Slashdot Mirror
Will 2009 Be the Turning Point For SSDs?
Iddo Genuth writes "Since first entering the consumer market about two years ago, solid state drives (SSDs) have improved significantly. While prices remain substantially higher than conventional magnetic storage, it is predicted that in 2009 SSDs will finally make an impact on both the consumer and business markets bringing blazing fast speeds at reasonable prices for the first time — will it finally happen?"
It seems likely, as Samsung began mass-producing both 128GB and 256GB SSDs this year. Intel and Micron have also posted recent breakthroughs which will help to bring the technology into the mainstream.
For laptops at least. There is no reason to not to have an SSD in your laptop.
I own an Asus Eee PC, which has a 4GB SSD. I take it with me everywhere and, being a butter-fingered oaf, I tend to drop it everywhere too. If the Eee had a conventional HDD I'm sure it would have given up the ghost long ago. But the Eee bounces along quite happily with no damage to the SSD. Solid state is great, especially for children and folk like me!
Just like the iPods suddenly being introduced as solid state units, things for SSD's will soon pass the threshold where it's suddenly viable for everyone. Only Samsung knows exactly when, but it seems clear that in the next six to eighteen months widespread SSD availability will trickle down from elite systems to mid-range.
I'm generally "Interesting," "Insightful," and even "Funny" here. What the hell happens to me at parties?
No no no, people have too big an investment in Windows to switch over to Linu.... what? SSD? Sorry, carry on...
The question should be "is this the year that SSDs will be price competitive with hard drives?" Until that day comes, SSDs will only sell in small quantities.
Money. HDD's will keep getting cheaper. I'm betting on 2010.
********* sig: If you don't like the law, get filthy stinking rich, and buy a better one.
will come likely before the year of the linux desktop.
What would bother me more than the high price is the limited number of writes.
Sure, there are ways to limit writes to the disk, like disable swapping and delaying writes whenever possible, but I would still rather go with a reliable HDD over a SDD.
I never dropped one of my notebooks until today, but then again I never had one that looked like a toy...
...the year of SSD on the desktop.
http://www.fusionio.com/ - why are we not hearing so much of them any more, or is there some other reason why nobody seems to mention them?
Need an ISP in South Africa?
If by "price competitive" you mean "equal $/GB," that day is far off. But if you mean "reasonable size and comparable write speed for less than $200," then that day will come in 2009 or 2010 for a lot of people, since many of us can get by fine with only 128GB.
it's not a problem anymore
http://en.wikipedia.org/wiki/Wear_levelling
I'm looking for a SSD cache driver for windows. I would like to have a hd-driver for vista which uses another harddisc (SSD) as a cache for other (spinning) harddiscs. My working set (including the OS) is probably below 32GByte, so a fast 64GByte SSD driver should be enough for general use. As I still have a lot of data (around 1TBype) which is only occasioaly used, a caching driver which usses a SSD would be the ideal solution.
Does anybody know such a software(driver)? I'm willing to pay, no need for open source...
It will be phased out (by Windows 7 or something similar) before XP will be phased out, so why bother.
Patents Drive Free Software as Hurricanes Drive Construction Industry
When comparing two computers, consumers go for the one with best numbers most of the time. They have no clue what harddrive throughput is, and even less clue about seek time. Capitalism provides the goods that sell, not the best-engineered goods (unless they sell better.. )
I bet the worldwide consumerist harddisk space utilization is about 15%, but most people don't realize this. Unless people have magically wised up, we won't see widespread SSD in laptops until they catch up pricewise.
Stop the brainwash
I wonder what effect it would have on McDonalds to say to everyone in the US, "Is 2009 finally the year people stop stuffing themselves with fattening poison?"
I doubt it would have any effect unless you made it explicit what the fattening poison was.
How many people need (or even have) 250GB+ in their laptops?!
In capacities from 30-60gb there is overlap in price ranges between SSD and HDD. Below that you can't get an HD drive, but SSD drives are available. SSD pricing has nowhere to go but down. HDD can drop relative prices, but only by adding more and more GB relative to your dollar.
That will keep HDDs alive for awhile in higher capacity drives, but the low low end is already ruled by SSDs (4GB, 8GB, etc as only options for netbooks). As time goes on SSD will move up from there, out-competing larger and larger capacity HDD until "boom" - they are produced more cheaply per GB regardless of total capacity.
I think that "boom" mark is sometime in 2010, but certainly the GP's point about laptops stands. Unless you are the rare person who needs a large capacity laptop drive, there is no reason not to have an SSD in your laptop now.
In the mid 1990s 'disk doubler' programs were popular, compressing data on the fly as it was saved to disk. After a few years, however, disk sizes increased sharply and the relationship between price and disk size is much steeper than linear (a 1Gibyte disk does not cost twice as much as a 500Gibyte disk). So hardly anyone bothers with dynamic compression any more. It is much easier to spend $40 more and get a drive that's twice as big.
However, with SSDs, even when the price falls, there is still an almost linear relationship between capacity and cost (since to get twice the capacity you need twice as many flash memory chips). And while the transfer speed is fast, it's still not keeping pace with the increase in CPU speeds. Compressing on-disk data with a fast compression scheme such as LZO is often faster than reading or writing to disk uncompressed. With SSDs you need much less complexity in the filesystem to get good performance, since minimizing seek time is no longer as important. Perhaps, then, adding file compression can be done more straightforwardly than the earlier compressed filesystems designed for rotating disks.
It won't do anything for your movie collection, but for virtual machine images and other bloat we put on our disks nowadays it could make quite a difference.
-- Ed Avis ed@membled.com
Last I saw a performance and power consumption test, SSDs did no better than mechanical HDs. Seek performance was much better, read performance not so much, and write performance was much worse, resulting in equivalent real-life desktop performance, at a much higher price.
A smart OS might be able to optimally split files between a SSD and a HD depending on usage patterns. I'm still waiting for a smart OS though, and somewhat object to an OS that has to span 2 partitions.
As for setting up your OS on a separate partition... about time you did it. It does not even require distinct physical HDs. I personally have been doing it since Win98 days, if not before.
The Cloud - because you don't care if your apps and data are up in the air.
When the helical fluorescent tubes that screw into regular lamp sockets came out, they were a flop. They cost $15 to $20. Despite being longer lasting than the equivalent dollar amount of incandescent bulbs, people didn't see them as a significant improvement. In one study group, a subject gave a remark that summed up their reticence: "This solves a problem I don't have."
So it is with SSD. It'll have to be enough cheaper than magentic storage and appear to be long lived enough so that people can overcome their unwillingness to switch from something that works just fine. Specs don't matter to the average user. Not getting stuck with an orphan matters far more. That point remains unproven. Thus SSDs do not solve a problem, but present one of their own. If and when both of these change, they'll be accepted.
"I may be synthetic, but I'm not stupid." -- Bishop 341-B
Speed, heat and power consumption are nifty talking points for those hyping SSDs, but SSDs aren't always very fast, and for the most part, the heat and power consumption savings are usually less significant than people assume.
I think Amdahl had a rule where you try to apply your resources to reduce the most significant piece of the puzzle, and in most notebooks, that's the CPU. Conventional notebook computers have a max consumption of 25-35W, notebook hard drives max out at about 3W. Even if SSDs were zero, your battery life in that situation might extend by 9%, not factoring in other parts of the computer, maybe reducing that figure to 6%. But SSDs do consume power, the charts I looked at was 30-40% savings, so a 3% savings might be a generous estimate. Things are a different with netbooks, because they usually do use much lower power CPUs.
My Mac Pro cold boots in 20 sec on a 7200 RPM hard drive. So I would expect that to go down to less than 10 seconds on really fast SSD.
As the island of our knowledge grows, so does the shore of our ignorance.
"Wow. Seriously.
The i-RAM is in another league in IOMeter...
Heh. The i-RAM is a finicky chunk of trash.
http://kernelslacker.livejournal.com/89113.html
Before 2008, SSDs were too small to use, or more expensive than the rest of your computer combined. In 2008, capacity increased and price dropped to a point where SSDs were a viable option for less than a 50% total system price premium you can now have an SSD that holds the OS, any normal (non-media intensive) apps you use, and a reasonable amount of data (excluding video or massive music/photo collections, which belong on a NAS device anyway.)
Things will only continue to get better for SSD, but flash memory has been playing hard-drive catch-up for more than a decade now, and it likely will be another decade before solid state storage is larger, faster (linear access) and cheaper than rotating media. What happened in 2008 was just SSDs overtaking the basic capacity needs of modern OSs at an affordable (to some) price.
My machines (all laptops/netbooks, I do not like desktops because they eat lots of power and are thus anti-ecological) are now equipped with SSDs for the OS (Debian GNU/Linux) and for non-OS stuff, which is actually very little, I just plug some fast SD or CF memory cards or roomy USB flash drives. I do not use any hard disks anymore, except for a few old machines that I hardly use now or for my servers. Everything works great. I feel as if I am running supercomputers - it's so fast. Just to make sure my SSDs will live for a long time, I use ext2 instead of ext3/ext4, and I configured my /tmp to live in a tmpfs filesystem. Filesystem fixing takes just a few seconds with SSDs, so the speed advantage of journaling ext3/ext4 does not hold anymore, and after all I never liked journaling filesystems at all. I see no reason why anyone would want an SSD bigger than 32GB/64GB for an OS, except for booting multiple OSes. For those running games or other programs that need fast disk access, it is always possible to plug an external SSD over eSATA (or Firewire) or put multiple SSDs into your machines if the motherboard supports that.
Of course, SSD's are too expencive if you need a data storage. But they are much more better suited for laptops (and especially netbooks). I also can imagine desktops with mixed drives -- fast SSD for OS, large conventional HDD for user data.
Read the GP and PP carefully, then read your note again.
GP said: if you have Vista, it is a good reason to buy SSD.
PP said: yes, but why bother with Vista.
You said what you said...
Patents Drive Free Software as Hurricanes Drive Construction Industry
fricking slashdot tricked me :( I thought you answered me, not an outmodded note, sorry.
Patents Drive Free Software as Hurricanes Drive Construction Industry
http://www.pricewatch.com/hard_removable_drives/
32gb 76.00
64gb 136.00
transcend and ritek are the lowest prices
Both include an HDTV tuner and Blu-Ray drive, both are fairly muscular "desktop replacements" running 64 Bit Vista.
The only distinguishing feature of significance is the 26" TouchSmart screen.
We are going to be seeing many more systems like these and at much lower price points - and the HD media they are designed for will eat up a lot of storage very quickly.
The geek may be focused on the netbook right now - but it is worth paying attention to what is happening in other markets.
Tom's Hardware reports that hard disks can still be more power efficient than SSDs. The good news is that SSDs are more efficient under load, and their idle power consumption is improving also.
What a fool believes, he sees, no wise man has the power to reason away.
When SSDs get to the mid-range price they start to look good for archival storage. The lifetime of NAND flash SSD is primarily determined by the number of writes, so they should be great for this purpose.
Also, I imagine that Asus paid far less for the 4GB SSD on the Eeepc 701 than they would have paid for any harddisk. The claim that hdds are cheaper is presumably per GB rather than per device which is perfectly capable of standard tasks such as word processing.
I am not an expert, but my limited knowledge says that we can kiss secure erase (fill with zero or random data) goodbye on SSD disks.
It is becoming hard enough to be certain that you deleted/overwritten a file with copy-on-write (ZFS and such) but with wear leveling any secure erase attempt will probably still leave with copies of your data on disk.
Even a full wipe disk procedure will leave some remnants in remapped parts of flash storage.
I do hope that somebody is tackling this issue, but it seems to me that the solution will only be available on the disk firmware level.
They will reserve SSD's for only the most high end of PCs and laptops and then market them as 'extreme' or 'ultralight' and bump the price 2 or 3x times the bottom rung of corresponding devices. It's all about margin. And SSDs will NEVER be retail priced below regular drives until manufacturers decide to stop building regular drives.
Most budget laptops poke along just fine with 80gb and 160gb hard drives. The main thing is getting the cost down.
You mean IDE (PATA)?
I found only 12 models ranging from 8 to 64GB on Newegg. All of the made by only three manufactures; Transcend, Ritek, and Super Talent.
Try this link here
Life is not for the lazy.
2007 was it
Climate Progress - Hell and High Water
I would like to use a SSD as my OS drive for a few of it's benefits. Overall noise level and speed are the two big things. Given that the drive itself is near silent is kinda obvious when dealing with noise levels but also the heat level and power consumption are lower. As such it's less cooling to deal with which then in turn can mean with a air cooling system less fan noise.
At this point the prices are low enough such that it would not be a big deal to get one and play around with it. However it would be nice to see them a bit bigger before I took the plunge.
Really, I know what I'm doing...Ohhhh, look at the shiny buttons!
The price gouging will continue and we'll have idiots in these SSD manufacturing companies wondering why people don't have $1000 laying around their house to by a SSD drive.
I have around 100gigs of music; yes, I like to haul the whole damn lot with me when I take my laptop - thank you very much. No, I don't want to ponk it on an external hard disk either.
The day when I start seeing 250gb SSD's that perform faster than traditional hard disks for radon writes and cost around NZ$150 - then I'll consider moving. Until that day, SSD will remain that unjustified luxury which I'll never be able to afford.
I think one can say confidently that SSDs do not have the same near-term catastrophic failure issues that HDs have. A SSD will be about as reliable as, say, the motherboard in a computer. Certain parts within the SSD, such as electrolytic capacitors, have limited life spans, but no more limited then the electronics inside a hard drive. Many people in the server space talk about putting their boot partition on RAID to ensure that the machine is still able to boot with a failed hard drive. You don't need to do that if you use a SSD for your boot disk. Because the SSD is no less reliable then the motherboard it makes little sense to have additional redundancy in that context. Once you are booting from reliable media you have a lot more redundancy options for the rest of the media accessed by the machine. For example, there is no need to RAID the local disks within the local hardware, the redundancy can be networked instead.
However, the ability to recover from a flash that has been sitting on a shelf too long is a real issue compared to a HD. Both suffer thermal degradation over time but even if a HD's moving parts become unusable it is still possible to do a surface scan and recover the data after a long period of time has passed, even if it costs a few thousand dollars to do it. Once a flash cell leaks into the ether the data is virtually unrecoverable. There is nothing to scan. Theoretically one can shave the top off the chip and use a tunneling microscope to scan it (the Taiwanese did this to read out 'protected' EEROM from integrated cpu chips years ago), but the expense would be enormous, in the hundreds of thousands of dollars per unit or more, with no re-takes if it fails (the chip would be effectively destroyed). Flash-based media is NOT archival storage.
This is even more true for flash cells nearing the ends of their lives, after they've been rewritten a lot. The first write in a freshly minted flash memory will survive on the shelf far longer then the last successful write before a cell fails. The achilles heal of flash is the wear issue, and this limits its usefulness in server environments unless you explicitly replace the unit once a year as part of your regular maintenance. The risk is you put an often-used SSD on the shelf and a few years later the entire data set is corrupted beyond recovery.
On the flip side, your average consumer does not actually generate a lot of data. One terrabyte worth of writes on a 256G medium is only about 4 rewrites assuming perfect wear leveling, well within the 100,000 rewrites available. The AMOUNT of data is irrelevant. It's the amount of REWRITING that matters. We all know that the vast majority of the data sitting on those terrabyte drives is static. The problem is much reduced as the media capacity of the SSD increases. In a sense, the SSD problem is the same as the backup problem. Since you have to backup your machines anyway, your average rewrite bandwidth is limited by virtue of your backup bandwidth being limited. This would be true for most large data stores as well.
So it comes down to the price we pay per gigabyte. SSDs are clearly still way too expensive, particularly with HD capacities likely increasing past 10 Terrabytes in the next 5 years. SSDs simply cannot grow at the same rate as HDs, they are severely limited by fabrication issues that HD manufacturers do not have. The HD manufacturer can put an immense expense into the construction of the relatively tiny disk head if need-be without increasing the cost of the overall unit very much. The same cannot be said for the fabrication of flash memory chips.
SSDs have their foot in the door, though. The price really only needs to come down another 30% or so for the use cases to explode. This is still nowhere near the equivalent cost per gigabyte of a HD, but it doesn't have to be to gain mass acceptance. At some point in the next 10 years a new technology will pop up, perhaps it will be IBM's magnetic memory! Perhaps something else, that will solve flash memory's wear issues. When that occurs the mass acceptance will turn into an explosion of use cases.
-Matt
You want trend? Here you go. SSD is going up!
No sig for now.
I'd like to know from an environmental perspective which tech will be the better. HDDs seem to have parts that are recyclable - e.g metal platters. The circuit board on the bottom is questionable.
SSDs it seems are just plastic, AFAIK. This has already 'failed' us from an environmental perspective, since in most cases people just throw out CDs. There's only so many coffee coasters one can have!
Disclaimer: I don't manufacture either HDDs or SSDs. I don't know what they made with. And would also which process to manufacture is 'friendlier'.
Still, it's just ridiculous. "Will this finally blah blah", it's a terrible preface to an article, whether it turns out accurate or not.
"Most people, I think, don't even know what a rootkit is, so why should they care about it?"
If everyone's hard drives (and net connections) are getting huge, there's no disincentive to increasing the size of everything. If, on the other hand, a significant percentage of your potential customer base are running netbooks (just take a look at how many Eee PCs were sold this year), then there's a significant incentive to making your stuff small enough that you don't cut them out of your potential market. So I think there will be some trend towards caring about storage efficiency, for mass-market end-user-targeted stuff at least.
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
For desktops that might be acceptable, but shoving a 15,000-rpm drive in a laptop is going to kill the battery life compared to an SSD, not to mention increase the noise output and heat-dissipation issues.
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
Who seriously has more than 40G of operating system and applications?
Store your movies, music, etc on an external or network drive.
*sigh* back to work...
WITH wear leveling, any hard drive would outlast an SSD.
Ever heard about SMART ?
Most hard disk sold in the last 10 years *DO* detect and remap bad sectors.
Well at least with proper BIOS and/or OS support to turn on the feature upon starting the computer. If using them under Windows with a crappy motherbard, YMMV.
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
....But please, don't call me until I can justify plugging them into my SANs. That means, versus mechanical:
1) Far better price per GB.
2) Monster MTBFs.
3) Far less power dissipation and HVAC loading.
Until these criteria are met, I'm sorry but as far as I'm concerned they're little more than CEO toys.
Regards;
As someone that has used several brands of SSDs in our embedded equipment which must meet extremely high levels of shock and temperature requirements I have had quite a bit of experience with this "bleeding edge" line of hardware.
Currently I have not seen a single SSD (True SSD, not CF cards that some people CLAIM are SSDs in their equipment) that have been reliable in the long term at all. CF card based boot drives are MUCH more reliable.
The worst of the drives (though those with the highest specs and claims) will reinitilize themselves or lose partitions one out of every 30-50 power cycles. Better ones will do it once out of every 100-500 cycles. Data loss is rampent. Conventional notebook drives in the exact same scenarios go thousands of restarts with no problem. (All failures are the result of a power cycle)
It'll be at least another 3 to 5 years before this tech has matured enough to be reliable for anything important.
Contrary to popular belief, coding is not all free blow-jobs and beer. Those things cost MONEY!
The advantages of SSD outweigh the disadvantages, especially for laptops. You have no moving parts so you'll get longer battery times (though the monitor is still the real hog there) much faster read and write times. The costs will continue to freefall while the capacities continue to shoot upwards. You only need to store your programs on the drive and anything where different run times might matter. The price per gig is still the domain of platter media but the read and write speed, size, power consumption, noise, and simplicity is already in the hands of SSD.
This would be similar to the setup many people have currently with a few raided raptors for the programs and then a bunch of massive but slow secondary drives for media. It's another step in the speed hierarchy of slower speed and larger media.
If you look at the rate of data increase thumb drives have made in the last couple years and compare that to hard drives you'll see that the rate of increase is such that SSD is going to surpass platter in short order. I'd bet my 4 gig thumb drive on it! Which is only worth about 8 bucks now (still have one new in package), and shouldn't even be worth manufacturing in a year or so.
It is no longer uncommon to be uncommon.
SSD's should be included in systems as an AUGMENT to hard drives, but never as a replacement.
Most people who use their systems for media have long writes/reads as a routine task.
spinning platters are still better performance at this than SSD's.
While the hypesters are also playing with the numbers trying to make SSD's look as dependable as hard drives, i'm just not convinced.
SSD's should be integrated into systems for storage of program files and other data which complement their strengths, but they should not supplant the already cheaper storage solutions for applications in which they are weaker.
VLC FOR MAC IS DYING! IF YOU DEVELOP, PLEASE SAVE IT!!
Yes, SSDs are great. And they become faster & have more capacity by the week. But they are still way more expensive. And if history told us one thing, it's that the cheapest solution wins. Period.
For Desktops too. Not because I'm a enviro-nazi who buys into Chicken Lil' Gore's Global Warming scheme, but because you want your system to boot fast and applications to launch in no time flat. But go for Single Cell and not Multi Cell Flash architectures. The single cells are the ones that are able to hit the theoretical maximums of the bus interface and don't have the stuttering problems. I think they've worked through a lot of the problems with the read/write cycles of Flash EEPROMs that plagued the technology earlier in the century and with dropping Flash costs, computer manufacturers and not just game enthusiasts could really get serious about fast computers that booted and launched apps from SSDs, while using HDDs for massive storage.
Some manufacturers have talked about hybrid drives, but I think you'll more likely see hybrid computers which employ both drive technologies with better efficiency. And yes, they should see great success in laptops because of energy savings and reduction of moving parts. I think we'll see massive drives used for iPods as well once the prices come down. I'd like to see them in Video Cameras as well, but I hope that the manufacturers don't integrate the drives like they currently do with HDDs, but keep them removable like their smaller cousins, the removable flash "sticks".
Actually, the price per gig is going to stop dropping. Currently, there's a worldwide glut for flash memory - so much so that creditors of one of the largest manufacturing plants forced the owners into bankruptcy because they figured they had to cut their losses - there's no quick turnaround in view. Once all the chips that are being liquidated below cost work their way through the system, prices should stabilize.
Also, I'd hope that the flash used in an SSD is better than those el-cheapo thumb drives, or you're going to find yourself waiting a long time to do anything ...
Platters also continue to get bigger in laptops. This spring, the largest drive I could get was 320 gigs (my lappy has 2 drives, so that gives me "only" 640 gigs). Now I can buy 500 gig hds for the same price I paid 6 months ago for those 320 gig drives. The "SSD uses less electricity" myth has been debunked in lots of places, ditto "It's faster". I wouldn't be surprised to see 1TB in hard drives by this time next year.
Also, cache sizes are going up.
Noise? I did a du -sh /home yesterday, which really gives the hard drive a workout. Couldn't hear a thing. Newer drives are QUIET!
I don't see SSDs taking the place of platters in regular laptops before the middle of the next decade. They have a long way to go in terms of capacity.
I had high hopes for the I-Ram. I was planning on buying one many years ago. I'd *really* love it if someone would manufacture a reliable RAM-based disk.
Anyway, read on. Also, wtf is up with your crazy formatting?
ON LINUX though? Yes, maybe it is "finicky",
In computers, stability depends largely on 2 things in hardware:
A.) Drivers
The iram is an SATA disk that uses the PCI bus for power. Gigabyte provides no drivers for the iram. (Before you argue this point, check out what "drivers" they offer on their web site.) :D
When using PATA or SATA disks, the only driver that matters is the driver for the IDE or SATA controller. Imagine what a world of hurt we'd be in if each model of harddrive required a special driver. Thankfully, there's a single spec that you need to adhere to to have a functioning PATA or SATA drive.
If the majority of Linux SATA or PATA drivers were crap, I'd imagine that we'd be seeing more broken systems -and bug reports- out there than we already do.
(Maybe worse also, if the user & his anecdotal evidence, is an "idiot @ the wheel driving"
This guy is a kernel hacker. (Check the CREDITS file of a recent kernel tarball.) I doubt that it's a PEBKAC issue. Others have reported on his blog that using a certain type of memory makes the iram function correctly. You could ship the right RAM to him, and ask him to try again. ;)
As I said before, I'd *love* to have a reliable verification that this thing worked. If I had one, I'd buy one next month... as a Christmas present to me... for how awsome I am!
Also, I personally have a CENATEK "RocketDrive"... &, I use it as I outline + for 7-8 yrs. now going strong & it's fine...
Lovely. :) It's not the iram.
CENATEK ROCKETDRIVE = PC-133 SDRAM memory, PCI 2.2 ISA bus
I could be incorrect here... maybe. You typically have a card that works in a PCI bus *OR* an ISA bus... not both. Care to clarify your statement?
AND, besides: Windows, per this article (specifically Windows 2000) does a better job of using SSD's apparently than any other OS out there...
I don't imagine that you read Alterslash?
Anyway. The methods used by the folks in the article in question are questionable, at best. Check out this comment thread and this comment thread.
Pretty much every PC gamer.
More binary multiples of metric capacity.
Oh, say does that Star-Spangled Banner entwine / The myrtle of Venus with Bacchus's vine?
LOL, just personal style is all... what's with YOUR LACK OF IT? That knife, cuts BOTH ways...
----
Who's cutting here? I was unaware that I was talking with an emo kid. ;)
"I'd *really* love it if someone would manufacture a reliable RAM-based disk"
I have one, that I mentioned iniially, a CENATEK "RocketDrive"
Ah. I'm -shamefully- going to have to move the goalposts on this one... at 4X the cost per MB of DDR1 RAM, PC-133 RAM is too expensive for me. : (
I used SSD's OR software based Ramdisks/Ramdrives & showed HOW they can aid performance,
Good job, there... demonstrating how moving to a device with a higher throughput and lower average seek time increases performance for IO bound tasks. :/ Did they teach you that in your MIS courses, or during your Associates' Degree?
"he iram is an SATA disk that uses the PCI bus for power. Gigabyte provides no drivers for the iram. (Before you argue this point, check out what "drivers" they offer on their web site.)"
I know the technology... Then, apparently?
Your problem is that LINUX itself isn't using the hardware abstractions for HDD's on the SATA circuit properly apparently, rather than this being a driver issue...
Pardon? Please remind me, how does an OS interact with a chunk of hardware?
OR, that Linux drivers are not supplied for the IRAM by Gigabyte, & no kernel dev. has built a GOOD solid one yet... take your pick.
There *is* no driver for the iram. It's an SATA device.
Speaking of SATA devices... :)]
I spent a little while looking at the SATA driver for the controller in my desktop machine. There appear to be two device-specific quirks in it. One limits a particular Maxtor drive to UDMA5. The other limits the maximum number of transfered sectors for some Seagate drive. These quirk handlers do not seem to be in all of the libata SATA drivers that I've looked at tonight.
Is it possible that the iram needs special handling? Yes. Is it possible that Gigabyte hasn't gotten the word out to the Linux kernel devs? Yes. Is it likely? No.
It's more likely that the iram is *very* picky about the type of RAM that it's paired with. If you can get a working iram out to Mr. Jones -and have him create a detailed report on his success- then you'll have a rhetorical leg to stand on. [And I'll purchased a fantastic present for myself next month.
"This guy is a kernel hacker"
... & this means WHAT to me?
This means that he's a meticulous fellow who can *probably* figure out how to install and debug an SATA device.
"Lovely. :) It's not the iram."
Uhm... I never said it WAS!
Please try to keep up. ;)
I said "Heh. The i-RAM is a finicky chunk of trash."
You then point to the track record of a *totally* *different* *device*. Is old age shortening your attention span?
You have a point here, & it IS, good to question any analysis, by all means... HOWEVER, sometimes? I "question the questioners"!
Lovely. What has your analysis of the objections raised to the article in question revealed?
That in Windows, Gigabyte's IRAM works just FINE... & LINUX, per his own evidence? It apparently does NOT... nuff said...
Until you produce a repro recipe you haven't said anything. :)
Produce the details of your functioning configuration. iram revision, RAM make and model, RAM layout, SATA chipset, mobo model and revision, OS version and patch level, driver revisions for all of the above (when appropriate).
Until you come forth with that, you're just another AC blowing smoke.
my last reply set ALL of that straight, here:
You mean the part where I said: :)
"The iram is an SATA disk... Gigabyte provides no drivers for the iram."
Then you said:
"Your problem is that LINUX itself isn't using the hardware abstractions for HDD's on the SATA circuit properly apparently"
Then I said:
"Pardon? Please remind me, how does an OS interact with a chunk of hardware?"
Then you said:
"Drivers & a 'HAL' (hardware abstraction layer), elementary stuff."
And I had preemptively replied:
"There *is* no driver for the iram. It's an SATA device."
Even if there were a driver, it wouldn't fix broken hardware. No amount of software can fix destroyed HDD armatures. No amount of software can correct a memory controller that's wildy out of whack.
You mentioned the Windows HAL. I noticed that, but had to run off to work and only had time for a quick reply. :D]
Why, exactly are you bringing this up? IIRC, Linux kernel drivers don't use a HAL... at least, not like the diagram for Windows driver stack seems to indicate. They work -for better or worse- directly with the hardware. Does an in-kernel HAL make for better drivers? If so, how? [You claim to be a knowledgeable Windows kernel driver developer. Educate me.
All I had to do was backup my initial 2 statements:
Incorrect. All you had to do was address my initial statement:
"Heh. The i-RAM is a finicky chunk of trash."
You haven't produced a repro recipe for a known working configuration. You've gone on and on about your education, credentials, and published works while handwaving in the direction of the hardware in question. I don't care about *you*. I care about *the* *hardware*. :)
If you can get a known working configuration in the hands of a kernel developer who then confirms the configuration's state, I'll go out next month and buy an iram and appropriate hardware. I'll add what quirks -if any- are needed for stable operation of the iram to the SATA driver for my chipset. I'd *LOVE* to have an excuse to get my name into the CREDITS file of the kernel.
Including ... attempts to put words into my mouth I never stated as well... apk
When did I do this? Include citations.
That linked review does not mention any specifics about the memory that was installed on the iram. Stop selling the sizzle. Start telling me what's in the steak.
Are you this evasive and abusive in person? If so, and if your resumé comes my way I'll strongly advise to not hire.
Cheers!
Hello, APK.
*This* is why I use a single slashdot account. If I have something to say to another user, I *always* attach my name to it. I stand behind everything that I say on this site and others, karma be damned.
You put the Coward in Anonymous Coward.
*chuckles*
http://episteme.arstechnica.com/eve/forums/a/tpc/f/51009562/m/3680937305
http://episteme.arstechnica.com/eve/forums/a/tpc/f/12009443/m/757093113/p/2
http://episteme.arstechnica.com/6/ubb.x?q=Y&a=tpc&s=50009562&f=12009443&m=1810993821
(Especially:
http://episteme.arstechnica.com/eve/forums/a/tpc/f/12009443/m/1810993821?r=2310969821#2310969821
)
I had hoped that you would have been informative at some point in our conversation. It's a pity that you were not.
Please return to guarding your bridge.
I've sifted through a substantial chunk of your conversations. I hope that this online persona is something that you've ginned up for kicks. If it's not, you've wasted a horribly large chunk of your life.
You've been at this for more than ten years. If you are as you present yourself, you haven't learned a single thing in all that time. That's at least a tenth of your life pissed away. If this APK persona *really* is you, you're being justifiably pitied and shunned.
Answer this simple set of questions...
You have failed to address my initial challenge to you.
Take the last comment. I can get nothing good from you.