Slashdot Mirror

One. The 180GXP's outer-zone transfer rates weigh in at a respectable 56.2 MB/sec

Two. The drive more properly act like twins in WB99's transfer rate tests. Here both drives post an outer-zone score of 56.5 MB/sec

Does this mean you will give me two cookies? I like chocolate chip.

Storage Review is, IMO, the best site for hard drive reviews.

Seagate Barracuda ATA V, Serial ATA Version

And don't forget to contribute to their Drive Reliability Database!

Storage Review is, IMO, the best site for hard drive reviews.

Seagate Barracuda ATA V, Serial ATA Version

And don't forget to contribute to their Drive Reliability Database!

Storage Review is, IMO, the best site for hard drive reviews.

Seagate Barracuda ATA V, Serial ATA Version

And don't forget to contribute to their Drive Reliability Database!

theres another review at storage review

Here's another (and IMO better) review of the SATA Barracuda V. And they don't use that joke of a drive benchmark Sandra.

http://www.storagereview.com/articles/200301/20030 110ST3120023AS_1.html

StorageReview has a good review that compares it to it's parallel ATA brother.

The review on HEXUS.net left a great deal to be desired. HD Tach and SISandra are interesting numbers, but hardly representative of how the drive will react in the "real world." StorageReview has posted a much more comprehensive set of benchmarks on this drive at StorageReview Although StorageReview does not yet have the formal review posted, some interesting results do emerge. The SATA Barracuda V drive beats the PATA Barracuda V drive in most benchmarks. For instance, the SR High-End DriveMark 2002 goes from 285 for the PATA to 355 for the SATA. However, since the SATA drive has an 8MB cache vs a 2MB cache on the PATA drive, it's not clear how much the improved results are due to the interface versus the cache.

Unfortunately, the numbers are not yet available for the File Server DriveMark test, which might give an indication of how much the drive benefits from support for tagged command queueing like SCSI drives have.

Note that the performance results for the SCSI drives versus the Barracuda V are not a valid indication of the raw capability of the SATA interface. Virtually all of the SCSI drives are 10k and 15k RPM drives, which one would expect to be substantially faster than a 7K RPM drive such as the Barracuda.

Finally, the explanation on HEXUS.net as to why the drive slows down at the end of the HD Tach test is simply wrong. The review says that "[The slowdown] is due to the sectors at the end of the disk being physically further from the drives starting point." The reality is that the drive slows down at the end of the test because the inner rings are smaller and therefore less data passes under the head for each revolution of the disk.

No, it's a Barracuda V, not IV.

StorageReview, uh, reviewed the PATA model a couple of months ago; they found it to be slightly quieter than the Barracuda IV, with largely similar performance.

You seem to have forgotten StorageReview.com.

I can't see ATA-100 IDE disks realistically competing with Ultra-320 disks. Instead of trying to pinch pennies and hope that it would satisfy the requirements, we decided to go with what works.

I have seen those as well, but real field experience has told me otherwise. There's just not enough quality built into IDE disks to realistically call them server-class material. I have a few old compaq pentium class machines pushing 7 years old that have been running non-stop for all 7 years and not dropped a disk. I've yet to see a IDE disk pull that off.

I think you were looking at seek times, my laptop drive gets better than 16 MB/sec. The WD 200JB gets almost 60 MB/sec transfer rate.

Here's a review page for the WD 200 GB drive and others.

I think you were looking at seek times, my laptop drive gets better than 16 MB/sec. The WD 200JB gets almost 60 MB/sec transfer rate.

Here's a review page for the WD 200 GB drive and others.

OK so... Serial ATA debuts at 133MB/s AFAIK, while the current ATA/6 Spec is also 133MB/s. Firewire runs at 400Mb/s, or rather 50MB/s if we are to convert. So yes, is a tad slower. HOWEVER, ATA/66 is generally considered fast enough for modern drives, since the average drive bursts slower than that. In fact, in a comparison of the 4 fastest IDE drives available at storagereview.com the western digital 200MB 7200RPM 8MB cache drive managed to win out with a sustained transfer rate of 16.4MB/s. I'm not even going to mention that IDE has a maximum cable length (32 inches i believe) that precludes its use externally, and firewire does not. So you were saying?

They got excellent performance reviews on Storage Review but no reviewer can travel forward in time a few years to see how the drives hold up.

The result is that we have IBM drives in all our production database servers, web servers, and app servers. And I picked the hardware. Who said no-one ever got fired for buying IBM? Guess it's true, as I didn't lose my job over it.

AnandTech had an interesting article here on the drives, and why they went bad (poor microcode that handles the interval between tracks as the drives heat up).

I *am* a Storagereview regular (I post there as Mercutio, the second non-admin user whose account was re-created after the crash).

The issue was *not* a disk crash, but the fact that SR's colocation facility wanted to charge $x more to run proper backups, and SR couldn't afford it. During a regular upgrade to either MySQL or phpBB (don't remember which), their DB got dumped on accident. Eugene, SR's admin, posted very early after the site came back up that he has a small stack of DDS and DAT drives sitting around his home that he would've loved to install, if only their ISP would've let them.

Incidently, Storage Review's self-reporting reliability database is back up and running now, if you'd like to participate, feel free, but I'm convinced that self-reported statistics are of fairly little value.

Also, a lot of SR's regulars, including myself, chose to create our own community, distinct from SR, in case Storage Review either shuts down or loses its database again. We can be found at Storage Forum. SR's general membership is not aware of our site - we don't advertise it there out of courtesy to SR's admins, but if you spent time on SR's forums and wonder where Tannin, Clocker, P5_133XL, JamesW, time and some of the other mainstays went, well, now you know.

I think a collection of real stats which were somehow reliably collected would be really useful in terms of all this commodity hardware

Storage Review had such a database at once upon a time. It was widely hailed as the most comprehensive database of the kind, and pretty accurate (given that "reliable collection" is an oxymoron when it comes to the net).

Then their hard drive crashed and they lost everything.

Yes, it's horribly ironic. It also struck me as really freaking idiotic that a website dedicated to storage wouldn't back up their own data. I'm not an SR regular, so I didn't follow the story that closely at the time.

As it happens, SR is now restarting the reliability database. It'll take time to get accurate data, of course, but it's better than nothing. Here's hoping they succeed.

And that this time, they have backups.

"Ever since our launch over four years ago we've been bombarded with e-mail asking us to address the reliability of hard drives. Well folks, this is it... the culmination of months of discussion, research, and development. We're pleased to unveil our 2nd-generation SR Drive Reliability Database!"

I have to agree with alsta here and vehemently disagree with the moderation "flamebait."

Lets got over this supposed flamebait.
* SCSI has much better seek times than IDE disks
This is irrefutable. This is in industry rule. I refer people to the fastest hard drive I could think off the top of my head here: http://www.storage.ibm.com/hdd/desk/ds180gxp.htm Deskstar 180GXP - Average seek time - 8.5 ms
and to here: http://www.seagate.com/cda/products/discsales/mark eting/detail/0,1081,549,00.html 15K.3 Model Number: ST373453LC Seek time: 3.6 ms avg

Now, I don't know about you people but an increase in seek performance that is easily 2.4 times better that the best IDE for something that occurs that many times a second, well, I'm convinced that the drive is considerably faster. Think of any "worst case" scenarios, and this extra speed is likely never to go un-wasted on a computer.

I am also in accord with alsta's skepticism that SATA will be anything but a consumer grade technology. I am an ardent supporter of Firewire and SCSI, and it clear the SCSI standard has much to offer because implementations of SCSI over IP are planned to deprecate FC in favor of iSCSI over 10GE. To me this SATA is a day late and performance short. I think it is nice we can now clean up the crap connectors, but I will not be deluded into believing that SATA has a prayer in terms of beating SCSI.

I also have seen many reviews on IDE RAID and must concur that it is nearly impossible to IDE up to single drive SCSI performance without doing some hardcore RAID-ing. I cannot provide links to support this statement, but peruse through a site like Storage Review and you can see clearly where and why and how SCSI drives cremate their IDE counterparts.

I have IDE and would buy SATA for mass cheap storage at home, but it was a sad day when PC vendors stopped offerering SCSI upgrades from the factory on their cheesier machines and Apple stopped using them by default. This essentially was the advent of the "Geo" or "Kia" of the computer world. I hate hackneyed car analogies, but in this case, as I have seen in acerbic reviews of the said cars, "Why buy this cars where there are better used ones around?", directly applies. I can think of many "used" scsi drives and how badly they destroy consumer grade stuff with ease. This is both from L&F and measure performance metrics.

IDE does not support tagged commands, and it is still unclear if SATA's implementation will be as robust as SCSI. This alsta's statement is again correct with regards to terrible simultaneous access. Try running a busy Unix box with 100s of people copying files and doing this or that, compiling crap, etc. The disk needs to be serious about handling jumpy situations. Seek time and command tagging comes in handy here.

Unfortunately larger buffers can only mask problems. There are many situations where consistency is not guaranteed, and where the cache can easily be blown. I like buffers to be there to make an already fast situations move along more regularly, like a capacitor helps regulate power. I don't like an already bad situations being masked by case specific buffering optimizations.

I will ,as alsta indicates he will, continue to use SCSI as my most preferred storage bus. I cannot think of reasons not to, if I have an dumping ground for "crap" in my IDE large capacity hard drives. Also suspect is the standard being ratified over a year ago and nothing materializing yet. Also, I think the SMART works better in SCSI, I think sector sparing is essential and IDE and apparently SATA wont do that, and I like 5 year drive warranties not ONE like most IDE drives moved to now, and I liked support, and I like knowing that the company I bought the device from made an okay profit so I can get amenities like advanced replacement. It's a preferred choice, and if you can afford it, so it.

Just because you may not be able to afford it or don't think storage is not the way you should spend your hard earned money, don't knock SCSI. And certainly don't come to Slashdot and suppress other people's views on the subject.

• cable size
  
• interoperability issues caused by multiple drives per cable
  
• bandwidth per drive
  
• cost of the controllers
  
• cost of the cables
  
• cost of the drives
  
• Low reliability caused by multiple devices physically attached to the same cable that can bring parts of the bus or the whole bus down
  

The Barracuda V is actually somewhat quieter than the Barracuda IV they used.

Use the extra leeway to add a few fans; don't forget, if everything's running close to their design limits now, it'll probably get hairy if you have a hot summer.

Plus it's really a good idea to keep components like HD's fairly cool. Let them fry and you risk reducing the service life of the drive and increasing the chances of data loss. You at least want reliable storage, right?

Also, you should be careful with that huge-ass Zalman cooler. They're very heavy, and will happily tear off the socket if you happen to move the machine anywhere. The full Cu version is about 200g heavier than AMD's maximum recommended weight.

The Barracuda V is actually somewhat quieter than the Barracuda IV they used.

Use the extra leeway to add a few fans; don't forget, if everything's running close to their design limits now, it'll probably get hairy if you have a hot summer.

Plus it's really a good idea to keep components like HD's fairly cool. Let them fry and you risk reducing the service life of the drive and increasing the chances of data loss. You at least want reliable storage, right?

Also, you should be careful with that huge-ass Zalman cooler. They're very heavy, and will happily tear off the socket if you happen to move the machine anywhere. The full Cu version is about 200g heavier than AMD's maximum recommended weight.

The Barracuda V is actually somewhat quieter than the Barracuda IV they used.

Use the extra leeway to add a few fans; don't forget, if everything's running close to their design limits now, it'll probably get hairy if you have a hot summer.

Plus it's really a good idea to keep components like HD's fairly cool. Let them fry and you risk reducing the service life of the drive and increasing the chances of data loss. You at least want reliable storage, right?

Also, you should be careful with that huge-ass Zalman cooler. They're very heavy, and will happily tear off the socket if you happen to move the machine anywhere. The full Cu version is about 200g heavier than AMD's maximum recommended weight.

And they include heat and noise reports in their excellent reviews. Highly recommended for any HDD purchase.

Storagereview.com has had noise and heat statistics for years.

Actually, it is a better reference than this quoted article because you can tell SR.com to compare all the drives you are interested in purchasing and get good* benchmarks, heat/noise, and can sort by specific benchmark.
Go to the website, click "database" (near the top) and choose your criteria. In ten seconds you can find out the noise/heat/speed of every drive SR has ever reviewed, with a rather nice labelled bar graph for clarity.
You can also visit the forums and get advice from some of the most knowledgeable people in the IT industry, and get information that is difficult to come by anywhere else--for example, that Samsung makes the most reliable (albeit close to the slowest) IDE hard drive. SR was also the first to discover that Seagate planned to reduce their warranty and that there are terrible SCSI performance bugs in Windows XP, among others.
A very good resource, and it's been slashdotted without the server being brought to its knees. (It runs Linux/Apache/PHP)

Storage Review has been doing noise and measurement tests in thier reviews for several months now.

Hey Sivar.

Mickey, who likes to deny that he's a WD employee, over at Storagereview.com says the top-of-the-line model will probably, actually be three 66.7GB platters while the lesser models the in lineup will remain 60GB/platter.

IIRC, that's the same thing WD did for their 100GB drive.

If you're the Sivar who frequents SR, you'll probably know me btter as Mercutio.

This is really old news... the press release is dated June 25th. I found out about this last month from storagereview.com.

Also, Maxtor has not said anything about a 200GB drive yet, despite the title of the headline.

look at this one too, though. the numbers you were comparing are for two pretty different models--different capacities, platters, etc.

and here's a quote pulled from the above link:
"To differentiate their offerings from the competition, one of WD's largest OEMs recently requested an ATA drive with an 8-megabyte buffer. The manufacturer responded by retooling its current flagship, the WD1000BB, with an 8-meg cache."

which suggests that the cache bump was the only difference.

I'm looking at a page on storagereview.com regarding the BB and JB models.
Summary:
Xfer rates: outer( BB: 49.3 JB:49.0) inner( BB:29.2 JB:29.2)
They don't mention the type of data they are writing, but it appears to be sequential reads/writes, probably in sector sizes. In any case the numbers are essentially identical. Looking at the 'desktop performance' page, there are wider, but still rather insignificant differences in performance. Certainly small enough that other factors could be causing some or all of the difference between drives.

Like I mentioned in my previous post, I'm not an expert here. In fact, you seem to have quite a bit of knowledge based on your other posts in this thread.

So I'm going to punt (ie. appeal to authority): storagereview.com's hard drive reference.

While it may be true that a faster parallel equivalent can be created for any serial system, it may not be economical to do so. If it's cheaper to double the frequency of your transmission than to double the number of connections then it makes sense to stay with serial (or in this case, revert to it). According to the reference I linked above, it looks like this will be the case for the next while.

The current best fast machine with lots of expandability and a not-outrageous price seems to the be the Shuttle SS40. It's a pretty sexy and silent little box, with firewire to boot. pricewatch suggests this barebones box will run you about $US 350. According to Storage Review, the Seagate Cuda IV is the quietest drive on the market, but the Western Digital JB series are only a bit louder, and their 8mb buffer makes them hella fast. Throw in the fastest Duron or Athlon XP you can get your hands on and some CAS2 DDR, and off you go.

Or you can just go to Smalldog and get the fastest Powerbook G4 you can afford, which serves as a pretty darn good desktop replacement, especially the new one with a 17" LCD attached via the DVI connector (-:.

Maxtor does rock. Put simply, after that down period about six years ago, they got their sh*t together and started making a quality product, and they haven't given up. The price is right, the performance excellent (good to see Maxtor picked up Quantum's tendency to make fast-seeking IDE units.

The other really good product right now is Western Digital. They're IDE only now, unfortunately, but it take a lot of balls to stand up and recall drives from consumers, to fix a manufacturing flaw. They did it, and they earned my respect.

Samsung drives also have a really strong reputation.

In comparison we have IBM, whose last 15k SCSI unit doesn't even best Maxtor's latest 10k Atlas, and whose 7200rpm ATA models are limited by either the "Deathstar" rep or the limitations of a specificied Powered On Hours of Service specification that no one else seems to be using.

We also have Seagate, which makes some fantastic and unique products (the last 50-pin 7200rpm SCSI drive) in SCSI, and has IDE products that, frankly, suck dick. U-series drives have lousy reliability and performance that's matched by two-year old drives that are 1000rpm SLOWER. Even worse, WD's recent 5400rpm products come to wit 2% of Seagate's amazingly quite 7200rpm Barracuda IV in most benchmarks.

Most of my knowledge comes from either Storagereview.com or from Storageforum.net

They have an excellent website: good selection, well laid out, good navingation tools (View by name, View By Price, include tax etc.) and good ordering system. They have good prices and very reasonable (my last order €8 on ~1½ kg) shipping charges which importantly is with DHL Express (2 days), so you can track your shipment on the DHL website (which is brilliant - I've been stuck in limbo several times not knowing when or if a shipment will arrive when buying from other retailers like dabs.com). And no I don't work for Komplett, just a happy customer.

As many others have said it will probably not be cheaper when you build your first machine but you will get higher quality parts. What this means is that when it comes time to upgrade (in 9-12 months) you only need to upgrade part of your system (say, only motherboard, processor, memory and graphics card). Also having bought quality parts any you upgrade can still continue to have a useful life as a server or SO's machine.

If you are going to build your own machine you do need to do your homework. Overview sites like http://www.arstechnica.com/, http://www.sharkyextreme.com are useful but don't always get it right. I find component/area focused wesites invaluable. Here are some good examples: http://www.motherboards.org/ , http://www.3dsoundsurge.com/ , http://storagereview.com/

Also a good idea is to lurk for a while in some of the product newsgroups / online forums.

One thing that you should not forget is that building your own PC is a lot of fun! It's interesting, satisfying and educational. So in the long run I think that it is both cheaper and more rewarding.

1. First get an idea of how much you can afford to spend.
2. Think a bit about what sort of tasks you want the computer to do. Do you want high end video for gaming? Do you want to build a PVR? Do you want to build a small server to host web/ftp/email services over a broadband connection?
3. Go online and do some research to see what's out there to fulfill the role you envision for the machine. arstechnica, tom's hardware, anandtech, storage review, and other sites usually have good information on recent and upcoming technologies. I do a lot of looking to see what's out there and what's around the corner, then go back and revise my budget accordingly.
4. Decide what you need to buy. I don't generally go for the biggest, fastest, best, because it's generally twice as expensive (or more) as it will be in just a few months. I don't buy the cheapest stuff either, as it's usually of inferior quality, obsolete, or will give inferior performance compared to spending a small amount more on something better. I look at the price/performance curve, and generally buy in the "knee-bend" of the curve. The only exception is if there's something dirt cheap available for a non-critical component that doesn't make much of a difference (like a floppy drive, NIC, or keyboard) or an absolutely critical high-priority component that the system *needs* in order to perform its role adequately (like a GeForce card for a gaming station) or a SCSI controller for a file server.
5. Shop around. You can try pricewatch.com to get an idea what stuff is going for these days. But I find that shipping makes finding a real bargain somewhat difficult. That's especially true if you buy from more than one vendor. I try to go through one vendor, for simplicity's sake, and right now my choice is Newegg.com. They have very good service and their prices are often near the top of the pricewatch search results anyway. You can try local stores, too. Stay away from chains like CompUSA and Best Buy, and support small local businesses run by knowledgable, competant people. Their prices will generally be about twice the lowest you'll find on pricewatch, but you may find the convenience of not paying for shipping, not having to wait for delivery, and having someone to go to for questions and advice useful. If you're more experienced, you probably don't need that, but few people know everything about everything, and everyone you talk to can potentially teach you something.
6. Put it together. There's plenty of guides out there on the web that will go into detailed instructions on how to put a PC together if you need help. PC Mechanic is a good example, and there are many others out there. Read the instructions a few times until you know what you're doing, then do it.

A VIA C3 can't be compared to Athlons. I own a VIA C3 933 (its in a Shuttle SV24, the first of Shuttle's mini cube computers) and I recently did a LAME encoding test on the VIA C3 933 (on the fv24), a Celeron 300A@450 (on an Abit BH6) and a P3 1Ghz (on a Tyan Trinity 400). Encoding speeds were 1.1x, 1.9x, and 4.0x respectively. If the C3 is that much slower than a 4 year old Celeron, can not compare it to a 1800 Athlon XP.

Using a heat pipe and a slow rpm 80mm fan this new board can keep the 1800 Athlon XP cool, and still keep noise low. The Seagate Barracuda IV drives have been measured at 41.3db (Idle Noise at Storage Review), and they are silent. I have 4 of them, I know.

that's the reason why that WD ATA133 drive with 8MB cache scores so great, it can burst up to 8MB at up to 133MB/sec

Not quite. The only ATA/133 drives in existance are made by Maxtor. Those 8MB cache Western Digital drives are built with ATA/100 interfaces. Not that it matters to any measurable degree, the Maxtors don't actually benchmark any better when run off of an ATA/133 controller vs an ATA/100.

See Storage Review for more information.

StorageReview's "High-End Drive Mark 2002" uses "Content Creation Winstone 2001" to gather performance information from programs like Premiere, Photoshop, and Soundforge. Details here.

If you view the ranking for the High-End benchmark, which uses the same testbed, you'll see that the Western Digital WD1200JB (an ATA drive) out-performs 10 current families of SCSI drives (ranging for 7200 to 10000 rpm), leaving only 3 drives above it (one 10000, and two 15000).

So, are you using one of those three drives? If not, it appears your pricey "must need" SCSI solution is currently bested by a lowly ATA drive.

StorageReview's "High-End Drive Mark 2002" uses "Content Creation Winstone 2001" to gather performance information from programs like Premiere, Photoshop, and Soundforge. Details here.

If you view the ranking for the High-End benchmark, which uses the same testbed, you'll see that the Western Digital WD1200JB (an ATA drive) out-performs 10 current families of SCSI drives (ranging for 7200 to 10000 rpm), leaving only 3 drives above it (one 10000, and two 15000).

So, are you using one of those three drives? If not, it appears your pricey "must need" SCSI solution is currently bested by a lowly ATA drive.

Reality check. PC100 SDRAM CPU to memory is about 200MB/s

No, you are in serious need of a reality check. My 512MB of PC100 SDRAM benchmarks as being around 800MB/s with memtest.

Here are a couple of web sites that agree with this also...

http://www.a1-electronics.co.uk/Memory/SDRAM.sht ml
http://www.pcmech.com/show/memory/154/
http:/ /www.savingxoom.com/ddrmemory1.html

Should I provide more?

Drives don't get better than perhaps 45MB/s for outer diameter of platter and more like 25MB/s for inner diameter,

Western Digital Caviar WD1200JB: 48.8MB/s outer, 29.2MB/s inner.

The Seagate Cheetah X15-36LP does 60.5MB/s outer and 45MB/s inner, for a comparison of a 15k SCSI drive, with a 5.9mS access time.

but this is for a strictly linear transfer from platter to RAM and does not accomodate the +7ms AVERAGE seek time.

Is it not obvious that I am speaking purely about maximum sustained transfer rates? You can't get the maximum values if we're not talking about sequential transfers. But thanks for the pointer AC.

If the option comes out to get SCSI performance from an IDE drive I'm going to take it."

Review of the Western Digital 1200JB (The 8MB Cache Special Edition.)

With desktop performance and capacity vastly superior to the competition as well as a surprisingly low operating temperature, the Caviar WD1200JB reaffirms Western Digital's preeminence in the IDE desktop performance segment. In fact, for desktop usage, the JB bests all 10k RPM drives save only Maxtor's Atlas 10k III.

Once again we're obligated to point out an interesting fact. The hardware enthusiast market, comprising a significant portion of StorageReview.com's readership, has always pledged it would respond enthusiastically to the world's first 10,000 RPM drive. These folks want the performance of a 10k RPM SCSI drive without the SCSI premium. The WD1200JB, like the WD1000BB-SE, delivers the desktop performance of a good 10k RPM drive according to tests constructed from real-world, high-level applications. If you want SCSI's performance without its price or capacity limits, the WD1200JB is the drive for you.

for all of you nutty people argueing

cpu utilitzation and general myths

proof

There really arent many good generalizations you can make. Like most things the issue is more complex. Sure there is a stigma attached to both scsi and ide. Sure there is an infrastructure in place on both sides that further creates the rift. Desktops have mass market ide controllers and drives with great enconomies of scale, and scsi with a huge plethora of external storage crap, exotic high end hardware, built in hot swap physical interface (SCA), and endless other crap

If you had none of that to contend with (pretend it all doesnt exist), and you were a drive manufacturer and/or a controller manufacturer judging purly on technical applicability, which curent and working (no serial ata or serial scsi in which case these 490+ arguments back and forth on ./ become even more pathetic) incarnation of both standards would you use for high end? Which would you use for mass market? Ends up the same as it is now? no shit.

Hopefully the serial versions of these "standards" will finally put an end to the mac vs pc type bs. Both will have all the most modern tricks, and both will be implemented (parts created) in a way that suits their respective markets.

Lastly, two things:

-the cpu utilization
if you have real need, 20% is way better than 40% (some people do use apps that beat the shit out of hard drives all day). The argument that it doesnt matter if the app isnt threaded or async with reads/writes is somewhat bullshit. Its true that blocking on the drive for a thread is blocking on the drive. But if you have a nice new OS from the last 5-6 years, most of the writing and reading go though the system file cache, and much of the time you are async. Writing can be completely async if you want it to be, and reading ahead by both the drive and the os really do happen. But if you block you block. NT kernel OS takes way better avantage of doing stuff while an app is blocked and has very nice syncronization and interrupt handling. Linux is getting way better too.

-drive differences
You know how cpus and memory get binned by manufacturers, i.e. separated by how well the chips run, usually by speed? Think of IDE and SCSI not as interfaces, but as bins. Even if you make spacial platters just for IDE and special ones for SCSI, just think of how many more platters will be good enough for IDE for a good price point if you do 5400 or 7200 rpms. Like wise what quality chips and standards would you apply. What you make into a war is just economics and binning of designs and part tolarances accoring to market segment demands.

for all of you nutty people argueing

cpu utilitzation and general myths

proof

There really arent many good generalizations you can make. Like most things the issue is more complex. Sure there is a stigma attached to both scsi and ide. Sure there is an infrastructure in place on both sides that further creates the rift. Desktops have mass market ide controllers and drives with great enconomies of scale, and scsi with a huge plethora of external storage crap, exotic high end hardware, built in hot swap physical interface (SCA), and endless other crap

If you had none of that to contend with (pretend it all doesnt exist), and you were a drive manufacturer and/or a controller manufacturer judging purly on technical applicability, which curent and working (no serial ata or serial scsi in which case these 490+ arguments back and forth on ./ become even more pathetic) incarnation of both standards would you use for high end? Which would you use for mass market? Ends up the same as it is now? no shit.

Hopefully the serial versions of these "standards" will finally put an end to the mac vs pc type bs. Both will have all the most modern tricks, and both will be implemented (parts created) in a way that suits their respective markets.

Lastly, two things:

-the cpu utilization
if you have real need, 20% is way better than 40% (some people do use apps that beat the shit out of hard drives all day). The argument that it doesnt matter if the app isnt threaded or async with reads/writes is somewhat bullshit. Its true that blocking on the drive for a thread is blocking on the drive. But if you have a nice new OS from the last 5-6 years, most of the writing and reading go though the system file cache, and much of the time you are async. Writing can be completely async if you want it to be, and reading ahead by both the drive and the os really do happen. But if you block you block. NT kernel OS takes way better avantage of doing stuff while an app is blocked and has very nice syncronization and interrupt handling. Linux is getting way better too.

-drive differences
You know how cpus and memory get binned by manufacturers, i.e. separated by how well the chips run, usually by speed? Think of IDE and SCSI not as interfaces, but as bins. Even if you make spacial platters just for IDE and special ones for SCSI, just think of how many more platters will be good enough for IDE for a good price point if you do 5400 or 7200 rpms. Like wise what quality chips and standards would you apply. What you make into a war is just economics and binning of designs and part tolarances accoring to market segment demands.

But wait, that's not all... included is a great review of RAID.

But wait, that's not all... included is a great review of RAID.

If you check out Storage reviews File Server Benchmark database, you'll see that the fastest ATA drive scores well below half what a 15,000 rpm Fujitsu drive does.

Back when the IBM Deskstar thing was going on, Storage Review put together a reliability survey where people posted what drive they had (I don't think the drives could be first manufactured before 1998 to be included), how long they had used it, and whether or not it had failed, was still running, and so on.

The survey is currently down for maintenance, but whenever it comes back up, just go to this page, sign up, and browse the results. Of course, some of them probably haven't been updated in a while, so you may not get the most reliable info, but it's still better than info that was published at the same time the drive came out.

Back when the IBM Deskstar thing was going on, Storage Review put together a reliability survey where people posted what drive they had (I don't think the drives could be first manufactured before 1998 to be included), how long they had used it, and whether or not it had failed, was still running, and so on.

The survey is currently down for maintenance, but whenever it comes back up, just go to this page, sign up, and browse the results. Of course, some of them probably haven't been updated in a while, so you may not get the most reliable info, but it's still better than info that was published at the same time the drive came out.

Go see StorageReview.com's main page... No need to spread FUD.

One of the current limitations of the ATA standard is that maximum drive size is 137.4GB. While we're not quite there yet, it seems like this could become a problem at least by mid-2003.
I'm surprised that the opportunity was missed to address this with the introduction of Serial ATA.
For the curious, the limit comes about since only 28bits are used for the sector number in the ATA protocol. (2^28 * 512 bytes = 137.4Gb).
This is straying dangerously off topic now, but its quite amusing to look at the history of arbitrary hard disk size limits: (from The Storage Review)
PC/XT Parameter (10.4 MiB / 10.9 MB) Barrier
FAT12 Partition Size (16 MiB / 16.7 MB) Barrier
DOS 3 (32 MiB / 33.6 MB) Barrier
The 1,024 Cylinder (504 MiB / 528 MB) Barrier
The 4,096 Cylinder (1.97 GiB / 2.11 GB) Barrier
The FAT16 Partition Size (2.00 GiB / 2.15 GB) Barrier
The 6,322 Cylinder (3.04 GiB / 3.26 GB) Barrier
The Phoenix BIOS 4.03 / 4.04 Bug (3.05 GiB / 3.28 GB) Barrier
The 8,192 Cylinder (3.94 GiB / 4.22 GB) Barrier
The 240 Head Int 13 Interface (7.38 GiB / 7.93 GB) Barrier
The Int 13 Interface (7.88 GiB / 8.46 GB) Barrier
The Windows 95 Limit (29.8 GiB / 32.0 GB) Barrier
The 65,536 Cylinder (31.5 GiB / 33.8 GB) Barrier
The ATA Interface Limit (128 GiB / 137 GB) Barrier
And only four of them are due to Microsoft...