Advances in New Western Digital Drives

An anonymous reader writes "The Western Digital Caviar SE16 WD2500KS 250 GB hard drive has 300 MB/sec transfer rate the drive has a monster 16 MB cache, both of which should make it one of the best performing 7200 RPM drives on the market. WD categorizes this drive in the "Highest Performance" section of its desktop market, so its safe to assume that is has solid performance without the expense of an enterprise level drive. With products like this available, advances are being made in the storage industry that are not being rivalled by those in other areas of computing, especially considering the price level of this drive."

Comments

This is not new or special

[Anonymous Coward]

WD released this drive at least 3 months ago, and other drives with 16mb caches have been out even longer.

This is just another useless anonymously submitted article by Sal Cangeloso that may in fact be a slashvertisement. Notice the price listing on the first page, unless of course you have your ads blocked.

Re:This is not new or special

[MoonBuggy]

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.

Re:This is not new or special

[ergo98]

Wow.

Clearly it's a slashvertisement, as all of the linked articles are

• Terribly, terribly, terribly written
  
• Incredibly abusive of readers, spreading the limited, technically vacuous horrific prose over a dozen pages
  

If the Slashdot crew accepted those submissions without payment then they should commit hari kari now, because their use on this planet is done. If they did receive a kick-back - which I think is unquestionable - then I think this pretty effectively puts them on notice.

Good catch.

Remarkable that Slashdot is at such a vulnerable time, when there is a tide of credible competitors emerging, and they pull stunts like this.

Re:This is not new or special

[timeOday]

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.

According to the article, the 250GB bursts hit 171 MB/s, so actually it would be hindered by SATA1. Burst speed isn't my #1 consideration anyways, but it's something.

More importantly, could two (or more) SATA1 drives on a SATA2 bus exceed 150 MB/s in total? I would think not, in which case SATA2 is a big advantage if you want multiple drives on a bus. (I'm sure somebody will correct me if I'm wrong.)

To me the most interesting thing in the article was how close commodity SATA drives have come to the Raptor. The SATA drive has a slightly faster sustained speed, and the access time is only 4% higher. Are there some other SCSI drives with higher performance now?

Re:This is not new or special

[Eugene]

and you notice most of the slashvertisement are repeated offenders, you have to wonder if there's some sort of deals strike between /. and those people.

Re:This is not new or special

[spatenbrau]

According to the article, the 250GB bursts hit 171 MB/s, so actually it would be hindered by SATA1.

Seeing how the overall data-rate off of the heads is only in the 60MByte/sec to 90MByte/sec range, all this talk of 300MByte channels is bordering on dishonesty with numbers. The burst rate sounds like it is simply the speed at which the on-board cache can be read at. That isn't going to a number that influences much other than artificial benchmarks.

This article is just another article from an ever growing number of "fan-boy" review sites that read like ad-copy. A real review would test the disk throughput with something similar to:

dd if=/dev/wd0c of=/dev/null bs=1m

and then note the true MBytes/sec that the disk achieved. This is the best-case number that essentially allows the disk to stream with very little track-to-track stepping. Good disks will be able to do 60MBytes/sec on the outer tracks, but will usually slow to 2/3rd's that speed on inner tracks.

Re:This is not new or special

[InvalidError]

HDDs have been able to burst 150+MB/s out of their on-board caches... but the actual heads-to/from-platter peak transfer rates are much less than 1Gbps (~100MB/s) even for the fastest drives. HDDs able to max out an SATA-1.5G link all alone are still many years away.

3Gbps SATA is useful for storage subsystems, like SATA-attached RAID controllers - no need to waste a PCI(-E/X) slot to get decent performance anymore and it also leaves more PCI(-X) bandwidth available to other devices. Another purpose is SATA multi-port switches where one SATA-3G port may have multiple SATA-1.5G devices attached to it. I think some people are also considering SATA for clustering networks.

Re:This is not new or special

[rew]

could two (or more) SATA1 drives on a SATA2 bus exceed 150 MB/s in total? I would think not, in which case SATA2 is a big advantage if you want multiple drives on a bus.

Well...... I'd vote against two drives on one bus. SATA is point to point. Max one drive per connection.

So the article, and the WDC website claim 300MB per second transfer rate. That's THEORETICAL buffer-to-host. Apparently someone measured that at 170 Mbyte per second.

Platter to buffer is an impressive 748 Mbit per second. That's an impressive 93.5 Mbyte per second!!!!! Read on and "sustained max" is 65 Mbyte per second. Duh. That's pretty normal for a 2005 drive. Nothing out of the ordinary.

Now about the advantage of SATA2 (300MB/s) versus SATA1 (150MB/s).

You get to use the extra bandwidth if you let the disk buffer (16 MB) fill with data from the platter (65Mb/sec) -> about 250 ms. And then suddenly you decide that you need all that data in the computer's main memory.

If this happens just once, you win some 200ms. That's hardly noticable. It would matter if it happens lots of times in a row. But it is a very very funny traffic pattern where your disk is able to cache 250 ms worth of data into its buffer while the computer doesn't "see it coming", and has to take full advantage of the much smarter drive. Right! Nah.

The buffer should be large enough that if you're streaming say 200Mbyte per second off 4 drives in striping RAID, the drive should "stay ahead", and while you're handling the other three drives, the buffer shouldn't overflow. So the RAID block size should not exceed about 10 mbyte. Well, that's outrageous. The buffer is QUITE large enough.

At 7200 RPM, or 120 rotations per second, and 65 Mbyte per second. we can calculate the data density to be about 0.5 Mbyte per track. So with a buffer of more than two tracks (one megabyte), you quickly approach the theoretical throughput.

Really, there is nothing special about this drive.

Re:This is not new or special

[InvalidError]

I thought Intel, AMD, ATI, nVidia and many others being sued by Microlinc over packet-based serial links for computer interconnects (a story from what I call the "dormant patent" department - wait for your stealth invention to become common practice then come out of hibernation to sue everybody for whatever they are worth) would be far more newsworthy... but that topic got rejected when I submitted it a few days ago and we get this instead.

Re:This is not new or special

[Shanep]

According to the article, the 250GB bursts hit 171 MB/s, so actually it would be hindered by SATA1. Burst speed isn't my #1 consideration anyways, but it's something.

Drive quoted burst speed comes from or to on drive cache anyway. That cache is good to help the drive sustain it's highest read transfer rates through read-ahead (when the OS comes back for the next block, it has already been read from disk) and also an OS can send small writes to the drive faster. But in practice this mostly just helps a disk to meet it's highest sustained transfer rates. The burst speed sounds good and 16MB cache sounds good, but in these modern times, when we use OS' which use free memory as buffer/caches, we have a LOT of memory and that memory is REALLY FAST, on-drive caches are mostly being used as buffers. As far a caching goes, they don't really get used all that much, since re-reading a block will almost always come from system RAM before it comes from drive cache RAM. Sure it is true that the read-ahead caching on the drive is caching, but in practice it is mostly used as a buffer.

Are there some other SCSI drives with higher performance now?

From a practical point of view or from a meaningless burst speed point of view due to large on-drive caches and fast busses?

I have a Fujitsu SCSI320 drive which sustains about 94MB/s at the beginning of the disk, which slowly tapers off to about 64MB/s at the end of the disk. That is faster than the raptor and this SCSI drive is also faster than the raptor in other aspects like read service times, I/O rates, etc.

There have been Fujitsu, Maxtor, Seagate and Hitachi SCSI drives faster than the raptor for a long time. The Maxtor Atlas 15K II is really fast.

In fact, as far as sustained reads and writes go, access times and sustained I/O, has SCSI EVER lost the top spot?

Re:This is not new or special

[Not The Real Me]

SCSI has always held the top spot.

This IDE has a buffer to disk speed of 93.5 megs/sec. Interestingly enough, the article fails to mention what the CPU load is.

For all important items, I use a SCSI, usually Ultra160 since U320 is still quite expensive. IDE is what I use for secondary storage since IDEs do chew up CPU cycles.

Re:This is not new or special

[timeOday]

The burst speed sounds good and 16MB cache sounds good, but in these modern times, when we use OS' which use free memory as buffer/caches, we have a LOT of memory and that memory is REALLY FAST, on-drive caches are mostly being used as buffers.

I've questioned the usefulness of hdd cache compared to OS main memory cache before on slashdot and gotten flamed. Unfortunately I've still never seen any benchmark that convinced me of whether large onboard cache really helps, or just helps results on benchmarks which intentionally avoid OS disk caching. If anybody has some hard info, post a link.

In fact, as far as sustained reads and writes go, access times and sustained I/O, has SCSI EVER lost the top spot?

Sure, SCSI drives always had the quickest seek (access) times. The highest RPM drives were offered only with SCSI interfaces. That's what set them apart as "server" drives. I don't think there have been any 15K SATA or PATA drives, have there?

Re:This is not new or special

[Anonymous Coward]

I'm from a japanese company. We are using 700gig maxtor and seagate hard disks.

Re:This is not new or special

[Shanep]

I've questioned the usefulness of hdd cache compared to OS main memory cache before on slashdot and gotten flamed. Unfortunately I've still never seen any benchmark that convinced me of whether large onboard cache really helps, or just helps results on benchmarks which intentionally avoid OS disk caching. If anybody has some hard info, post a link.

I don't have a link at the moment with any hard info. But I did recently test re-reading a 1GB file in FreeBSD 6.0 Release on my AMD XP2800+ with 2GB DDR ram...

came out to about 588 MB/s.

(that's 2^20 MB/s and not the bogus 10^6 MB/s.)

I might be able to dig up a link which proves that larger on-drive caches can actually hurt performance, since I did see a benchmark at Storagereview which showed this in two almost exactly the same WD drives which only differed in cache size (same model drives, except one was a "Special Edition" with larger cache only)....

Re:This is not new or special

[Anonymous Coward]

Remarkable that Slashdot is at such a vulnerable time, when there is a tide of credible competitors emerging, and they pull stunts like this.

You must be new around here. Their [Slashdot's editors] credibility went out the window back in 2003. It's been all downhill for at least 2 years now.

Re:This is not new or special

[cytg.net]

uhm .. where does the raptor fit in this equation ? still no.1 dog ?

Nice ad

[Anonymous Coward]

I wonder how do paying subscribers feel about seeing ads before everyone else!

Re:Nice ad

[Anonymous Coward]

I'm not a suscriber, but I can tell you that it makes me feel like keeping my money!

Re:Nice ad

[Phroggy]

We're not especially thrilled about it.

YAPR

[legLess]

Yet Another Press Release. Nice to see that Taco's tight editorial control hasn't been impaired by too much turkey. The guys at XYZ Computing are giving each other high-fives right now.

Re:YAPR

[hcob$]

Heh, the tight editorial control is probably a small side item to the tight fiancee' in his bedroom. Just a thought!

Thank you

[agrippa_cash]

Thank you Slashdot, for bringing to my attention this exciting new service or product!

Advances that aren't being rivaled?

[Anonymous Coward]

Is the poster serious? Hard drive performance is one of the slowest areas of advancement in PCs there is. Granted that there's legitimate reasons for that, but to say that because its got a bigger cache we're seeing advances not seen anywhere else is laughable.

Compare a video card from today to one two years ago, and do the same thing with hard drives. The amount of "advancement" in the video cards far outpaces the drives, except for the really big drives that can store weeks worth of pr0n at once.

Re:Advances that aren't being rivaled?

[Rosco P. Coltrane]

Compare a video card from today to one two years ago, and do the same thing with hard drives.

I'm trying, but really the VGA plug won't fit the IDE connector. I'm so confused...

Re:Advances that aren't being rivaled?

[Seumas]

The poster copied and pasted those comments directly from the press release.

Re:Advances that aren't being rivaled?

[MtViewGuy]

Actually, hard drives have gotten faster thanks to the following:

1. Common usage of 7200 rpm drives. With 7200 rpm speeds, data is written and read faster off the drive.

2. 8 to 16 MB hard drive memory cache. With the memory cache that big many hard drive access operations are quite a bit faster.

3. Faster interfaces. The arrival of ATA-100/133 IDE and Serial ATA interfaces have substantially increased data transfer rates in and out of the drive.

I expect within the next few years we'll see the following:

1. Hard drive spindle speeds on IDE/Serial ATA drives will exceed 10,000 rpm commonly but with the same noise level and power usage as today's 7200 rpm drives.

2. Hard disk memory cache will reach 32 to 64 MB.

3. Most drives will switch to the Serial ATA-II interface with data transfer rate performance double that of current Serial ATA drives; further down the road, we could see a third-generation Serial ATA interface that sport double the data transfer rate of Serial ATA-II drives.

By 2010, we could finally see the breakthrough that will lead to non-volatile high-speed solid state storage that will rival hard drives in storage capacity but with data transfer rates far faster than any hard drive--think of it as essentially the equivalent of running a RAM drive but with true non-volatile storage. Unlike today's flash memory, these new solid-state storage devices can be written to trillions of times.

Re:Advances that aren't being rivaled?

[shibashaba]

Reminds me of my days at RadioShack. Dad brought his parent in and asked for an adapter to go from the serial port on their external modem to their monitor. I told them it couldn't be done, but they insisted that we have all these adapters there must be one. My clueless boss who couldn't even hook up his own vcr(he offered me money to do it for him) tried ever adapter to see if there was one that would do it.

God only knows what they thought they were trying to do.

Re:Advances that aren't being rivaled?

[TubeSteak]

Try plugging it into the SATA port

Re:Advances that aren't being rivaled?

[Tough Love]

You missed the main driver of hard disk transfer speed: density increase.

Re:Advances that aren't being rivaled?

[cowboy76Spain]

It is just that you are not trying hard enough...

Re:Advances that aren't being rivaled?

[Grishnakh]

I don't see it this way. When I look back over all my computers from 1991 to now, hard drive performance and capacity seems to be the most obvious thing that has increased. Back then, 40MB drives were common, and it took a long time to read all that data. Now, I can read that much data off my hard drives in less than a second, and 400GB drives are becoming common--a 10,000x increase in capacity. Back in the old days, I really had to worry a lot about what I had stored on my HD, because the space was quite limited, even with the smaller software of the day. Now, I don't even have to think much about it unless I'm storing lots of movies.

What other factors in computers have increased so much in that time?

Network speeds? Nope. Back then, I had a 2400bps modem, and 9600bps was fairly common. Now, the most you can have is 56000bps (theoretical), only a 23x increase. Pathetic. Good thing we have broadband now, but that's an entirely different thing. For LAN networks, we had 10Mbps ethernet back then; I'm not sure if 100Mbps was out by that time or not. Now, 100Mbps is common for most places (home networks, etc.), and GbE is getting common, though it's probably used a lot more in datacenters. That's a 100x increase.

CPU? Well, we now have 3.8GHz P4 processors (which perform about as well as much slower Athlons...), and while they're certainly much faster than my old 20MHz 286 in 1991, I really don't see much difference in regular desktop usage between my 3.6GHz P4 and my old 1GHz Duron from 3-4 years ago, or my 300MHz Celeron before that, unless I'm running transcode or something (i.e., not often). Word processing, web browsing, etc. all looks about the same to me, although I can open more browser windows now with 1GB of RAM which was uncommon 5 years ago. Furthermore, CPU performance has now hit a brick wall, and multi-core is the only way past it, which isn't helpful for single-threaded apps.

Local non-HD storage? Back in 1991, we had 1.44MB floppies, and now 4.7GB DVD+/-R discs are common, a 3,264x increase. I'd call this probably the second most noticeable and usable improvement in computers besides HDs, and interestingly enough, these are also mostly mechanical in nature, not silicon-based.

Video cards? Back in 1991 or so, I had a video card that could display 1024x768. These days, the highest resolution most people run is 1280x1024, not much of an improvement, and the highest is usually 1600x1200. Whoopee. Monitors have gotten bigger for most people, but they had huge monitors back in 1990 too, except they were really expensive. Of course, now video cards have entire processors on them specialized for 3D graphics, but what good is this? If you're a normal computer user, it's pretty much useless (no, teenagers who spend all their time playing video games are not "normal computer users"). GPU technology is great for console systems, but this discussion is about PCs, not video games.

Therefore, I'd say that hard drive performance is definitely the most obvious, most important, and most usable area of advancement for PCs over the last 15 years.

Re:Advances that aren't being rivaled?

[Anonymous Coward]

Video cards advancements are not one bit more interesting / better than hard drive ones IMHO.

Both have had similar increases in their respective main purpose - the 3D accelerated video card is faster at rendering 3D stuff, and the hard drives store more stuff.

Both are getting more memory (video memory for video cards, more cache for hard drives)

Both are getting newer/faster ports (PCI-Express for video cards and SATA for hard drives)

Both are getting other minor advancements in other places that don't really matter that much...

in comparison, I'm FAR more excited by hard drive advances than video card advances. Storing more stuff on hard drives is REALLY a good and useful thing (something I've never had enough of - and possiblt never will). Whereas with video cards - as a non gamer - I can't care less how fast the useless case heater goes. They can make super-duper-PCI-Mega-Express SLI-Extreme cards clocked at 3THz (and cost 4500$ each) that need 2 power supplies per card just to run it (so they can get 60 thousand FPS in whatever stupid game), but I'm perfectly happy with onboard video or any old AGP card (heck, even a old 8MB PCI ATI Rage video card is enough). There's nothing these old cards won't do besides gaming (and even then, they suffice for games that didn't just come out in the last few months). My newest PC has intel 900 video, and it's plenty. No plans on upgrading video on there - ever. Best drivers ever BTW. Next PC will have onboard video too. Storage? Hell yes! In fact I'm ordering a couple big HDs this weekend. That'll actually be useful.

Re:Advances that aren't being rivaled?

[pantherace]

1. I don't expect to see that. As of right now the ONLY 10Krpm SATA drives I know of are WD's raptors, which have a small capacity, compared to 7200rpm drives. One might suggest that the Raptors are modified SCSI hard drives, where 10K is fairly common and 15K is not unknown. (Oh, and really expensive hard drives, are common.)

2. Possibly, but that doesn't really matter that much. Either the drive is reading it, in which case you can expect to get maybe a maximum of 60MB/sec off a standard drive, or it's in a tiny 8MB cache. If it's in that 8MB cache, chances are it's going to be in the much larger cache in system memory, for those operating systems which support it.

3. Most will move to it. However, there's no performance benefit to SATA 2 vs SATA 1. (Improved support for Command Queueing, a couple of other improvements.)

We are starting to finally surpass UDMA/66's threshold. It will be quite a while before we pass UDMA/100. Drives aren't much faster. The other thing that's remained pretty much constant (IDE/SATA) for quite a while is seek times, sadly.

Re:Advances that aren't being rivaled?

[joto]

8 to 16 MB hard drive memory cache. With the memory cache that big many hard drive access operations are quite a bit faster.

Bah. I have 2GB of RAM. Most of it functions as disk cache. I'll be willing to bet that it gives me a lot more performance than the measly cache in the disk-drive. The cache in a hard drive is there simply because you need to store stuff before/after you transfer it across the SATA-bus. It can probably be calculated pretty precisely how much you need. Since this number is pretty small anyway, doubling or quadrupling it doesn't help performance much.

Unlike today's flash memory, these new solid-state storage devices can be written to trillions of times.

Now why would I want that? Assuming I overwrite the entire non-volatile high-speed solid state storage device once per second, a (US) trillion writes is going to take me 31710 years.

Re:Advances that aren't being rivaled?

[Anonymous Coward]

CPU performance has now hit a brick wall,

i beg to differ, the only brick wall involved in the current equasion is the one some intel exec is banging his head against for the sinking of the itanic.. and the equally profound 'instantly vaporizes into a cloud of superheated plasma in the event of a heat sink failure, and require a heatsink roughly the size of kansas to dissipate all 1000 watts of waste heat' that it would take to get the pentium 4 to clock at the frequencies they had on the roadmap for today's high end machines.

there really is no brick wall, smaller fab processes, improved processors with smaller gates and more capacitors... all those things are progressing fine, what 'seems' like a brick wall is actually just an engineering and marketing nightmare ;)

dual core capabilities arose out of the ever growing processing requirements of windows vista. in order to make sure that all the code on your machine is approved to run on microsoft computers, and that you're not some nasty pirate they need to shut down... well microsoft needs it's own dedicated processor to handle all that so that you can continue to work normally ;)

Re:Advances that aren't being rivaled?

[vrt3]

CPU? Well, we now have 3.8GHz P4 processors (which perform about as well as much slower Athlons...), and while they're certainly much faster than my old 20MHz 286 in 1991, I really don't see much difference in regular desktop usage between my 3.6GHz P4 and my old 1GHz Duron from 3-4 years ago, or my 300MHz Celeron before that, unless I'm running transcode or something (i.e., not often).

You don't see much improvement in regular desktop usage precisely because all the other components haven't had performance increases as much as the CPU. Memory is notoriously falling more and more behind. And many tasks are I/O-bound rather than CPU-bound, which means that speed increases in the CPU won't help unless the I/O bottlenecks get faster. One of those bottlenecks is in many cases still the HD.

Re:Advances that aren't being rivaled?

[Grishnakh]

i beg to differ, the only brick wall involved in the current equasion is the one some intel exec is banging his head against for the sinking of the itanic.. and the equally profound 'instantly vaporizes into a cloud of superheated plasma in the event of a heat sink failure, and require a heatsink roughly the size of kansas to dissipate all 1000 watts of waste heat' that it would take to get the pentium 4 to clock at the frequencies they had on the roadmap for today's high end machines.

I disagree. Intel definitely hit a brick wall with the P4 at 4GHz because of thermal issues, and the Itanium seems to be another issue altogether (its main problem is that crazy EPIC architecture just didn't pan out for most workloads), but AMD isn't in the clear either. Yes, they certainly have a far superior architecture, for both instructions-per-clock and for overall power consumption, but they're not increasing their clockspeeds at any amazing rate either, and they're moving to dual-core just like Intel, probably for the same reasons. I imagine AMD might have some thermal barriers as well just like the P4; where the Athlons really shine is in their off-peak or idle power consumption, which of course is what most desktop computers spend most of their time doing (waiting for user input).

BTW, Intel is still pushing the Itanic as much as ever. They haven't given up on it yet.

Fab processes aren't getting that much smaller; they're at 65nm now, but it doesn't look like they can get much smaller without running into serious quantum effects.

As for Vista, it's not the only thing that has high computational requirements. I've been using Linux on my home computer since '98, and while I'm certainly a big fan of it and can name many advantages it has, speed really isn't one of them for most of the desktop software we use (KDE, etc.). If anything, it's slower than XP at most GUI stuff (assuming a fresh install of XP which hasn't become bogged down by a lot of spyware, worms, and viruses yet), probably thanks to XP running the GUI in the kernel.

Also, as a Linux user who regularly has many browser windows, an MP3 player, and other stuff all running simultaneously, I think dual-core will be helpful for all OS users, not just Vista ones. I think this is something the CPU companies should have done a long time ago, back when multitasking became normal, instead of constantly pushing higher clockspeeds (with consequently higher power consumption).

Re:Advances that aren't being rivaled?

[Grishnakh]

You don't see much improvement in regular desktop usage precisely because all the other components haven't had performance increases as much as the CPU. Memory is notoriously falling more and more behind. And many tasks are I/O-bound rather than CPU-bound, which means that speed increases in the CPU won't help unless the I/O bottlenecks get faster. One of those bottlenecks is in many cases still the HD.

I'm not so sure about this.

It's true that memory is falling more and more behind. While the bandwidth is constantly increasing (DDR, DDR2, dual-channel, etc.), the latency of DRAM really hasn't improved much in a very long time, and this is a big problem if you're multitasking desktop apps, or running a workload that doesn't involve streaming lots of contiguous data (such as databases).

However, cache hides all this pretty well.

The biggest problem I think with today's CPUs is the pipelining. Every time there's a context switch, or a branch misprediction, the CPU has to dump the pipeline and start over. It's the whole short-pipeline vs. long-pipeline argument: a super-long pipeline (P4) does really well if there's no branching in the code you're executing, but sucks if there is. A super-short pipeline (older CPUs) does better at code that has lots of branches, but then you can't pump up the clockspeed on the CPU. I don't think eliminating the I/O bottlenecks will really affect performance that much for most applications.

The other big problem I see, however, is the latency problem with hard drives. HDs can push a lot of data, but their latency is horrible (in the milliseconds) due to the mechanics involved. The only way around this is probably solid-state or holographic storage. But my original point was that, compared to all the other parts of a desktop computer, hard drives in my perception have improved the most noticeably compared to the other parts, mainly because of the storage capacity and the transfer rate (latencies are better but not that much: my 1991 drive was 28ms, now they're down to 3ms). I just don't see that CPUs have improved in performance in such a way that is as noticeable to me as a user as the massive amount of storage space available to me now.

Re:Advances that aren't being rivaled?

[joto]

Network speeds? Nope. Back then, I had a 2400bps modem, and 9600bps was fairly common. Now, the most you can have is 56000bps (theoretical), only a 23x increase. Pathetic. Good thing we have broadband now, but that's an entirely different thing.

Why is it an entirely different thing? My cable modem is still a modem, right? FYI it does contain a modulator and a demodulator, thus making it a modem. Or do you think the difference between analog phone lines and coax is that big? Or is it the difference between digital signal sent between the computer and the modem over an RS-232 compared to sending it over ethernet? As far as I'm concerned, my cable modem has just as much to do with old phone modems, as a modern harddisk has to do with an antique harddisk. Sure, some interfaces have changed, but so has harddisk interfaces. From 9600bps to 26Mbps (the most my cable company offers), is a 2700x increase.

By the way, in 1991, you could probably buy the Intel 486 DX4 100Mhz, and larger harddisks were certainly available, although I guess 40MB was pretty typical of the PC market.

Re:Advances that aren't being rivaled?

[Grishnakh]

No, they're entirely different things. Analog phone modems are limited by the available bandwidth on the public phone network, which is 64kbps (you do know that your phone conversations are digitally modulated at 64kbps and put onto T-1 lines, right?), not by any technical limitation in the modems or technology.

10Mbps Ethernet existed back in the 80's. If phone companies wanted to (and there was a market for it), they could have installed 10Mbps ethernet to houses across America just like they have now with DSL and cable modems.

Network access speeds to homes has always been an economic problem, not at all a technical one. All the other problems discussed were mostly technical problems.

What do hard drive interfaces have to do with anything? HD interfaces are designed based on the speed of the drives. We didn't have SATA-II interfaces back then because hard drives were so slow. If you need a faster hard drive, you can just install an adaptor for the faster interface. You can't just call up your local phone company and ask them to increase the bandwidth limit of voice phone lines.

Sorry, the DX4-100 wasn't available until 93 or 94. I was in college (92) when the DX2 came out, and clearly remember it. The fastest thing in 91 was the 386DX. Hard drives weren't available much over 100MB in 91. I had an 80MB drive, and it was considered huge, since I had to partition it into 3 drives because of DOS's stupid 32MB limit.

Re:Advances that aren't being rivaled?

[damsa]

Some people for some unknown reason call the big box that houses the computer a modem. I suppose it could be called a modem as it does modulation and demodulation.

Re:Advances that aren't being rivaled?

[Shanep]

2. 8 to 16 MB hard drive memory cache. With the memory cache that big many hard drive access operations are quite a bit faster.

Actually, increasing on-drive cache sizes have shown to DECREASE access times.

There was a classic example with a WD product which also came in a special edition with much larger cache. I think it was 2MB versus 8MB. Exact same drive, except the "special edition" had the larger cache... oh and slightly slower access times.

Apparently this comes down to the management of larger on-drive caches taking longer to complete per read request.

For best performance, on-drive buffer/caches should not be any larger than they need to be to act most effectively as buffers. Especially since a large on-drive cache is not much good when system RAM is being used as a buffer cache, at MUCH higher speeds. At the end of the day, on-drive caches are good to a point, but making them larger than they NEED to be just hurts performance. It is of course, good for marketting though. ; )

Re:Advances that aren't being rivaled?

[Shanep]

In 1991, I had a 200MB "Brand Technologies" IDE hard drive. When people at my college at the time were talking about what sorts of computers they had at home, they were sceptical to non-believing that I actually had a 200MB drive! Which from memory transfered data at about 600kbytes/sec. ; ) That drive only lasted about a year and I'd never heard of "Brand Technologies" ever again. Hmmm, maybe I should have bought that 105MB Seagate.

I remember an Amiga 500 owner being amazed when I told him I had 4MB RAM.

PS, pron at 1024x768 256 colours was pretty awesome in 1991. I can remember watching images getting written into the frame buffer. You could actually see it draw it was so slow. ; )

Oh then there was that time that an Amiga 500 owner was gloating about the really shitty mouse resolution (Microsoft) he was witnessing in class. I let him gloat for a while and then pointed out that we were in text mode and the blocky jumping he was seeing was due to that and not the mouse resolution. Going into Windows 3.0 shut him up real quick on that issue.

Re:Advances that aren't being rivaled?

[Anonymous Coward]

An AmigaOS user was impressed by Windows 3.0?
OK, so he had a measly A500, and he might have been stuck with AmigaOS 1.x, but my BS detector is still blinking furiously...

NOBODY was impressed by Windows pre-95, and between 95 and XP/S2k3 only morons were impressed.

Yeah, I use Linux, Windows, AmigaOS and (shudder) MacOS at home. This isn't zealotry speaking.

Re:Advances that aren't being rivaled?

[WuphonsReach]

I'm not so sure that 7200rpm has a lot to do with it. The bigger issue for transfer rates is areal density (I think that's the term). If you can pass twice as many bits/sec under the drive heads at the same RPM, you end up with twice the transfer rate.

A good example of this is to compare older, 40GB 7200rpm drives with newer 300GB 7200rpm drives. The 300GB drives are (probably) a higher density platter and should reflect a higher transfer rate.

I doubt you will see 10k rpm drives in a 3.5" package (well, maybe... the Raptors are 10k rpm, but I'm not sure that they're not 2.5" disks). I'm too lazy to do the math at the moment, but you'll want to take a look at (a) the speed of the outer edge of the platter at various RPMs and (b) the centrifigal force that the edge of the platter is undergoing at higher RPMs. Plus the issue that in order to spin a disk at faster RPMs, it requires more energy (exponential?). I'm almost positive that the 10k and 15k RPM SCSI drives are all 2.5" platters.

If/when perpendicular recording finally hits (which will roughly double current capacities per platter) we might see another speed boost in throughput.

Re:Advances that aren't being rivaled?

[Angry Toad]

Some people for some unknown reason call the big box that houses the computer a modem.

That's only fair, since as we all know the monitor is actually called the "computer".

Re:Advances that aren't being rivaled?

[Shanep]

I wasn't saying he was impressed by Windows 3.0. I was saying that Windows 3.0 allowed him to see that the mouse resolution of those old Microsoft mousies was not terribly blocky like using them in text mode might have alluded.

Interesting Fact

[matr0x_x]

A little known fact about the WD2500KS is that it has a sister WD2800KS due out in 4 months with double the storage and 35% higher performance. Of course the cost isgoing to be MUCH higher too

Re:Interesting Fact

[discord5]

Not if they can plug it on slashdot for free. 30% marketing reduction cost guaranteed.

Anonymous Coward posts Slashvertisement

[Yahweh Doesn't Exist]

nothing to see here.

desktop hard drives are quite possibly the most boring technology possible, except maybe non-wireless network cards. who cares?

Re:Anonymous Coward posts Slashvertisement

[Anonymous Coward]

desktop hard drives are quite possibly the most boring technology possible, except maybe non-wireless network cards. who cares?

There is quite a variation in quality when it comes to ethernet cards. When you want to sustain close to gigabit speeds, the el cheapo ethernet cards aren't going to cut it.

Now, very few people care about that, or need that level of performance, but some of us do.

Re:Anonymous Coward posts Slashvertisement

[Anonymous Coward]

True. But I am very exciting about the upcoming 56.7 kbps modems!

Oh puhleeese

[$RANDOMLUSER]

A 3-platter 8.9mS seek-time 7200 RPM drive with a 16MB cache? You better use this puppy for video files, 'cause the only thing that's more tuned for sequential access is a tape drive.

File this under "Ads that matter".

Big, Slow Drives

[jimmyhat3939]

Note to hard-drive manufacturers:

Please come out with a larger, slower drive for those masses of us who want to store very large quantities of data but don't care so much about 7,200 RPM or large cache sizes and whatnot.

When will the 1TB hard drive come out? When oh when?
--
Free 411! 1-800-411-SAVE

Re:Big, Slow Drives

[TubeSteak]

While I agree with you that there's a market for such drives, the mfg's might be afraid that it'd canibalize their other sales.

They sell plenty of whitebox 5400rpm drives to the major computer assemblers (dude, buy a dell) and its hard for them to get consumers to buy more HDs. I can't image why they'd want to offer a larger & cheaper alternative to their money making drives.

Re:Big, Slow Drives

[SpinJaunt]

I second that; slow and reliable.. there is a market here.

Re:Big, Slow Drives

[shibashaba]

I think it's a great idea. All these performance numbers are mumbo jumbo to the avg consumer. If they payed any attention to the specs listed on the box along with the drivel comming out of the salesman's mouth they'd be in an uproar over actually getting less than 20% of the performance promised. On the other hand, insanely large drives at extremely low prices would probably entice more people to buy.

Of course the main problem is the relative complexity for a new user in using their new hard drive. It maybe somewhat easy to install, but having to make new directories and constantly redirecting programs to use the new drive is a bit much for a lot of poeple. How many people have you seen get frantic when they get lost and can't find their My Documents folder?

Re:Big, Slow Drives

[Saeger]

No, you wouldn't really want a single expensive 1TB drive eggbasket -- what you'd want is a couple smaller drives to RAID together for redundancy plus performance higher than a single, big, slow drive could provide.

The great thing about the monster capacity drives being released, though, is that the $/gigabyte sweetspot shifts up a notch. 500GB SATA drives are still > ~$0.70/GB, but the 250GB and 300GB drive sweetspots can be had for about ~$0.35/GB (or less if you do the rebate hassle).

Re:Big, Slow Drives

[Steffan]

No, you wouldn't really want a single expensive 1TB drive eggbasket -- what you'd want is a couple smaller drives to RAID together for redundancy plus performance higher than a single, big, slow drive could provide.

Actually, yes, I would. I'd want eight of them to put into a raid 5 array. That's still only 7TB. You make the incorrect assumption that someone would only want 1TB total.

Re:Big, Slow Drives

[TCM]

I'd want eight of them to put into a raid 5 array.

No you wouldn't. You would want 2^n+1 drives in a raid5 array to maintain at least some performance.

Re:Big, Slow Drives

[toddestan]

No, you wouldn't really want a single expensive 1TB drive eggbasket -- what you'd want is a couple smaller drives to RAID together for redundancy plus performance higher than a single, big, slow drive could provide.

Because a single drive would likely be cooler, quieter, and more energy efficient than a bunch of 7200RPM drives in a RAID array. As for backups, I would just buy a second one and a USB/FireWire case and use that.

Re:Big, Slow Drives

[Sketch]

> They sell plenty of whitebox 5400rpm drives to the major computer assemblers (dude, buy a dell) and its hard for them to get consumers to buy more HDs.

Are you sure about that? I bought one of the Fry's weekly special bargain-basement Linspire boxes for $159 a few weeks ago and even it came with a 7200rpm (40GB) drive. Dell and friends can't be too far behind...

Re:Big, Slow Drives

[Steffan]

2^n? n being what exactly? Evidence, please?

Re:Big, Slow Drives

[TCM]

Well, n being variable of course.

An optimal RAID-5 set consists of 3 disks, 5 disks or 9 disks and so on. This is to keep the block size of a stripe (excluding parity) at 2^n so that common filesystems map 1:1 onto it.

To quote Greg Oster, the developer of RAIDframe, a software RAID implementation on NetBSD:

http://mail-index.netbsd.org/current-users/2002/04 /19/0011.html

"The 'problem' with 4 disks is that you have (effectively) 3 data disks.
Since most times you're doing a 'power-of-two' write (e.g. 16K or 32K),
it's impossible to divide that power-of-two data by 3 and have a nice
full-stripe write. That leaves you with doing partial writes all the
time, and those are the ones that kill RAID 5 write performance."

From that I figured the 2^n+1 rule.

Meta-Comments

[TubeSteak]

1. I don't like the warranty
2. I've had bad experiences with WD drives
3. I've had great experiences with WD drives
4. 250 GB isn't really 250 GB*
5. This review isn't comparing similar drives
6. My RAID array is faster
7. RAID-0 isn't really redundant

And my quick summary of the aritcle:
$125 (50 cents per GB)
SATA
Not the fastest drive on the market

*In this case, the formatted drive really does hold 250 GB

Re:Meta-Comments

[Anonymous Coward]

Besides which, hard drives have been hanging around at 250GB or thereabouts for ages now. Where is the $300 20TB hard drive for my PC at home, that's what I want to know? (and yes, I do need it).

Re:Meta-Comments

[chris_eineke]

$125 (50 cents per GB)
SATA
Not the fastest drive on the market
Lame. ;)

Re:Meta-Comments

[Anonymous Coward]

Where is the $300 20TB hard drive for my PC at home, that's what I want to know? (and yes, I do need it).

That's a lot of porn. Aren't you raw by now?

Slashvertisement.

[imsabbel]

Its getting more and more annoying...
So this drive is great... says WD.
So obviously is MUST be great.

And i really like reading that it has a 16" monster cock... ^h^h^h^h^h^..^h 16Mbyte monster cache. You can really feel the journalistic integrity OOZING out between the letters. I mean, thats SOO great considering that currently my windows uses 360Mbyte as file cache, connected with 6.4Gbyte/s.

And a 250Gbyte drive is SOOOO revolutionary. I mean, thats the smell of the future. Almost as if we were already in the 3rd millenium.... oh wait, we ARE there, and drives of this size have been around for 2.5years+ already.

And Sata-2 transfer limits are SOOOO useful as a dazzling number when your drive barely reaches 70Mbyte on the outermost tracks for the first Gbyte.

Re:Slashvertisement.

[Anonymous Coward]

Journalistic integrity? Slashdot?? You want journalism go to The Register or the BBC, don't waste your time here?

Doesn't do any good if

[WindBourne]

the drive has crashed. I will no longer buy WD; crappy quality.

Re:Doesn't do any good if

[Rosco P. Coltrane]

the drive has crashed. I will no longer buy WD; crappy quality.

You know what's funny (well, sad): I've had my first encounter with a WD drive in 1994, and it died on me after slowly messing up all my files. I've dealt with other WD disks since (both consumer and enterprise), and they always turned out to be troublesome.

1994, that's almost 12 years. Sheesh, I wonder how a company can spew out shite products for 12 years and still be alive...

Re:Doesn't do any good if

[Garg]

Amen to that. I had one crash several years ago. Then I read several people say they'd improved, so I bought another one last year. Blew up a month out of warranty. Never again.

Re:Doesn't do any good if

[cowbutt]

It's naïve to assume that the relative reliabilty of each vendor's drives remain static compared with each other. The 'top dog' position rotates irregularly, as does the 'PoS' position. Currently, I'd say that Seagate are top for reliability, with WD close behind with their "special edition" models (and each is backed by 5 years and 3 years warranty, respectively). I'd say that, right now, anecdotally, Maxtor are in the 'PoS' position; everyone I know whose lost a drive recently was using a Maxtor. OTOH, I have a 120M Maxtor drive from 1993 which still runs and a 1.3G WD from 1995 which was troublesome by 1997 (but still runs if you tap it right on power-up). I also have a 1.2G Quantum from 1992, a 4.3G Fujitsu from 1997, a 6G IBM from 1998, a 30G Maxtor from 1999, 3*80G WD SEs from 2002, a 20G 2.5" Hitachi from 2002 and 2*200G Seagates and a 60G 2.5" Hitachi from 2004 which still run with no problems.

The important thing is to research the reliability of the vendors on the market at the time of purchase, and not to rely upon either positive or negative reputation.

Next most important is to keep your drives cool, on a clean power supply, and away from vibrations.

Re:Doesn't do any good if

[WindBourne]

Actually, the quality depends mostly on where manufactuered and what techniques. For years, I would buy nothing but quantums (never lost one and some are still going 15 years later). IBMs were good (7 years on them), and now I am running Samsungs(4 years). Over the years, I have also bought a number of Seagates, Hitachi, Fujis, Maxtors, and WDs. All of these have died after several years. Every so often I have tried these and am disappointed. For now, I will stay with Samsungs.

Re:Doesn't do any good if

[Random Destruction]

Are maxtors really that bad? Ive head rumors of them sucking, but never heard a story first hand of troubles. Just wondering cause I have 2 Diamondmax 300gb drives, and was about to buy another. The only reason I dont get the seagates (I've heard they're really nice) is the cost difference, and the fact Ive only seen favourable reviews of the maxtor line.

Re:Doesn't do any good if

[billcopc]

Statistical manufacturing defects aside, I'd say the #1 reason for a failed drive is a cheap system. That 200$ PC uses a 7$ power supply and no fans except the CPU. Not all 300watt power supplies are created equal.

These hard drives need juice and they need cooling. I have been a Maxtor nut forever because they run faster than any WD or Seagate, but they run hot. The average moron with their PC in a desk drawer will kill one of them in the first month. I've been running my raid-0 for two years now without a hitch. The trick ? I always stick a nice big 120mm fan right across the hard drives, blowing around them. And believe me, they don't sit idle all day. I've got 6-way Raid-0 for a reason; I thrash them harder than your average SQL server.

Now I'm citing Maxtor because they tend to run the hottest (performance driven), but this applies to all hard drives. If you let heat stagnate, you will kill any electronic device, it is merely a matter of time. Take care of your gear and it will last a long time.

Re:Doesn't do any good if

[Anonymous Coward]

I won't buy one of these ever. Here in Brazil WD HDs are known for being the most crappy HDs ever marketed over here, rarely lasting over 6 months. I don't know if they're really that crappy or if they just dump whatever haven't passed QA in Latin America, but I'm not willing to try it again.

Once I had the pretty stupid idea from buying a pre-built computer that came with a WD HD, during the 2 year warranty period it needed to be replaced 3 times. After the warranty expired, I bought one from Fujitsu that still works today without a single bad block.

Bought one from Samsung in August 2002, lasted about 18 months. The one I bought from Seagate in October 2002 still works just fine, the only issue I had with it is that a NTFS partition suffered from pretty nasty metadata corruption after a few XP crashes (some games easily gives it the BSOD), after a reformat, everything worked pretty fine.

Re:Doesn't do any good if

[Shanep]

Doesn't do any good if the drive has crashed. I will no longer buy WD; crappy quality.

A word of advice from someone who was hurt by a flakey 340MB Maxtor many years ago. If you do this, eventually you will never want to buy ANY drive again. I have come across poor quality drives that died quickly with:

Maxtor
IBM
Hitachi
Fujitsu
Toshiba
WD
Seagate

Every drive manufacturer has its share of bad batches or makes a tech mistake which has big consequences. Some people get hurt and then complain in real life and on the net and then replace that drive with some other manufacterer, get lucky with that drive and proclaim how great that company is. Stick around long enough and you will come full circle and hopefully by that time you'll have realised that a good backup procedure should be as critical to you as your data is. You should also hopefully realise by then that overall, they're mostly close to each other in quality.

I used to sing the praises of Seagate and WD and complain about Maxtor and then find LOTS of people who agreed and about the same amount of people who disagreed.

Re:Doesn't do any good if

[Shanep]

Next most important is to keep your drives cool, on a clean power supply, and away from vibrations.

I recently purchased a Fujitsu SCSI320 drive which had some interesting entries in one of the support pdf's, regarding expected lifetime versus heat:

Measured surface temperature: Estimated drive life:

40C or less: 5 years
41C to 45C: 4.5 years
46C to 50C: 4 years
51C to 55C: 3.5 years
56C to 60C: 3 years
61C and more "Strengthen cooling power so that the DE surface temperature is 60C or less".

Re:Doesn't do any good if

[WuphonsReach]

Yep yep yep.

I learned that lesson after killing a 7200rpm SATA drive. (Actually, I learned that lesson back in 1998 with SCSI drives, but I was being lax.)

That's why I like things like the newer PC cases that put the drives sideways and stick a 120mm fan to pull air over them. (Antec Sonata, Antec p160, etc.)

The other key bits in my toolkit are bay coolers. One lets you put up to (3) 3.5" drives into (2) 5.25" bays (try MWave for these), the other is a "4 in 3" bay design (CoolerMaster). If you don't pack them full (e.g. only put 2 drives in the 3:2 unit, or 3 drives in the 4in3 unit), the 80mm/120mm fans on the front keep even hot 7200rpm drives cool to the touch. Plus, the 80/120mm fans are *quiet* when compared to the normal 2x40mm fans used on regular 5.25" bay coolers.

As for power... I used to have a (6) drive ATA RAID that would constantly drop a disk every few weeks. Nothing physically wrong with the disks, the array would simply drop the drive and start rebuilding with the hot spare. Upgrading to a better UPS along with a better case/powersupply fixed the issue for good. (The array stopped dropping drives.)

Re:Doesn't do any good if

[springbox]

I used to like the Maxtor drives because they were really quiet by comparison to the noisy drives they were replacing, but unforutnately every one we bought ended up being crap. One computer had a Maxtor drive that one day, for no apparent reason, just stops spinning when the computer is turned on.
The one I was using in my computer recently kept doing weird things when it was powered on after being slightly chilled. The first time I did this, some files at the beginning of the drive were a little messed up, but other than the drive freaking out and reporting a string of garbage for its name on power up, it worked just fine. The second time I started it up cold really killed some important data on it. Basically killed the beginning of the drive. Still trying to recover data from the image.

Re:Doesn't do any good if

[WuphonsReach]

Some people get hurt and then complain in real life and on the net and then replace that drive with some other manufacterer, get lucky with that drive and proclaim how great that company is.

And the rest of us plan for failure by using RAID in addition to backups (and system images). I hate running systems without RAID, because I *know* that eventually that drive is going to fail at the worst possible moment.

(I probably have close to a dozen IBM "Deathstars" (the 72GB models that everyone hated) that are still chugging right along. I've probably replaced *2* of them in the past few years and those drives failed early in the cycle and those were likely killed by heat.)

Re:Doesn't do any good if

[Shanep]

And the rest of us plan for failure by using RAID in addition to backups (and system images).

I couldn't agree more. I worry about the people who use RAID *as* their only "backup" and then find out the hard way that it does not protect from most forms of user error.

Advancements in ads...

[Anonymous Coward]

First the "article" is very short and each paragraph is divided on a separate page where ads take as much space as the actual content. Second, the real transfer rate of a hard drive is 35-62MB/s instead of 300MB/s.

Product quality

[Mr Smidge]

Great! Now when can we expect similarly advanced levels of production and refinement in the spelling and grammatical skills of our summary writers?

300MB/s my arse

[Darren Winsper]

That drive uses SATA 300MB/s, which means a peak speed, not a sustained speed. It seems the drive can manage 50-60MB/s sustained.

Re:300MB/s my arse

[Anonymous Coward]

Step 1: Buzzword compliance Step 2: Slashvertisement Step 3: Profit!

WD hard drive quality: you get what you pay for

[digidave]

Western Digital SE drives are consumer-level drives not known for having high quality.

WD also sells IDE and SATA RE and RE2 enterprise drives with MTBFs of 1 - 1.2 million hours. Why would anybody want to halve the MTBF of their drive by getting an SE drive just to save $30?

Their RE and RE2 drives (or Raptor if you don't need huge capacity) are very high quality. These drives really kick ass and come in 8 MB (RE) and 16 MB (RE2) cache models. I bought four of the REs for a server and they've been performing flawlessly.

Re:WD hard drive quality: you get what you pay for

[cowbutt]

WD also sells IDE and SATA RE and RE2 enterprise drives with MTBFs of 1 - 1.2 million hours. Why would anybody want to halve the MTBF of their drive by getting an SE drive just to save $30?

Because, according to the WD literature for the TLER functionality of their RAID Edition drives, they are designed not to attempt 'heroic recovery' for longer than 7 seconds on the assumption that RAID at a higher level will use ECC to recover any errors. RE drives are not intended for use in plain stripe sets, or as single drives.

Oh, and I have 3 80G SE drives from 2002 which still run fine.

Re:WD hard drive quality: you get what you pay for

[sapgau]

Cool, thanks!

Where have you been living, in a bubble?

[Anonymous Coward]

"With products like this available,"

Yup, drives like this have been around for the last 6-12 months. They've probably shipped tens of thousands of them and you think they're cutting edge?

"advances are being made in the storage industry that are not being rivalled by those in other areas of computing,"

Not really, have a look at the access time - 8.9 ms - this drive is just as fast as one from 8 years ago, it's just bigger. And guess what? that's why it has a 16MB cache. More platters, more heads, more cache plus greater data density equals... same access times. Hard drives don't scale up as well as other technologies.

"especially considering the price level of this drive"

Hang on a second, you can get cheaper than this. You can also get WD Raptors, which although smaller in capacity, are much, much faster. In fact, this is just a hard drive, like many other hard drives.

These are the stories I hate. Pointless, heartless drivel passed by the editors who well, don't really edit, and appear to be out of touch with their readers, not to mention their market segment. An absolute, total and utter waste of screen inches - the kind of crap I'd expect to spout forth from a zit-faced store assistant who didn't know a molex connector from his arse. An embarrassment to read on Slashdot really. Shame on you.

Re:Where have you been living, in a bubble?

[Slashcrap]

These are the stories I hate. Pointless, heartless drivel passed by the editors who well, don't really edit, and appear to be out of touch with their readers, not to mention their market segment. An absolute, total and utter waste of screen inches - the kind of crap I'd expect to spout forth from a zit-faced store assistant who didn't know a molex connector from his arse. An embarrassment to read on Slashdot really. Shame on you.

Couldn't agree more. The thing about this story that pisses me off is the "300MB/sec transfer rate !!1!!!one!!". We're fucking geeks. We know the difference between a theoretical SATA performance figure and the rather less impressive 60MB/sec or so that you're actually going to get with this drive. In other words about the same as you're going to get with any similar model.

The 300MB/sec figure is pure marketing drivel. That's what turns this from a story into another sodding Slashvertisement.

Relieving the greatest bottlebeck

[patricksevenlee]

Great stuff. From what I have read (more knowledgeable folks can chime in if I'm wrong), the biggest bottleneck these days in a personal computer is the hard drive. We have much faster processors, faster graphics cards, faster system bus, faster memory and the slowest part of a personal computer is the hard drive which compared to the other components of the system, might as well be a turtle racing a Ferrari. I noticed when I boot my Powerbook off the same OS image on my laptop (4200 rpm drive) compared to on my external Firewire 800 7200 RPM 8 MB cache drive, there's a massive difference in speed and responsiveness. Same computer, same OS image, only difference is the hard drive. Faster hard drives imo will relieve the greatest bottleneck.

Re:Relieving the greatest bottlebeck

[$RANDOMLUSER]

To a certain extent, you're right. Faster rotation means higher transfer rates and lower rotational latency. But the Powerbook drive spins at 4200 RPM to save power. More RPMs means more watts means less battery life. The external Firewire drive, with its own in-the-wall power, can use as much power as it wants, and therefore have a faster motor and bigger cache.

From TFA

[SteWhite]

And if you spend 30 seconds looking at the article, as CmdrTaco should have, you will see that this drive does not deliver 300 Mb/sec. As reported by SiSoft Sandra, it gives 52 Mb/sec. Which many other high performance drives can match. The 300 Mb/sec figure is cache to host transfer speed, which with a 300 Mb/sec transfer and 16 Mb of cache, could be sustained for a whopping 0.0533333... seconds. Wow.

Re:From TFA

[this great guy]

We all agree that the 300 MB/s figure is only relevant in the case of burst transfers, between the host and the disk's cache (some benchmarks show that some disks are able to go above 200 MB/s). But if I were you, I wouldn't be so quick into saying that a 300 MB/s SATA link is useless (well you don't say it but you seem to think it). I have myself recently built multiple storage servers with 4+ SATA or SCSI disks, and in my experience those kind of minor details can sometime have an big unexpected impact in some very particular utilization cases. Now I am not saying that everybody absolutely need 300 MB/s SATA links, but I am just saying that without a comparison of 150 vs. 300 MB/s SATA links in real-world scenarios nobody can say that 300 MB/s is useless, and AFAIK not a single well-known hardware website has ever done such a comparison.

Of course there are some other obvious advantages into using 300 MB/s SATA links. For example if you connect 2 or 3 disks on a single SATA port using a port multiplier, a 150 MB/s SATA link will be quickly saturated while a 300 MB/s SATA link won't. Indeed recent SATA disks (e.g. the Seagate 7200.8 family) can reach 68 MB/s of sustained transfer rate, multiply this by 2 and you get 136 MB/s, which is 90% of 150 MB/s, that means that if the overhead of the SATA protocol is higher than 10%, then a 150 MB/s SATA link will not let you use the full potential sustained transfer rate of 2 disks.

16 mb cache eh?

[TheSkepticalOptimist]

Had it on my Maxtor for the last 3 months. Way to catch up with the times.

But in general, most hard drives are still severely underperforming, regardless of their specs on paper. Its the single biggest bottleneck on today's systems, causing system hangs and stutters on even the fastest systems.

This industry needs a kick in the ass!

300mb/s transfer rate on a system capable of procssing 8GB of data per second, that is nothing to rave about. Also, most systems still work off the principle that you can only read or write one operation at a time. Sure caches offer speed improvements, but there is no reason why a hard drive can't have multiple read/write heads to access different sectors of the disk as the same time, turn a SINGLE drive into a STRIPE set. It can be done if you put your mind to it.

In order to get decent performance out of hard drives today, you have to buy 3 or more drives and setup a RAID 5 system and waste one drive for redundancy. But of course, the hard drive makers want you to do this, buying 3 drives instead of 1 to get decent performance is their goal, I am sure.

The problem is, hard drives have reached a point where they are cheap commodities. The leaders in this field have long since figured out how to make cheap and reliable drives while increasing storage space proprotionally to a reduction of price. Prices for hard drives keep getting cheap, and hard drive makers are not making that much money off them anymore.

This is why the whole external hard drive fad has started up, taking a $50/unit hard drive, stuffing it into a $25/unit external enclousure, and charging $300 retail for it. Add a back up button and maybe a USB port on the front and you suddenly create a "Must Have" product.

Because of this, there is no motivation to improve the technology. They figured out a few years ago how to dramatically increase storage space breaking what they preceived to be a physical barrier, and since then hard drive storage capacities double every year. With the ability to stack bits on top of each other, we will hit terrabyte storage capacities next year easily. But they are using the SAME TECHNOLOGY, the same magnetic media, read/write heads, packaging, I/O boards and chips, cache, etc, etc, etc. They may tweak these componenets to work with higher capacities, or improve performance somewhat, but nothing has really changes in terms of how hard drives are manufactured and designed. Compare this with the CPU industry that re-invents itself every 18-24 months.

Where are solid state hard drives? Where is my obscenely fast gamer performance extreme drive capable of feeding data to my video card in real time? Where is my tiny thumb sized drive capable of storing terrabytes of data?

The hard drive industry is just dolling out minor improvements and tweaks to existing technology, and expecting to be slapped on the back every time they boost storage capacity by a third or transfer rates by a quarter. Something seriously needs to happen in this industry to make hard drives hot technology again, its grown quite stale and cold over the last 10 years. Until then, I am underwhelmed with these kinds of press releases. Way to go Western Digital, your doing what EVERYONE else in the hard drive industry is doing! Sucking!

Re:16 mb cache eh?

[v1]

but there is no reason why a hard drive can't have multiple read/write heads to access different sectors of the disk as the same time

It's called "seek time". The more massive (heavy... more parts, more heads) the read arm has, the slower the seek time is. The heads have to travel a shorter distance, but it requires more time to move them that distance. You're robbing Peter to pay Paul.

Though the idea of a single drive striping, say across platters, is a nice idea. Really even that could be done with one platter, since each platter has two surfaces. (top/bottom) Though that leaves many points of single failure still... onboard controller card, stepper motor, arm mechanics, any of which can fail and cause total data loss. About 1/2 the drive failures I've seen involve the drive no longer being able to spin up or stay spun up, so I don't think this can be considered anywhere near as failure-proof as say, a two drive mirror.

Re:16 mb cache eh?

[pooly7]

Sure caches offer speed improvements

Surely, you mean that having afilesystem cache has more importance than the cache on the hard drive... which is pretty much pointless..

Re:16 mb cache eh?

[Anonymous Coward]

It can't be the software bloat? Nah, software guys get a free pass on any pile of steaming shit they serve up.

Re:16 mb cache eh?

[Anonymous Coward]

Had it on my Maxtor for the last 3 months. Way to catch up with the times.

yeah, but it's a MAXTOR... i mean, WD is crap, but maxtor is like the crap of something that eats crap.

Re:16 mb cache eh?

[Shanep]

It's called "seek time".

I assumed he was talking about having multiple servo/arms to employ multiple read/write heads. I've been wondering for a long time if we would ever see this in SCSI drives, to drive up their high I/O even more. High speed SCSI drives already use physically smaller disks. Having seperate read/write heads on seperate servo/arms at opposite ends of the drive could be a really good thing.

It would of course increase complexity though and thus reduce durability.

Re:16 mb cache eh?

[v1]

That's actually not a bad idea, although the software for interleaving heads at different locations would be scarry to write. Probably not terribly much more than current though, considering the command queueing capability of modern drives. The onboard controller card would certainly get more complex though.

That, and remember the reason HDs are rectangular is because of the arm assembly. If you want to add another one of those at the other end of the drive, the drive gets longer by about 2 inches. HD size is fairly well established at this point, so you might have serious problems fitting a drive like that into a standard case or enclosure.

Doubling the number of moving parts would also have to affect reliability and MTBF.

Last snag I can think of is that the head positioning would not be precisely identical for the two arms. So you'd have TWO heads running the top of platter 1 instead of 1 head. Unless they were perfectly aligned, they wouldn't be exactly on the same track on the platter, and that would have to affect performance as one head tried to read the data the other head wrote at a slightly different position.

Heh... this would also be a scarry nightmare for the data recovery places to try to deal with.

Re:16 mb cache eh?

[Anonymous Coward]

"Where are solid state hard drives?" - by TheSkepticalOptimist (898384) on Thursday November 24, @03:47PM

See here:

http://hardware.slashdot.org/comments.pl?sid=16927 4&cid=14112464

* :)

(Take a read of that thread, per your inquiry, for some ideas on how to use them)

That all said, well, they ARE & have been here for years now...

(YES, they are a bit costly, but less than other comparable solutions & they last as well (had mine for 2-3 years now, still chugging along no problems)).

And, as I stated in the other thread URL above? They run on LINUX as well as Windows-NT based OS' (NT/2000/XP/Server 2003).

APK

P.S.=> They're here & have been for years, affordably so (relatively speaking) & work VERY well, per the specs on 'creative uses of ramdisks', an article I did years ago for a competitor of theirs while on contract coding a tuner for their work, "EEC Systems/SuperSpeed.com", & their SuperCache/SuperDisk programs.

I used to use SuperSpeed.com's software-based solutions well before I did that review on the hardware-based unit by CENATEK & have changed to utilizing this solid-state unit vs. software based solutions ever since (even though I had created one of my own in software based off the MS-DDK template with a front-end tuner for resizing/reparameterizing it, & that's how CENATEK knew who I was when I inquired with them - which was surprising in & of itself)...

Why change?

No utilization of onboard motherboard RAM is why (where software based solutions DO use that) so it can be used for caching purposes (or to run programs w/out as much chance for paging to pagefile.sys etc.) & to have the pagefile.sys be on its OWN partition (#1 of 2 total) on a solid-state disk, as to only 1 of many possible uses of such a device... there are MANY more, especially for 'diskbound' processes! apk

Re:16 mb cache eh?

[Shanep]

Yes, it probably would be overly complex. However, in regards to head placement accuracy between two seperate arms, today modern drive heads are guided by servo location information on the actual disks themselves. So it might not be too hard to achieve.

Re:16 mb cache eh?

[v1]

My experience in working with direct disk control is a little stale, but the problem I was referring to is not which track you are on, but being in the "center" of a given track. I am assuming modern hard drives have a 1:1 ratio between stepper motor steps and disk tracks. Since there's no way to increase the resolution (reliably) to any more than a single step on the stepper, (half and quarter-tracking not being considered) if the head is say... 1/4 track off from its twin on the other arm, there's no way to correct for this since the stepper is pulling the head to where it believes is the center of the track and cannot deviate. Considering the extremely fine tolerance between individual tracks on a platter, it wouldn't be unreasonable for one head to be 1/2 track off in positioning from its twin, which would lead to a totally unreadable signal. You are lucky to get a good read 1/4 track off. And if your tolerance is randomly + or -, 1/4 track + on track 5 and 1/4 track - on track 6 will lead to "bleeding" of data between tracks.

So unless the heads can be physically aligned to within 1/4 track or better of eachother, (and I strongly doubt they can) then this idea will not work.

Re:16 mb cache eh?

[Shanep]

the problem I was referring to is not which track you are on, but being in the "center" of a given track.

Oh right. Yes that would seem to pose a big problem. Have you heard the odd noises some of these new big drives make periodically? I bought 2 120GB Seagates (yeah, not big any more) and every now and then they make this high pitched noise which Seagate claims is head position calibration. I guess this is due to the extremely tight tolerances now being used. I wonder if they can do that for one arm, if it means that they could actually make 2 arms feasible? Or perhaps this calibration movement is too small to allow calibration width of a whole track wide?

I don't know. For high I/O I'd rather see cheap RAM drives and systems with lots of RAM to avoid slower busses anyway.

Desperately needed

[alphorn]

I wonder when we're gonna get an ad filter that catches Slashvertisements.

fail rates

[Keruo]

Have they improved overall quality also?
I've had 50% fail rate (6 drives in one machine, one doa, two broken down after less than month in use) with western digital sata drives.
I haven't lost any important data, but it's annoying to take machine apart every two weeks and send hdd back for warranty replacement.

Re:fail rates

[lorenlal]

I did lose some critical data on my last WD...

Since then, I've been trying to figure out what drives I should get for home. I mean, 250GB is nice and all... but the last WD I got lasted about a year, and then outright died with no warning...

Well, not really *no* warning... there were 3 entries in the system log saying the disk had a bad sector. I guess the 4th was the first sector.

It was a VERY sad day too. It was only a 60 GB Drive... but I'm sure (since I'm a typical slashdot reader) you all know what 55GB of that drive contained.

I now have a RAID 1 array setup with Seagate drives, with a 5 year warranty on them. I can't lose that again.

I couldn't care less what happens to my OS... I can get that back easy.

Re:fail rates

[WuphonsReach]

(Inserts the usual litany)

Top killers of hard drives (causing them to die early deaths):

1. Heat -- what temperatures are your drives running at? My rule of thumb is anything over ~45C is too hot (because you have no margin of error for fan failure or A/C failure). Grab a copy of SpeedFan (for Windows) or use lmsensors(?) in Linux.

2. Power -- Either poor power from the AC mains or an overwhelmed/cheap power supply. Get a better power supply (or get the proper size one) and evaluate your AC power.

Re:Save the kids...stop Apple!!!

[coaxeus]

Um. Flamebait or are you actually completely insane ?

300 MB/sec!!

[Anonymous Coward]

Wow, that's astonishing. That's like 10x better than everythi...oh wait, the advertiser is just talking about bus speed. Which is meaningful of course...I mean what tiny percentage of HD reads actually involve, y'know, reading the HD?

Who let this idiot post?

Re:300 MB/sec!!

[Anonymous Coward]

> Who let this idiot post?

if ((getUID(CmdrTaco) == 1) && youDontLikeIt())
{
goAway();
}

Re:300 MB/sec!!

[Anonymous Coward]

The same idiot that let you post.

Submitter is kind of clueless?

[hklingon]

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.

Re:Submitter is kind of clueless?

[shibashaba]

I'll take a slower scsi driver over SATA/IDE crap any day. Scsi still blows away everything else in terms of random access and the fastest driver on the market are still scsi or sata. They've had 15K and 20K drives available for years(at extremely high costs) but no ones ever bothered to make them with anything other than scsi or fibre channel interfaces. I'd go fibre channel but I haven't found an econimcal way of doing it yet. That and I'd think I'd finally need to upgrade my 650Mhz duron...

Slashdot needs an "adverts" topic

[Tim C]

Come on guys, we get slashvertisements like this so often it's only fair to give them their own topic. You don't even have to make it hidable (although is that fixed yet anyway?), but I think you owe it to all of us to at least be honest about it. Pretending like this just insults our intelligence.

Silly Question...

[Manip]

So it runs at 300 MB/sec; but can you get 300 MB from it? .. I mean throwing out general performance numbers like that is completely meaningless.. How much of that data is in the cache? Does it before at 300 MB/sec for more than 16 MB? What if I do a number of seeks, how long does it take then?

Point is you can't just create numbers and throw them out... The fairest way to do it is to compare a few similar drives using identical testing software that reflects real life read/writes on a disk over a period of time.

I would also like to see advances made in drive redundancy; far more so than speed. Why is it when I have four or five platers in a drive, that any one failure can cause a 100% data loss? Shouldn't the data loss be limited to just that plater or read head? ... Perhaps a little R&D in that area, I know I'd pay more for data security.

Re:Silly Question...

[evilviper]

Why is it when I have four or five platers in a drive, that any one failure can cause a 100% data loss?

What are you talking about? I've never had a problem on one platter lead of 100% data loss. As a matter of fact, I can't remember the last time I had any problems with a specific platter... It's always the heads or electronics that fail.

Short of practically building two complete drives in one, they can't have redundant independent systems like you want, so why don't you just buy two big cheap drives, and setup a RAID array for yourself? Then you get both performance and data protection.

L@@K!! CHEEP

[Anonymous Coward]

The summary reads like an eBAY listing. Can't you do any better /.? How about some original content for a change instead of poorly disguised commercials?

And that's how Slashdot is getting lower and lower

[xdesk]

Can we get rid of that sh*t !

Now only if.

[NidStyles]

...they weren't so damn loud when they spin up. I also have never been able to have a Western Digital drive last more than a year. I generally stick to Seagate.

lol

[js3]

how much money did you get paid to post that? I thought it was generally accepted that the harddrive industry was lagging behind everyone else! I don't care how fast it is, just make it reliable :)

slashdot now has pop-ups!

[braindead]

Slashdot now serves pop-up ads!

I read it on a comment yesterday, I couldn't believe it... but now I can, because I've seen it happen. Slashdot just served me a pop-up to thinkgeek! And this is on a mac running Safari, so the machine shouldn't have spyware on it.

Between the increase in slashvertisement, and now this... good bye, Slashdot! It's been good while it lasted.

I'm sure this will be moderated off-topic, but there's no meta forum so... besides, I don't care about my karma anymore. You can have it.

One of these days...

[Anonymous Coward]

...hard drive has 300 MB/sec transfer rate the drive has a monster 16 MB cache...

It's called punctuation, guys. Use it.

I sincerely don't understand this

[pepijn84]

I've been following slashdot for some time now, but never EVER have I seen an 'post' like this. Who did this? Is this a joke? Can someone please tell me what's going on here? I need to know!

Re:I sincerely don't understand this

[pepijn84]

Why do I suck? Can you explain? That would help a lot. Thanks.

Sustained transfer rate?

[miffo.swe]

I dont care about spurious theoretical cache transfer rates. What i care about is the sustained transfer rate and the ability to do more than one thing at a time. Come to think of it i think i really hate HDs. When o when will we have solid state long time memory in our computers without moving parts?

Re:Sustained transfer rate?

[TheRaven64]

You can get dual-CF to IDE adaptors for almost nothing from eBay - just plug in a couple of 1GB flash disks and you've got a 2GB solid state hard disk. Of course, it costs about 100 times as much per GB as a hard drive, but it's getting there. Once it gets to about 10GB I might be quite tempted by the idea of a laptop with a flash drive and put everything else on a nice big RAID NAS device.

Re:Sustained transfer rate?

[evilviper]

When o when will we have solid state long time memory in our computers without moving parts?

Just as soon as you're willing to pay 100Xs more for the option. You can do it right now if you want... I had a PC running on just 32MB of compactflash several years ago.

Re:Sustained transfer rate?

[Anonymous Coward]

"When o when will we have solid state long time memory in our computers without moving parts?" - by miffo.swe (547642) on Thursday November 24, @04:16PM

Go here:

http://www.cenatek.com/

I did the "Independent User's Review" on the front page of their website, other reviews are within the events/press pages so you can see others' findings as well as my own in various usage scenarios.

* :)

They cost a bit, but less than other solutions for what you're looking for per your comment.

(They're already here, & they work great + last (had mine for @ least 2-3 years now))

They're outstanding, especially for diskbound processes. Makes sense, there's no mechanical parts movement latencies & running in RAM totally as to whatever you deem to see fit to run from one.

E.G.-> I place my pagefile.sys onto the first half of mine (2gb total RAM onboard, in 2 x 1gb partitions)

2nd half/partition of it is %temp% environment ops for OS & app, webpage caching, & %comspec% environment ops (cmd.exe).

And, I run my SETI@Home units from it as well!

(Currently I am @ 3 hrs 13min 5 sec each avg. processing time per unit - that's PRETTY quick, considering again, that I did my first 50 units on an OLD system that took 24 hrs. per unit, & later on one that only took that down to roughly 7 hours per unit)

Using this ramdrive solid-state ramdisk card this way has helped me cut my SETI@Home processing times into less than 1/2 from 7 hrs per unit, literally!

(Well, that & faster CPU's of course + faster motherboard &/or RAM technologies of today in the mix as well)

I.E.-> I did my first 50 units back in 1999 on an AMD K6-III @ 450mhz cpu system w/ much slower RAM & mobo technology as well - that took 24 hrs. per unit!

Later, a Pentium III Dual/SMP 1ghz (each CPU) + PC-133 SDRAM unit only managed to take that down to 6 hrs. 58 min. using the RocketDrive.

My latest rig Pentium 4 3.2ghz + DDR Ram & this RocketDrive took it to the figure above (currently @ 3 hr. 13 min. 5 sec. & decreasing still at 1.5-2 sec per unit processed)).

Yes, you can use them on LINUX also, not just Windows NT-based OS (NT/2000/XP/Server 2003), before anyone inquires on that or yells & screams about that as well.

APK

P.S.=> You can't boot your OS from it (yet), but other than that?

They're there & they work for speeding things up quite a bit & can be striped/spanned into a single large 16gb "disk" (4x 4gb maximum memory configuration per-each-ramdisk board) based on PC-133 SDRAM!

So, if you have diskbound processing you want sped up, these can help & exist already (for years now in fact, I have had mine since iirc, 2002-2003)... apk

All HDD's Suck

[AgNO3]

So Maxtor sucks, WD sucks. Seagate sucks, (yes I have been thru 3 seagate drives this month all warrenty replacements) Hitachi sucks. So what HDD doesn't suck? Please advise.

Re:All HDD's Suck

[n0d3]

now THAT is a good question.

Since nobody really has a good answer, I'll stick with enterprise level drives, like the raptor with it's 5 (yes FIVE) year warranty.

Re:All HDD's Suck

[Txiasaeia]

Samsung - quiet, fast, reliable, good warranty. I'm currently using a Samsung Spinpoint SP2014N 200GB PATA 7200 drive - great, great stuff.

Re:All HDD's Suck

[Anonymous Coward]

um most drives already have 3 years and 5 year warranty's arent exactly uncommon

Sloooow

[jadin]

Give me optical or give me death!

http://atomchip.com/_wsn/page3.html

Re:Sloooow

[f8l_0e]

Dear jadin,

      Thank you your order, but due to fact that we do not have any optical processors in stock, we will have to substitute your order with death. It should arrive within 3-5 business days.

                                                                                                    Your atom chip representative.

Nice but...

[snevig]

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.

MOD PARENT OFF-TOPIC FOR AD IN POST

[Anonymous Coward]

Parent has ad in post. At least have the decency to put it in your sig like all the other slash-whores.

How about a good SATA raid card?

[The_Morgan]

A PCIe card with about 8 ports that doesn't cost over $400-500.

I saw the press release about this:
http://www.broadcom.com/products/Enterprise-Small- Office/Storage-Solutions/BCM8603
but no cards with it yet.

Just Cheaper, Please

[Doc Ruby]

I'm pretty happy with drive performance. All I really want is lower per-byte prices. A RAID means drives can deliver data in parallel for faster data transfer; multiple RAIDs on a SAN or a PCI even faster. I want all their R&D going into making it cheaper. HDs right now cost $0.31:GB for 250GB drives. When that's down below $0.05:GB, I'll be interested in hearing about faster transfers on individual drives.

TROLL! DO NOT MOD Doc Ruby UP!

[Anonymous Coward]

You are a submarine troll. Know what that means? You post to Slashdot for a week looking for karma and then burn it all off on blatantly offensive comments. Remember that whole flaming tree you posted about a gay governor a few months ago? How about that whole unfounded Griffin critcism?

That's *MR.* Self-Righteous Asshat.

Mods, don't feed this guy. Maybe without a karma stash he won't go on these trolling runs.

--
Trolling all trolls since 2001.

Western Digital Reliability - not that bad

[Anonymous Coward]

I for one am sick of the "I bought 2 drives and one went bad so therefore WD has a 50% failure rate!".

I personally have built over 50 computers (all with WD hard drives) in the last 2 years and we abuse the heck out of those systems, and we have very few drives go out percentage wise, maybe 1 in 15 at the most. And we're using 90% consumer level IDE/SATA drives, and the rest are raptor 36gigs mainly (we have some 74Gigs in a raid on one machine that have ran for over a year flawlessly now). I haven't seen ANY DOA drives or drives that fail in less than a month, maybe the people saying this are ordering their drives from cut-rate vendors that drop-kick the things?

Re:Save the kids...stop Apple!!!

[Anonymous Coward]

I'm not insane...I'm a good Catholic.

And now my confimration word is "creaming"?! What sort of perverts run this site?

You mean 244Gbyte.

[Beardo the Bearded]

Seriously, someone should be going to jail for putting fraudulent values on the box.

There are 1024 bytes in a kb, not 1000. Saying there's 1000 is false, it's wrong, and it's fraud. It's like Intel saying the 1.8GHz chip is 3.6GHz because they're using a harmonic.

Re:You mean 244Gbyte.

[Deviant Q]

No. There are 1000 bytes in a Kilobyte, and 1024 bytes in a Kibibyte.

Re:You mean 244Gbyte.

[digid]

Actually you are wrong. I am not sticking up for hard drive industry and it only becomes misleading because the hard drive industry and operating systems report their values in different bases. These units have been standardized by the International Electrotechnical Commission (IEC). They have standardized a "megabyte (MB)" to mean 10^6 bytes or 1,000,000 bytes. However operating systems report in what they should be calling "mebibytes (Mib)" where one MiB is equal to 2^20 bytes or 1,048,576 bytes. Because of the use of different bases and depending on what filesystem the partitions are formatted with it appears the hard drive industry gave you the shaft. The "gigabyte (GB)" is also standardized as 10^9 bytes or 1,000,000,000 bytes and the "gibibyte (GiB)" standardized as 2^30 bytes or 1,073,741,824 bytes. If you want more information on the historical confusion of this read this article: Bruce Barrow, "A Lesson in Megabytes," IEEE Standards Bearer, January 1997

Re:You mean 244Gbyte.

[TCM]

Actually, you are wrong. In the good ol' times before this Kibi bullshit, capitalisation of 'k' and 'b' mattered unless you made it unambiguous by spelling out byte and bit.

1kb = 1000 bits
1Kb = 1024 bits
1kB = 1000 bytes
1KB = 1024 bytes

Re:You mean 244Gbyte.

[LocalH]

No, there are 1024 bytes in a kilobyte. Kibibyte is revisionist nonsense and most people that I know laugh at such idiocy.

Re:You mean 244Gbyte.

[Shanep]

IEEE Standards Bearer, January 1997

I am aware of those standards. However I refuse to adhere to them outside of my work life and will always provide a disclaimer when refering to data sizes on the net.

Standards boards have made some VERY VERY STUPID decisions in the past. And this is one of them.

For a very long time MB, GB, etc was actually meaningful in a computer science sense, since modern digital computers use... well... you know... BINARY!?!?!

2^ is much more meaningful in Comp Sci and digital binary systems than 10^ is. 10^ does not FIT well, much less fit perfectly like 2^ does.

I would like to meet the complete and utter retards at the standards board who thunk up this pure fucking genius idea. "Hey, I know! Lets take a unit of measurement which FITS PERFECTLY and has been used for DECADES and COMPLETELY FUCK IT AND THE INDUSTRY UP so as to pander to CORPORATE DESIRES!"

I call on all geeks who care, to refuse to adhere to that bullshit "standard", continue to use the old proper 2^ based standard and provide a disclaimer to what they mean and the ridiculous reason for why the disclaimer is needed.

MiB should be 10^6 and
MB should have REMAINED 2^20.

Re:You mean 244Gbyte.

[Anonymous Coward]

Just because you dumbfuck yanks don't want to use international standards doesn't mean you have the right to bastardize them.

Kilo = 1000. End of story.

BUS SPEED != TRANSFER RATE!

[SuperBanana]

250 GB hard drive has 300 MB/sec transfer rate

Uh, no. Fastest almost any drive can transfer data off the platters is about 60-70MB/sec, and that's only the very tip-top of the line drives.

What they mean is that it is a SATA-2 drive, which has a maximum wirespeed of 300MB/sec.

I know this gives you faster access to the 16MB of cache- but main memory is much more 'accessible'(Gigabytes/sec makes even 300MB/sec seem slow), there's a hell of a lot more of it, and the OS is in a much better position to use the system's memory cache more intelligently. The drive has no "knowledge" of the "big picture" - ie what the user is doing, system load, the IO pipeline, the filesystem, etc.

Re:BUS SPEED != TRANSFER RATE!

[Shanep]

Uh, no. Fastest almost any drive can transfer data off the platters is about 60-70MB/sec, and that's only the very tip-top of the line drives.

Actually, top of the line SCSI drives are actually pushing 100MB/s.

Yes, that is 2^20 Megabytes and not the bullshit 10^6 MB.

Screw You Fu.

[Anonymous Coward]

"desktop hard drives are quite possibly the most boring technology possible, except maybe non-wireless network cards. who cares?"

I hear that case screws are going to be the new hotness. Pass it on.

Re:Save the kids...stop Apple!!!

[coaxeus]

ok insane then just checking

Actually 20MB/sec

[heroine]

The transfer rate during normal use is 20 MB/sec and has been for 10 years. No-one has ever made a hard drive go faster during normal use. Sequential reads from outer tracks have gotten up to 60MB/sec and bus speeds have allowed sequential RAID accesses from outer tracks to get up to 250 MB/sec but why pay for something advertized to perform at a level you'll only see 1% of the time?

Re:Actually 20MB/sec

[Shanep]

The transfer rate during normal use is 20 MB/sec and has been for 10 years. No-one has ever made a hard drive go faster during normal use. Sequential reads from outer tracks have gotten up to 60MB/sec and bus speeds have allowed sequential RAID accesses from outer tracks to get up to 250 MB/sec but why pay for something advertized to perform at a level you'll only see 1% of the time?

Where did you pull this 20 MB/sec figure? And what is this "normal use" for which you speak?

For some of the things I do, I do actually see about 58 MB/sec on a not new 120GB Seagate.

I find this static 20 MB/sec figure very strange. Meanwhile, I find faster disks to be very much noticably faster during use than slower disks.

Re:Actually 20MB/sec

[WuphonsReach]

Older, smaller drives (40GB - 72GB), maybe.

Stupid stat, but under Linux, when synchronizing a 300GB software RAID1 set, I'm seeing transfer rates of anything from 30-60GB/s. The 5400rpm 300GB drives clocked in at the lower end of that range, while the 7200rpm 300GB drives clocked in at the upper end of the range.

Or, copying from disk to disk on a Windows box (7200rpm 250GB drives), I'll see transfer rates of 30-40MB/s.

+5 Funny

[Anonymous Coward]

Dammit. My first +5 Funny when I post AC (and it wasn't supposed to be funny :( ). Can I redeem get my well-deserved karma by having the same IP? ;)

Continuing the proud tradition of WD drives.

[Anonymous Coward]

Yes, but this model lasts a full two months before overheating/spinning a bearing/crashing and losing all your data, a 200% improvement over prior WD models.

7200RPM *is* slow

[erice]

Please come out with a larger, slower drive for those masses of us who want to store very large quantities of data but don't care so much about 7,200 RPM or large cache sizes and whatnot.

A *fast* drive is 15-20K RPM.

Technology marches on and what used to be considdered fast is now slow.

Crapola

[ff1324]

WD = JUNK

December 2004 - Purchase WD 180 GB HD. Install in Dell Dimension. Sits happily on in desktop machine on desktop. Runs fine until...

March 2005 - Suddenly, loud screeching noise comes from within the tower. Sounds like a mouse got his balls stuck in the CPU fan. WD drive is kaput. Only lost backups. No biggie. Sent off to WD for replacement. Replacement recieved and installed.

September 2005 - Drive saving baby videos and baby pictures (of my most adorable little daughter) and then one day has an identity crisis. It cannot be found by windows. But it can be seen by Knoppix. Begin copying everything like mad off of the disk. Then, the mouse returns and gets his other testicle caught in the fan.

October 2005 - Have sworn off WD as complete crapola. Gave drive to a forensics friend to attempt rescue of remaining videos and baby pictures. Thanks, WD for losing my kid's first six months.

I know...bad boy for no backup, but what are the chances of having two bad drives in 10 months? Apparently with Western Digital drives, its about the same as getting your balls caught in a fan twice in the same time frame.

Re:Crapola

[Anonymous Coward]

"what are the chances of having two bad drives in 10 months?"

For you, I'd say about 100%.

Your backups should have been on Kodachrome. We know your daughter's first six months are important to you. You should have asked yourself if her first six months are important to her great grandchildren.

When are you Americans going to learn that the future is more than four years out? When?

Re:Crapola

[Anonymous Coward]

Instead of blaming your stupidity and bad luck on Western Digital, get a film camera or purchase a backup solution.

Hard drives crash. I've seen simulataneous failure on a $100,000 RAID-5 array before. Yes, that means complete data loss.

About time

[sc0ob5]

"With products like this available, advances are being made in the storage industry that are not being rivalled by those in other areas of computing" It's about time that the storage industry has come to the game, for years the hard drive has been the bottleneck in any computer system. The drive benchmarked 52MB/s which is still quite obviously the bottleneck of any system made after 1998. Sure it's great to have faster hard drives but lets be realistic here, hard drives are slow and some improvments have to be made.

16MB cache is huge?

[erice]

Since when? The first hard drive I owned was a Quantum 105 Prodrive. 64K cache for a 100MB disk.
A comparable size cache for the Maxtor would be over 128MB. The 16MB cache it actually has isn't huge. It's puny. It's just a little less puny than the cache's the other cheapskates puts on their drives.

Thank you.

[Beardo the Bearded]

That's a little embarassing.

Thank you for the correction. I had always thought the wrong thing. I hadn't even heard of a gibi prefix for measurement until you and the other responder pointed it out.

Re:Thank you.

[MechaStreisand]

No, you had not thought the wrong thing. The computer industry has for years used 1024 to mean 1K. We don't use the revisionist IEC or SI prefixes. Hard drive manufacturers have used the SI prefixes to confuse and screw over their customers, and that's the only real reason anyone's tried to adopt the new standards. But the real problem is with the hard drive manufacturers and their deceitful marketing. If that practice had been made illegal, there'd be no confusion.

I'm not the only one who feels this way.

The 93.5 MB/s transfer rate actually....

[LazLong]

The anonymous moron is repeating the same mistake that the xyz computing article did. Namely, paying too much attention to the interface speed. Current interface technology is capable of pumping data far faster than any single drive is able to achieve. Thus, with SATA being a single device point to point protocol, you need to pay more attention to the drive to buffer speed, not the buffer to host speed. Thus, the theoretical maximum throughput of this drive is limited to it's 93.5 MB/s disk to buffer speed.

Monster?

[harlows_monkeys]

My video card on my gaming PC has 256 MB of RAM. My cell phone has 24 MB. My thumb drives have 128 MB and 1 gig.

16 MB is not a "monster" amount of RAM anywhere except hard drives. Why are they lagging so far behind everything else in this area?

Amazed

[KrAzY MoNsTeR]

I am amazed at the number of people stating this is an uter-crap slashvertisement !
I mean, if this is crap, why even loose 5-10 minutes of your time writing long comments about how crappy this "story" is ? Just move on, nothing to see here

And yet... I did it too !

Quality?

[DarkVader]

For years now, I've recommended that one drive manufacturer be avoided at all costs - Western Digital.

The longest life I've ever gotten out of one of their drives was about a year, and I've had several die within a month of installation. I don't think I've had one last less than 48 hours, so if you only need 2 days of data storage, they might be ok.

Now, because of this, I haven't touched one of their drives (other than to recover data, and then throw it in the nearest trash can) in several years. Have they gotten better?

Or is this another one of their "increased performance" stunts that reduces reliability again?

Re:Quality?

[Anonymous Coward]

Unfortunately their 'quality' must have gotten worse because I just replaces two of them on the SAME RMA cycls...what I cann a 2-car RMS TRAIN, (that's the main drive that went, causing the RMA, one received drive that didn't work at all, then the second received drive)...I've had 3 and 4-car RMA TRAINS before too.
Not only that but their so-called support is slow and inept at best...'we have less than a 1% failure rate so we cannot in good counscience send you another drive until we investigate your system'...yadda...yadda...yadda...
Quite simply they are disposable drives that are meant to break after a whire, thereby to make more sales for them...maybe forced obsolescence or something.
In shore, AVOID *ANY* WESTERN DIGITAL PRODUCT CRAP LIKE THE P;AGUE...Want specifics? I'll give you drive serial numbers, dates, and everything.
For them to be advertising is like big phucking CRAP!!!!

Re:Quality?

[Anonymous Coward]

Be nice, they're the industry leader ..
.. in fail rates.

If ./ can greenlight an anonymous troll singing praises about Western Digital as a headline, twice then it is only fair for this anonymous troll to inform you that of all the HD's he's owned, the only ones to fail were the WD's.

After the 5th time I learned my lesson.
Show them my new motto ?

"Anyone but Western Digital in 2005"

longevity

[Anonymous Coward]

How long will these new drives last in day to day mostly always on mode? That to me is a more important criteria. I'd like a drive I know is good for a decade or more easily than a faster larger one that may or may not last a couple of years.

Two different markets, some folks want a ferrari, I'd rather have a nice diesel that lasts 1,000,000 miles with little maintenance and a very low chance of failure. What are the 1,000,000 mile "diesel" equivalents in the new hard drive market now?

Typo?

[winphreak]

Is it just me, or did the editors get lazy on Thanksgiving. I mean, sure, pie, I'm all for it, but come on!

"The Western Digital Caviar SE16 WD2500KS 250 GB hard drive has 300 MB/sec transfer rate the drive has a monster 16 MB cache,"

Oh, and for the article below, it's Purgatory

WD quality

[Anonymous Coward]

Affordable and fast, maybe, but is it still a standard WD piece'o'shite?

Quantum did it w/ "bigfoot"

[absinthminded64]

Quantum produced a slow large (both physically and in storage capacity) drive to cater to this market. I dont think they went too far.

Re:Quantum did it w/ "bigfoot"

[Overzeetop]

Yes, but at the time, the amount of digial video in the typical computer user's realm was fairly small. With both DV and DVD video easy to get on to disc, and the large quantity desireable now (HTPCs, for example), there is a market that just didn't exist back then.

SATA1 vs. 2 comparison

[lemaymd]

Here's a comparison between comparable SATA1 and 2 drives, although it doesn't really look at link saturation like you mentioned: http://www.cluboc.net/reviews/hard_drives/hitachi/ T7K250/

I have an nForce4 with SATA2 links, but I'm running SATA1 drives. (7K250) I wonder if it still gets 300Mb/s total shared link bandwidth?

Re:SATA1 vs. 2 comparison

[this great guy]

http://www.cluboc.net/reviews/hard_drives/hitachi/ T7K250/

Well this comparison is not really interesting (and I was looking for real-world performance studies, not bench results): it shows a maximum read burst speed of only 135 MB/s for the Hitachi disk (SATA 3.0 Gbps) and 127 MB/s for the Raptor one (SATA 1.5 Gbps), while I have seen other websites' benchmarks reaching more than 200 MB/s during burst transfers in the past. So there is definitely something that went wrong in the hardware or software setup. And I can't say what because the author provide so few technical details... Regarding your question, it depends:

• If you are using a port multiplier supporting 3.0 Gbps SATA links, then the "host-side" link will be running at 3.0 Gbps and the "disk-side" one at 1.5 Gbps.

• If you are using a port multiplier supporting 1.5 Gbps SATA links or if you don't use any, then all of your links will be running at 1.5 Gbps.

But I guess this is what you expected, didn't you ?

Small, fast drives

[joib]

Note to hard-drive manufacturers:

Please come out with smaller (2.5") and faster (10krpm) desktop drives that don't cost a fortune (like laptop and enterprise 2.5" drives), and allow many fast, cool, and quiet drives in a SFF.

When will the desktop market transition to 2.5"? When oh when?

Hard drive cache is a waste of time

[Anonymous Coward]

Think about it: hard drive cache is a bunch of RAM on the far side of the hard drive controller interface, which means you're still limited to the drive controller interface speed, which is never going to be as fast as memory controller (Northbridge/CPU-integrated) interface speeds.

It's a waste of time providing hardware cache on the drive. Far better to use main memory, under control of the driver and OS. Access to that will be much faster. Especially with an OS like Linux, where you don't need to do any cache configuration; it simply uses all available RAM for its cache.

And of course caching will be completely useless for any kind of sustained sequential/streaming usage, such as multimedia recording/playback.

Not quite revisionist

[jabelar]

The confusion stemmed from networking and radio base-10 measurements conflicting with computing base-2 measurements. I do agree that harddrives should conform to computing history (i.e. 1 GB memory should fit in 1 GB drive space), but the IETF did have to come up with some compromise for two **equally legitimate** engineering histories. The networking terms won because they were congruent with general science standards.