blades as IBM and over 5 times as many as Dell. The businesses buying HP BladeSystems probably saw the right solution rather than just another box with check marks on features.
Here's a thought: maybe our technology isn't just 2x or 5x better, maybe our sales people are twice as good as IBM and 5 times better then Dell, and as for our service and support perhaps we can claim to instill that level of confidence over our competitors?It may be a stretch but whatever way you look at it, there is no doubt it’s a great time to choose the HP BladeSystem...despite all the noise surrounding the blades market.
On the way to work Friday, I snapped this picture . At first glance, it's a car that ran out of gas. Take a closer look and it's a Prius. Huh?!? How do you run out of gas in a Prius? Can you imagine what was going through his head? "My super-efficient electric hybrid car ran out of gas in my own neighborhood?"
Which brings me to that datacenter. A datacenter has a gas gauge too. I wonder how many CIO's are checking it regularly? At the current rate, datacenters will demand more and more energy for power and cooling than the facility or the local grid can support.
(Don't let this happen to your datacenter)
In my estimation, you have 3 options:
1. Invest to hold more gas, i.e. figure out how to bring more power to the datacenter. (a Prius holds only 11.9 gallons)
2. Get better milage from your servers, storage and AC.
3. Stop growing
Option 2 is the only good one and it's not so hard to achieve. If you have servers in production that are 5 years old or more, you have a huge opportunity to not only increase your performance, but to save more energy. Taking a 100 servers from 600 watts to 200 watts of power (and multiplying that with virtual servers) can not only save you big bucks every month, but extend the gas milage of your datacenter.
If you want more ways to extend the life of your datacenter, check out Tips for Data Center Efficiency by Greg MacSweeny of the Wall Street Journal who did a lot more research on the topic.
Influencer Marketing, HP ConvergedSystem
More than 25 years in the IT industry developing and managing marketing programs. Focused in emerging technologi
es like Virtualiza tion, cloud and big data.
HP Converged Data Center Infrastructure
EG Global Marketing, HP Servers
I am a member of the Enterprise Group Global Marketing team blogging on topics of interest for HP Servers. Check out blog posts on all four Server blog sites-Real
ity Check, The Eye on Blades, Mission Critical Computing and Hyperscale Computing- for exciting news on the future of compute.