Slashdot Mirror

The price is pretty much irrelevant in this case. The fact is that manufacturers such as Seagate are offering 500 GB drives meant for personal use.

http://www.seagate.com/products/personal/barracuda .html

See specifically:
http://www.seagate.com/cda/products/discsales/mark eting/detail/1,1081,705,00.html

The price is pretty much irrelevant in this case. The fact is that manufacturers such as Seagate are offering 500 GB drives meant for personal use.

http://www.seagate.com/products/personal/barracuda .html

See specifically:
http://www.seagate.com/cda/products/discsales/mark eting/detail/1,1081,705,00.html

True, the Plus did not have an internal hard drive... originally. It came with 1MB RAM and one internal 800k floppy. But... I installed an INTERNAL 20MB 5.25" ST-225N Seagate hard drive into it, by mounting it diagonally to the CRT, and soldering the SCSI connections directly to the motherboard. It was great!

Performance-wise it was OK (my previous machine was an Atari ST), but the thing had a great GUI for its OS, and with Lightspeed Pascal graphics was easily accessible.

When I think about those years, I stop even considering complaining about my PBG4 not being fast enough :-)

Close, but still no cigar.

1. It goes into the OS filesystem cache. After 5 seconds the modified data gets flushed to the disk (sometimes set to 30 sec).

That's if the OS is completely unloaded. Sure, maybe after 5 seconds it becomes eligible to flush, and will wait in line right behind anyone else whose turn came up. Is the wait likely to be very long? No. Can it be very long? Bet your data.

2. It is written to the hard drive. Here, it sits in the hard drive controller's on-board cache until the head arrives at the write point, which is a fraction of a second.

That's if the disk is completely unloaded. Modern disk firmware is extremely intelligent about ordering, but they optimize for performance and do not care very much about getting your data out of cache right away. Using NCQ we have observed write latencies on the order of ten seconds. It could probably get even higher, but we'd force a flush rather than letting it get away with that.

3. It is written to disk.

Yup.

--
Dum de dum.

Enterprise class means it's designed to be deployed across an entire enterprise/organization with centralized management, out of the box.

You're awfully generous to the vendors out there. Let's take a look:

Seagate sells "enterprise class" Cheetah hard drives. How one would deploy a hard drive across an entire organization with centralized management does not immediately jump to mind.

Intel makes "enterprise class" chipsets.

Logitech's V500 Cordless Notebook Mouse is apparently a true enterprise-class wireless solution.

I just chose three companies at random and plonked in "site:companyname.com enterprise-class" into Google.

2.2W max

I'm willing to pay a premium for a small, reliably bus-powered USB2 hard drive. However, I need at least 5Gig and come xmas it's possible I'll be needing 8Gig.

Why yes, yes I do. It's the Seagate LD25, 2.5" appliance oriented drive.

Article saying which drive is used.

PDF spec sheet from Seagate.

I haven't been able to dig up any pricing info on the drives themselves. They come in 20/30/40gb capacities.

The most interesting thing on that page was a link to a hard disk encryption software in an ad.

Compare it with the Seagate Cheetah wich offers 96MB/s sustained data transfer rate while the sustained transfer rate is undocumented on the Diamond Max. Same goes for the average seek time that is OK, now I'm comparing two completely different divisions of disks with completely different pricing. My point is that the /. article is a little overrated.

Here's a random 7200RPM Seagate SATA drive. Note that the average sustained transfer rate is greater than 58MB/sec. Most any midrange [7200RPM] drive (UATA/100 or SATA) should be able to sustain 50MB/s at this time, and a 5400RPM drive oughtta be capable of a solid 35-40.

A RAID-1 does have performance benefits on the read side, since the read can be spread out across multiple drives. That said, for overall use, a RAID-5 gives the best bang for the buck. In specialized situations where redundancy and read speed are most important, but capacity is not, a RAID-1 is the cost leader over the capacity afforded by a RAID-10. However, a properly designed RAID-10 with the same capacity will beat a RAID-5 for writes (no pairity calculation), and be faster on reads (more heads), *and* live through at least one drive failure without the same performance degredation a RAID-5 would feel.

Of course, this all varies with the quality of the implementation. Cheap cards are generally cheap because they're not worth much money. Smart programmers aren't cheap. Put those two facts together, and we may have found the performance problem with some of the inexpensive controllers. :)

BTW, yes, I'm primarily working on storage system benchmarking and performance tuning right now. Thanks for asking. ;)

Actually, this drive is a 5 platter design (see here and here), as they are using 100 GB platters. Seagate has announced a 500 GB drive coming in Q3 with 4 platters, which will use (at least) 133 GB platters. (133 GB platters has been used by Seagate for its 7200.8 series of drives. Their 250 GB drive just has two platters!)

Reducing the number of platters have a number of advantages -- including, as you say, reduced heat, reduced power consumption due to a smaller motor, enabling a low-profile instead of a usual 1 inch form factor, and reducing the cramming of platters and heads inside the drive. A disadvantage is naturally that data will be more crammed on to the platters, but all disks with 133 GB platters have worked well for me. Thus, I think I'll wait for the next Seagate drives instead of buying this one.

I have a Seagate 120 GB 7200 rpm IDE drive (ST3120023A) in my Mac that is dead silent.

You seem to be confusing the recently announced Hitachi Travelstar 7K100 (which is already shipping) with the long beforehand hyped Seagate Momentus stuff.

Hitachi just came out with a 7200 RPM 100 GB drive.

Sort of. According to this paper from Seagate, the main differences between SCSI and ATA are:

SCSI drives are individually tested, rather than tested in batch

SCSI drives typically have a 5 year warranty, rather than 1 year for ATA (note that Seagate's ATA drives also have 5 years, and WD's Special Edition -JB ATA drives have 3 years).

SCSI drives usually have higher rotational speeds (i.e. 10K or 15K RPM vs. 7200RPM)

SCSI drives usually make use of the latest technology. ATA uses whatever older technology has been cost-engineered to a suitable price-point

The physical and programming interface

I also suspect that SCSI drives have a larger number of reserved blocks for remapping, and that they remap blocks on read operations when the ECC indicate that a block has crossed some threshold of near-unreadability. This would account for a) SCSI drives' lower capacities and b) a report I had from a SCSI-using friend running BSD who reports that a 'remapping' message turned up in his syslog without needing any special action to invoke.

By contrast, in my experience, ATA drives only remap failed blocks on write operations. Lots of people think that when a drive returns a read error on a file, it's only fit for the bin, but I've forced the remapping to take place by writing to the affected blocks (either by zeroing the entire partition or drive using dd or badblocks -w, or by removing the affected file then creating a large file that fills all unallocated space in a partition, then removing it to reclaim the space).

Nowdays Seagate has a bunch of 15000 RPM drives. Their sustained transfer rates are supposed to approach 100 megs a second.

In my personal experience, I have two 2GB Seagate drives (old!) in my router at home. They've been running non-stop for about three years, and they were recycled from even older desktop machines. To put that in perspective, I've lost 2 out of the four Western Digital drives I've bought within two years, and I've lost more IBM drives than I can count. So I can't recommend Seagate drives highly enough.

http://www.xbitlabs.com/news/storage/display/20031 014160044.html http://www.seagate.com/cda/newsinfo/newsroom/relea ses/article/0%2C1121%2C1555%2C00.html

Also, just partition the damn hard disk if you can't boot off something larger than 137 gig. However, it sounds like a bios problem to me....

Nope

Well here's a link to a 300GB drive from Seagate. A bit pricey though at around $1400US street price. Haven't seen any larger drives for SCSI.

This is seagates 2.5" drive for the server market.
Spins at 10K....

http://www.seagate.com/products/discfamily/savvio/

Hardly. All else being equal, if you double the rotational speed, you double the bulk transfer rate. Also, rotational delay is the major factor in the drive's average seek times.

Bulk transfer rate is more important in most applications

I would contend that seek time is more important for most applications (transaction servers, database access, web servers, booting PCs etc) than transfer rate (used mostly by media-intensive industries).

If it spins twice as fast but has half the density, it has the same bulk transfer rate.

Why half the density? Why not the same density but 50% higher spin (and transfer) rate?

6) interest in SCSI is outdated. SATA with one (competent) controller per disk has better characeristics.

Not according to this article, and others. It's improving, SATA NCQ/TCQ is a big help, but its only advantage is price, still. 10K and 15K SCSI drives have real advantages in both transfer rate and seek times.

Hardly. All else being equal, if you double the rotational speed, you double the bulk transfer rate. Also, rotational delay is the major factor in the drive's average seek times.

Bulk transfer rate is more important in most applications

I would contend that seek time is more important for most applications (transaction servers, database access, web servers, booting PCs etc) than transfer rate (used mostly by media-intensive industries).

If it spins twice as fast but has half the density, it has the same bulk transfer rate.

Why half the density? Why not the same density but 50% higher spin (and transfer) rate?

6) interest in SCSI is outdated. SATA with one (competent) controller per disk has better characeristics.

Not according to this article, and others. It's improving, SATA NCQ/TCQ is a big help, but its only advantage is price, still. 10K and 15K SCSI drives have real advantages in both transfer rate and seek times.

Hardly. All else being equal, if you double the rotational speed, you double the bulk transfer rate. Also, rotational delay is the major factor in the drive's average seek times.

Bulk transfer rate is more important in most applications

I would contend that seek time is more important for most applications (transaction servers, database access, web servers, booting PCs etc) than transfer rate (used mostly by media-intensive industries).

If it spins twice as fast but has half the density, it has the same bulk transfer rate.

Why half the density? Why not the same density but 50% higher spin (and transfer) rate?

6) interest in SCSI is outdated. SATA with one (competent) controller per disk has better characeristics.

Not according to this article, and others. It's improving, SATA NCQ/TCQ is a big help, but its only advantage is price, still. 10K and 15K SCSI drives have real advantages in both transfer rate and seek times.

so we can start using drives like the savvio without those bulky cables. The 2.5" form factor is supposed to allow higher speeds w/ lower power consumption.

Make that both reilabilty and speed for me. PATA/SATA disk are still lagging horribly behind stuff like SCSI disks and their 10k RPM offerings.

PS: If you want reilabilty for cheap, check the Seagate Barracuda series (i own this one) - cheap, VERY reliable and also damn quiet. I can't tell if the thing is running or not by listening to it.

As other posters have mentioned, software raid is fine for RAID 0, 1, 0+1. As you get to RAID 3,RAID 5, and RAID 6, however, your processing requirements go up quite a bit.

A SATA RAID 5 card with hardware XOR engine and a DIMM slot for cache might be a cost-effective option for you. (Goes for ~$180 on Pricewatch, or ~$240 on Dealtime)

Oh, and I would have goine with HGST, Western Digital, or Seagate for your drives... but I suppose hardware failure is what RAID 5 is for :)

I looked on Seagate's web site and according to it, their fastest notebook drive is 5400RPM:
http://www.seagate.com/cda/products/discsales/inde x/1,,,00.html
Not even 7200 RPM. So, it looks like you were just making that up.

>It is too bad that Apple only offers the slower 5400rpm drives in their notebooks.

I agree. I got the Hitachi 7200RPM drive last week and the performance difference is noticeable, though not really twice as fast - more like 50% faster than the 8MB 4200RPM dog that I had before. (Yes, I used benchmarks that were relevant to what I use it for, which is software development.)

The 1600x1200 screen point is perfectly valid. Apple seems to be more interested in widescreen displays than high resolution; even the 17" doesn't have 1600x1200 resolution. This might be because of the pixel size issue (how to fit 1600x1200 in a small form factor) but that shouldn't be a problem with software scaling (96 dpi vs. 72 dpi vs 150 dpi or whatever). You'd see the same amount of content on the screen but it'd be at a higher resolution, and scaled/smoothed in OS software if the individual application wasn't smart enough to adjust itself accordingly.

>And I did mis-mention two of the specs on this model

OK so that's three features you happened to "mis-mention". That kind of undermines your argument when you're trying to explain how behind the leading edge Apple is... your own best example doesn't have those features either.

I did search for about a half hour before posting the grandparent post. I think I would stick with Dell or Alienware personally because I don't mind spending a bit more for support and some assurance of quality from a known vendor. I'm also surprised that IBM, who once carried the torch of very expensive but also very full-featured laptops, doesn't appear to have anything in this class. Oh well.

Warning: I do have a slight AMD bias, as they're in my machine now. But I'm posting anyway.

AMD, and I'm just supposing here, is a bigger customer than caseoutlet.com. Volume buying is advantageous in buying PC components for three reasons: Price, brand, and component quality are now negotiable. Go to https://my.seagate.com/guest to see an example of volume pricing/corporate partnerships in action. Being able to take the volume advantanges to the "target market" is AMD's strategy. Howerver, your parent poster is not part of this target market, which gives caseoutlet's Mini-ITX box some advantages.

1. Quality--I'm supposing, that with more buying power, they get to see the actual data that OEM statisticians use when they come up with that wonderful MTBF number, and get first pick on the drives that thus have higher TBF hours. Not every hard drive that has the same model number has the same failure rate.

2. Brand. According to this article on Cnet, AMD will stock these with Seagate and Samsung Products. From my standpoint, they just tend to be "better" than the random components that fit the general description of "DDR 128MB" or whathaveyou that caseoutlet.com features.

3. Price. The machine you talk about costs $296/$342 vs. $185. $185 is a lot easier for me to afford than than $296/$342, and I'm supposing people the PIC is targeted to think the same. A 10 GB hard drive bought in volume from the manufacturer vs. an 80 GB harddrive bought from a company who went through a distributor who bought from the manufacturer will likely be cheaper. Same with the RAM.

Power usage is another--people in the target markets don't exactly have the same quality electric service as Western markets; therefore every watt you save makes a difference. And the guy running the server might be concerned about how long the box could last on battery backup. The AMD Geode is a low-power version of the Cyrix MediaGX with MMX and 3Dnow. The GX 500 consumes 1.1W of power. The Eden 533 consumes 2.5 - 5 W of power, depending on whether the above link is an ESP or -N. Likely ESP as the -N is more embeddable and what I assume costly. I don't have model numbers so I can't compare the other components individual power usage.

Plus this is AMD's thing, and they're not gonna use a Via CPU in there when they have their own better solution. Moreover, as AMD has their market defined (perhaps too narrowly by not offering an optional RJ45 port), they can stick whatever components that fit that market in the box.

It's all about market, however. Your parent poster, somebody computer-literate in a developed nation, does not seem daunted by the task of getting a non-Windows OS on this working (It will likely be easier on the Eden box). If he's willing to cross demographics, then it's an ideal solution for his needs.

--sean

30 disks in what looks like 3Us of space for 4Gb/s of throughput.

These drives aren't performance laptop drives, they are meant to run 24/7 and get lots of work to do.

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

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

I'm not sure about how much space FFXI needs, but a CF/microdrive slot would probably be able to cope.

The drive was designed in Singapore and manufactured in China. Seagate, once a California company, is now so multinational they barely have US operations. They've closed plants in Ireland, Mexico, Mayalasia, and Singapore because those places weren't low-cost enough.

Here's the ST1 drive manual. Expect a glut of these things in January, once the holiday season business has been fulfilled and the production lines are running at full speed.

I guess with 6 GB RAM each they shouldn't have to do much (or ANY, if I was running this) swapping, and if the jobs are tweaked to not use the hard drives too intensively, they might be OK. If what you do uses the hard drives for much, they are sh*t, to put it mildly. If you could plug these into the blades, they's be very useful, quick machines. But you can't yet.

The really crap thing is, if you do want SCSI drives in the IBM blades, you connect a module ot the side of the blade which gives you a couple of proper SCSI drive bays. Which halves the number of blades-per-bladecenter to 7.

Given the bladecenter is 7U tall, you'd be better off with 7 1U servers with SCSI bays already in and better NIC options. The internal networking of the bladecenter is awful for everything but the simplest low-requirement setups - it's hideously expensive to give each blade a couple of gigabit connections.

Even these cheap little things are 1U, take 2 U320 SCSI drives, and have dual Gigabit connections built-in.

And I *still* can't get USB dongles to work with thes fscking blades, grumble grumble.

Having said all that, when can I play on this thing? My Folding@Home could do with a bit of a boost, and with Hyperthreading I could have 2016 units running simultaneously.... although it might get a little warm behind the racks, 1008 2.8 GHz Xeons pump out a good bit of heat!

I'm guessing it could use Seagate Savvio Drives - 10k RPM, SATA or FC, 36 or 72 GB, in a 2.5" drive designed for servers.

I have no evidence, but they are perfect for this type of application.

Ooops. I was wrong. The headquarters of one division of seagate is in Bloomington, Minnesota (a suburb of Minneapolis/St. Paul): the The Recording Heads operation.

Didn't the article say something about the guy in question being in this division? Maybe because he worked for this division, that's why they're suing him from there.

- Peter

Do read up on some of the fundamentals of RAID: Everything you need to know (and lots you don't) is probably at least mentioned in the PC Guide on RAID. Look through that. Things like hot swap and hot spares are important to understand. Finally, you should remember to check compatability. Unfortunately, I for instance have not been able to find much of anything in the way of controller cards that is compatable with OS X (except the obvious, the XServe RAID). So I have something set up on a BSD box in my server closet that I then link to, more like a storage appliance. Happily, the 3ware cards and many others are now compatable with a wide variety of *nix and BSD flavors along Windows, but do check to make sure.

Last but not least, remember this!: RAID is *not* a backup solution, but an highly redundant onsite storage system. Have another form of backups, even if it is just a RAID 1 off site, or DVD-Rs, or something. If a disaster happens (thieves, fire, nuclear destruction, John Ashcroft) on site storage won't save you.

The press release says:

The new warranty applies retroactively to applicable hard drives shipped since June 1, 2004.

But Seagate's 5 year warranty FAQ says: (http://www.seagate.com/support/service/faq/5year_ warranty.html)

The warranty is retroactive to all eligible drives purchased after 7/1/2004.

I checked the warranty status of a Seagate drive I bought in beginning of June, and it says "Expiration 14-JUN-2005", so the press release is actually a bit misleading.

Read your link again-- it says that distributors will only get return for credit, but that customers can get a replacement drive direct from seagate in years 4 and 5.

From the warranty:

Beginning on the date of shipment to its direct customer and continuing for the published warranty period, Seagate represents that the Products are new or, if they contain remanufactured or used components, are the equivalent of new in performance and reliability and warrants that each Product failing to function properly under normal use, due to a defect in materials or workmanship or due to nonconformance to the agreed upon specifications, will be repaired or exchanged, at Seagate's option and expense.

I don't think he was trolling. Yes, there are no 10k IDE drives. But his point stands: you don't really need a 10k drive (7200 + 8MB cache performance is very close, and quieter) to upgrade your CPU/mobo/RAM to play Doom3. You can do it later, if you like, or better yet wait for the drives with NCQ to see a real performance difference.

I think you based your argument on false, or at least exaggerated assumptions, and the parent post pointed that out without trolling at all.

This thing ran an Oracle database, mail/web servers, did nfs/nis, supported two dozen X-terminals and at least 50 text terminals. We would run out of memory only very occasionally, when people started doing stupid things like run their window manager on the server itself rather than use the one built-in the X terminals.

The machine was not fast, but it ran to the department needs and people weren't less intelligent because of this. Maybe quite the opposite in fact: since you didn't want to compile your progamming assignment every couple lines, people were more considerate about writing quality code in the first place and make use of the resources we had more efficiently. This produced a generation of programmers who were concerned about writing good code.

Today, any a 2GHz+ PC with 1GB+ of ram would put the machine we were using back then to shame in terms of raw computing power and even i/o, with the proper supporting hardware (fast scsi disks, cyclades serial ports board, etc.)

One last thing about Linux IIRC, part of the memory used by programs is actually shared if two or more users use the same application, so memory utilization is efficient in a multi-user setup.

Technically, that statement is correct, of course, but in practice the interface you choose determines the quality of mechanism you can buy with it; SCSI drives are engineered with different cost/reliability/longevity assumptions and tested individually, ATA drives are batch-tested. For more details from the horse's mouth, see This paper from Seagate on the differences.

As it happens, I use quality PATA drives (WD Special Edition, right now) in all my personal systems, so I'm not even a SCSI bigot ;-). I chose WD SEs because the price/performance/reliability was right for me and they are one of the few ranges of ATA drives that still come with a 3 year warranty. Most ATA drives only come with 1 year (especially OEM models) and most SCSI drives come with 5 years.

--

500 GB... hello editors?

In response to a recent article on Slashdot, both the RIAA and the MPAA have announced a partnership with Seagate, Inc.

The details of this new partnership are sketchy, but it seems that it will entail the automated delivery of detailed information on everyone that purchases the new Seagate 400GB SATA hard drive. This comes from the assumption that the only reason anyone would really need that amound of drivespace is to store their growing collection of music and movies. Understandably, downloaders and rippers are tired or poor quality movies and audio, and as such this new drive will allow them to contain all their new high-bitrate media in one central location.

In a related story, the RIAA has officially sued Seagate because this new hard drive gives people the capability to store pirated music on their computers. Said an RIAA spokesman, "We feel this is a gross violation of artist's rights, and that it's our responsibility to protect them."

Well, that's quite a bit higher than my PC's hard drive - if it is also measured over 2 milliseconds. Of course, it could be anything, but I'd guess that they must be fairly sturdy - I've heard complaints about the batteries dying but not the hard drives. Still, some sort of reference to, say, how high above a concrete street/carpeted floor it could be dropped without damaging it might be more helpful.

Finally, note that on modern drives, you can seek all the way across the disk in only about 30-50% more time than you can seek a short seek. Thus keeping your blocks close to the current cylinder but not in it has very limited value. Note that this is not the case on optical (CD/DVD) disks.

Bzzt. Wrong. Thanks for playing.

Seagate Barracuda 7200.7 Plus product manual. This is a modern drive. Look at page 17 of the PDF, section 2.7, "Seek Time". Track to track seek is listed as sub 1ms, while average seek is 8.5ms (for read). Latency (the rotational aspect), which is separate, is an average of 4.16 (as it should be for a 7200 RPM drive). So a short seek is 8 times faster than an average seek, much less a whole-drive seek. So keeping your blocks close to the current cylinder but not in it still has high value.

Additionally, if you can keep your data in the same track, you don't have any seek time, just rotational latency. And the size of track groups has been growing as densities have been growing. So there are lots and lots of blocks in the same track that aren't within readahead range.

And fragmentation is not a bugaboo. It's a fact. When you have random allocation on a volume, it will get fragmented.

Now you misuse the term "random allocation". When talking about disk, random allocation means that you randomly choose your next block--which certainly will cause fragmentation. I think what you are looking for is random file creation. However, under FFS, if you maintain sufficient free space, it is very unlikely that real fragmentation will occur even with random file creation/deletion. Yes, you won't be able to store all of your files contiguously. But as the grandparent points out, the old FFS block allocator finds "nearly optimal" blocks. From the original paper on FFS, you don't get serious fragmentation-related performance issues until you reach 90% disk utilization (there's an '86 FFS paper I can't find an electronic copy of which does a better analysis, but even the '84 paper has the 90% figure). At 90% utilization, nearly every file system ever starts getting severe performance problems due to fragmentation.

You can go back after the fact and unfragment it, but doing so in any serious fashion when writing files actually degrades performance due to the extra effort required.

You should read about log-structured file systems sometime. Like Sprite. The base idea of a log-structured file system (LFS) is that you don't try to keep your blocks the same. You write a log of changes, and stream that out continuously to make maximum use of your available write bandwidth. This has the severe downside of causing horrific freespace fragmentation, since every change to a file means the affected blocks are reallocated, and the old blocks are now garbage. So you have continuous freespace compaction (called segment cleaning in the paper). LFSs didn't catch on because at the time, they needed a large amount of free space compared to more traditional "overwrite" file systems to maintain performance. However, recent work with log file systems shows that the changing performance characteristics of disks (much higher bandwidth but same seek/rotational delays) have tipped the balance to log structuring. Regardless, the cleaning process is precisely going back and unfragmenting your data, and is necessary for a LFS.

HFS+ does nothing to prevent fragmentation except for use super-clusters.

As pointed out by others, Apple's later implementations do defragmentation of smaller files when they are accessed.

NTFS could do this, but I believe they do not. However, NTFS on servers has an allocation block size of 8K

Having worked on many bad HDs, I keep this list of links to all the manufacturers HD testing programs:

Maxtor/Quantum
http://www.maxtor.com/en/support/downloads/powerma x.htm

IBM/Hitachi
http://www.hgst.com/hdd/support/download.htm

Seagate
http://www.seagate.com/support/seatools/index.html

Western Digital
http://support.wdc.com/download/#dlgtools

Fujitsu
http://www.fcpa.fujitsu.com/download/hard-drives/

As most people have agreed, this is a bad mark on IBM's record. I respect them for their pro-Linux attitude (despite the fact it may partially be due to retaliation on MS) and think they have contributed a lot to the field, this is why it's so unfortunate.

Thankfully this problem doesn't effect me as I use almost all SCSI devices, however I have noticed my IBM SCSI drive hasn't quite been up to par recently. And I had to RMA it already once... hmmm. I think I'm sticking with Seagate from now on, I love my ST336607LW. :)

Forget IBM drives, Seagate or Maxtor produce the best quality hard drives