IDE is here to stay in the high end market, and it's going to kick SCSI's ass. Why pay 3X more per drive for the same HDA with a different interface board?
This is from the server in the first link above. Note that most of the write bottleneck is caused not by the drives but by the hardware RAID5 controller.
Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP/sec %CP
bedford 1G 24436 11 22834 13 83890 43 361.2 2
The idea was that students could tag places as they saw fit.
They've been doing this in cities for years. You really should leave the house more.
The other API for this "tagging" was apparently developed by some kids in the mid 80s. It involved various cans of spray paint, and optionally some varying spray tips for control.
Thanks. I'll put that in my sig. Something has got to give, and soon. The editors of this site need to come clean with us. How can they push public disclosure for everything corporate, but not even tell us when they are outright breaking their own rules.
I'm surprised no one is using a cluster though. With hardware prices so cheap, a 6 node cluster can be built for less than $1500. I am doing that right now in fact.
I am in total agreement with you about how algorithms are overriding in determining performance. I do think that algorithms that are on the same order of algorithmic growth will not be fairly compared to each other with diverse hardware like this though.
I mean I know a O(n) will always beat an O(n^2), but with dissimilar hardware, you aren't going to be able to compare 2n+34 with 2000n+100, if you get my drift. A large constant coefficient difference in two algorithms may be concealed under a fast processor.
It's not perfect, but they manage to have a large number of interesting boards with a good S/N ratio.
Basically, anyone can "recommend" a post once, the best posts out of all the boards go into a "best of" board for a while. Noise is removed by usually responsible moderators, who tolerate offtopic posts, and usually only remove completely offtopic new threads, and spam.
There are also many boards dedicated to metadiscussion. These are often heated arguments, and usually fall on deaf ears, but at least people can get it out of their system.
Slashdot is facing a huge rebellion, of several hundred users that are vocal, and don't like the current system.
I hope The High Ranking Mexican Food has some big plans for this Friend/Foe system, because the current system isn't cutting it, and secret editor moderation is only making the rebellion grow.
Fool.com has a friend/foe system, it is much less sophisticated than Slashdot, but you can go to a special area and see the posts your friends have made recently, and the foes are basically implemented as a killfile, you won't see any posts made by an Ignored Fool.
Recommendations aren't like karma, you can look and see how many you have total, but it doesn't mean anything, you get no special privilege (other than possibly getting on the best of board for a single post with dozens of recs) from having lots of them, so no one whores for them as much.
Anyway, Slashdot doesn't need to reinvent the wheel, they need to look at other successful large internet message boards, and take the best from them.
I'm an idiot, I forgot I have it set to always give offtopic posts an automatic +1 bonus when I read logged in. Since I set that up, I've noticed a lot of supposed offtopic posts that are very good.
I also forget about it being set that way, as was the case earlier.
I agree, except about the part that Linus not caring about kernel stability. He cares very much about kernel stability, but he doesn't attack the problem on the testing level. He is more interested in the general choices that will be made that might affect stability, not testing implementations of those decisions. I'm sure he reads every patch he applies that will affect stability. He may not understand all the logic in them, since some are very poorly documented and non-obvious, but he does seem to do more than blindly merge code that "looks good".
Linus knows his place in the big picture, and I think he does a very good job at not getting down and dirty and doing things like stress testing and benchmarking. The guy at the top should make general direction decisions and keep his nose mostly out of implementation, unless it would affect the future of the general directions of the code. For example, he wouldn't want to apply a patch that closed the door to other modifications later in some way, modifications that he seems as a future general goal of the kernel.
Maybe I'm just nitpicking at a slight overgeneralization on your part, but I think it's important to remember that Linus has a difficult job, and he generally does it very well.
As for the hardware, you are free to use what ever you want. It would be impossible to try to get all participants use the same computer-power and to make sure that they do.
Imagine....:)
Without equal hardware platforms, this will be hard to be more than just entertainment. It isn't much of a good benchmark of the programs involved.
This is especially true when you consider that certain processors are usually faster at certain critical operations in cases like this. It also apparently doesn't ban ASICs and other things that could make a huge difference. On the plus side, maybe we will start seeing PCI chess accelerator cards.:)
Being a computer guru is also a very difficult set of skills, at least being a good one. (It's easier to hide lack of skill with computers than with music though).
But, I think you miss my whole point.
If, in the country and the world I was born in, music and art skills were highly valued, and music and art related jobs were highly paid and necessary jobs, then I would have learned as best I could any music or art skills.
If I liked computers, and there was no money in them, then I would probably take it on as a hobby at most. I sure wouldn't waste my education on computers if the skills weren't in demand.
Hacking is fun because it requires you to be adept at something.
But anyway...
People are totally biting a red herring in this debate anyway, it's not a debate about usablility, it's a debate about userspace vs. kernel space. Linus thinks that it isn't necessary to provide kernelspace functions just for this program, and he is absolutely right. That is the ONLY thing at issue here, not freedom, or the future of Linux or any other BS.
I agree totally. I installed a cheapo motherboard with integrated everything (sound, video, network), and it all works. I was amazed. 2.4 is definitely the kernel of choice for any system that wasn't designed from the ground up to only have known safe hardware.
Yeah, I get what you are saying. It's sort of like they meant the commas in the OS list to be subordinated, but it comes out as if any of the requirements will do They could have used parenthesis around the OS list.
These nitrogen systems are causing condensation on most of the motherboard. Unless you could encase the computer in completely dry air, it's going to get wet.
You tell me how long a wet motherboard will run... These things are more of a novelty, not usable systems.
It looks like you just pour the nitrogen into that big metal bucket that sits on the processor. This is more of a novelty than a usable system, I'd bet the nitrogen boils off in less than an hour.
Slashdot Mirror
Yeah, Right
Reads at >80MB/Sec writes ~25MB/sec. Cost 1/3 of what a SCSI equivalent cost.
I can't believe you guys modded a troll up to 3...
/sec %CP
I guess this sucks?
Or This?
This?
This?
These?
This stuff?
IDE is here to stay in the high end market, and it's going to kick SCSI's ass. Why pay 3X more per drive for the same HDA with a different interface board?
This is from the server in the first link above. Note that most of the write bottleneck is caused not by the drives but by the hardware RAID5 controller.
Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
bedford 1G 24436 11 22834 13 83890 43 361.2 2
The idea was that students could tag places as they saw fit.
They've been doing this in cities for years. You really should leave the house more.
The other API for this "tagging" was apparently developed by some kids in the mid 80s. It involved various cans of spray paint, and optionally some varying spray tips for control.
GigsVT has posted 666 comments. [...]
Hehe Yeah I noticed that.
If this was discovered almost 2 years ago, then aren't and chips bought in the last couple years bug free?
Thanks. I'll put that in my sig. Something has got to give, and soon. The editors of this site need to come clean with us. How can they push public disclosure for everything corporate, but not even tell us when they are outright breaking their own rules.
Speaking of RIP, I work at a litho printer.
We want to get our harlequin RIP onto linux and off of SGI, we mostly are doing DCS and PS RIP. Any sugesstions?
gigs at vt dot edu
How is a message that was the first to mention Gentoo Linux redundant?
Either that, or you were selling useless garbage that could be done locally for no subscription cost.
You are incorrect about the SMP.
1,26GHz PIII Dual Tualatin
512MB
1GHz PIII Dual
512MB
1,2GHz Athlon Dual
1GB
800MHz PIII Dual
256MB
700MHz Xeon Quad
512MB
Etc...
I'm surprised no one is using a cluster though. With hardware prices so cheap, a 6 node cluster can be built for less than $1500. I am doing that right now in fact.
I am in total agreement with you about how algorithms are overriding in determining performance. I do think that algorithms that are on the same order of algorithmic growth will not be fairly compared to each other with diverse hardware like this though.
I mean I know a O(n) will always beat an O(n^2), but with dissimilar hardware, you aren't going to be able to compare 2n+34 with 2000n+100, if you get my drift. A large constant coefficient difference in two algorithms may be concealed under a fast processor.
Check out the system on fool.com.
It's not perfect, but they manage to have a large number of interesting boards with a good S/N ratio.
Basically, anyone can "recommend" a post once, the best posts out of all the boards go into a "best of" board for a while. Noise is removed by usually responsible moderators, who tolerate offtopic posts, and usually only remove completely offtopic new threads, and spam.
There are also many boards dedicated to metadiscussion. These are often heated arguments, and usually fall on deaf ears, but at least people can get it out of their system.
Slashdot is facing a huge rebellion, of several hundred users that are vocal, and don't like the current system.
I hope The High Ranking Mexican Food has some big plans for this Friend/Foe system, because the current system isn't cutting it, and secret editor moderation is only making the rebellion grow.
Fool.com has a friend/foe system, it is much less sophisticated than Slashdot, but you can go to a special area and see the posts your friends have made recently, and the foes are basically implemented as a killfile, you won't see any posts made by an Ignored Fool.
Recommendations aren't like karma, you can look and see how many you have total, but it doesn't mean anything, you get no special privilege (other than possibly getting on the best of board for a single post with dozens of recs) from having lots of them, so no one whores for them as much.
Anyway, Slashdot doesn't need to reinvent the wheel, they need to look at other successful large internet message boards, and take the best from them.
I'm an idiot, I forgot I have it set to always give offtopic posts an automatic +1 bonus when I read logged in. Since I set that up, I've noticed a lot of supposed offtopic posts that are very good.
I also forget about it being set that way, as was the case earlier.
I agree, except about the part that Linus not caring about kernel stability. He cares very much about kernel stability, but he doesn't attack the problem on the testing level. He is more interested in the general choices that will be made that might affect stability, not testing implementations of those decisions. I'm sure he reads every patch he applies that will affect stability. He may not understand all the logic in them, since some are very poorly documented and non-obvious, but he does seem to do more than blindly merge code that "looks good".
Linus knows his place in the big picture, and I think he does a very good job at not getting down and dirty and doing things like stress testing and benchmarking. The guy at the top should make general direction decisions and keep his nose mostly out of implementation, unless it would affect the future of the general directions of the code. For example, he wouldn't want to apply a patch that closed the door to other modifications later in some way, modifications that he seems as a future general goal of the kernel.
Maybe I'm just nitpicking at a slight overgeneralization on your part, but I think it's important to remember that Linus has a difficult job, and he generally does it very well.
Yeah, so people will steal huge amounts of TVs to sell them back, just like people steal huge amounts of guns to sell back at these events.
It's just an easy fence.
Apparently, they mass moderated all of them back up to 0 from -1.
/. archive.
This is a clear case of editors abusing their power. Someone archive this, since we know it isn't going into the
As for the hardware, you are free to use what ever you want. It would be impossible to try to get all participants use the same computer-power and to make sure that they do.
Imagine....
Without equal hardware platforms, this will be hard to be more than just entertainment. It isn't much of a good benchmark of the programs involved.
This is especially true when you consider that certain processors are usually faster at certain critical operations in cases like this. It also apparently doesn't ban ASICs and other things that could make a huge difference. On the plus side, maybe we will start seeing PCI chess accelerator cards.
Being a computer guru is also a very difficult set of skills, at least being a good one. (It's easier to hide lack of skill with computers than with music though).
But, I think you miss my whole point.
If, in the country and the world I was born in, music and art skills were highly valued, and music and art related jobs were highly paid and necessary jobs, then I would have learned as best I could any music or art skills.
If I liked computers, and there was no money in them, then I would probably take it on as a hobby at most. I sure wouldn't waste my education on computers if the skills weren't in demand.
Does this clear things up?
Hacking is fun because it requires you to be adept at something.
But anyway...
People are totally biting a red herring in this debate anyway, it's not a debate about usablility, it's a debate about userspace vs. kernel space. Linus thinks that it isn't necessary to provide kernelspace functions just for this program, and he is absolutely right. That is the ONLY thing at issue here, not freedom, or the future of Linux or any other BS.
Really? Sweet.
A couple months' (weeks'?) testing on developer workstations is not sufficient for an "enterprise" class operating system.
Linus doesn't test the kernels at all, except to make sure they compile his config and work well enough to boot.
I don't know what testing you refer to.
I agree totally. I installed a cheapo motherboard with integrated everything (sound, video, network), and it all works. I was amazed. 2.4 is definitely the kernel of choice for any system that wasn't designed from the ground up to only have known safe hardware.
Up2date solves dependancies with RPMs. I've found most people who don't like RedHat and RPMS aren't using them very effectively.
Yeah, I get what you are saying. It's sort of like they meant the commas in the OS list to be subordinated, but it comes out as if any of the requirements will do They could have used parenthesis around the OS list.
These nitrogen systems are causing condensation on most of the motherboard. Unless you could encase the computer in completely dry air, it's going to get wet.
You tell me how long a wet motherboard will run... These things are more of a novelty, not usable systems.
It looks like you just pour the nitrogen into that big metal bucket that sits on the processor. This is more of a novelty than a usable system, I'd bet the nitrogen boils off in less than an hour.
Still, pretty amazing.