AMD has released faster new ATI Catalyst drivers for Linux customers of its ATI FireGL professional graphics cards. The 8.49.7 Linux driver provides 33 percent faster OpenGL performance than the previous driver, claims the company.

(Click for larger view of the ATI FireGL V3600)

The drivers support the ATI FireGL V3600 professional card (pictured above), as well as the high-end ATI FireGL V8650, which offers a 2GB frame-buffer memory configuration. The driver is also said to be compatible with the consumer-level ATI Radeon graphics card.

The performance claims are based on OpenGL performance using the SPECviewperf 9 1280×1024x32 ugnx-01 subtest, says AMD. The tests were run on an HP xw4600 with an Intel Core2 Extreme Q6850 processor clocked at 3GHz and a 1333MHz FSB. The system was equipped with 8MB L2 cache and 4GB RAM, and ran Linux Red Hat 4.6. The results are said to be published here.

AMD released Catalyst 7.10 graphics drivers for the Linux desktop in October. The 7.10 release included a preview release of AIGLX (Accelerated Indirect GLX) support for the ATI Radeon, and it also supported ATI FireGL 8700 and later products. The AIGLX support was said to improve OpenGL 3D performance.

Version 8.49.7 of the ATI Catalyst driver is available for download, here, says AMD.

Selling businesses on the benefits of Linux has been a tough proposition for many years. Common reasons cited for not moving to the open-source operating system include system complexity, lack of in-house IT skills and a shortage of business applications. Both the open-source software community and the vendor world have done a lot to address these shortcomings, and the inroads gained are plain for all to see.

“Linux servers posted their second consecutive quarter of solid growth with year-over-year revenue growth of 8.4 percent for a total of $1.8 billion in the quarter,” said Matt Eastwood, an analyst at International data Corp. (IDC). “Linux-based servers now represent 13.7 percent of all server revenue.”

That percentage clearly demonstrates that Linux has made it out of the fringes. Not surprisingly, small businesses usage is also on the upsurge. Take the Whitelaw Twining Law Corp, for example. This 25-person law firm migrated from Windows 98 and Windows 2000 to SUSE Linux by Novell Inc.

“Migrating from Windows 2000 to SUSE Linux Enterprise Desktop is no more difficult for end users than migrating to Windows Vista,” said Richard Giroux, IT manager at Whitelaw Twining. “We did a little up-front training with our employees and have had almost no help desk calls since.”

Maybe it’s time, then, to take another look at Linux on the desktop and/or the server side. We’ll look at the seven areas you need to consider.
Hardware

Compared to only a few years ago, the hardware and component support for Linux is much more encouraging. You’ll fine far more processors, drivers, graphic cards and peripherals that support Linux than ever before.

“Companies have a vast range of devices and machines at every price and performance level,” said Gerry Carr, marketing manager at Canonical Ltd., the company that supports a desktop Linux version called Ubuntu. In most cases, therefore, hardware compatibility is not going to be an issue for any small business considering the Linux leap.
Linux Server

To combat the idea that it’s “hard-to-learn”, Linux now offers a lot of user-friendly server packages. These systems are set up to make it relatively easy for small businesses to install and run Linux themselves. Examples include server software by Red Hat Inc., SUSE Linux by Novell and Ubuntu Server Edition by Canonical.

While these products are less complex than before, that doesn’t necessarily mean an inexperienced business owner can download them and be off and running. “Skills can be an issue, particularly on a Linux server,” said Carr. “You might well have hired a Microsoft-trained IT staff and they will need to be re-trained for Linux or you may need new staff with Linux training.”
Support

If the idea of importing new Linux talent scares you away from the proposition, another option is to use the support arms that have evolved within the Linux community. Red Hat and SUSE, for example, offer server software starting at $349 per year with basic support rolled in. More comprehensive support costs upward of $1,000 in some cases. Ubuntu is offered free by download, and support costs $750 per server per year

“Linux is a great solution for small business customers because it helps them avoid high licensing costs, viruses, vendor lock-in, hardware upgrades and unstable servers and desktops,” said Adam Viele, a technology specialist at CDW Corp. “Small businesses that choose an enterprise-class version of Linux will get a comprehensive IT solution along with the reliability of enterprise-class support a smaller business may not be able to afford otherwise.”

Desktop Linux

Plenty of progress has also been made on the desktop side of the ledger. Both Novell and Ubuntu serve as good examples. Once again, Ubuntu is available for free download ($250 for support per year). SUSE Linux for the desktop costs $50 per desktop (support not included). There are deals available for bulk purchases.

But it isn’t just the Linux vendors that are jumping on the bandwagon. PC makers are starting to support Linux much more broadly. Companies such as Dell, HP and Lenovo are pre-loading desktop Linux on certain computer models.

“[PC makers] are certifying many Linux distributions, from Novell to Red Hat and Ubuntu, on a growing list of servers, notebooks and desktops,” said Grant Ho, senior product manager for Linux and open platform solutions at Novell. “At the end of the day, this is ultimately allowing organizations to access Linux much more easily and to enjoy its benefits out of the box.”

Software

Whoever thought we’d live to see the day when Microsoft would actually embrace open source. Yet Microsoft has an active partnership with Novell SUSE Linux to create compatible products such as Office document formats and management platforms that are compatible both Linux and Windows.

Beyond that, Linux applications are multiplying rapidly and are available now in most areas of the business world. You can replace Microsoft Office with OpenOffice.org, use Firefox for Web browsing, Evolution for e-mail, Pidgin for instant messaging and Banshee for music management, just to name a few.

“The software that businesses need to run is available for Linux now, and many of them are free,” said Carr. “We will also see applications like IBM Lotus Notes and Domino Server available for Ubuntu by the year’s end that is a direct Outlook replacement, which is the one piece of software that keeps many businesses in the Microsoft world.”

Not everything is covered, though. There may be some proprietary products you need to have which just don’t have a Linux equivalent. The finance department, for example, might have an application it would be difficult to replace. But even here, the solution for those wanting to move to Linux would be to retain a few licenses for the folks in finance, and change the rest of the gear to Linux.

For Windows application that have no Linux alternatives, you can make use of Wine, an open-source Linux platform that allows you to run Windows applications such as Microsoft Office, multi-media applications, including QuickTime and Windows Media Player, and even games such as Max Payne and The SIMS on top of Linux. Desktop virtualization can also be used in some cases to run Windows applications on Linux.

Cost

The oft-cited motivation for switching to Linux is economics. According to Carr, OpenOffice is more than good enough that people should question having to pay licenses for Microsoft Office – the same for Windows Vista.

“While cost is part of it, your staff should in no way feel they are getting inferior systems to use,” said Carr. “They are often faster, easier to use, more reliable, without spyware, malware and viruses, more Internet-friendly and better presented.”

Whitelaw Twinning, for instance, evaluated a move to Vista, as well as to various Linux distributions. It selected SUSE Linux for desktop. “We evaluated solutions based on the ability to create a safe environment, as well as what it would cost us in time and money to maintain them,” said Giroux.

He estimated the change reduced hardware costs by 30 percent and desktop maintenance time by 20 percent.
Gradual Change

What SMBs shouldn’t do, though, is take the big bang route to Linux. Start out with a desktop or two, or a couple of servers and get a feel for the system. Armed with initial successes, it provides the motivation to roll it out further into the business.

And according to analysts, more and more small businesses are heading in the direction of Linux.

“The reputation that Linux is too technical for both administrators and end-users is rapidly fading,” said Ho. “From our experience, we see SMBs moving to both server and desktop Linux in a wide variety of industries – retail, financial services, public sector, non-profit – all around the world.”

Steve Langasek has announced the availability of the delayed first alpha release of Ubuntu 8.10, code name “Intrepid Ibex”: “Welcome to Intrepid Ibex Alpha 1, which will in time become Ubuntu 8.10. Alpha 1 is the first in a series of milestone CD images that will be released throughout the Intrepid development cycle. The primary changes from Hardy have been the re-merging of changes from Debian and the upgrade of the Linux kernel to a pre-release version of 2.6.26. As with the beginning of any development cycle, the Intrepid one has seen the merge floodgates open once again. This merge not only brings in lots of new version of various packages, but also a fair number of totally new applications.” Read the release announcement and release notes for further details. Only the “alternate” installation images have been made available with this release; download them from here: intrepid-alternate-i386.iso (698MB, MD5, torrent), intrepid-alternate-amd64.iso (697MB, MD5, torrent). Also released: Kubuntu 8.10 Alpha 1 and Xubuntu 8.10 Alpha

It is estimated that the data storage sector consumed about 61 billion kilowatt-hours (kWh) in 2006 (1.5% of total U.S. consumption, or roughly equivalent to the amount consumed by 5.8 million average U.S. households). These numbers are only expected to grow.

The energy used by the nation’s servers and data centers is growing at an unsustainable rate. Not only that, but web servers are notoriously inefficient. For example, computer servers are used at only 6 percent of their capacity on average, while data center facilities operate at roughly 65% to 75% efficiency, meaning that 25% to 35% of all the energy consumed by servers is wasted (converted to heat).

If we are to even consider reducing our energy consumption and carbon footprint, the growing demands generated by our web servers must be near the top of the list of possible improvements. And the Department of Energy agrees.

Researchers at DOE’s Pacific Northwest National Laboratory (PNNL) in Washington and National Renewable Energy Laboratory (NREL) in Colorado are hard at work figuring out ways to make our data storage infrastructure more efficient by running them at lower temperatures. The technology exists to achieve efficiencies of 80% to 90% in conventional server power supplies. Moving this heat source away from the server allows the cooling efforts to be focused on the computing elements.
Alternative Cooling Approaches
(from PNNL’s Energy Smart Data Center)

* Evolutionary progress is being made with conventional air cooling techniques that are known for their reliability. Current investigation focuses on novel heat sinks and fan technologies with the aim to improve contact surface, conductivity, and heat transfer parameters.
* One of the most effective air cooling options is Air Jet Impingement. The design and manufacturing of nozzles and manifolds for jet impingement is relatively simple.
* The same benefits that apply to Air Jet Impingement are exhibited in Liquid Impingement technologies. In addition, liquid cooling offers higher heat transfer coefficients as a tradeoff for higher design and operation complexity.
* One of the most interesting liquid cooling technologies are microchannel heat sinks in conjunction with micropumps because the channels can be manufactured in the micrometer range with the same process technologies used for electronic devices.
* Liquid metal cooling, used in cooling reactors, is starting to be an interesting alternative for high-power-density micro devices. Large heat transfer coefficients are achieved by circulating the liquid with hydroelectric or hydromagnetic pumps. The pumping circuit is reliable because no moving parts, except for the liquid itself, are involved in the cooling process. Heat transfer efficiency is also increased by high conductivity. The low heat capacity of metals leads to less stringent requirements for heat exchangers.
* Heat extraction with liquids can be increased by several orders of magnitude by exploiting phase changes. Heat pipes and Thermosyphons exploit the high latent heat of vaporization to remove large quantities of heat from the evaporator section. The circuits are closed by either capillary action in the case of heat pipes or gravity in the case of Thermosyphons. These devices are therefore very efficient but are limited in their temperature range and heat flux capabilities.
* Thermoelectric Coolers have the ability to provide localized spot cooling, an important capability in modern processor design. Research in this area focuses on improving materials and distributing control of TEC arrays s

Capturing Waste Heat

Reusing the waste heat from a data center may not make the server room itself more efficient, but depending on how heat is reused, it can save a company a significant sum of money. In its report to Congress last year on data center energy consumption, the federal Environmental Protection Agency suggested the practice. And the idea has gained traction, according to Mark Fontecchio of SearchDataCenter.com.

For example, in Winnipeg, Canada a media company called, Quebecor, efforts have been made to take the heat from the 2,500-square-foot data center on the ground floor and use it to heat other parts of the building.

Because of the cool Winnipeg climate, engineers decided to make use of that cool air by installing air-side economizers that draw in outside air. The economizers include baffles that open to varying degrees depending on the outside temperature and how much cooling the data center needs.

After the air cycles through the approximately 100 eight-way servers, it warms up in the process. It then goes into an overhead plenum, where about 10% of the air is re-circulated to warm the outside air that comes into the data center.

Another duct out of the exhaust plenum to the intake duct of the editorial office upstairs. Quebecor also added a second thermostat to its editorial offices; the first controls the traditional heating furnaces. That whole process used up another 60% of the waste heat. The data center dumps the remaining 30% into the adjacent warehouse.
AC-DC?

For electricity flowing all the way from power plants to the wall socket, alternating current is far superior. But for the short transmissions inside those computers DC power prevails. The search for ways to convert AC to DC more efficiently is leading some data center companies to consider a DC-centric approach.

It’s easier to transmit AC over long distances; DC requires thick copper cables or bars, instead of comparatively lightweight wires. But DC becomes a more serious possibility for power once AC reaches a building.

Converting from one form of power to another in a computing environment may not be performed efficiently, especially at the server level, and even then, the resulting waste heat may be deposited in the rack or computer room at a point that requires further effort to dispose of it with the air handlers. Unfortunately, there is disagreement in the community over how to address these inefficiencies.

* DC advocates argue that plugging servers into AC power is inefficient, and switching systems to DC would cut down on waste heat and component failure.
* Proponents argue that using DC outside the server removes some of the inefficiencies of power supplies that convert AC electricity to DC. Servers without such power supplies don’t have to contend with as much waste heat and attendant component failure.

But according to NPPL, substituting DC power in data centers as a replacement for conventional AC power has not yet made significant inroads into many data centers because the technology is unfamiliar to many facility engineers.

Despite the wide-spread use of DC power in telecommunications, there is reluctance within the computer industry to switch to new technologies without field experience showing that the switch could be done safely and would have operational and economic benefits without causing unanticipated problems.

If DC would in fact be a more efficient type of power within servers themselves, might it be possible to site server farms to take advantage of the DC provided by integrated renewable energy generating systems such as solar PV and wind?

When it comes to the U.S. government’s computer security, we in the tech press have a habit of reporting only the bad news—for instance, last year’s hacks into Oak Ridge and Los Alamos National Labs, a break-in to an e-mail server used by Defense Secretary Robert Gates … the list goes on and on. Frankly that’s because the good news is usually a bunch of nonevents: “Hackers deterred by diligent software patching at the Army Corps of Engineers.” Not too exciting.

So, in the world of IT security, it must seem that the villains outnumber the heroes—but there are some good-guy celebrities in the world of cyber security. In my years of reporting on the subject, I’ve often heard the National Security Agency’s red team referred to with a sense of breathless awe by security pros. These guys are purported to be just about the stealthiest, most skilled firewall-crackers in the game. Recently, I called up the secretive government agency and asked if it could offer up a top red teamer for an interview, and, surprisingly, the answer came back, “Yes.”

What are red teams, you ask? They’re sort of like the special forces units of the security industry—highly skilled teams that clients pay to break into the clients’ own networks. These guys find the security flaws so they can be patched before someone with more nefarious plans sneaks in. The NSA has made plenty of news in the past few years for warrantless wiretapping and massive data-mining enterprises of questionable legality, but one of the agency’s primary functions is the protection of the military’s secure computer networks, and that’s where the red team comes in.

In exchange for the interview, I agreed not to publish my source’s name. When I asked what I should call him, the best option I was offered was: “An official within the National Security Agency’s Vulnerability Analysis and Operations Group.” So I’m just going to call him OWNSAVAOG for short. And I’ll try not to reveal any identifying details about the man whom I interviewed, except to say that his disciplined, military demeanor shares little in common with the popular conception of the flippant geek-for-hire familiar to all too many movie fans (Dr. McKittrick in WarGames) and code geeks (n00b script-kiddie h4×0r in leetspeak).

So what exactly does the NSA’s red team actually do? They provide “adversarial network services to the rest of the DOD,” says OWNSAVAOG. That means that “customers” from the many branches of the Pentagon invite OWNSAVAOG and his crew to act like our country’s shadowy enemies (from the living-in-his-mother’s-basement code tinkerer to a “well-funded hacker who has time and money to invest in the effort”), attempting to slip in unannounced and gain unauthorized access.

These guys must conduct their work without doing damage to or otherwise compromising the security of the networks they are tasked to analyze—that means no denial-of-service attacks, malicious Trojans or viruses. “The first rule,” says OWNSAVAOG, “is ‘do no harm.’?” So the majority of their work consists of probing their customers’ networks, gaining user-level access and demonstrating just how compromised the network can be. Sometimes, the red team will leave an innocuous file on a secure part of a customer’s network as a calling card, as if to say, “This is your friendly NSA red team. We danced past the comical precautionary measures you call security hours ago. This file isn’t doing anything, but if we were anywhere near as evil as the hackers we’re simulating, it might just be deleting the very government secrets you were supposed to be protecting. Have a nice day!”

I’d heard from one of the Department of Defense clients who had previously worked with the NSA red team that OWNSAVAOG and his team had a success rate of close to 100 percent. “We don’t keep statistics on that,” OWNSAVAOG insisted when I pressed him on an internal measuring stick. “We do get into most of the networks we target. That’s because every network has some residual vulnerability. It is up to us, given the time and the resources, to find the vulnerability that allows us to access it.”

It may seem unsettling to you—it did at first to me—to think that the digital locks protecting our government’s most sensitive information are picked so constantly and seemingly with such ease. But I’ve been assured that these guys are only making it look easy because they’re the best, and that we all should take comfort, because they’re on our side. The fact that they catch security flaws early means that, hopefully, we can patch up the holes before the black hats get to them.

And like any good geek at a desk talking to a guy with a really cool job, I wondered just where the NSA finds the members of its superhacker squad. “The bulk is military personnel, civilian government employees and a small cadre of contractors,” OWNSAVAOG says. The military guys mainly conduct the ops (the actual breaking and entering stuff), while the civilians and contractors mainly write code to support their endeavors. For those of you looking for a gig in the ultrasecret world of red teaming, this top hacker says the ideal profile is someone with “technical skills, an adversarial mind-set, perseverance and imagination.”

Speaking of high-level, top-secret security jobs, this much I now know: The world’s most difficult IT department to work for is most certainly lodged within the Pentagon. Network admins at the Defense Department have to constantly fend off foreign governments, criminals and wannabes trying to crack their security wall—and worry about a bunch of ace hackers with the same DOD stamp on their paychecks.

Security is an all-important issue for the corporate world, too, but in that environment there is an acceptable level of risk that can be built into the business model. And while banks build in fraud as part of the cost of doing business, there’s no such thing as an acceptable loss when it comes to national security. I spoke about this topic recently with Mark Morrison, chief information assurance officer of the Defense Intelligence Agency.

“We meet with the financial community because there are a lot of parallels between what the intelligence community needs to protect and what the financial community needs,” Morrison said. “They, surprisingly, have staggeringly high acceptance levels for how much money they’re willing to lose. We can’t afford to have acceptable loss. So our risk profiles tend to be different, but in the long run, we end up accepting similar levels of risk because we have to be able to provide actionable intelligence to the war fighter.”

OWNSAVAOG agrees that military networks should be held to higher standards of security, but perfectly secure computers are perfectly unusable. “There is a perfectly secure network,” he said. “It’s one that’s shut off. We used to keep our information in safes. We knew that those safes were good, but they were not impenetrable, and they were rated on the number of hours it took for people to break into them. This is a similar equation.”

LINUTOP

Overview
Linutop is a ready-to-use small computer, designed to reduce maintenance costs.
Low maintenance

The Linutop operating system is stored on an internal flash memory and cannot be altered by virus or mishap.

Initial state can be recovered at each restart.
Low deployment costs

Linutop is delivered with free standard ready-to-use Linux software: Firefox, Open Office, VLC Media player… and can be easily customized with additional software.
Energy saving

With no moving parts, Linutop offers a completely silent (0 dB), energy-efficient operation in an extremely small package.

Linutop customers are:
- Hotels, Museums, Public Terminals…
- Shops, Bars, Point-of-Sale Terminals, Kiosks…
- Schools, Offices, Factories…
Coming later this year

CHERRYPAL

CherryPal is taking cloud computing mainstream in a big way with a soon to be released green personal computer. This green PC comes in a small, affordable package weighing just 10.5 ounces and consuming no more than two watts of power. The triple-core processor only has one fifth of the components of traditional computers, boots-up in 20 seconds, and promises to be faster than Vista and mac’s OS-X.

CherryPal had us doing our computer research to understand the power behind utilizing cloud computing. The PC contains only 4GB of flash storage, 256MB of memory, and a power architecture-based 400MHz Freescale mobileGT MPC5121e chip on a Linux operating system. To the everyday user, this means that most of the computer resources will be owned and accessed by a third-party provider in a data center – the type of service on demand similar to the way we program a Tivo. It also means that computer viruses will truly be a thing of the past for Cherrypal users.

For those of you who are a little more tech savy, here’s a more complete list of CherryPal’s Hardware:

* Freescale’s MPC5121e mobileGT processor, 800 MIPS (400 MHz) of processing
* 256GB of DDR2 DRAM
* 4GB NAND Flash-based solid state drive
* WiFi 802.11b/g Wi-Fi
* Two USB 2.0 ports
* One 10/100 Ethernet with RJ-45 jack
* One VGA DB-15 display out jack
* Headphone level stereo audio out 3.5mm jack
* 9vDC 2.5mm 10 watt AC-DC adapter power supply
* 10.5 ounces
* 1.3? high, 5.8? x 4.2? wide

Skeptics standby, CEO Max Seibold stands firmly behind his product believing it will not only deliver on energy savings and cost, but also on speed, making it “the most affordable, greenest computer on the market.” According to Seibold, CherryPal will be able to appease the music collectors, the gamers, and those looking for a simple to use word processor. While official pricing hasn’t been released yet, sources say to look-out for prices well under $400 sans the monitor, keyboard, and any additional accessories necessary to run the desktop. Look out for an early August release along with a laptop to follow in the near future.

GNOME users will find a lot to like in openSUSE 11.0. openSUSE’s GNOME is very close to upstream GNOME, because Novell and openSUSE want to do as much work as possible in the upstream release. However, we do modify GNOME’s artwork to provide a unified look and feel for the distro. The default GNOME configuration, such as panel layout, is slightly different than “stock” GNOME, and the openSUSE GNOME team backports a number of bug fixes into our GNOME release to ensure stability and the best possible GNOME experience.

GNOME 2.22 in openSUSE 11.0 includes the GNOME Virtual File System (GVFS), with better support for networked file systems, PulseAudio for better sound management, improvements in Evolution and Tomboy, and much more!

Ensuring your servers stamp as small a carbon footprint as possible on the earth and in your data center can encompass everything from making sure they are shipped in recyclable packaging to hiring an analyst who can predict the total life-cycle environmental impact.

For this test, we examined power consumption as a way to judge whether Windows Server 2008 or Linux is, in fact, the ‘greener’ operating system. As the price of power hits record heights, power reduction mechanisms shipping within an operating system should play a key role in you energy conservation plan.

Our tests point to Linux as the winner of the green flag by margins that topped out at 12%. But we must note that our results are full of stipulations imposed by our test bed, and as the more truthful car advertisements might warn — your wattage may vary.

We ran multiple power consumption tests using Windows Server 2008 Enterprise Edition, Red Hat’s Enterprise Linux (RHEL) 5.1 and SUSE Enterprise Linux 10 SP1 on four, popular 1U server machines, one each from Dell and IBM and two from HP. The results showed that while Windows Server 2008 drew slightly less power in a few test cases when it had its maximum power saving settings turned on, it was RHEL that did the best job of keeping the power draw in check across the board.

The variable settings allowed by both Windows and Linux – which let you toggle between having a high energy efficient server vs. a high performing one – can certainly have an impact on overall server consumption. But again, your mileage will also vary given the workloads you place on your servers and whether or not you’re using popular virtual machine hypervisors to support multiple operating system instances on the same physical server (see related story).

The edge in either test category will likely not last as operating systems become more finely tuned to work in lockstep with advanced server chipsets, and as additional coding techniques that more closely tie operating systems and applications to power considerations take hold across the industry.

Part of the current “green” operating system difficulty lies in the disconnect between how an operating system and its applications can be optimized to let the underlying system quiet itself down to a lower power-consuming state while at the same time not sacrificing the ability to react to servicing application (and therefore system and user) needs.

In our testing, we found that the CPU ‘throttle-back’ mechanism – the main technique for how an operating system can aid in reducing a server’s energy draw — requires new firmware and updated drivers that specifically support that feature. Only the IBM x3550 and the HP DL-360 G5 arrived ready for optimal power conservation. The HP DL-160 and Dell 1950 servers required several updates throughout our six-week test period to accommodate the CPU throttling features of Windows 2008 and Linux.

We truly know from the trenches that it really isn’t easy getting your servers to be green.
CPU conservation

No matter the operating system, Windows or Linux, the leading form of power conservation comes from throttling back the CPU to let the server rest during quiet activity times. Spinning down hard disks to a quieter state is the other major power-saving setting available to Windows servers.

Even though Linux desktop distrobutions can use the Advanced Configuration and Power Interface (ACPI) specification, which is designed for laptops, rather than servers, that feature was not implemented by Red Hat or SUSE for the servers we tested.

Some chipsets are designed for throttle-back, while others (especially older ones, predating 2007) always work at full pace and power full time. Only in the past three years have processors shipped from Intel, Advanced Micro Devices, Via Technology, and others in the x86 family have been specifically designed to cycle between fast (and higher power consuming) and slow (power savings) states.

The systems used in our testing ship with Intel Xeon multi-core CPUs, which can support throttle-back (manifested by slowing down the CPU clock so that the power strobes through the CPU more slowly against the slowed clock); but as we stated earlier the server’s BIOS and firmware must be sufficiently upgraded to correctly supported this. The IBM x3550 and HP DL-160 house a single quad-core CPU (of different models, see How we did it), while the Dell 1950 and HP DL360G5 each housed two quad-core CPUs for a total of eight cores.

Once throttled back, the millions of transistors in CPUs can turn back on almost spontaneously at virtually the speed of the CPU (we could detect no latency issues in our testing), and can throttle-back down at nearly the same speed. The throttle back condition can save quite a bit of power in the four systems we tested, but most other electronics within the system remain on and therefore continue to consume power. Because the system must be ready to service application requests, it must have at minimum, some electronics running to monitoring application, user, network and other peripheral service requests. This minimal amount of power drawn is what you see measured in our quiescent state (sometimes referred to as minimal ready-state) results.

Operating systems must allow a CPU to throttle back to this minimal ready state, to be considered green from the power consumption perspective, and both Linux and Windows allow for this. However, there is a ‘tickless’ version of Linux on the horizon that may prove to have power savings characteristics. System interrupt ticks are ‘time slices’ that the operating system uses to queue activities, and they’ve been traditionally set in the past half dozen plus years to a 1,000 ticks per second, each of which serves as an interruption to the CPU. A tickless version of the Linux kernel now reportedly exists that interrupts the CPU less frequently, but was not part of the Linux distribution kernels we tested — although that addition is planned in future editions of Red Hat and SUSE.

The second-class Linux support policies of the Mozilla foundation continue… I imagine the reasoning went something like it has always gone in the past: “the platform that matters most is the one where we, the Foundation, get the most market penetration.”

Webkit, here I come.

Shuttleworth wants to organize major releases into three separate “waves” which would each include different components of the desktop stack. The first wave would include fundamental components like the Linux kernel, the GCC compiler, graphical toolkits like GTK+, and development platforms like Python and Java. The second wave would include the desktop environments and desktop applications, while the third wave would be the distributions.

Although a unified release cycle would reduce much of the complexity associated with building a Linux distribution, the concept poses significant challenges and offers few rewards for software developers. Achieving synchronization on the scale that Shuttleworth desires would require some open-source software projects to radically change their current development models and adopt a new approach that isn’t going to be viable for many projects.
Understanding time-based release cycles

A time-based release cycle implies issuing releases consistently at a specified interval. The development process for projects that employ this model generally involves establishing a roadmap of planned features and then implementing as many as possible until the project reaches the code-freeze stage near the end of the interval, at which point the features that haven’t been finished get deferred. The focus shifts to debugging and quality assurance until the end of the interval, when the software is officially released.

This model works well for many projects, particularly the GNOME desktop environment. One consequence of this model, however, is that it forces developers to work incrementally, and it discourages large-scale modifications that would exceed the time constraints of the cycle. Sometimes that window just isn’t large enough to merge and test major architectural changes that were incubated in parallel outside of the main code tree.

When that happens, developers have to ask themselves whether the benefits of the new features outweigh the detrimental impact of the regressions (like with the GVFS adoption in GNOME 2.22, for example). Sometimes they have to decide to pull out features at the last minute or push back the release date to allow for more debugging. These are hard choices, and, as Shuttleworth himself notes, making those choices requires a lot of discipline.

Although time-based cycles can work well for some projects, attempting to force all projects to adopt this approach and then correlate these universally could seriously degrade the development process. If projects begin to depend on synchronization, then delays at any level of the stack would cause disruption to every other layer. This could put enormous pressure on individual projects to stick to the plan, even if doing so would be detrimental to the program and to its end users.