Slashdot Mirror

Simple math and obvious reasoning clearly shows...

Allow me to interrupt. Does this really shound authoritative to you? My comparison was between multiple platters and a %25 increase in density. If it was triple desnsity, I wouldn't have made the argument. I suppose that's what you meant by "obvious"?

And you might bother to realize that those three pairs of heads cannot move independantly on a modern hard drive

OK, it's now been established that neither of us know much about hard drive engineering. Anywhere else this would make us humble ;-) The point is that I wasn't claiming independent movement. I was expecting lock-step movement, so you could consider the tracks read simultaneously as part of a larger logical track. Unfortunately, I suspect Agripa knew what he was talking about, and that head alignment can only be achieved on one head at a time.

Finally, would you like an example of a dual platter drive which is much quieter than this supposed gift to modern science? The Samsung Spinpoint is highly recommended for HTPCs. Funny how in the /. review the Barracuda is the quietest. You fell for it didn't you. I guess there is more to it than what's obvious.

My advice to you? Be like a hard drive. Read more. Write less.

A USB enclosure for a 2.5" HD is cheap, small, and convenient, but which of these drives would be best for this?

Obviously speed doesn't matter.

Probably the most important factor is power consumption since these enclosures run off the USB power which is barely enough for these drives. The WD drive is strange in that it gets very good numbers for operating power dissapation and noise, but then is 2nd worst for startup power dissapation. I guess that puts it out of the running.

Here's the relevant page:
http://storagereview.com/articles/200511/notebook_ 7.html

It really makes me question the use of a laptop drive (and a slow one at that) in the cheapest Macintosh, but oh well.

at least these guys know what they talk about

and their Recommended sections give you all the damn facts you need in the easiest possible way to read them

Storage Review has the Hitachi 7K500 as the best desktop performer out there right now.

Their review of the WD2500KS compares it to the Hitachi 7K400 and the WD clearly loses out.

The 7K500 is compared to the 7K400 in its review and the next-gen performance boost is quite clear.

Storage Review has the Hitachi 7K500 as the best desktop performer out there right now.

Their review of the WD2500KS compares it to the Hitachi 7K400 and the WD clearly loses out.

The 7K500 is compared to the 7K400 in its review and the next-gen performance boost is quite clear.

Storage Review has the Hitachi 7K500 as the best desktop performer out there right now.

Their review of the WD2500KS compares it to the Hitachi 7K400 and the WD clearly loses out.

The 7K500 is compared to the 7K400 in its review and the next-gen performance boost is quite clear.

Ok. All slashvertisement comments aside, I get as excited about 'teh new hotness' in drives as much as the next person. But this is SO poorly submitted. 300MB/sec? PLEASE. You MIGHT get 70% of that speed doing a transfer from that 16mb buffer to the controller, but that is just misleading. Without even reading, I'm guessing they're talking about 3Gb/sec SATA-II. Woo. So that is wrong. "Interface Speed" is what you wanted to say there. Not "Transfer Rate".

What about "WD Characterizes this as the highest performance section of the desktop market." Wrong again. Helooo??? Raptor??

I mean. Talk about something cool, at least. New TCQ optimizations? Read-before-write? 24/7 100% duty cycle?

SR is a decent place to check out reviews and benchmarks. Do your homework! Astroturf like this only spreads confusion and disinformation.

I got a 15k RPM SCSI drive from hypermicro. It is a seagate, 73gb. It was only about $250 with an adaptec controller (which wasn't a whole lot more than a WD74 gb raptor at the time). At the beginning of the disk, it has over a 90Mbyte xfer rate on a 160mbyte/sec interface, which totally crushes all this other crap. My drive is (was?) the leading drive on non-raid configurations on hdtach's website, even against the 400gb SATA WD behemoth. 2x36gb raptors are about the same speed as one decent 15k RPM scsi disk.

I haven't really looked, but I would guess the drive in the post is what.. neighborhood of 60mbyte/sec? 70? Meh. Meh I say. We didn't even talk about I/Os/sec. between 7200 rpm, 10k RPM and 15k RPM.

The idea of an article like this on slashdot is not bad. It is just that this article is misleading and/or wrong and isn't really news at all. And so on and so forth.

Not only is it an advert, it's an incorrect one. If you want to be using an "enterprise level" drive, it's the 400GB WD4000KD you should get - same series (Caviar SE16), but the hardware is physically identical to the newest 400GB 'Raid Edition 2' from WD. The 400GB Caviar SE16 model is based on the 10k Raptor family of drives designed for maximum speed, whereas the 250GB SE16 is descended from the standard-issue Caviar family. The only place where the 250GB model beats the 400GB is the support of a 300MB/s SATA2 bus rather than the 150MB/s of SATA1, but since no drives can actually deliver anything like 150MB/s transfer, it's redundant anyway.

Note that I don't intend to advocate any one of these drives - I couldn't care less what you buy, I just want to lay out the facts properly.

1. 17MB/sec. http://www.bigbruin.com/reviews05/review.php?item= oczrally&file=1
2. 60 MB/sec. http://www.usb-2-0.com/what-is-usb-2-0.html#2.%20H ow%20fast%20is%20USB%202.0
3. 60 MB/sec. http://www.storagereview.com/articles/200511/HDS72 5050KLA360_2.html
4. 11 MB/sec. http://www.tomshardware.com/storage/20050520/usb_f lash_drives-09.html
5. 35 MB/sec. http://www.anandtech.com/printarticle.aspx?i=2515

It's 1.5 times as fast as your average flash, and only half as slow as your typical USB hard drive.

With 500GB drives, it would take 7340.032 drives to attain 3.5PB... with NO redundancy.

Height (mm) 25.4
Width (mm) 101.6
Depth (mm) 146

1. First.
2. Second.
3. Third.
4. Fourth.
5. Fifth.

Here ya go (just the first link I found).

Obviously, MTBF doesn't mean what you think it does.

Because that functionality is supposed to be handled by the RAID controller, and if the drive has it enabled you can end up losing performance as the two Command Queue Controllers fight each other.

From the excellent storagereview.com article: "TCQ must be supported by both the controller and the hard drive itself."

That's with TCQ being NCQ but for ATA-4.

Are there current SATA raid controlers even able to use Command Queuing? If not how long until it is possible. It may be a feature that couldn't be used at this stage but later revisions might.

According to storagereview.com the "upcoming Promise FastTrak TX4200" of a year ago uses it; as the article is over a year old I'd surmise there a plenty more.

I agree that there should be more low-noise/low-power drives, but to compare some of the existing drives, check out Storagereivew. Somewhat dated but good info.

Quite right. The storage review faq provides a nice summary of the issue.

Here is the response to the same question asked elsewhere. I had always wondered my self. I personally would love to have a 1Tb disk now (despite the argument that drives double every year anyway).
direct link to reason

OK I did my homework

http://www.storagereview.com/ is now trying to put reliability data in their reviews. Not sure how well it works, but it at least seems better than nothing. They have not reviewed this drive yet, but you can check out how some recent drives from all the major manufacturers are doing.

June 25, 2004

...

From the plethora of data presented above, we can draw several conclusions:

1. SATA TCQ and SATA RAID have the potential to deliver benefits to the server market just as great as those of SCSI TCQ and SCSI RAID.

...

http://www.storagereview.com/articles/200406/20040 625TCQ_1.html
Seems like the same thing according to this.

There is also a good one at storage review:
http://www.storagereview.com/guide2000/ref/hdd/per f/raid/index.html
The original posted article is quite lame - they say raid 10 can only survive 1 drive failure, this is wrong it can survive 2 if they are not in the same mirror set.

...I like this guide better.

Yes, it's a little old. But, I found it to be very comprehensive, especially for its day (remember, RAID 0 and RAID 1 were only beginning to show its face in the consumer market when the guide was written). It's actually a mirror of another page, but since I stumbled upon this one first, I don't remember where the original is or what it might have been called, or, for that matter, which pages/paragraphs were in the original and which ones were not.

RAID 5 may be the most powerful RAID configuration for the typical user, with three (or five) disks required.

Raid 5 can be configured with a minimum of three drives.

Interested in RAID? Google, or check out: Storage Review's excellent information.

I hate Seagate. The are an untrustworthy company with an inferior product. Hitachi or WD is good. Maxtor is okay, but they sometimes have quality control issues. (luckily their drive usually fail with in a few weeks if they do have a quality problem). Storage Review is always a good place to go to get less biased information. Especially on specific drive models (which is what really matters when you are buying drives).

While this is a nice device, it's still bottlenecked by the PCI bus. Notice the speed on the specifications page - a true SATA drive can achieve this, and Ultra320 SCSI can shame it as long as you get a 64-bit PCI or PCI-X controller (like http://www1.shopping.com/xPF-IBM_ULTRA320_SCSI_CTR LR_2, although I suggest Adaptec instead of IBM). See http://www.scsita.org/aboutscsi/ultra320/faq.html for info on Ultra320. You get a lot more storage for the buck here. It's not solid-state, but a 73GB drive (15k RPM) -- see http://www.storagereview.com/articles/200209/20020 901ST373453LW_1.html -- can be had for under a grand.

Now... about large memory systems... what is the purpose of such a large device? Databases? Image manipulation? Analysis? If the PHB just told you to go out and buy something with more buzzwords, I'm sorry, but that's probably not going to solve whatever problem you have. What would the benefit be of having a single machine, as opposed to an expandable cluster of machines? Besides the cooling and electrical, anyway. If you have a legitimate need for such a large amount of memory in a SINGLE computer, you should definitely consider a Sun workstation or (more appropriately) a brand new Sun server.

Maybe the Hitachi folks should stop singing and concentrate on shipping. On January 10 Hitachi announced the 500GB 7K500 drive would ship "first quarter 2005". It is now mid April, where is it?

Then download Feature Tool from Hitachi to turn it off http://www.hitachigst.com/hdd/support/download.htm

Take a look at the Reliability Survey on http://storagereview.com/

The old Seagate Barracuda IV and V models were even quieter, but the 7200.7 is a bit noisier than the Samsungs. Check out StorageReview's database for a detailed comparison.

Many things you say are true, but with respects to speed you are simply wrong. You say in another comment that you don't have any hard data - well, I'm looking at hard data, namely the current issue of the German computing mag c't. The average sustained transfer rate (read) of the 5400 rpm 2.5in drives are within 20 to 30 MB/s, while the 7200 rpm 3.5in drives routinely transfer at 45 to 55 MB/s, with 10krpm and 15krpm drives scoring even higher, obviously. And in a recent test on StorageReview a 10krpm (!) 2.5in HD targeting servers doesn't fare very well, either.

Money would be better spent on RAID, rather than dual core or dual processor.

Actually RAID doesn't noticeably speed most things up in a desktop environment in my experience.

http://faq.storagereview.com/tiki-index.php?page=S ingleDriveVsRaid0 has this to say:
Dont assume RAID 0 offers increased performance for all or even most applications... and dont assume that transfer rates reflect application-level performance.

Perhaps the money is better spent on more RAM? :)

one site where people actually take the time to characterise drive noise from sensical distances, silentpcreview.com, has ignored storagereview's noise measurements for some time now, as they are out of touch with reality. the difference between a 7200.7 and a samsung sp1614n is night and day, if you actually own one of each as i do.

luckily, mike chin has access to some of the best sound measuring equipment and an office with an ambient background noise of 15 dBA or so. he's done some great reviews of fans in this environment, but hasn't turned to hard drives yet. but here's a silentpcreview article comparing the samsung directly to the 7200.7, i think you'll see how much more effort they put into acoustics than storagereview.

Not according to storagereview.com. While the Samsung is quieter, I don't think 0.3 dB qualifies as "quite a bit louder". And that is the only drive quieter than the Seagate.

Of the Maxtor lines with a statistically significant number of entries in the storage review reliability database the only one with an above average number of failures is the DiamondMax Plus 9, which I unfortunatly recently had to "upgrade" to as it was the only high capacity drive I had available (bought it on sale a year ago for $80 for a 160GB version, now I know why it was so cheap). With this in mind I back up all the data I care about to a couple of older DiamondMax D740X drives which have a significantly better than average track record. IBM/Hitachi and Western Digital seem to be much more hit or miss, and Seagate is by FAR the champion of reliability, guess I will probably put up the extra couple bucks for the Seagate drive next time, and also explains why almost all server drives I've seen in the last couple years were Seagate.

Of the Maxtor lines with a statistically significant number of entries in the storage review reliability database the only one with an above average number of failures is the DiamondMax Plus 9, which I unfortunatly recently had to "upgrade" to as it was the only high capacity drive I had available (bought it on sale a year ago for $80 for a 160GB version, now I know why it was so cheap). With this in mind I back up all the data I care about to a couple of older DiamondMax D740X drives which have a significantly better than average track record. IBM/Hitachi and Western Digital seem to be much more hit or miss, and Seagate is by FAR the champion of reliability, guess I will probably put up the extra couple bucks for the Seagate drive next time, and also explains why almost all server drives I've seen in the last couple years were Seagate.

The Barracuda 7200.7's go up to 200G; I have an 80G, 2 160G's and 3 200G's and they've been very good. The 7200.8's go up to 400G (3 * 133G platters; as dense as it gets) and they're *expected* to continue the good spell Seagate seem to be having.

Storage Review are good for comparing drives. They don't have 7200.8 reviews yet though, and their reliability database isn't going to be of much use for them for a while.

Hard drives have been stuck in the 200-300g range for almost 5 years. The innovation in this sector has hit a brick wall damn near.

Hard drives have been stuck in the 200-300g range for almost 5 years. The innovation in this sector has hit a brick wall damn near.

I disagree. Here is a comparison I made from storage review Storage review comparison I tried to pick drives of the same family with different capacities. If you look, you will see that there isn't a strong correlation between capacity in a family and througput.

The read-write heads, being fixed, no longer require a large amount of support hardware. All of the heads will likely be integrated into a single component, and the heads are absolutely miniscule. They really are tiny things. Here is a document on storageworks detailing the technologies of the heads in use on hard drives today. Thin film is a common process for making hard drive r/w heads...

There are also benefits to having a rectangular storage device, especially in the area of space savings (prototypes are bound to be large) and if you're not rotating the media you don't have to take measures to ensure that it either will not expand under spin, or will expand only by predictable amounts. This would not be a problem in a rectangular device.

The key advantage of SCSI drives over SATA drives is the number of simultaneous I/Os they can process, not transfer rates or access times. This advantage holds even among drives of equal speed and density. According to StorageReview.com, the fastest 10k RPM SCSI drive (Maxtor Atlas 10k) can handle 275 I/Os per second, while the fastest 10k RPM SATA drive (Western Digital Raptor WD740GD) can only do 226 I/Os per second. The fastest available SCSI drive ( the 15k RPM Fujitsu MAS3735) can process a whopping 366 I/Os per second! You won't notice the difference for local disk, but that's a huge difference when multiple processes are reading/writing to the disk simultaneously, as in a typical SAN/NAS shared disk environment: a SATA drive will hang on some processes, while a SCSI drive won't.

The key advantage of SCSI drives over SATA drives is the number of simultaneous I/Os they can process, not transfer rates or access times. This advantage holds even among drives of equal speed and density. According to StorageReview.com, the fastest 10k RPM SCSI drive (Maxtor Atlas 10k) can handle 275 I/Os per second, while the fastest 10k RPM SATA drive (Western Digital Raptor WD740GD) can only do 226 I/Os per second. The fastest available SCSI drive ( the 15k RPM Fujitsu MAS3735) can process a whopping 366 I/Os per second! You won't notice the difference for local disk, but that's a huge difference when multiple processes are reading/writing to the disk simultaneously, as in a typical SAN/NAS shared disk environment: a SATA drive will hang on some processes, while a SCSI drive won't.

I can't be certain for sure, but I know a *big* limitation of older IDE/ATA drives was that the controller could only talk to one device at a time (per channel maybe?) My guess is SATA would not have that limitation since it's a serial interface (no bus), but I know for sure that with SCSI there is no such limitation.

IIRC, SATA is also including some of the advanced SCSI abilities - TCQ/NCQ (read more here), but still falls shy of the complete list (including Packetization, QAS, & Negotiation and Domain Validation [reference]). Not entirely sure if those increase performance in any measureable amount, but I'm sure it doesnt hurt.

Ever since I had my new 2gb drive die (yes, that long ago) I wanted nothing to do with IDE anymore and gradually phased it out of my system entirely to all SCSI. Never been disappointed. Sure, all my friends joked for being anal about it but I was more than happy (except for the prices). For most applications there was not that big of a performance increase but if you partition your system intelligently across several different physical drives you can really see a difference.

The platter diameter in fast rotating disks have been smaller and smaller (thus explaining the not so great capacity compared to ATA drive that use full 3"5 platers, not rotating fast).

The common platter size went from 3"5 to 3" to 2"6 to 1"8, it was only a matter of time that they decided to package it in a smaller enclosure, the 1U market explains a lot... See that very old review (Y2K) or that Seagate whitepaper (pdf) about why smaller is faster...

Tom's Hardware [tomshardware.com] has nothing to worry about from IBM.

IBM's GXP Deathstar hard drives [slashdot.org], as/. regulars are well [slashdot.org] aware of [slashdot.org], are exactly that. Death comes to your data on these drives eventually [techreport.com]. Too bad for a large number of customers [techreport.com], it came sooner rather than later.

When the news first broke [techreport.com] on these drives, some [techreport.com] tech sites [storagereview.com] came out [viahardware.com] with the news, and others [tomshardware.com] kept fairly silent. Silence isn't a crime. But continuing to use Deathstars in review gear should be. Why? Because some readers, myself included, used reviews and testing gear examples from Tom's Hardware to build our first computers. Take advice and recommendations from the experts, and you get a better computer, right?

As the current/. story points out, why bite the hand that feeds you advance facts on hardware under ndas, and direct contact with company engineers?

Consumer Reports [consumerreports.org] buys everything [consumerreports.org] they test. With the money that Tom's Hardware has made from advertising on its site (from reader views), they should be doing the same.

Don't take my word for it. Check the dates of when the Deathstar stories first appeared. Then check the hardware reviews on Tom's Hardware. Not just hard drive reviews. Check reviews of other hardware related or dependent upon hard drive speed to get some benchmarks or results. Then see what hard drives are used in the benchmarks, and in the review gear.

While some of their readers went down in flames, others were announcing that the there was a problem, and they continued on as if nothing was wrong. They may have acknowledged the problem in a small story or two iirc (maybe not even that), but they continued using the hard drives in their review gear, without a footnote or warning about them.

Why? emx

Well I'm sorry your drives suck. My (admittedly fast for its day) three-year-old drive "manages to maintain at least 50 MB/sec halfway through before eventually decaying to an inner-zone rate of 34.9 MB/sec" according to StorageReview.

Many of the current 7200 RPM models manage a 60-down-to-35 MB/sec gradient. Recent 10,000 RPM drives are proportinally faster. People that have the cash to buy fast DVD writers are more likely to be in posession of fast hard drives to go with, and there is no reason to limit the DVD writing technology when it is apparent many people can get a benefit.

Even the best HDD's hit only 60MB/s on the outside of the platters. That's a 15K RPM medium (by todays standards) density HDD. The best IDE high density HDD is the Maxtor Maxline 300GB SATA drive with an outside transfer of only 38MB/s this is a 7200RPM 100GB/platter drive. Assuming linear growth in transfer in relation to density even 200GB/platter won't hit 100MB/s @ 7200 RPM. All numbers are from storage review's performance database.

Storagereview.com has a drive reliability survey (free reg. required).

storage review says about 64MB/s on the outside of the platter for the best performing 15K RPM drive (which is a 74GB drive not a 140GB one). So, to swamp an U320 bus with sustained transfers you will need at least 6 drives, not the 3 that some people keep spouting around here. So if you need 6 drives to saturate the bus, why have a few high capacity drives when more drives gives you lower latency and gets you to max sustained transfer.