Slashdot Mirror

So I guess the first four drives here don't exist?

Looks like >100gb per disk on SCSI to me.

This will provide the capability for people to store the entire printed contents of the Library of Congress on a single disc drive in their notebook computers

Hm. Storing Internet snapshots(*)? Or, perhaps, using a never-overwriting filesystem that keeps all versions of a file around, or at least a full journal...

(*) Or, for that matter, do as the Seagate press release suggests and store one Library_Of_Congress unit in a notebook computer...

'course, that's if the heating, cooling and laser don't add too much overhead in terms of size, weight and cost. It's not specified in either article.

Even something as mundane as switching to high-resolution uncompressed true-color movies might take advantage of more space. Say, 2048x1536, 24-bit color, 24fps = what, 216MBps required, which should be something like 1.48TB for a 2hr movie. ;)

('course, there's the obvious question of how do you transport that, and whether the drive can sustain sufficient throughput... That kind of network bandwidth available to consumers would probably make Jack Valenti spontaneously combust, but unless newer, far denser DVDs or a suitable replacement media appeared, uncompressed video ain't too useful to him.)

This isn't reporting, it's reprinting a press release verbatim. Jebus. Here's the original, from Seagate's site.

Hard drive testing programs:
IBM -- Drive Fitness Test
Maxtor -- Powermax
Western Digital -- Data Lifeguard Tools Utilities: DLGDIAG
Seagate -- SeaTools
Fujitsu -- Diagnostic Tool
NOTE: Some of these tools may work with all drives, but this (free) collection should cover quite a few drives.

Check out this PDF, it's quite interesting.

Don't forget about LTO drives. Yes, they're very expensive, but they're advertised as being able to backup ~ 50GB/hr. Their capacity is rated at 100GB native/200GB compressed. At these rates, it would take, ideally, a little over 4 hrs. and 1 - 2 tapes (depending on compressibility of the data) Considering that the LTO tapes are $75 - $100 each, it might make sense to have a DDS3 or DDS4 drive in addition to the LTO. This would allow you to store your differential/incremental backups to the smaller device rather than wasting money and capacity by using the larger LTO tapes for relatively miniscule amounts of data. You should be able to find one of those smaller drives for just a little more than a weeks worth of LTO tapes. Obviously, if you're changing more data than fits on the smaller tapes then forgo the smaller drive. A drool worthy tape drive: Seagate's LTO Drive

the right place is to point to ST3120023AS and not ST3120023A

The noise ratings at Storage Review are interesting..
The Seagate Datasheet for the Barracuda IV shows 25dB idle noise.

I have one 40GB and one 80GB Barracuda drive, they are very quiet, I have to get very close to the system to hear them. The sound of the 40GB drive is easily drowned out by the tiny 150W PSU fan on the power supply.

I personally like the sound of my hardware revving up. It gives me this really Tim the Tool Man Taylor masculine feeling.

My home server runs on a pair of old 4.3GB Seagate Barracudas, striped with LVM. They're jumpered to spin up only when the SCSI controller first "pings" them at power-up, so one starts up a few seconds after the other. The effect is almost like the engines on an airplane spinning up...and that's the way (uh-huh uh-huh) I like it...:-)

>maybe one day they'll figure out how to make dual read heads with independent actuator arms (i.e at 0 degrees, and at 180 degrees) on the same platter.

The Seagate Barracuda 2HP used dual read/write heads to achieve blazing (for that time) performance - 2HP is short for "Two Heads Parallel".

See also this page, which has a write-up on the 2HP and why the concept ultimately did not catch on, as well as some other examples of unusual disk technologies.

In addition, HD designers are not easily going to overcome the fact that it takes a while to move the head from the inside to the outside of the platter.

They haven't exactly been making much progress here, either. Compare the seek-time specs for the Seagate ST15150W, one of the first 7200rpm hard drives, to the Western Digital WD1200JB, one of the most advanced IDE hard drives currently available. The ST15150W (Barracuda 4) has been around for years, but it still boasts faster track-to-track, full-stroke, and average seek times. IME, while the sustained data rate from the 'Cudas isn't that impressive (I measured about 6 or 7 MB/s from them once), it'll still deliver better small-file and medium-file performance than many newer drives...especially IDE drives, and especially if you have lots of scattered accesses going at once.

If you have the money for SCSI or Fibre Channel, you can get faster seek times with current products (the ST336752LW boasts a 4-ms average seek time and a full-stroke seek time faster than other drives' average seek time...being a 15krpm drive also doesn't hurt :-) ). Migrating this kind of performance into desktop IDE hard drives would make more of a difference than ATA133.

In addition, HD designers are not easily going to overcome the fact that it takes a while to move the head from the inside to the outside of the platter.

They haven't exactly been making much progress here, either. Compare the seek-time specs for the Seagate ST15150W, one of the first 7200rpm hard drives, to the Western Digital WD1200JB, one of the most advanced IDE hard drives currently available. The ST15150W (Barracuda 4) has been around for years, but it still boasts faster track-to-track, full-stroke, and average seek times. IME, while the sustained data rate from the 'Cudas isn't that impressive (I measured about 6 or 7 MB/s from them once), it'll still deliver better small-file and medium-file performance than many newer drives...especially IDE drives, and especially if you have lots of scattered accesses going at once.

If you have the money for SCSI or Fibre Channel, you can get faster seek times with current products (the ST336752LW boasts a 4-ms average seek time and a full-stroke seek time faster than other drives' average seek time...being a 15krpm drive also doesn't hurt :-) ). Migrating this kind of performance into desktop IDE hard drives would make more of a difference than ATA133.

I hunted all over the net looking for benchmarks of SCSI systems versus IDE systems, and couldn't find a damn thing. Sure, people benchmark SCSI hard drives versus IDE hard drives, but nobody ever bothers to benchmark SCSI RAID versus IDE RAID.

I got so sick of it I said what the hell, and ordered up a pair of raid arrays for doing my own tests.

Test system configuration:
Supermicro P4DP6 Mainboard with two Intel Xeon 2.2GHz processors, and 4GB of memory.
Microsoft Windows 2000 Server

No I did not have time to test this under Linux before I had to get these bad boys ready for prouction. I doubt the benchmark results would have been much different, I've seen 3Ware running under Linux at Linuxworld and they kick some serious ass.

IDE setup:
3Ware Escalade 7450 Raid Controller
Three Seagate Barracuda ATA IV Drives (7200RPM 9.5ms access time)
This was set up in a RAID5 configuration.

SCSI Setup:
Mylex AcceleRAID 352 Raid Controller
Three Seagate Cheetah LVD160 Drives (15,000RPM 3.6ms access time)
This was also set up in a RAID5 configuration.

Benchmarking utility used:
HD Tach 2.52

Here's the bottom line I got out of my benchmark tests.

SCSI Performance
CPU Usage: 2.1%, Access time 6.1ms
Read Speed: Max 37.6MB/s Min 11.6MB/s Avg 30.8MB/s
Write Speed: Max 8.5MB/S Min 5.4 MB/s Avg 7.5 MB/s

IDE Performance
CPU Usage: 3.1%, Access time 14.2ms
Read Speed: Max 31.8MB/s Min 4.3 MB/S Avg 18.3MB/s
Write Speed: Max 48.7MB/s Min 12.3MB/s Avg 36.4MB/s

I was a bit shcoked to see the IDE do so well. It annihilated the SCSI in terms of sheer write performance but lagged behind a bit from the read performance. CPU use isn't a factor for most people, who really cares if you lose 1% more of your CPU to the IDE compared to the SCSI.

Those 15,000 RPM drives were loud as jet engines, and they got hot enough that I was thinking of cooking some bacon strips on them. They were too hot to touch. The IDE drives on the other hand were barely audible even with the case off, and remained completely cool to the touch through the whole test without even a fan on them. You tell me which of those two types of drives is going to have a longer MTBF...

I didn't even use high performance IDE drives for that test. I'd also like to point out that the Mylex card was 66MHz/64bit, whereas the 3Ware card was 33MHz/64bit... so the 3Ware card was holding its own even though it was running at a slower rate of speed. I wonder what will happen in future generations of these controllers when they turn up the speed and improve the code...

Cost... I coul have built three of those IDE Raid systems for the price of that one SCSI system.

Space... The IDE drives were 80GB, the SCSI were 36GB. IDE owns SCSI in terms of space. We have some bigass databases where I work so that's actually fairly important to us.

Unless you REALLY need that 6.1ms access time or the extra ~20% in read performance you are far, far better off with an IDE Raid at this point.

The guys at Toms and Anandtech really need to do a major article on this stuff...

For the skeptical, here's a link to the screenshots of the HDTach benchmarks I ran. Be GENTLE guys we do not have tons of bandwidth for this...

IDE vs SCSI

IDE is on the top, SCSI is on the bottom. Interesting how SCSI is fairly linear but IDE is really sloppy and just running all over the place.

I hunted all over the net looking for benchmarks of SCSI systems versus IDE systems, and couldn't find a damn thing. Sure, people benchmark SCSI hard drives versus IDE hard drives, but nobody ever bothers to benchmark SCSI RAID versus IDE RAID.

I got so sick of it I said what the hell, and ordered up a pair of raid arrays for doing my own tests.

Test system configuration:
Supermicro P4DP6 Mainboard with two Intel Xeon 2.2GHz processors, and 4GB of memory.
Microsoft Windows 2000 Server

No I did not have time to test this under Linux before I had to get these bad boys ready for prouction. I doubt the benchmark results would have been much different, I've seen 3Ware running under Linux at Linuxworld and they kick some serious ass.

IDE setup:
3Ware Escalade 7450 Raid Controller
Three Seagate Barracuda ATA IV Drives (7200RPM 9.5ms access time)
This was set up in a RAID5 configuration.

SCSI Setup:
Mylex AcceleRAID 352 Raid Controller
Three Seagate Cheetah LVD160 Drives (15,000RPM 3.6ms access time)
This was also set up in a RAID5 configuration.

Benchmarking utility used:
HD Tach 2.52

Here's the bottom line I got out of my benchmark tests.

SCSI Performance
CPU Usage: 2.1%, Access time 6.1ms
Read Speed: Max 37.6MB/s Min 11.6MB/s Avg 30.8MB/s
Write Speed: Max 8.5MB/S Min 5.4 MB/s Avg 7.5 MB/s

IDE Performance
CPU Usage: 3.1%, Access time 14.2ms
Read Speed: Max 31.8MB/s Min 4.3 MB/S Avg 18.3MB/s
Write Speed: Max 48.7MB/s Min 12.3MB/s Avg 36.4MB/s

I was a bit shcoked to see the IDE do so well. It annihilated the SCSI in terms of sheer write performance but lagged behind a bit from the read performance. CPU use isn't a factor for most people, who really cares if you lose 1% more of your CPU to the IDE compared to the SCSI.

Those 15,000 RPM drives were loud as jet engines, and they got hot enough that I was thinking of cooking some bacon strips on them. They were too hot to touch. The IDE drives on the other hand were barely audible even with the case off, and remained completely cool to the touch through the whole test without even a fan on them. You tell me which of those two types of drives is going to have a longer MTBF...

I didn't even use high performance IDE drives for that test. I'd also like to point out that the Mylex card was 66MHz/64bit, whereas the 3Ware card was 33MHz/64bit... so the 3Ware card was holding its own even though it was running at a slower rate of speed. I wonder what will happen in future generations of these controllers when they turn up the speed and improve the code...

Cost... I coul have built three of those IDE Raid systems for the price of that one SCSI system.

Space... The IDE drives were 80GB, the SCSI were 36GB. IDE owns SCSI in terms of space. We have some bigass databases where I work so that's actually fairly important to us.

Unless you REALLY need that 6.1ms access time or the extra ~20% in read performance you are far, far better off with an IDE Raid at this point.

The guys at Toms and Anandtech really need to do a major article on this stuff...

For the skeptical, here's a link to the screenshots of the HDTach benchmarks I ran. Be GENTLE guys we do not have tons of bandwidth for this...

IDE vs SCSI

IDE is on the top, SCSI is on the bottom. Interesting how SCSI is fairly linear but IDE is really sloppy and just running all over the place.

The only 7200RPM SCSI drive made these days is the Seagate Barracuda, which is $300 for 36GB: $8.33/GB.

You should really see the The Barracuda 180 w/16 MB cache it rocks. We built a little media server with 9 of these in a RAID 5 array with a tenth for a hot spare. 1.4 TB, 250 users have access and it just zips along.

Granted it is $1800.00 per drive, but it is a far cry from 36 GB.

Love looking at the history of technology and all that, but what about looking into the future?

We've got holographic drives coming soon for your digital cameras. We've got more space than you know what to do with.

With IBM out of the picture, the microdrives of the future will have to come from somewhere else.

Where? Whom?

In other news, three project submissions by Seagate Technologies, codenamed "U Series", "Barracuda" and "Cheetah X15", and one submission by Plextor (codename "40X") were rejected by the science committee. In a joint declaration, the spokespersons of the two companies declared that "We are deeply dismayed that such an outdated technology has been chosen in place of our state-of-the-art submissions."

The speaker of the science committee was not available for comments.

I don't know of any such resource, but there's surely sufficient users here to form an idea of what to buy and what not to, just from their experiences.

Only last week I was agreeing with fellow LinuxSA members that Seagate, Fujitsu, and IBM drives are reliable, and Maxtor and Western Digital drives are not. The last-mentioned brands seem far more likely to seize or develop bad clusters after a few years of use.

I also does not seem coincidental that larger reputable companies seem to sell those drives perceived to be reliable and smaller "iffier" companies (such as those marketing only on cost) seem to sell those drives perceived to be unreliable.

I also took mine apart this afternoon and I wasn't able to get the hard drive to work connected to my PC either. BIOS would always give a "Drive error" message, and Linux: "Cannot read partition table" ...

In mine, however, the hard drive is a Seagate ST310211A (http://www.seagate.com/support/disc/ata/st310211a .html) with a sticker on the drive "Firmware 6.55". Maybe they modified the firmware in some way, just a thought.

I also took pics but I don't have enough bandwidth on this measly adsl connection to be slashdotted ;)

SCSI is dead.

For most consumer and single-user environments, IDE is plenty fast enough. Even in the small server market, IDE is adequate.

SCSI won't be around as a serious disk option for much longer, I suspect.

(The storage I use at home is a mix of IDE and SCSI. The x86 boxen got IDE because it was cheap (though the 100GB Western Digital I bought recently is now in a FireWire case so I can schlep it between home and work). The Apples (a IIGS and a Mac Quadra 610) got SCSI because it's what they expect. I'll be building a "new" server soon with a pair of P!!!-500s that was given to me...the motherboard I bought for them has onboard UW SCSI, so I might snag a Barracuda or three from the local used-parts place and see how Linux runs on SMP.)

Not to mention that USB has killed SCSI for things like scanners.

(FWIW, I have lots of stuff that plugs in through serial, parallel, or SCSI. I even have a device now that uses FireWire (a hard drive, and I'd strongly consider a DV camcorder over VHS-C or 8mm, if I needed one). I've never bought anything that used USB, though...already had a nice SCSI scanner, SCSI Zip, various AT/serial/PS/2 keyboards and mice, etc.)

The 80GB ones are a little hard to find, but 40GB are available for just over a hundred bucks.

Game boxes will be very quiet in the future because they're going to have PVR functions and what not, and you don't what your box drowning out the T-vision.

I'd like to see some actual work put into researching a quiet box. How about using Seagate's U series drives which is actually designed for home entertainment applications?

(By the way -- how exactly does aluminum dampen noise? Gotta dig out that physics book again dammit...)

1. Hard drive. Obviously he didn't do much research into quiet hard drives. First, a quick scan of hard drive reviews at Tom's Hardware suggests that Fujitsu drives are usually the most silent. However that is not the glaring mistake: missing the Seagate Barracuda IV is.Besides being faster than any 5,400 rpm drive it is also the quietest drive ever. You literally have to press your ear against it to hear it.
   
2. Holy Case. Sure some people might think it looks cool (I think it looks about as cool as cutting a big hole in the hood of a car). But it can't be quiet. If this really was a "quiet" machine then wouldn't he have chosen a quiet case? Perhaps something with extra thick sides and few rattling parts (thumbscrews?).

It's not Anand, Its just a direct copy of Seagate's own news release. http://www.seagate.com/cda/newsinfo/newsroom/relea ses/article/0,1247,1156,00.html

It actually appears to be a pretty much verbatim copy of the Seagate press release (Well, at least the online version)

It's a huge old 486 server case with room for 6 FULL HEIGHT drives (ahh, the days when seagate made 1.7gb scsi2 drives that take up the space of 2 cdroms...), 8 or 9 card slots and ~20 ports for db9/db25 ports. It's got my secondary DNS/IRC server in it now, but I'd gladly trade it for another AT case. I sure don't need all the space for a machine with 2 NICs and a video card. The power supply might not be adequate for your needs, but it is a 350W.

I only used DOS for the time it lasted (single line, anyway), with as low as a 2MB 12-Mhz 286 with an old 5 1/4" 40MB Seagate (ST-251N) MFM Hard Disk (the N was the 28MS version, not the 40MS :) with mono HGC like card for disply.

Sounds like the system I built in early '91 (or was it '92?) to run my BBS, only I snagged a 125-meg drive from another sysop in town pretty cheap (I thought $200 for an ST-1144A was cheap, anyway).

BTW, the N suffix on a Seagate drive means it's SCSI, not MFM. This page on Seagate's website describes the ST-251N. Maybe you meant ST-251, which was MFM.

Crystal Reports can be integrated into your application itself as well and features a killer report designer and query builder interface and great printed reports. Crystal Reports can publish report datastraight to the web as well. For more information, check out Seagate's web site.

Business Objects is very popular for its interactive report functionality, where you can drill down into your query getting different levels of information. It helps you avoid information overload in large reports and is generally the tool of choice for doing crossreporting on related queries. For more information, check out Business Object's web site.

-Pat

What about InfiniBand, which all the major PC hardware design people seem to be involved with? This takes a "switched fabric" approach to linking function blocks together, via Switches (which is where Brocade hopes to be the next Cisco). Need more CPU power or more memory? Hot-plug a module into the Infiniband Switch. Version 1.0 of the spec. is available for download at the site, for those interested.

The successor to IDE is already on the way: Serial ATA. Reportedly, PC makers like it because the thin cables allow them to build smaller systems with better cooling. V1.0 is not going to be much faster than UltraATA/100, but they say there's room for growth there.

Plus, you can have fibre channel (not fiber) hard drives right now, from Seagate (example), IBM (example), etc., and the big storage guys are heading that way too. Fibre Channel doesn't always mean Optical - these drives use a 40-pin "copper" connection, which can be a cable or a backplane (for hot-plugging). The SCSI-3 protocol is carried over the Fibre Channel interface, meaning that with a FC driver loaded, the drives look like SCSI devices.

Anyone see a trend here? It's the end of the parallel interface in all its forms, much as USB and FireWire are replacing the humble parallel port...

Alternatively, store all of your important data on a Conner CFS1275A. Probably one of the worst drives ever built. Had no less than five of them die on me in one week. Just wait for the "thunk-thunk-thunk" sound, and you're all set.

The guy is obviously a fiend... cjsnell said it best here =)

Why buy it when it's easy enough to build if you have fairly decent skills at soldering? The core components you need are:

QLogic QLA2100 FC card
FC hdd (ST19171FC - 9G or ST318304FC - 18G) just two examples
'T-Cards' (which you can manufacture quite easily)

More info available from the links in my above post "Looks like they ripped someone off"

The guy is obviously a fiend... cjsnell said it best here =)

Why buy it when it's easy enough to build if you have fairly decent skills at soldering? The core components you need are:

QLogic QLA2100 FC card
FC hdd (ST19171FC - 9G or ST318304FC - 18G) just two examples
'T-Cards' (which you can manufacture quite easily)

More info available from the links in my above post "Looks like they ripped someone off"

As a result, when you turn the drive on and off regularly, it should last much longer and wear less, according to Maxtor. The company rates the drive for at least 50,000 on/off cycles with a component design life of at least five years.

Maybe I just got lucky, picking a couple drives at random from these sites? Maybe a "Contact Start Stop" is different from Maxtor's new 50000 "on/off cycles" ??

I tried to look up the similar spec for my little Hitachi DK23AA-12 laptop drive, which I've abused in so many ways while working my my little homebrew mp3 player (ok, shameless plug)... but Hitachi doesn't seem to have a spec about the number of times you can start/stop the drive. Just for one last try, I pulled up one of IBM's laptop drives, the Travelstart 20GN (page also covers larger models), and they have a spec of 300000 "Load/unload cycles". I wonder if a "load/unload cycle" is similar to a "contact start stop".

Sometimes I wonder if hard drive specs (other than formatted capacity) really mean much anyways.

What are the differences between Windows Me and Windows 2000?

Windows Me is structurally based on the 16-bit DOS (Disk Operating System) code base, although it is a native 32-bit operating system. The underlying technology of Windows Me is very similar to the software platform on which Windows 95/98 was built. Windows 2000, in contrast, was designed from the Windows NT software platform, and on a completely different code structure. Windows NT and Windows 2000 are native 32-bit operating systems built upon a 32-bit code base.

Our company bought 4 of them about 3 months ago, for use as a file cluster. Seagate makes the ST173404LW. They're Ultra160, 10k RPM, and great for speed, but cost us around $1700 each.

These are often merged in a single tool, but concatenation of disks is not strictly speaking a RAID function.

This is wrong, in the begining, RAID was meant to concatenate disk sizes. Rendundant Array of Inexpensive Disks means that many small disks are cheaper than one big disk.

As for mainboards, the Abit KA7-100 is out and new chipsets will support ATA/100 as well (like the SiS730s).

We're still waiting...deeply buried in their Web site (or maybe not) is a quiet mention that the drives are expected out Q1 or Q2 of 2000.

So, it's nice to see the advance to 15KRPM, but this doesn't mean you'll be able to buy one anytime soon! Seagate seems to savor the big announcement about new tech waaaayyyy in advance of when you will actually be able to buy it.

I have a Seagate 10,000rpm disk that pulls 27mB/sec easily on the bonnie test. And that's with a tagged queue depth of only 8 on a UW controller. The drive supports LVD and much deeper queues, so I'm sure it can go even faster.

Sure, faster disks are going to be nice. But they're going to be pretty demanding on the bus. If a 15,000rpm disk is even 50% faster than a 10,000rpm disk, there's not room for many neighbors on a LVD bus. Forget UW SCSI - it'd be a bottleneck with even one of these disks. Looks like it's finally time to break out the fiber...

i'm always bugged when a press release garners more attention than real products. seagate makes 50G drives today. you can get them today here .(also they have some drives which are slightly less than $10/G) or read the specs on the 50G here .

cool -- large, but cool.

i'm always bugged when a press release garners more attention than real products. seagate makes 50G drives today. you can get them today here .(also they have some drives which are slightly less than $10/G) or read the specs on the 50G here .

cool -- large, but cool.

People don't realize how many tehnical companies are up around these parts: and I will kick anyone's ass who says this town is cold-- as soon as I get my tongue removed from this flag-pole... But seriously: There are a lot of hi-tech companies around here: Seagate, Digi International, SGI, Comtrol, and of course IBM (Rochester, MN). South Dakota had the "Silicon Prairie," we have the "Technical Tundra." I'm going out for ice-cream... -AP (Minnetonka, MN) [Min-uh-TONG-ka]

And of course, a single drive can't pump data through a slow FireWire bus any faster than it can a fast SCSI bus. ;^)