<<
No, it's not important. The on-disk cache isn't there for throughput,
it's there because of the disk's rotational latency.
>>
I am not speaking about sustained throughput, I am speaking about burst
transfers. So in this regard, I maintain that yes, a 300 MB/s sata link
will make a difference and will improve (some) workloads.
How? With DMA the rest of the system doesn't have to sit around waiting for the transfer to finish, so why does it care about the burst rate for such a small amount of data?
"When data is exchanged to/from the disk's cache, data throughput of 250+ MB/s can be achieved for a fraction of a second. Even if it's only for a fraction of a second, it is still important (else manufacturers would not even put cache memory on disks)."
No, it's not important. The on-disk cache isn't there for throughput, it's there because of the disk's rotational latency.
In order to increase throughput in a useful way, it would have to be larger than the OS's cache, which will be several 10's (or maybe a few 100's) of MB, depending on how much memory you have. The only reason it's useful at all is that the OS doesn't know the disk geometry and so *can't* do the type of caching the on-disk cache does (which is to store one "track" worth of data, so that an access that doesn't require moving the heads doesn't have to wait for the disk to rotate to the right position).
"Why is old-growth forest more important than a parking lot?"
Because parking lots are hot, ugly, and a lousy place to go for a walk. Also as I understand it, forests tend to do good things to air quality (which you care about, because you have to breathe that air).
"More notebooks have been sold than desktops at retail over the last few quarters, but desktop sales regained some ground to finish nearly even with notebooks..."
Why? Yes, desktops are more upgradeable, cheaper, and more powerful, but have they actually increased their lead in any of these areas? I'd think that with USB and Firewire, laptops would actually be catching up in upgradability. The way companies seem to have been focusing on power consumption lately, they should be catching up in power. And the prices should only get better as volumes go up (aside from Moore's law, which doesn't count because it applies to desktops as well).
Why would people move back to desktops? Or is it that desktops have started getting cheap enough that people are switching from "family computer" to "cheap desktop for everyone"?
From the article and the so-called "datasheet" (It is nothing of the sort.) on their website, this system apparently does 2 things:
Content-addressed storage
Stores diffs instead of full files where possible
(1) removes duplicate entries, which is good for repeated backups to the same place. (2) is good for storing similar files, *if* you can find them. It sounds almost like their storage is addressed with some form of non-crypto hash that only changes slightly between similar files ("no disk I/O", so they must be able to match things without actually looking at them).
Overall, it sounds like what they do is very similar to git packs, except they claim to be able to do it without lots of I/O, which claim sounds like the specialized hashes. If this is the case, it'd be good for never-deleted nightly backups to the same disk and for systems with lots of similar files. It would get very good "compression" in those cases compared to dated.tbz files, but it wouldn't be (as) significantly better than other tools designed for that kind of usage.
Of course, if used to just compress your 100GB movies folder it still wouldn't be able to do much of anything. Implying that it would, as TFA does, sounds totally bogus. I doubt it would be more than 2-3x better than any other compressor designed for what it's being used for. (Supposedly git packs are really good like this, because of the "similar files" thing.)
The "only" thing which makes the life/not-life distinction fuzzy is that it is capable of directing production of additional copies of itself, such that it fufils all the requirements for evolution*. I put "only" in quotes, because it is a pretty big thing, and is arguably the only requirement for something to be "life."
Computer viruses can also direct the production of additional copies of themselves...
"Aren't the HDDs in a compressed environment in the aircraft though?"
Yes, it's pressurized, but not to the same pressure as at ground level (that would take too much work). I sort of recall hearing that HDDs can have trouble if they live on high mountains, too.
First of all: Profit? These are university physicists, not a company trying to trick you into buying something. The most they profit will be a pat on the back from the physics community.
No, they could use it to get increased research grants/funding... with the possible result of getting a raise, and the definite result of the university not needing to charge really-insanely-rediculous tuition. (As one of my professors explained, us students only pay about 20% of what's needed for the university. The government also pays about 20%, and the rest has to come from grants/funding that the professors bring in.)
Encourage companies to trade with them, and encourage them to push the boundaries of what's allowed there. Let the people see what they're missing out on.
This License gives unlimited permission to privately modify and run the Program, provided you do not bring suit for patent infringement against anyone for making, using or distributing their own works based on the Program.
So patent law mixed with how I use the software, and privately at that. Can I use GPLv3 software in a company (it's not private, usually)? Can I modify it, but not distribute it outside the company? If I don't do this privately, but as a "corporate" person, then it's not private, so I can do what I want (of course not).
"Privately" would be "not for distribution", so for your own personal use for you, or for internal use by a company.
"If you don't redistribute the software, you can do anything you want with it. Unless you sue people, in which case you can only do what copyright law says you can (which isn't very much)."
There is a proposal in it that would discourage or disable the use of GPL software for DRM, by stating that software under the new GPL cannot constitute an "effective technological protection measure".
[...] Being an "effective technological protection measure" seems like a matter that can't be waived, any more than my signing a stipulation that I wasn't born in August affects my birthday.
"Please note that since source code will be available for any GPL "technological protection measure", it will be very much ineffective."
Can you please prove (using religion, of course) religion? I mean, for something that claims to be The Truth, surely it can demonstrate that it is, itself, The Truth?
Except that I'm pretty sure that a lot of religions *don't* try to prove things. Y'know, that whole "faith" thing.
Slashdot Mirror
Ah. Now it makes sense.
I am not speaking about sustained throughput, I am speaking about burst transfers. So in this regard, I maintain that yes, a 300 MB/s sata link will make a difference and will improve (some) workloads.
How? With DMA the rest of the system doesn't have to sit around waiting for the transfer to finish, so why does it care about the burst rate for such a small amount of data?No, it's not important. The on-disk cache isn't there for throughput, it's there because of the disk's rotational latency.
In order to increase throughput in a useful way, it would have to be larger than the OS's cache, which will be several 10's (or maybe a few 100's) of MB, depending on how much memory you have. The only reason it's useful at all is that the OS doesn't know the disk geometry and so *can't* do the type of caching the on-disk cache does (which is to store one "track" worth of data, so that an access that doesn't require moving the heads doesn't have to wait for the disk to rotate to the right position).
Because parking lots are hot, ugly, and a lousy place to go for a walk. Also as I understand it, forests tend to do good things to air quality (which you care about, because you have to breathe that air).
Yeah, but that's not new, and so shouldn't affect this. Desktops have always been better that way, why would people not notice until now?
Why? Yes, desktops are more upgradeable, cheaper, and more powerful, but have they actually increased their lead in any of these areas? I'd think that with USB and Firewire, laptops would actually be catching up in upgradability. The way companies seem to have been focusing on power consumption lately, they should be catching up in power. And the prices should only get better as volumes go up (aside from Moore's law, which doesn't count because it applies to desktops as well).
Why would people move back to desktops? Or is it that desktops have started getting cheap enough that people are switching from "family computer" to "cheap desktop for everyone"?
Tim
- Content-addressed storage
- Stores diffs instead of full files where possible
(1) removes duplicate entries, which is good for repeated backups to the same place. (2) is good for storing similar files, *if* you can find them. It sounds almost like their storage is addressed with some form of non-crypto hash that only changes slightly between similar files ("no disk I/O", so they must be able to match things without actually looking at them).Overall, it sounds like what they do is very similar to git packs, except they claim to be able to do it without lots of I/O, which claim sounds like the specialized hashes. If this is the case, it'd be good for never-deleted nightly backups to the same disk and for systems with lots of similar files. It would get very good "compression" in those cases compared to dated .tbz files, but it wouldn't be (as) significantly better than other tools designed for that kind of usage.
Of course, if used to just compress your 100GB movies folder it still wouldn't be able to do much of anything. Implying that it would, as TFA does, sounds totally bogus. I doubt it would be more than 2-3x better than any other compressor designed for what it's being used for. (Supposedly git packs are really good like this, because of the "similar files" thing.)
Tim
Yes, it's pressurized, but not to the same pressure as at ground level (that would take too much work). I sort of recall hearing that HDDs can have trouble if they live on high mountains, too.
TimSo, saying there is no next big thing is the next big thing?
TimNo, they could use it to get increased research grants/funding... with the possible result of getting a raise, and the definite result of the university not needing to charge really-insanely-rediculous tuition. (As one of my professors explained, us students only pay about 20% of what's needed for the university. The government also pays about 20%, and the rest has to come from grants/funding that the professors bring in.)
TimEncourage companies to trade with them, and encourage them to push the boundaries of what's allowed there. Let the people see what they're missing out on.
Tim
Tim
Tim
So... unskilled people think they are skilled, and skilled people know that they are skilled. Maybe everyone just thinks they're skilled?
Some people do actually seem to treat it as such, flaming questions about their accepted theory rather than answering them.
Tim
Tim
"If you don't redistribute the software, you can do anything you want with it. Unless you sue people, in which case you can only do what copyright law says you can (which isn't very much)."
Tim
IANAL
Tim
What about NOAA?
Tim
Then the Windows ports are flawed. A proper rootkit is neither seen nor heard.
Tim
Tim
Tim
Tim