Ext3 defragments itself automatically No it doesn't. While ext3 does try to keep files contiguous and inodes in directories close to one another, it definitely does NOT do any defragmentation. ext2/3 filesystems have a history of getting highly fragmented over time and it gets worse the less free space you have on the disk.
The ONLY way you can defragment a file is to copy the fragmented file to another partition, remove it and copy it back. If you want to defragment a complete ext2/3 filesystem, make a backup of the filesystem using tar, delete the original and restore the backup.
No, this is not something you want to do while other software may be looking for the file.
Of the common filesystems available for Linux (ext2/3, xfs, jfs, reiserfs) the only one that supports online defragmentation is xfs (using the xfs_fsr utility) and this has to be scheduled manually.
Fragmentation in ext2/3 files is a huge problem when appending to files over long periods of time. You can check the fragmentation of any file on ext2/3 using the filefrag utility. Make a copy of a highly fragmented file (even to the same partition) and you will see the number of fragments go down dramatically, unless you don't have much free space left on the partition and the space you have free is also highly fragmented.
The usual reason that tap tastes like "crap" is because it contains an excess of minerals and residue when the upstream water source has a high level of algae.
A simple charcoal filter (either a Brita or an inline charcoal filter) goes a long way towards reducing that taste.
A basic reverse-osmosis system will remove it completely, but wastes some water in the process.
As the previous reply suggested, just going to your local grocery store and getting water out of those water dispensers that you drop quarters in to will also do the trick, they typically have water that tastes the same as bottled in my experience (but I prefer the carbon filters since it's a PITA to schlep all that water back home).
Frankly, that is the #1 reason that diesels aren't selling in the US right now.
Currently even the cleanest diesel cars due out this year are just barely clean enough to squeak by US emissions standards. Particulate and NOx emissions are insanely high compared to to gas cars.
Producing a car that gets great mileage (and low CO2 emissions) AND low pollutant emissions as well is not an easy task. The Prius hybrid is still by far the leader in fuel economy AND low emissions.
By the time this VW diesel hybrid is out, the next generation Prius will be out shortly. Don't forget that the current Prius is already nearly 5 years old - and no-one has anything that really competes in terms of fuel economy, emissions and practicality.
It seems pretty clear that people are using other remote vulnerabilities to gain local user access and then using this local root exploit to install their "malware".
Get those boxes updated as quickly as possible, folks!
Solar power as of yet, is not effective enough to produce the energy of a major coal plant (with the same density of land area used). That is only true if you don't account for the vast amount of land used to mine coal.
I suggest people interested in energy to read Scientific American's A Solar Grand Plan which outlines a realistic way end U.S. reliance on foreign oil while slashing greenhouse gas emissions by using solar power.
hybrids aren't available in any significant quanties yet either. Toyota, Honda, Ford and GM all make a wide variety of hybrids that you can go out and buy TODAY. All of which improve upon the gas mileage of the equivalent car more or less significantly depending on the sophistication of their hybrid system (GM has a number of mild-hybrids on the market which only marginally improve gas mileage).
If I want to buy a diesel, I have only 3 choices, VW, Mercedes and Jeep (and I have no idea what ones are actually available right now, but I can't find any information on VWs site about the 2008 Jetta Diesel, and it's not on fueleconomy.gov, either). Maybe by the end of the year there will be a wider choice as manufactures clean them up enough to meet TIER 2 BIN 5 emissions standards.
Please tell me where I can go buy biodiesel without setting up a brewing station on my patio. Even the nearest E85 is about 15 miles from where I live and even further from where I work. I expect the nearest biodiesel station to be the same.
We aren't talking about individual cases, we are talking about averages. Is your average hybrid driver seeing 40+? Nope, check the statistics. The average hybrid is meeting their 2008 EPA estimates. Look it up on fueleconomy.gov. So that means that YES, your average Civic Hybrid driver is getting 42 mpg and the average Prius driver is getting 46 mpg.
All the cases where I've seen a Prius getting less than 40 mpg are the result of short trips less than 10 minutes in cold weather. But in these conditions, all cars get crappy mileage compared to their EPA estimates.
The horse is obviously dead at this point, so this will be my last reply.
First you say biofuel-diesel is the way to go.
Then you brush off diesel-hybrid because it's not available yet. But wait, diesel biofuel isn't available in any significant quantities yet either.
Do you see the problem with your argument? You do this all over the place.
Your claim that hybrids are less efficient than their gas-only counterparts is simply false in many cases is false. If you want to make that argument, I can also claim that in many cases, hybrids completely blow anything else out of the water since many people regularly average 60+ mpg.
I can drive a Prius like a bat out of hell (jack-rabbit starts, 80+mph freeway speeds), and it still gets about 40mpg. I drive a Civic the same and it gets about 30mpg.
Nope, not bullshit, and you proved it yourself. It's a temporary pollutant. You stop producing it, it goes away. It has no lasting effect on the environment. You obviously haven't lived in any areas where smog is an issue. Please try it, and see how much you like all those NOx emissions instead of hiding behind your "temporary pollutant" argument. If you want to use it, it also applies to CO2, if we stop producing it, CO2 levels will go down as it gets absorbed by the environment.
We're talking about technology that is better for the environment. On a toe to toe basis, the modern diesel wins without question. Availability has nothing to do with it. If there were more demand for diesels in the US, there would be more availability. Please, modern diesel does not beat a modern hybrid on a toe to toe basis. I will readily admit that each has it's benefits and drawbacks for particular situations, but you diesel fanboys would rather turn your blinders on.
Never mind the fact that you diesel fanboys completely ignore the fact that you can combine the two and get the best of both worlds. In fact, you see this happening right now, look at all the diesel-hybrid buses that are being bought by municipalities which *gasp* significantly reduce CO2, NOx and particulate emissions. Now if diesel is the perfect technology as you so proclaim, how is a hybrid able to improve upon it?
Take off your blinders and realize that there is more than one solution to the problem, and in fact, the solution absolutely requires us to tackle the issue from multiple points.
Kidding myself? I could tell you the same and to stop measuring pollution in only miles per gallon.
I never said that diesels would never match the emissions levels of gasoline cars. Emissions technology has come a long way recently - just the fact that they do have models now that meet CARB standards is a testament to that. The drawback (for now) is that clean diesel technology does not come without a price - just like hybrid tech.
I personally think that combining diesel and hybrid technology could be another stepping stone towards reducing our impact on the environment. But people always seem to want to turn things into a hybrid vs diesel argument when in reality both technologies could be part of the solution.
It causes a bit of asthma if you're prone to it and some other respiratory issues in cities So you're willing to cause a good number of people unneeded health risks? Good thing you're not making the decisions on acceptable emissions requirements. Don't you think there's a reason why CARB has created the toughest emissions requirements in the entire US (which slowly the rest of the country is adopting, state by state)? Could it be - gasp - that I people would prefer to breath clean air?
the thing about NOx is that it's a temporary pollutant and has very little lasting effect Bullshit. When you live in an urban setting where the NOx output is constant and always there, you can no longer claim it's a "temporary pollutant".
blah blah blah on how biodiesel kicks a gasoline hybrid's ass 1. Thanks for omitting the fact that biodiesel happens to create more NOx/smog forming pollutants than petro-based diesel. 2. Thanks for arguing for biodiesel when it's availability is next to non-existant outside of the EU (just like E85 is next to non-existant outside of the midwest).
If you wanted to spout off about the benefits of biodiesel, perhaps you should be honest about it's drawbacks? I've driven behind biodiesel cars. Frankly, they smell like crap and the odor made me sick to my stomach. Just like driving behind a regular diesel, I have to switch from fresh to recirculated air. I can't imagine what a whole road full of them would smell like.
Biodiesel is no panacea to the environment. Hybrids aren't either.
But at least hybrids are developing technology (battery/electric) which is most likely to provide the best drivetrain for future cars - the pure electric.
The Prius and Civic hybrids are "look at me" cars. I'm not sure why you call the Civic hybrid a "look at me" car, when it clearly looks the same as it's non-hybrid counterpart so it hardly draws any glances given the popularity of the Civic.
The TDI's are easily their equal with 10+ year old tech, and the VW Lupo (not available in the US...) is just in a different class altogether. I love it when people compare apples to oranges. Have you bothered to compare the amount of pollutants one of your TDIs emits compared to the Prius which has the lowest emissions of any car sold in the US? Or perhaps considered that's why only a few diesels for 2008 have finally cleaned up their act enough to actually be legal for sale in the US and are still in the highest polluting category of cars?
And yes, you're right, the Lupo is in a different class altogether - comparing a 2-door city car which weighs less than 2000 pounds (the smallest class of car available) to a medium size family car weighing just under 3000 points is just nuts.
Why can't they make the hybrid cars look nice for God's sake....? There is only one car on the market which is only available as a hybrid, the Prius.
Everything else is available with our without the hybrid drivetrain, so I don't quite follow your thought process unless you think all those cars are also ugly?
With proper battery management the number of times a battery can be charged/discharged goes up significantly.
For example, in hybrid cars on the market today, for example the Prius, the battery management system carefully monitors battery voltage levels and maintain a battery charge between 40-80%. This is because discharging batteries below 40% capacity and charging cells past 80% will reduce the number of cycles you can get out of a battery. The Prius battery pack as a whole has a very low failure rate because of this. Typically when the battery pack goes "bad", the majority of the cells that make up the pack are fine, but a couple cells have failed and no longer hold a charge which kills battery pack performance as all current must flow through those bad cells.
The battery management system if a full electric car can be even more sophisticated. For example, the battery pack in the Tesla has every individual cell monitored for voltage and performance. In addition, if a cell goes bad, it has the ability to bypass that cell so that performance of the battery pack as a whole will remain largely unaffected.
The number of cycles a battery will endure between 60-100% charge or between 0-40% charnge is significantly lower than the number of cycles it will endure between 40%-80% charge.
With careful charge management, batteries could easily be used to help offset load peaks in the grid by ensuring that the cell pack state of charge remains within set boundaries designed to minimize the effect on battery life. Doing so will basically make any reduction in cell life due to it's use on the grid negligible.
Sounds about right. Each 7200rpm hard drive will add close to 10w during idle.
WD recently launched some low power drives, but they don't spin at 7200rpm. Performance is quite good considering and power draw is about half of a comparable 7200rpm drive.
One of the biggest power draws these days are graphics cards. Often, graphic cards will draw as much power as the rest of the system. It's typical for the cheapest graphics card to add 10 watts to the power draw of the system when idle, with 25-50+ being common for medium to high end cards. Unfortunately, current graphics cards don't do much in the way of reducing power draw when idle.
If you don't do any serious gaming, sticking with the onboard graphics will often reduce power draw significantly. If your mobo doesn't have onboard graphics, picking an inexpensive fanless graphics card will draw the least power.
If you were using onboard graphics, I would expect your system would idle around 55w (+-5w or so). Peak power draw would be less than 100w. With the GPU you're using, I'd guess that it adds add 10-20w at idle and another 50w at peak. It'd be interesting to see what the actual numbers are.
Something people often forget is that a good PSU with active power correction will also significantly reduce the apparently load on a UPS (as well as the grid if you don't have a UPS), not to mention that PSUs with APC are normally significantly more efficient. For example, if your system draws 100w but your PSU has a power factor of.5, you are actually pushing twice as much current through the AC line as a system drawing 100w but a power factor of 1. This ends up doubling the load on your UPS if you have one.
These days it's fairly easy to build a system which idles below 50w as long as you're informed. A bit more research will get you something in the 30-35w idle range if not lowre. I do wonder what you had in your old Socket 754 machine which caused it to idle at 100w. I suspect it had an inefficient PSU and a mid-high end graphics card or wasn't using Cool'n'Quiet. All recent AMD systems I've seen which support Cool'n'Quiet idle at 60w or less unless you have a power sucking GPU.
I do not understand the fixation on CPU scheduling when there are so many other things that need attention. [Heck, if disk IO performance is so broken, I certainly don't have the guts to try out the new firewire code in 2.6.22 as well and add another variable into my life.]
Check out the "per device write throttling" patches which improve this behavior a significant amount. The patchset is currently on the 10th revision.
Well damn. That's just... embarassing. Why's everyone using linux if it sucks so much?
I suspect that the Solaris/FreeBSD schedules aren't completely fair and instead are boosting the priority of certain processes to achieve interactivity... but I could be wrong, I haven't actually tested them. Not to mention, how many people actually load up their machines to loads over 10?
The latest versions of CFS are much better than earlier revisions (not sure what version exactly the grandparent tested exactly, 2.6.22 was pretty early for CFS the latest 2.6.22.5 has accumulated a number of fixes/improvements) so the situation has likely improved already.
Ripping it out [the scheduler] every 6 months and calling it "stable" seems a bit off to me.
If you want a stable kernel, don't use the vanilla kernel. Linus has repeated stated that a perfect kernel is not the goal with his tree. His goal is to promote the development of the kernel which maintains some sense of stability but he pretty much guarantees that it will not be perfect.
The process of creating a bugless kernel requires that all new development stop for an extended period of time. Which is what happened (mostly) with the old style odd/even kernel development and as a result, you end up with massive upheaval between the so called stable releases (which never were all that stable in the first place).
If you want something rock solid and stable, use a vendor's kernel with long release cycles. Try RHEL/CentOS, Ubuntu LTS or Debian.
I fully expect that in the next few years diesel cars will be available that are as clean as current gas cars, but diesel cars available today are not as clean.
I personally am looking forward to a diesel PHEV, the combination of the two should produce some impressive fuel economy.
If the PZEV cars get the same fuel efficiency as conventional vehicles, then they are consuming the same amount of carbon and putting the same amount of CO2 into the atmosphere. Yes, you are correct.
So how can they be less polluting than a lawn mower? The article must NOT be including CO2 as a pollutant (the same view the Bush administration took of the Clean Air Act). So these vehicles probably emit less sulfur and nitrogen compounds and particulates, but the same amount of CO2. Yes, again you are correct. Go sniff the tailpipe of a lawnmower, then go sniff the tailpipe of a new big V8 car. Tell me which one is more pleasant and doesn't make your eyes water and cough.
In fact, catalytic converters (which do most of the exhaust cleaning in your typical car) are also partly to blame for increased CO2 emissions since catalytic converters tend to self-destruct and also do not clean the exhaust as well when run at lean air to fuel ratios. Nearly all cars on the market today run richer than is required in order to reduce exhaust emissions - at the expense of CO2 emissions. This is one reason why hybrids are able to improve fuel economy so much, by reducing or eliminating engine use when it is not efficient.
Until recently, not many people considered CO2 a pollutant, but this is why you are seeing much more emphasis on fuel efficiency recently (not to mention the large increase in fuel prices over the past 5 years).
Almost ALL of those euro diesel cars have less emissions than some of the best american gasoline cars. Please back this up with facts, please. If almost all those euro diesel cars were cleaner than the best American gasoline cars (do you mean American as in the Big-3 or American sold cars?) and got 80+ mpg, those manufacturers would be dumb to not sell them here in the states.
But there's a reason there aren't any diesel cars on the market here today - they are much dirtier than your typical gasoline engine and require expensive exhaust treatments to clean them up to today's standards.
It's fairly well known that large writes to the filesystem can cause huge read delays.
This seems to be aggravated by a number of conditions listed in the links posted by the parent post, but it's also aggravated when using ext3 and ordered data journaling as well (which is the default on most systems).
There is some work being done to reduce the huge latency in reads that can occur during heavy write loads with the "per device dirty throttling" patchset. Initial results look very promising.
This patch set seems to hold a lot of promise in being able to fix this problem, but I'm not sure what the latest status is or what kernel it will make it into. It could make it into 2.6.24 at the earliest.
But none of the latest Volkswagons, Mercedes and BMWs are clean enough for for sale in the USA (yet, should be able to in the next year). With fancy (and expensive) urea injection and particle capture exhaust systems they manage to meet emissions requirements, but they still aren't for sale.
BTW, did you remember to take into account the fact that diesel has ~10-20% more energy than gasoline and as a result ~10-20% more CO2 emissions for same fuel economy?
Hybrids won't really get good until they start putting LiIon batteries in them and give them plug-in capabilities, but even now your typical hybrid is worth 15-30% in fuel economy depending on the system.
BTW, anyone regularly getting less than 40mpg on their Prius either needs to have their car or driving checked out, everyone I know gets 45+mpg in real world driving.
Slashdot Mirror
The ONLY way you can defragment a file is to copy the fragmented file to another partition, remove it and copy it back. If you want to defragment a complete ext2/3 filesystem, make a backup of the filesystem using tar, delete the original and restore the backup.
No, this is not something you want to do while other software may be looking for the file.
Of the common filesystems available for Linux (ext2/3, xfs, jfs, reiserfs) the only one that supports online defragmentation is xfs (using the xfs_fsr utility) and this has to be scheduled manually.
Fragmentation in ext2/3 files is a huge problem when appending to files over long periods of time. You can check the fragmentation of any file on ext2/3 using the filefrag utility. Make a copy of a highly fragmented file (even to the same partition) and you will see the number of fragments go down dramatically, unless you don't have much free space left on the partition and the space you have free is also highly fragmented.
The usual reason that tap tastes like "crap" is because it contains an excess of minerals and residue when the upstream water source has a high level of algae.
A simple charcoal filter (either a Brita or an inline charcoal filter) goes a long way towards reducing that taste.
A basic reverse-osmosis system will remove it completely, but wastes some water in the process.
As the previous reply suggested, just going to your local grocery store and getting water out of those water dispensers that you drop quarters in to will also do the trick, they typically have water that tastes the same as bottled in my experience (but I prefer the carbon filters since it's a PITA to schlep all that water back home).
and cleans up the emissions
Frankly, that is the #1 reason that diesels aren't selling in the US right now.
Currently even the cleanest diesel cars due out this year are just barely clean enough to squeak by US emissions standards. Particulate and NOx emissions are insanely high compared to to gas cars.
Producing a car that gets great mileage (and low CO2 emissions) AND low pollutant emissions as well is not an easy task. The Prius hybrid is still by far the leader in fuel economy AND low emissions.
By the time this VW diesel hybrid is out, the next generation Prius will be out shortly. Don't forget that the current Prius is already nearly 5 years old - and no-one has anything that really competes in terms of fuel economy, emissions and practicality.
This local root exploit is very likely to be the one used to infect servers reference in previous Slashdot article Mystery Malware Affecting Linux/Apache Web Servers.
It seems pretty clear that people are using other remote vulnerabilities to gain local user access and then using this local root exploit to install their "malware".
Get those boxes updated as quickly as possible, folks!
I suggest people interested in energy to read Scientific American's A Solar Grand Plan which outlines a realistic way end U.S. reliance on foreign oil while slashing greenhouse gas emissions by using solar power.
If I want to buy a diesel, I have only 3 choices, VW, Mercedes and Jeep (and I have no idea what ones are actually available right now, but I can't find any information on VWs site about the 2008 Jetta Diesel, and it's not on fueleconomy.gov, either). Maybe by the end of the year there will be a wider choice as manufactures clean them up enough to meet TIER 2 BIN 5 emissions standards.
Please tell me where I can go buy biodiesel without setting up a brewing station on my patio. Even the nearest E85 is about 15 miles from where I live and even further from where I work. I expect the nearest biodiesel station to be the same. We aren't talking about individual cases, we are talking about averages. Is your average hybrid driver seeing 40+? Nope, check the statistics. The average hybrid is meeting their 2008 EPA estimates. Look it up on fueleconomy.gov. So that means that YES, your average Civic Hybrid driver is getting 42 mpg and the average Prius driver is getting 46 mpg.
All the cases where I've seen a Prius getting less than 40 mpg are the result of short trips less than 10 minutes in cold weather. But in these conditions, all cars get crappy mileage compared to their EPA estimates.
The horse is obviously dead at this point, so this will be my last reply.
First you say biofuel-diesel is the way to go.
Then you brush off diesel-hybrid because it's not available yet. But wait, diesel biofuel isn't available in any significant quantities yet either.
Do you see the problem with your argument? You do this all over the place.
Your claim that hybrids are less efficient than their gas-only counterparts is simply false in many cases is false. If you want to make that argument, I can also claim that in many cases, hybrids completely blow anything else out of the water since many people regularly average 60+ mpg.
I can drive a Prius like a bat out of hell (jack-rabbit starts, 80+mph freeway speeds), and it still gets about 40mpg. I drive a Civic the same and it gets about 30mpg.
Never mind the fact that you diesel fanboys completely ignore the fact that you can combine the two and get the best of both worlds. In fact, you see this happening right now, look at all the diesel-hybrid buses that are being bought by municipalities which *gasp* significantly reduce CO2, NOx and particulate emissions. Now if diesel is the perfect technology as you so proclaim, how is a hybrid able to improve upon it?
Take off your blinders and realize that there is more than one solution to the problem, and in fact, the solution absolutely requires us to tackle the issue from multiple points.
Kidding myself? I could tell you the same and to stop measuring pollution in only miles per gallon.
I never said that diesels would never match the emissions levels of gasoline cars. Emissions technology has come a long way recently - just the fact that they do have models now that meet CARB standards is a testament to that. The drawback (for now) is that clean diesel technology does not come without a price - just like hybrid tech.
I personally think that combining diesel and hybrid technology could be another stepping stone towards reducing our impact on the environment. But people always seem to want to turn things into a hybrid vs diesel argument when in reality both technologies could be part of the solution.
2. Thanks for arguing for biodiesel when it's availability is next to non-existant outside of the EU (just like E85 is next to non-existant outside of the midwest).
If you wanted to spout off about the benefits of biodiesel, perhaps you should be honest about it's drawbacks? I've driven behind biodiesel cars. Frankly, they smell like crap and the odor made me sick to my stomach. Just like driving behind a regular diesel, I have to switch from fresh to recirculated air. I can't imagine what a whole road full of them would smell like.
Biodiesel is no panacea to the environment. Hybrids aren't either.
But at least hybrids are developing technology (battery/electric) which is most likely to provide the best drivetrain for future cars - the pure electric.
And yes, you're right, the Lupo is in a different class altogether - comparing a 2-door city car which weighs less than 2000 pounds (the smallest class of car available) to a medium size family car weighing just under 3000 points is just nuts.
Everything else is available with our without the hybrid drivetrain, so I don't quite follow your thought process unless you think all those cars are also ugly?
With proper battery management the number of times a battery can be charged/discharged goes up significantly.
For example, in hybrid cars on the market today, for example the Prius, the battery management system carefully monitors battery voltage levels and maintain a battery charge between 40-80%. This is because discharging batteries below 40% capacity and charging cells past 80% will reduce the number of cycles you can get out of a battery. The Prius battery pack as a whole has a very low failure rate because of this. Typically when the battery pack goes "bad", the majority of the cells that make up the pack are fine, but a couple cells have failed and no longer hold a charge which kills battery pack performance as all current must flow through those bad cells.
The battery management system if a full electric car can be even more sophisticated. For example, the battery pack in the Tesla has every individual cell monitored for voltage and performance. In addition, if a cell goes bad, it has the ability to bypass that cell so that performance of the battery pack as a whole will remain largely unaffected.
The number of cycles a battery will endure between 60-100% charge or between 0-40% charnge is significantly lower than the number of cycles it will endure between 40%-80% charge.
With careful charge management, batteries could easily be used to help offset load peaks in the grid by ensuring that the cell pack state of charge remains within set boundaries designed to minimize the effect on battery life. Doing so will basically make any reduction in cell life due to it's use on the grid negligible.
Sounds about right. Each 7200rpm hard drive will add close to 10w during idle.
WD recently launched some low power drives, but they don't spin at 7200rpm. Performance is quite good considering and power draw is about half of a comparable 7200rpm drive.
One of the biggest power draws these days are graphics cards. Often, graphic cards will draw as much power as the rest of the system. It's typical for the cheapest graphics card to add 10 watts to the power draw of the system when idle, with 25-50+ being common for medium to high end cards. Unfortunately, current graphics cards don't do much in the way of reducing power draw when idle.
.5, you are actually pushing twice as much current through the AC line as a system drawing 100w but a power factor of 1. This ends up doubling the load on your UPS if you have one.
If you don't do any serious gaming, sticking with the onboard graphics will often reduce power draw significantly. If your mobo doesn't have onboard graphics, picking an inexpensive fanless graphics card will draw the least power.
If you were using onboard graphics, I would expect your system would idle around 55w (+-5w or so). Peak power draw would be less than 100w. With the GPU you're using, I'd guess that it adds add 10-20w at idle and another 50w at peak. It'd be interesting to see what the actual numbers are.
Something people often forget is that a good PSU with active power correction will also significantly reduce the apparently load on a UPS (as well as the grid if you don't have a UPS), not to mention that PSUs with APC are normally significantly more efficient. For example, if your system draws 100w but your PSU has a power factor of
These days it's fairly easy to build a system which idles below 50w as long as you're informed. A bit more research will get you something in the 30-35w idle range if not lowre. I do wonder what you had in your old Socket 754 machine which caused it to idle at 100w. I suspect it had an inefficient PSU and a mid-high end graphics card or wasn't using Cool'n'Quiet. All recent AMD systems I've seen which support Cool'n'Quiet idle at 60w or less unless you have a power sucking GPU.
Check out the "per device write throttling" patches which improve this behavior a significant amount. The patchset is currently on the 10th revision.
For more information, check out this LWN.net article: http://lwn.net/Articles/245600/
I suspect that the Solaris/FreeBSD schedules aren't completely fair and instead are boosting the priority of certain processes to achieve interactivity... but I could be wrong, I haven't actually tested them. Not to mention, how many people actually load up their machines to loads over 10?
The latest versions of CFS are much better than earlier revisions (not sure what version exactly the grandparent tested exactly, 2.6.22 was pretty early for CFS the latest 2.6.22.5 has accumulated a number of fixes/improvements) so the situation has likely improved already.
If you want a stable kernel, don't use the vanilla kernel. Linus has repeated stated that a perfect kernel is not the goal with his tree. His goal is to promote the development of the kernel which maintains some sense of stability but he pretty much guarantees that it will not be perfect.
The process of creating a bugless kernel requires that all new development stop for an extended period of time. Which is what happened (mostly) with the old style odd/even kernel development and as a result, you end up with massive upheaval between the so called stable releases (which never were all that stable in the first place).
If you want something rock solid and stable, use a vendor's kernel with long release cycles. Try RHEL/CentOS, Ubuntu LTS or Debian.
I fully expect that in the next few years diesel cars will be available that are as clean as current gas cars, but diesel cars available today are not as clean.
I personally am looking forward to a diesel PHEV, the combination of the two should produce some impressive fuel economy.
In fact, catalytic converters (which do most of the exhaust cleaning in your typical car) are also partly to blame for increased CO2 emissions since catalytic converters tend to self-destruct and also do not clean the exhaust as well when run at lean air to fuel ratios. Nearly all cars on the market today run richer than is required in order to reduce exhaust emissions - at the expense of CO2 emissions. This is one reason why hybrids are able to improve fuel economy so much, by reducing or eliminating engine use when it is not efficient.
Until recently, not many people considered CO2 a pollutant, but this is why you are seeing much more emphasis on fuel efficiency recently (not to mention the large increase in fuel prices over the past 5 years).
But there's a reason there aren't any diesel cars on the market here today - they are much dirtier than your typical gasoline engine and require expensive exhaust treatments to clean them up to today's standards.
Here's a post on how the above patchset can improve the responsiveness of the system under heavy write load:
huge improvement with per-device dirty throttling
And the thread referencing the latest version of the patch posted to lkml:
per device dirty throttling -v9
It's fairly well known that large writes to the filesystem can cause huge read delays.
This seems to be aggravated by a number of conditions listed in the links posted by the parent post, but it's also aggravated when using ext3 and ordered data journaling as well (which is the default on most systems).
There is some work being done to reduce the huge latency in reads that can occur during heavy write loads with the "per device dirty throttling" patchset. Initial results look very promising.
LWN article: Smarter write throttling
per device dirty throttling -v8
This patch set seems to hold a lot of promise in being able to fix this problem, but I'm not sure what the latest status is or what kernel it will make it into. It could make it into 2.6.24 at the earliest.
But none of the latest Volkswagons, Mercedes and BMWs are clean enough for for sale in the USA (yet, should be able to in the next year). With fancy (and expensive) urea injection and particle capture exhaust systems they manage to meet emissions requirements, but they still aren't for sale.
BTW, did you remember to take into account the fact that diesel has ~10-20% more energy than gasoline and as a result ~10-20% more CO2 emissions for same fuel economy?
Hybrids won't really get good until they start putting LiIon batteries in them and give them plug-in capabilities, but even now your typical hybrid is worth 15-30% in fuel economy depending on the system.
BTW, anyone regularly getting less than 40mpg on their Prius either needs to have their car or driving checked out, everyone I know gets 45+mpg in real world driving.