Seriously, there is no viable alternative to SATA or SCSI?

theplanb

Golden Member
Jan 12, 2001
1,239
0
0
I mean they've been around for ages. HDDs are easily the pick of the bottleneck in real PC performance IMHO.
If CPUs speed can be improved that fast, why not HDD? C'mon.. I hear about failed HDDs, noisy HDDs, bulky HDDs, all the time. And no one seems to do something about it.. I was really disappointed that the next generation of HDD is.. SATA.. how much improvement is that.

Of course, people will argue that HDDs don't need to be that fast. Maybe so. But I want, instant access on my files. Instant read and write of the files. I want the PC to be on and off instantly. I'll be really happy on the day when HDDs disappear completly..
 

AndyHui

Administrator Emeritus<br>Elite Member<br>AT FAQ M
Oct 9, 1999
13,141
17
81
The problem is mechanical moving parts. You can only physically move a chunk of metal (arm and read head) around so fast before you run into heat and noise issues.

Anything which requires mechanical movement is going to fail at some stage. CPUs, RAM, etc, don't have any moving parts and are not subject to these constraints.
 

sswingle

Diamond Member
Mar 2, 2000
7,183
45
91
SATA is going to get a lot faster. Also, hard drives have been getting quieter all the time. On my last set of hard drives, I could always hear the drive when it was being accessed. I can only hear my drives now if I put my ear right up next to the case.
 

oldfart

Lifer
Dec 2, 1999
10,207
0
0
Andy is correct. HDD is a mechanical device. Until we have a large capacity solid state storage device, improvements will be slow. It hasn't been that bad. Modern HDD's are dramatically faster than they were a couple of years ago,
 

tallman45

Golden Member
May 27, 2003
1,463
0
0
This problem of the disk subsystem being the choke point of any system has been going on for many years "before" the Pc was even invented. Old mainframe systems drives known as DASD were the same weak link to performance. Even Solid state disks will be the slowest components in your system. For example look at digital camera's. You can get a real spinning drive (IBM Microdrive) or solid state compact flash, using either still means that you have to wait till your data (image) is written to the media.

For instant on, try to use sleep mode, and boot only periodically
 

FishTankX

Platinum Member
Oct 6, 2001
2,738
0
0
Now, you're getting 2 things mixed up.

Hard drives, are the devices that read/write data to and from the system. It's amazing that they've progressed as far as they have. Unfortunately, there are only 2 major factors you can improve on in a hard drive.

1. Spindle speed - This depends on motors, and spindle speed decreases the size of the hard drive because the faster you spin it the lower density you need to maintain 100% accuracy in reads and writes. This boosts seek time and transfer rate, at the cost of data density.

2.Ariel density - This depends on the head and disc technologies, and increases the density of the data on the disc. This, while independent from spindle speed, together with spindle speed determines the size of a hard drive, per platter. It also determines the transfer rate of a hard drive, because with higher data density more data can pass under the heads per revolution.

This is the thing that determines the hard drive speed.

The next thing is interface. This is what SATA and SCSI. This is an entirely different beast, and is equivalent to a protocol that allows the hard drive to talk to the rest of the system. This could be regarded as a language, per say.

SCSI - Allows a maximum of 320MB/s per channel, at this time. SCSI is designed for workstation and server use and allows people to hook up as much as 20 devices per channel, and allows each device to queue commands from the system, to move data independent of the CPU *AND* to move data to and from other devices in the channel without dragging down anything else. This is because each device on the chain has it's own controller and thus can move data around by itself without the SCSI controllers intervention. While SCSI is only an interface per se, the hard drives that are designed for this interface have certain characteristics inherent to 'Heavy duty' and 'Work environment'.

First of all, these drives can be more expensive. Since they're for a work environment, where people get tremendous salaries and their productivity or the stability of systems critical to the company is at stake, they can and will afford to use the newest technologies in spindle speed, and since they generally don't need to store massive massive amounts of data, they use smaller platters to enhance seek time (Since the platter is smaller, the head has to move less far to get between the first and the last point on the disc. The disadvantage is that at the same areal density a smaller platter will hold less than a larger platter) as well as faster spindle speeds. The result is that SCSI hard drives hold significantly less than their IDE counterparts. Since IDE hard drives don't have massive speed requirements in the seek time department, they use larger platters (larger platters) and lower spindle speeds, to enhance data density and (consequently transfer rate). The disadvantage of this is that SCSI hard drives also can move smaller chunks of data around at significantly higher speeds than IDE, due to higher spindle speeds and smaller platters, while maintaining equal or significantly higher transfer rates due to the monstrous spindle speeds that they employ.

Serial ATA - Serial ATA was designed to solve a few problems regarding the IDE interface. First of all, the signaling was getting complicated (Needed too high of a voltage) as well as such massive cables, problems with sharing the bus with other devices slowing down the system, the need for command queuing, and much much more. Again, this is only the way that the system talks with hard drives. While it's nice to have every single device in the computer register as a master (something impractical with IDE interfaces) due to the fact that each cable connection is it's own master (Hence the 'Serial' ATA name) as well as smaller cables, ultimately the 'Performance' of the drive is very rarely bottlenecked by the ATA interface. Thus, Parallel ATA Is going to be bottle necked the same way IDE is.

IDE is built to satisfy consumers. Consumers want two things. More storage space, higher transfer rates, and cheaper price. Everything that was important with SCSI, save the higher transfer rates, is thrown out the door. Thus, they compromised SCSI to get the things that IDE users desired.

First of all, the cost was to high to allow controllers on everything so they threw out the SCSI interfaces 'controllers on everything' deal. This makes IDE significantly more stressful on the system than IDE under high workload situations, but who actually puts a huge workload on the IDE subsystem all the time? Very few users would run into the inherent downfall of the lack of onboard controllers.

Second of all, to succeed in more space for less money, they went with bigger platters (bigger so as to increase the sizes of the platters, without compromising seek time too horribly) to store more space. They also put more research into areal density with less emphasis on validation and testing to make sure it was completely safe. As long as it handled well under the normal PC environment with medium to medium heavy workloads it did okay. Normal IDE hard drives will not be subject to 24 hour workloads of 100% utilization so they don't need to conform to SCSI standards.

Second of all, lower spindle speeds were employed, because to the average consumer, trading heat, noise, and smaller sizes for faster seek times does not seem like a good trade. And for many, it isn't. (They don't care about how fast office loads. They want to be able to store more video and have a cheaper hard drive. Spindle speeds increase the cost of the hard drive.) So they went with lower spindle speeds than SCSI (Current generation being 5400 and 7200 versus 10,000 and 15,000 (And soon to be 17,000) ) to increase data capacity (remember that higher spindle speeds meant less space?) as well as give them something that allowed them to decrease the heat and noise of the drive.

That's just about it.

Just remember, you can easily shrink a chip to decrease the distance in-between two points and make it run faster. Lower voltages, less power, faster speeds. But increasing the areal density, transfer rate, and seek time of a hard drive is significantly harder. Anything mechanical, as the others have, have inherent tolerances much lower than electrical devices. Just think about it this way. Hard drives have progressed significantly faster than cars have. Or optical technology. (CD/DVD ROMs and burners).

As a general rule of thumb, electronic devices increase an order of magnitude faster than mechanical devices.
 

rade

Junior Member
Mar 22, 2003
23
0
0
Solid state flash media are plagued by a limited nr of rewrites before failure as well as slow read/write speeds, so it's questionable how useful they would be as a general purpose storage media. The real breakthrough cold come in the form of MRAM, magnetic RAM memory, which is solid-state, offers lightning-fast data access and is non-volatile (retains data after power off). It will take some time though before we'll see it in sizes appropriate for hard-drives, but it will probably appear soon as RAM memory and USB storage devices...
 

AndyHui

Administrator Emeritus<br>Elite Member<br>AT FAQ M
Oct 9, 1999
13,141
17
81
Heh. If you think hard drives haven't come far, I'd suggest you try going from a WD 10K Raptor to a Quantum Bigfoot 2.1GB.

Then we will all be able to hear your screaming from here. :p
 

FishTankX

Platinum Member
Oct 6, 2001
2,738
0
0
Originally posted by: rade
Solid state flash media are plagued by a limited nr of rewrites before failure as well as slow read/write speeds, so it's questionable how useful they would be as a general purpose storage media. The real breakthrough cold come in the form of MRAM, magnetic RAM memory, which is solid-state, offers lightning-fast data access and is non-volatile (retains data after power off). It will take some time though before we'll see it in sizes appropriate for hard-drives, but it will probably appear soon as RAM memory and USB storage devices...

*AHEM!*

The largest MRAM they have been succesfull in fabricating is 512K.

It's a *long* way off. I doubt MRAM devices will *ever* be in sizes that will be apropriate for mass storage. What I could see happening, is an MRAM cache on a harddrive.
 

Agamar

Golden Member
Oct 9, 1999
1,334
0
0
I think what will eventually happen is you will get SATA drives with ~64 to 128M of ram on them caching the data it *thinks* you want next. Already have a laptop drive out that has 16M, and my IBM Deskstar has 8 on it.
 

FishTankX

Platinum Member
Oct 6, 2001
2,738
0
0
Originally posted by: Agamar
I think what will eventually happen is you will get SATA drives with ~64 to 128M of ram on them caching the data it *thinks* you want next. Already have a laptop drive out that has 16M, and my IBM Deskstar has 8 on it.


Can't use RAM caches that large because if you ever loose power you've just lost 64MB of data. Or 128MB of data.

For laptops, such large caches are practical because the chances of a power outage is 0 to none.
 

Grminalac

Golden Member
Aug 25, 2000
1,149
1
0
Originally posted by: FishTankX
Originally posted by: Agamar
I think what will eventually happen is you will get SATA drives with ~64 to 128M of ram on them caching the data it *thinks* you want next. Already have a laptop drive out that has 16M, and my IBM Deskstar has 8 on it.


Can't use RAM caches that large because if you ever loose power you've just lost 64MB of data. Or 128MB of data.

For laptops, such large caches are practical because the chances of a power outage is 0 to none.


Well I do see this occuring, manufactuers will just have to include backup power units to allow the memory ample time to write to the hard drive or some other method. Imagine speed increases provided by caches of one gig greater in size.
 

wetcat007

Diamond Member
Nov 5, 2002
3,502
0
0
Hard Drives cant be improved on to a cetrtain point unless they are replaced with large scale flash memory.
 

FishTankX

Platinum Member
Oct 6, 2001
2,738
0
0
Originally posted by: Grminalac
Originally posted by: FishTankX
Originally posted by: Agamar
I think what will eventually happen is you will get SATA drives with ~64 to 128M of ram on them caching the data it *thinks* you want next. Already have a laptop drive out that has 16M, and my IBM Deskstar has 8 on it.


Can't use RAM caches that large because if you ever loose power you've just lost 64MB of data. Or 128MB of data.

For laptops, such large caches are practical because the chances of a power outage is 0 to none.


Well I do see this occuring, manufactuers will just have to include backup power units to allow the memory ample time to write to the hard drive or some other method. Imagine speed increases provided by caches of one gig greater in size.

How big of a backup power unit would you need to sustain 30 watts of power to the harddrives for 5 seconds? That's alot of powerdraw. Not very practical for a battery, unless it was a NiCD. Then you would need chargers onboard. Yuck.

The gain you would get with 1 gig of harddrive cache would be akin to the gains you would get with 1GB more of system RAM, probably less. You don't need that much cache, as the place where cache benefits is sequential reads/writes which tend not to be massive anyways. Cache is a huge benefit when you've got a lot of small files. Large files benefit more from transfer rate.
 

rade

Junior Member
Mar 22, 2003
23
0
0
Originally posted by: FishTankX
Originally posted by: rade
Solid state flash media are plagued by a limited nr of rewrites before failure as well as slow read/write speeds, so it's questionable how useful they would be as a general purpose storage media. The real breakthrough cold come in the form of MRAM, magnetic RAM memory, which is solid-state, offers lightning-fast data access and is non-volatile (retains data after power off). It will take some time though before we'll see it in sizes appropriate for hard-drives, but it will probably appear soon as RAM memory and USB storage devices...

*AHEM!*

The largest MRAM they have been succesfull in fabricating is 512K.

It's a *long* way off. I doubt MRAM devices will *ever* be in sizes that will be apropriate for mass storage. What I could see happening, is an MRAM cache on a harddrive.

I'm sorry if I made it sound like it was imminent :)
Considering the weight of IBM and others involved, and the major advantages of the technology, I don't doubt MRAM will start replacing DRAM in a few years time in home computers and when that happens the step to a solid-state MRAM-based HDD is just a cost issue, just like it is buying a DRAM-based solidstate HDD today. The difference though is that MRAM-based solidstate drives won't have the technical issues that DRAM-based drives like the Rocketdrive have, which is the reason why it's just an expensive niche market for now. Now, I don't know if we'll ever see it in sizes that will make it appropriate for *mass* storage but I'm pretty sure we'll see MRAM drives with enough GBs for an operating system, some installed programs and games as well as MP3 files and other personal stuff...

 

FishTankX

Platinum Member
Oct 6, 2001
2,738
0
0
The problem I see is that MRAM is no cheaper to fabricate than DRAM. It's only advantage is that it stays on when your computer is turned off.

I really doubt many people would pay 500$ for a 10GB harddrive a little while down the road, even if it does reach that cheap. I personally believe that MRAM harddrives will remain in the server market where seek time and data transfer rate are very important factors.
 

FishTankX

Platinum Member
Oct 6, 2001
2,738
0
0
What I could see is a pool of MRAM used as RAM so that boot times would be minimal. Replacing RAM with MRAM would probably be alot slower, but exponentially faster than harddrive.
 

Cerb

Elite Member
Aug 26, 2000
17,484
33
86
Originally posted by: theplanb
I mean they've been around for ages. HDDs are easily the pick of the bottleneck in real PC performance IMHO.
If CPUs speed can be improved that fast, why not HDD? C'mon.. I hear about failed HDDs, noisy HDDs, bulky HDDs, all the time. And no one seems to do something about it.. I was really disappointed that the next generation of HDD is.. SATA.. how much improvement is that.

Of course, people will argue that HDDs don't need to be that fast. Maybe so. But I want, instant access on my files. Instant read and write of the files. I want the PC to be on and off instantly. I'll be really happy on the day when HDDs disappear completly..
HDDs do need to be fast, but simple high school level physics gets in the way.
Let's see, you can get real 50MB/s from any reasonably modern drive.
...and you're complaining? It wasn't that long ago when that number was 15MB/s, and we're getting close to 10K RPM IDE drives (WD is there, but still not for average consumers) now.
 

FishTankX

Platinum Member
Oct 6, 2001
2,738
0
0
Generally flash drives are small but have an ultra high seek rate. It's only when you glue them together RAID style with a controller do they even begin to start to shine.
 

PaperclipGod

Banned
Apr 7, 2003
2,021
0
0
Originally posted by: FishTankX
Originally posted by: rade
Solid state flash media are plagued by a limited nr of rewrites before failure as well as slow read/write speeds, so it's questionable how useful they would be as a general purpose storage media. The real breakthrough cold come in the form of MRAM, magnetic RAM memory, which is solid-state, offers lightning-fast data access and is non-volatile (retains data after power off). It will take some time though before we'll see it in sizes appropriate for hard-drives, but it will probably appear soon as RAM memory and USB storage devices...

*AHEM!*

The largest MRAM they have been succesfull in fabricating is 512K.

It's a *long* way off. I doubt MRAM devices will *ever* be in sizes that will be apropriate for mass storage. What I could see happening, is an MRAM cache on a harddrive.

Thats what they said about 512k SDRAM modules... :D

 

FishTankX

Platinum Member
Oct 6, 2001
2,738
0
0
.....Yeah. 512K SDRAM modules. We're now at 2GB. And it's been *20* years. What does that tell you? By the time we're up to 8GB SDRAMs (Finally getting to the harddrives of *6* years past) we'll be lucky to see 512MB MRAMs.
 

Idontcare

Elite Member
Oct 10, 1999
21,110
64
91
Originally posted by: FishTankX
Originally posted by: Grminalac
Originally posted by: FishTankX
Originally posted by: Agamar
I think what will eventually happen is you will get SATA drives with ~64 to 128M of ram on them caching the data it *thinks* you want next. Already have a laptop drive out that has 16M, and my IBM Deskstar has 8 on it.


Can't use RAM caches that large because if you ever loose power you've just lost 64MB of data. Or 128MB of data.

For laptops, such large caches are practical because the chances of a power outage is 0 to none.


Well I do see this occuring, manufactuers will just have to include backup power units to allow the memory ample time to write to the hard drive or some other method. Imagine speed increases provided by caches of one gig greater in size.

How big of a backup power unit would you need to sustain 30 watts of power to the harddrives for 5 seconds? That's alot of powerdraw. Not very practical for a battery, unless it was a NiCD. Then you would need chargers onboard. Yuck.

The gain you would get with 1 gig of harddrive cache would be akin to the gains you would get with 1GB more of system RAM, probably less. You don't need that much cache, as the place where cache benefits is sequential reads/writes which tend not to be massive anyways. Cache is a huge benefit when you've got a lot of small files. Large files benefit more from transfer rate.

This seems to be a popular path of thinking as I see it continually repeated. What I haven't seen is anyone come to their senses and realize the only data or files a user will lose in the event of a power outage are those files which are either:

(a) open and modified at time of power outage, or
(b) modified and closed in the 2 seconds prior to this mysterious power outage that everyone is paranoid about happening every 30 minutes or so.

The size of the hard drive cache will not impact files and data lost by option (a) above. If your hard drive has 0MB of cache you will still lose all modifications to any instantaneously open files during the occurrence of a power outage.

Option (b), a closed file that has not had the modifications written to the physical platter, is impacted by the size of the hard drive cache. Given hard drive write speeds tend to be >30MB/s, the total quantity of data that would ever be at risk is quite small. Multiply the probability of these high-frequency power outages by the probability of having closed a file just prior to the power outage and you arrive at the total probability of a lost file. Of course, you will always lose the data and files from those which are open anyways.

So the question is this, in light of option (a) above, is the risk of extra data loss due to option (b) really worth all this paranoia about high cache laden hard drives? I don't think so.


Oh, and to answer the question regarding power draw of a hard-drive for 5s...Battery Data...an AA provides about 3 W-hr of power. Although not the correct voltage, the point is that it would be rather easy to supply enough power to your hard-drive to have it ride out a 5s power outage.

And no need to recharge, that is unless you are experiencing power outages every 30minutes, just replace the battery after you experience a series of frightening losses of power and you are tired of losing all your files that were open (not closed like the ones in your hard drive cache, they're safe now thanks to the battery) because you didn't buy a UPS to keep the rest of your computer up and running during power loss.

The reason we don't have 128MB caches on our hard drives is simple, it has nothing to do with FUD and everything to do with market economics. The day will come when hard drive manufacturers will have no choice but resort to placing 128MB of cache on their products to compete in the market, until then there is no need to release such a product and incur reduced profit margins relative to their competitors.

Having said that, don't stop spreading the FUD FishTankX, its humorous to read at times and we all need a little humor, don't we?
 

Idontcare

Elite Member
Oct 10, 1999
21,110
64
91
Originally posted by: FishTankX
.....Yeah. 512K SDRAM modules. We're now at 2GB. And it's been *20* years. What does that tell you? By the time we're up to 8GB SDRAMs (Finally getting to the harddrives of *6* years past) we'll be lucky to see 512MB MRAMs.

Do you actually work for Moto or have any clue about the market versus technology reasons MRAM is being produced in the current product mixes?