Sign in with
Sign up | Sign in
Your question

Flash-Based Hard Drives Cometh

Last response: in Storage
Share
August 13, 2007 10:45:07 AM

http://www.tomshardware.com/2007/08/13/flash_based_hard_drives_cometh/index.html

SanDisk's SSD5000 shows that flash-based drives really do offer superior performance, while consuming less power. Still, there are some drawbacks.
August 13, 2007 12:58:08 PM

Due to the nature of SSDs all of their problems should easily be overcome due to two factors:

1. Moore's Law - SSDs currently $10-15/GB, but Moore's Law will solve this one. The cost of raw flash is about $8/GB, and those chips probably aren't of the quality needed for SSDs, so as flash continues to drop at 30%/year so will the cost of SSDs.

2. Parallelism - SSDs will exhibit nearly linear increases in performance with increases in chip speeds and with increases of the number of flash chips. The 2.5" form factor and pricing constraints require that a small number of the densest chips be used, but if the device were scaled to 64GB with twice the chips in a 3.5" form factor, or 4-8x the flash chips in a PCIe or 5.25" form factor, the read and write performance would scale as well.

An aside, in laptops the HD form factor makes sense, but in desktops I wonder if a PCIe card wouldn't work better. PCIe 1x is capable of 2.5Gb/sec, so 4x PCIe would be much less of a bottleneck than SATA. the 3.5" form factor allows for an inch of height, totally unnecessary for a 1/8" thick PCB, but limits the surface area of the device. Even a low profile PCIe card would have larger surface area for greater chip count. A controller that presented itself to the OS as a storage device or RAID controller could be used, and conventional RAID designs would be unnecessary since each chip on the card operates independently of the others, so a 128 chip device should be as fast as 8x 16 chip devices. Assuming the controllers can keep up.
August 13, 2007 1:31:06 PM

I am just so tired of annoucements regarding these. I want to buy a couple of 64GB ones and put them in a RAID 0 array. There are many manufacturers already producing them but they seem to only be in the OEM channel. They really need to get more out in the channel.


Also about the statement that this is the fastest drive could be false. Here is a link to a site that has some benchmarks showing one sustaining 100MB/s read and 80MB/s write. These drives are at a huge premium though. I would love to see THG get a hold of some to test as I would trust the benchamrks coming from you as opposed to some random site.

http://www.dvnation.com/nand-flash-ssd.html
Related resources
August 13, 2007 1:50:10 PM

...trying to work out what the conclusion is for a DT gamer... I suppose read performance is by far the most important factor for in-game performance, since I'm guessing there is very little writing to the HDD during play? (Correct me if I'm wrong, i'm just guessing)

If that's the case, I suppose these flash drives are going to have a significant edge even over the faster raptors?

Thanks
August 13, 2007 2:19:58 PM

Well, I'm excited!
August 13, 2007 3:35:37 PM

What about "real world" benchmarks!?! How could you forget that? We all know how synthetic benchmarks can be quite different in "real world" benchmarks. I was excited when I starting reading the article when you mentioned a RAID 0 setup and that the read performance was better than the Samsung. I am disappointed and feel cheated that you didn't bother with the other tests / benchmarks.
August 13, 2007 4:30:29 PM

That was a well written article. Thanks.
August 13, 2007 4:55:06 PM

Thank-you, I've been waiting for a review of ssd's in raid 0. I'm still holding out for two 64's at under a thousand cdn$ and I'm jumping; maybe not too much longer.

This is the one upgrade that will make already fast systems feel faster day to day.
August 13, 2007 5:26:27 PM

No1sFanboy said:
Thank-you, I've been waiting for a review of ssd's in raid 0. I'm still holding out for two 64's at under a thousand cdn$ and I'm jumping; maybe not too much longer.

This is the one upgrade that will make already fast systems feel faster day to day.

Lol, nice avatar. I want to get me one of those Ariel Atoms. I saw that episode and ended up downloading that clip cuz that piece of art is as fast as @#$*.
August 13, 2007 5:40:16 PM

I think the caution against using SSD's on a server should be ammended somewhat. It seems to me that one of the easiest applications to justify their use on is as the OS Drive on a server. I use 15k SCSI drives as OS and swapfile drives on several systems (with large SATA drive arrays for data). I would have been interested to see the performance of SSD's relative to high performance drives (36gb and 72gb 10k sata and 15k scsi). 15k drives are pretty expensive (compared to 7200's), so SSD's are competing on much more favorable turf in that market.

I've never looked into it but I'd suspect it's possible to split much of the write intensive directory structure (User Data, swapfile, database directories, etc) from the basically read-only directories ('OS, Web Server, Application installation directories, etc...). It seems to me that would allow you to have your cake (wicked fast read access times) and eat it too (write heavy directories on normal HDD's).

August 13, 2007 6:18:55 PM

d_kuhn said:
I think the caution against using SSD's on a server should be ammended somewhat. It seems to me that one of the easiest applications to justify their use on is as the OS Drive on a server. I use 15k SCSI drives as OS and swapfile drives on several systems (with large SATA drive arrays for data). I would have been interested to see the performance of SSD's relative to high performance drives (36gb and 72gb 10k sata and 15k scsi). 15k drives are pretty expensive (compared to 7200's), so SSD's are competing on much more favorable turf in that market.

I've never looked into it but I'd suspect it's possible to split much of the write intensive directory structure (User Data, swapfile, database directories, etc) from the basically read-only directories ('OS, Web Server, Application installation directories, etc...). It seems to me that would allow you to have your cake (wicked fast read access times) and eat it too (write heavy directories on normal HDD's).

You get my vote. Well put. I'd very much like to see data comparing those different types of drives as well. How does it compare to the Savvio 15K 2.5" drives as well? That could be a close comparison as both can be/are used in web servers.
August 13, 2007 6:40:40 PM

Maybe they need to add cache to the flash drive to boost write performance?

Or maybe we will see dramatic speed improvements when a company experienced with making hard drives makes a flash one? They can add 8-16 MB cache and know how to write algorithms to manage it.

Sandisk is trying to create a HD that just works like a flash card used in a digital camera. :non: 
August 13, 2007 8:37:05 PM

What would be the best way to use the SSD in a system with consideration for larger data files - some of which you would like to have in a raid 1 setup for data security? Would you have two SSDs in raid 0 for operating systems and applications and two SSD's in raid 1 for data - or all in raid 5? If you wanted to increase data storage size and reduce costs, what would be the performance hit for have the two data drives on HD in raid 1?

I agree it would be nice to have some application benchmarks to see real performance. I admit I am not very knowlegeable in this technology and have difficulty translating the poorer write performance into the impact on applications.

Given that this apparently has the greated potential for increaseing performance, hopefully THG will continue with more reviews covering other areas. And hopefully just moving having the larger HD manufacturers move into this segment with larger production runs will reduce costs more quickly.

:bounce:  :bounce:  :bounce: 
August 13, 2007 8:57:38 PM

yeah, the ssds should easily offer superior application performance for the majority of applications, simply due to their virtually nonexistant access times... high transfer rates dont really matter much for typical uses, to be honest


however, if your access times were really really really slow, it wouldnt matter how high your STRs were (they could be as high as hundreds of terabytes per second, but youd seemingly never even get to the file to access it, to be able to then transfer it (thats an extreme example, but just there to point out an emphasis, that faster access times are oftentimes more significant than higher STRs are, for many things, though not all)
August 13, 2007 9:09:38 PM

choirbass said:
yeah, the ssds should easily offer superior application performance for the majority of applications, simply due to their virtually nonexistant access times... high transfer rates dont really matter much for typical uses, to be honest

however, if your access times were really really really slow, it wouldnt matter how high your STRs were (they could be as high as hundreds of terabytes per second, but youd seemingly never even get to the file to access it, to be able to then transfer it (thats an extreme example, but just there to point out an emphasis, that faster access times are oftentimes more significant than higher STRs are, for many things, though not all)

I agree with what you said, especially your extreme example of access times and STRs (sustained transfer rates). On www.anandtech.com they did a review of Super Talent's 16GB SSD ( http://www.anandtech.com/storage/showdoc.aspx?i=2982 ). It topped out at 20.5 MB/s average transfer rate but when you look at the "real wold" benchmarks/comaprisons, it's amazing how it still beats some of the other HDD's, even the Raptor! The SSD in this article has over 3 times the read performance or even 6 times in RAID 0, it'd be interesting to see how that compares!
August 13, 2007 9:14:44 PM

yep!, thats my point exactly... and is why raptors, even the oldest raptors from about 4 years ago, are still at least as fast as even the fastest current 7200s, when it comes to most everyday tasks and application uses (as hard as that might be for some people to accept)... the primary difference is going to be their access times, which are oftentimes nearly twice as fast as comparable 7200s, and why even 15k scsi hdds are faster even still for most uses, even when their STRs arent, as 15k scsi offer access times nearly twice as fast as raptors do.

im going to jokingly say that ssds are about on par for performance with 50k rpm or 100k rpm scsi hdds, lol, just for some perspective anyhow
August 13, 2007 9:35:03 PM

@rockyjohn -

RAID0 with SSDs is the only way that makes sense.

RAID1,5,10 all are designed to preserve data in the event of a hard drive crash. With SSDs, there should be no crashing. The MTBF should be several order of magnitudes greater, meaning using RAID5 would be preventing against the statistical equivelant of getting hit by lightning several times.

On the server space, if SSDs were used, RAID5 might make some sense, but a 15 drive RAID5 array would be fine. Now, it's good practice to limit RAID5 arrays to 5-6 drives.
August 13, 2007 10:10:33 PM

joex444 said:
@rockyjohn -

RAID0 with SSDs is the only way that makes sense.

RAID1,5,10 all are designed to preserve data in the event of a hard drive crash. With SSDs, there should be no crashing. The MTBF should be several order of magnitudes greater, meaning using RAID5 would be preventing against the statistical equivelant of getting hit by lightning several times.

On the server space, if SSDs were used, RAID5 might make some sense, but a 15 drive RAID5 array would be fine. Now, it's good practice to limit RAID5 arrays to 5-6 drives.

True. But putting these drives in RAID 5 or 6 would result in more writes, which current SSDs are not good at, so that would probably make them worse than they already are (for writing that is).
August 13, 2007 11:02:51 PM

joex444 said:
@rockyjohn -

RAID1,5,10 all are designed to preserve data in the event of a hard drive crash. With SSDs, there should be no crashing. The MTBF should be several order of magnitudes greater, meaning using RAID5 would be preventing against the statistical equivelant of getting hit by lightning several times..


Does that mean that two SSDs in RAID 0 would provide better data security - at least relative to hard drive failure - than two HDs in raid 1?

That would be great. Then I could put all my software and basic data on the SSDs and use one large HD to do a weekly backup of the basic data and store files that don't need to be backed up - e.g. audio and video. Now all I need is for the prices to drop to about half of where they are.
August 14, 2007 4:51:17 AM

I would actually be interested to see if one of these SSD drives would work well in a raid 1 with a normal drive so that the system could take advantage of the performance benefits from each drive for that server environment. Raid 1 usually need drives of similar performance but I'm just curious.
August 14, 2007 10:14:52 AM

Well I'm disappointed. Very, very disappointed.
I don't like ranting and raving, but hear me on this please. One drive costs say $500 (I don't recall the exact prices and I'm lazy to check). Sandisk was nice enough to send two drives to test in RAID configuration. It was however already mentioned in this discussion that solid state drives are very scalable as far as the number of flash chips on a single drive is concerned. Also that the performance would be directly affected by the number of chips running in parallel. So why not just double the number of chips for a single drive rather than limiting them and requiring from the consumer to buy several drives to get RAID performance? It is a blatant bid to get people to upgrade one small step at a time again as has been the case with many other types of hardware in the past. The only difference is that the technology is so much simpler. Forget about capacity. I am interested in performance. I was expecting more. I have no doubt in my mind that they are starting at the very minimum of what is possible right now. Just good enough to blow conventional hard drives out of the water. And I don't like it. I don't like being patronized into spending my money in such a way. All it will lead to is me waiting for a decent offering to come along. I will never buy a product I don't believe in.
To the manufacturers: Get off your profit hungry behinds and give us what we deserve. Spend money on good honest R&D to scale the technology by what you are capable of providing. Not by what people might be willing to put up with. Flash memory is well advanced and cheap at this stage. The pudding should be in how well you use it. And with improvements to the actual flash memory technology in the future so much the better.
Cheapskates
August 14, 2007 3:08:45 PM

Egregious said:
I would actually be interested to see if one of these SSD drives would work well in a raid 1 with a normal drive so that the system could take advantage of the performance benefits from each drive for that server environment. Raid 1 usually need drives of similar performance but I'm just curious.

Very interesting, I wonder how that would work. It'd be nice to see the results though. :) 
August 14, 2007 4:19:42 PM

Sq7 said:
Well I'm disappointed. Very, very disappointed.
I don't like ranting and raving, but hear me on this please. One drive costs say $500 (I don't recall the exact prices and I'm lazy to check). Sandisk was nice enough to send two drives to test in RAID configuration. It was however already mentioned in this discussion that solid state drives are very scalable as far as the number of flash chips on a single drive is concerned. Also that the performance would be directly affected by the number of chips running in parallel. So why not just double the number of chips for a single drive rather than limiting them and requiring from the consumer to buy several drives to get RAID performance? It is a blatant bid to get people to upgrade one small step at a time again as has been the case with many other types of hardware in the past. The only difference is that the technology is so much simpler. Forget about capacity. I am interested in performance. I was expecting more. I have no doubt in my mind that they are starting at the very minimum of what is possible right now. Just good enough to blow conventional hard drives out of the water. And I don't like it. I don't like being patronized into spending my money in such a way. All it will lead to is me waiting for a decent offering to come along. I will never buy a product I don't believe in.
To the manufacturers: Get off your profit hungry behinds and give us what we deserve. Spend money on good honest R&D to scale the technology by what you are capable of providing. Not by what people might be willing to put up with. Flash memory is well advanced and cheap at this stage. The pudding should be in how well you use it. And with improvements to the actual flash memory technology in the future so much the better.
Cheapskates


These flash chips are 2GB apiece. I think that's as state of the art as it gets right now. I don't think it would be cost effective for them to use 256 128MB chips, and the largest capacity chips will be the newest tech with the fastest read and write times, so using more lower capacity chips would not scale the same.

They could scale up to 64, 128, etc GB with more chips, but if people aren't going to buy a $500 HD replacement they probably won't buy a $1-2K HD replacement either.
August 14, 2007 4:30:59 PM

Egregious said:
I would actually be interested to see if one of these SSD drives would work well in a raid 1 with a normal drive so that the system could take advantage of the performance benefits from each drive for that server environment. Raid 1 usually need drives of similar performance but I'm just curious.


Most RAID algorithms are based on identical HW, writing a block to each drive, getting return results, writing another block to each drive, etc. Mismatched HW would move you to 2x the slowest drive at best, since the controller would be waiting on the slow drive all of the time.

Before NCQ was integrated into HDD's RAID controllers used to perform similar functions, and some high end RAID setups used HDD's with synchronized spindles, so that HD1 and HD2 were always reading or writing the same block off of a drive with no seek differential. Software RAID and new low cost RAID controllers ignore all of those mechanical optimizations, and that's part of the reason why a PERC or other high end RAID controller will have greater performance with the same drives.

Different algorithms might be able to take advantage of an HD/SSD combo, like Vista's Speedboost or whatever. Also, the hybrid HD/SSD's that have been predicted in tech news posts could be very high performance with the right algorithm. If you did have a 4GB SSD and a 100GB HD in one device there would be a learning curve on the algorithm as it figured out what sectors were hi read/lo write, so it would be hard to benchmark too..

Of course, the hybrid devices might never come out, and SSD might just become the HD replacement in a couple of years.
August 14, 2007 5:14:55 PM

mr_fnord said:
Of course, the hybrid devices might never come out, and SSD might just become the HD replacement in a couple of years.

They already are out!
August 14, 2007 7:19:36 PM

Aren't SSD still prone to finite write/rewrite bits? (So after like 100,000 or 1,000,000 write/rewrites the block just dies.) Or have they managed a way around that?

Until they do, I don't think SSDs will be a viable alternative to standard HDDs. Or at least prolong the lifespan to match disk based drives.
August 14, 2007 8:09:18 PM

diabloazul126 said:
Aren't SSD still prone to finite write/rewrite bits? (So after like 100,000 or 1,000,000 write/rewrites the block just dies.) Or have they managed a way around that?

Until they do, I don't think SSDs will be a viable alternative to standard HDDs. Or at least prolong the lifespan to match disk based drives.

It's dynamic though. The technology/algorithms exists where they can write to different cells and space out the write operations so it's not on the same one over and over again. Also so devices include extra space so when/if a cell (can't remember the correct term) goes bad it'll automatically move over to a new unused space.
August 15, 2007 6:22:09 AM

First, I thought this article was very well written and a GREAT explanation for how useful/worthless this technology is for it's price and your purpose for it. Here's 1 little recommendation...

Quote from the article:

Quote:
As command queues increase, the single hard drive does not even scale up, as this flash-based HDD does not support command queuing.


When I read the article and saw that, my first response was 'OMG.. the latest and greatest technology with no command queuing?'. Then after thinking about it, command queuing is pointless for flash based technology as you do not have any reason to 'optimize the order of operations' for flash memory. It's basically the same for anything anywhere. It would be nice if you write a comment that although it doesn't support command queuing, if it did the benchmark wouldn't change anything.

Now, on another note, write caching in OSes. If you have data stored in the cache of the hard drive itself to be written and the computer blue screens(reset button hit, whatever) is the data wiped or is the data written? What does the hard drive go through when the machine reboots? Does it execute some kind of 'write cache flush to disk' command? And what does the Flash drive do? I'm just thinking in terms of stability is 1 better or worse for write caching. Obviously write caching random writes on a flash drive will yield the biggest gains.

And heck for that matter, if windows XP(and linux for that matter) has a serious system error, does it flush the write cache before it reboots or is the data lost to the ether forever? I've always wondered these things, and I guess this is a good time to ask.

Thanks

-Cyberjock

August 15, 2007 6:50:51 AM

mr_fnord said:
Most RAID algorithms are based on identical HW, writing a block to each drive, getting return results, writing another block to each drive, etc. Mismatched HW would move you to 2x the slowest drive at best, since the controller would be waiting on the slow drive all of the time.

Before NCQ was integrated into HDD's RAID controllers used to perform similar functions, and some high end RAID setups used HDD's with synchronized spindles, so that HD1 and HD2 were always reading or writing the same block off of a drive with no seek differential. Software RAID and new low cost RAID controllers ignore all of those mechanical optimizations, and that's part of the reason why a PERC or other high end RAID controller will have greater performance with the same drives.

Different algorithms might be able to take advantage of an HD/SSD combo, like Vista's Speedboost or whatever. Also, the hybrid HD/SSD's that have been predicted in tech news posts could be very high performance with the right algorithm. If you did have a 4GB SSD and a 100GB HD in one device there would be a learning curve on the algorithm as it figured out what sectors were hi read/lo write, so it would be hard to benchmark too..

Of course, the hybrid devices might never come out, and SSD might just become the HD replacement in a couple of years.




Well I could see it being done with a more intelligent raid 1 controller that keeps track of recent data that hasn't been mirrored yet to the second flash drive. It could write to the platter hard drive(best performance) and if there is a request for said data before the mirroring, the fetch would be from the most recent data based on best performance. The mirroring could happen during idle time.
On the other hand the manufactures could just build drives with mega huge caches with non volatile ram.
August 15, 2007 8:15:57 AM

mr_fnord said:
These flash chips are 2GB apiece. I think that's as state of the art as it gets right now. I don't think it would be cost effective for them to use 256 128MB chips, and the largest capacity chips will be the newest tech with the fastest read and write times, so using more lower capacity chips would not scale the same.

They could scale up to 64, 128, etc GB with more chips, but if people aren't going to buy a $500 HD replacement they probably won't buy a $1-2K HD replacement either.


I'm not so sure. Are the 8GB thumb drives you get everywhere these days based on a different type of flash chip? The 2GB versions are all dirt cheap these days. 1GB even more so. In any case. I was reflecting more on the number of chips per drive. Why not give two options? One with the standard number of chips and one with double the number running in parallel Surely this should be cheaper to make than two separate drives. And therefore cheaper to buy in the end. Are there any technical problems with doing so? I can't imagine there is. All you end up with is exactly what RAID does, except there should be less overhead. Also less travel distance for the data. What is preventing them from going this route.

I think 32x1GB chips should give double the performance that 16x2GB chips can deliver. And 32GB is a sweet spot as far as I am concerned. For the personal computer at least. The main aim in my mind would be to install only the operating system on it and keep the rest of the space reserved for paging. The Documents and settings and program files folders can be mapped to a standard ATA/SATA drive, preferably SATA150. This should speed up boot time, OS HD IO operations and the traditional page file bottleneck. In short. It would speed up everything that matters for a PC user.


August 16, 2007 12:45:46 PM

I'm confused as to why these things cost so much. I can get a high performance, name brand 16 GB compact flash card for $150. This is for the 133x flaver which I believe is the fastest available. 2 x 150 = 300, not 500. Granted, they have to build in the SATA or PATA interface but surely that doesn't cost $200.

In response to Sq7's comment about 2 drives in RAID vs double the chips on 1 drive. The only advantage I can see to a RAID config is double the interface bandwidth. Of course, if you use SATA 300, then it wouldn't make a difference since these babies only read at 70mbps each. .... "ONLY" :kaola: 
August 16, 2007 2:23:39 PM

I have some experience with running windows off of compact flash and although its very fast there are disadvantages. Unless you do something to minimise writes like install EWF then windows will kill the card in a matter of days.

Have they done something to solve this problem with this device or is it still a huge drawback that has been overlooked?
August 16, 2007 3:34:40 PM

What about RAM Drives like the i-RAM.
I'm surprised we are not seeing more devices like this that support 16gb or more RAM as well as faster DDR2 memory.

Sure the price would be crazy, but for real speed freaks could see people going for it. Especially since the performance difference would be crazy. Just imagine running your DB from a drive like that.

Of course you would need serious backup, but it would rock.
August 16, 2007 3:47:09 PM

ElKeeed said:
I have some experience with running windows off of compact flash and although its very fast there are disadvantages. Unless you do something to minimise writes like install EWF then windows will kill the card in a matter of days.

Have they done something to solve this problem with this device or is it still a huge drawback that has been overlooked?

What program is EWF?
August 16, 2007 7:24:58 PM

First time on the Forums and not sure how to add a message into the discussion...I seem to find only choices to Reply to specific messages, so apologies if I've got it wrong.

I'm a long time computer and Photoshop user, but not a techie or someone who builds his own machines. I will soon be taking my first steps into HD video editing (serious amateur not pro), and a 2x SanDisk SSD 5000 RAID 0 setup sounds like a great way to go, but I've not been able to find a system maker who includes SSDs in its options list (Dell seems to but only in its laptops). So...I'm looking for advice on makers that are including SSDs as drive choices.

Also, (I know this isn't the place) any system advice on setting up a machine for optimal Photoshop and HD video editing would be great, or pointers to a good user forum where I can learn about it.

Many thanks, _/\/\ichael{R}
August 16, 2007 7:42:38 PM

Quote:

However, the relative low power-consumption performance isn't because of the flash technology, but is due to the interface. The new SanDisk drive uses a Serial ATA/150 interface that consumes 0.5 W when idle, which is 10 times higher than the power consumption of the Samsung device, which consumes 0.05 W when idle.


Does the drive not support SATA power saving capabilities? It should be able to power the phy down and save more than a measly .6w between active and idle.
August 16, 2007 9:08:11 PM

I have a question for those more generally knowledgable about hardware than myself. I recently read an article about stable video editing, which I do quite a bit of. The author recommended keeping a separate hard drive or partition for the OS to keep any junk from building up that could interfere with the video clips.

I have started to look into building a new system and am keeping this advice in mind. Because I am doing storage intensive work it will be a long long time before I will be able to go all flash.

I was thinking about buying a 16bg or 32 gb flash drive for my OS (XP for now) and then using a normal drive for everything else.

The performance drawback to the flash drive seems to be the slow write speeds, and my assumption is that the OS wont do much writing and so should run quite well on a flash drive.

Does this plan makes sense?
Would it make any noticeable difference?

Thanks
August 20, 2007 2:53:15 PM

bmichener said:
I have a question for those more generally knowledgable about hardware than myself. I recently read an article about stable video editing, which I do quite a bit of. The author recommended keeping a separate hard drive or partition for the OS to keep any junk from building up that could interfere with the video clips.

I have started to look into building a new system and am keeping this advice in mind. Because I am doing storage intensive work it will be a long long time before I will be able to go all flash.

I was thinking about buying a 16bg or 32 gb flash drive for my OS (XP for now) and then using a normal drive for everything else.

The performance drawback to the flash drive seems to be the slow write speeds, and my assumption is that the OS wont do much writing and so should run quite well on a flash drive.

Does this plan makes sense?
Would it make any noticeable difference?

Thanks

Where (on which drive) will you keep your windows swap file?
August 20, 2007 3:14:37 PM

With standard hard disks it makes sense to have separate drives for swap files (with Photoshop I've always had separate drives for both the Win swap file and Photoshop's. But with the near instant speed of an SSD, would I be wrong in thinking that separate drives for swap files are no longer important? Specifically for HD video editing, what drive setup would you recommend without going to overkill?
August 20, 2007 4:46:02 PM

mgr said:
With standard hard disks it makes sense to have separate drives for swap files (with Photoshop I've always had separate drives for both the Win swap file and Photoshop's. But with the near instant speed of an SSD, would I be wrong in thinking that separate drives for swap files are no longer important? Specifically for HD video editing, what drive setup would you recommend without going to overkill?

But SSD's are quite a bit slower at writing than standard HDD's, so it doesn't seem like a good idea, to me at least.
What type of drive interface are you looking at for video editing (SAS or SATA)? Also, are you looking for pure performance or large capacity as well?
August 20, 2007 7:54:08 PM

For when the flash drives for desktops?
August 20, 2007 9:35:24 PM

micheljq said:
For when the flash drives for desktops?

What what what?
August 21, 2007 12:46:06 AM

gwolfman, you say, "But SSD's are quite a bit slower at writing than standard HDD's, so it doesn't seem like a good idea, to me at least.
What type of drive interface are you looking at for video editing (SAS or SATA)? Also, are you looking for pure performance or large capacity as well?" (I don't know how to use the forum's quote feature yet...gunna go read up after this message.)

Have I misread about the write speed of SSDs, that they are only slower in situations of continuously repeated write requests in such programs as databases but not in situations with single writes with even small delays between them? Not having done any HD video editing, I'm not familiar with how the apps write to disk, but are you sure the "slow write" issue with SSDs would be a problem there?

I don't know enough yet to answer your question about SAS(?)-vs-SATA, but for HD video editing I suspect I'll be wanting both reasonably large capacity as well as performance. A conventional disk would be fine for storage, but I'm wondering about one or a RAID-0 pair of SSDs as a "work disk" in addition to a RAID-0 pair for drive C:. But I don't know enough yet to make informed decisions about this.
August 21, 2007 7:07:26 PM

mgr said:
gwolfman, you say, "But SSD's are quite a bit slower at writing than standard HDD's, so it doesn't seem like a good idea, to me at least.
What type of drive interface are you looking at for video editing (SAS or SATA)? Also, are you looking for pure performance or large capacity as well?" (I don't know how to use the forum's quote feature yet...gunna go read up after this message.)

Have I misread about the write speed of SSDs, that they are only slower in situations of continuously repeated write requests in such programs as databases but not in situations with single writes with even small delays between them? Not having done any HD video editing, I'm not familiar with how the apps write to disk, but are you sure the "slow write" issue with SSDs would be a problem there?

I don't know enough yet to answer your question about SAS(?)-vs-SATA, but for HD video editing I suspect I'll be wanting both reasonably large capacity as well as performance. A conventional disk would be fine for storage, but I'm wondering about one or a RAID-0 pair of SSDs as a "work disk" in addition to a RAID-0 pair for drive C:. But I don't know enough yet to make informed decisions about this.

http://www.tomshardware.com/2007/08/13/flash_based_hard...
The write speed of one of the SanDisk SSD's is about 1/2 of what you get for a good 3.5" drive. Two of them in RAID 0 would be about equal to the write speed of one good 3.5" drive. If you can afford two of these, then your amazing read speeds would outweigh the slower write speeds. The slow writing reference I mentioned above is related to where your swap file for the OS and editing program would be (that's where my concern was).



SATA = Serial ATA
SAS = Serial Attached SCSI

Basically the SAS connectors look just like a SATA connector but it's capable of running a modified version of the SATA protocol that allows a significant improvement in data transfers. The drives have faster spindle speeds of 10,000 and 15,000 RPM's instead of the usual 7,200 that desktop HDD's have. This allows for greater performance compared to a regular SATA desktop HDD. The trade off for the improved performance is you would need to purchase a SAS controller, lower capacity drives, and a higher cost per gigabyte. That's why I asked if you wanted high performance or large capacity because there is a big difference there between the two technologies.

http://www23.tomshardware.com/storage.html?modelx=33&mo...
The link above is from Toms's HDD charts. Both SATA drives offer good read/write performance and offer 750GB or 1000GB. You might also want to look at the new Seagate 7200.11 SATA drives that are coming out soon, they are supposed to have really good read/write performance. Quote: "Speedy performance at 105Mb/s sustained data rate" http://www.seagate.com/www/en-us/products/desktops/barr...

Does that help any?
-GWolfman
August 21, 2007 7:50:27 PM

gwolfman said:
What program is EWF?


EWF is Enhanced write filter. Its part of windows embedded that lets you save disk writes to ram and then write them all out at once or forget them entirely when you turn off. You can move the files across to regular XP or theres a program available that does the same thing but I'm not sure what that is called.
August 21, 2007 9:20:12 PM

Gwolfman, you say...

"http://www.tomshardware.com/2007/0 [...] erformance
The write speed of one of the SanDisk SSD's is about 1/2 of what you get for a good 3.5" drive. Two of them in RAID 0 would be about equal to the write speed of one good 3.5" drive. If you can afford two of these, then your amazing read speeds would outweigh the slower write speeds. The slow writing reference I mentioned above is related to where your swap file for the OS and editing program would be (that's where my concern was)."

But when I look at the chart, the Average and the Maximum write speeds are much faster than the fastest hard drive in the list, no?

In the Conclusion of the review, the writer says...

"Multiple random write access, as required in our database and fileserver, reveals the Achilles heel of the SSD 5000: Writing to lots of different cells slows the SSD down so much that even conventional 2.5" hard drives offer better I/O and file-write performance."

But do the slow speeds that apply to database writes, also apply to conventional writes...or to the writes of the OS swapfile? The review seems to say (to my uneducated ear) that normal write speeds with the SSD are much faster than conventional drives...so I must be missing something.

Thanks for explaining what the SAS drives are and for the advice about the new Seagates.
August 21, 2007 11:05:55 PM

mgr said:
But when I look at the chart, the Average and the Maximum write speeds are much faster than the fastest hard drive in the list, no?

Thanks for explaining what the SAS drives are and for the advice about the new Seagates.

That's compared to 2.5" (laptop) drives in the chart (if my memory serves me correctly), not the conventional 3.5" desktop drives. So if you'll be doing your editing on a laptop, then yeah, but why buy slower 2.5" drives (excluding SSD's) for a desktop when you can fit standard, faster performing 3.5" drives in a desktop.

And no problem about the explanation. I think those Seagates should be out within a month or so.

-GWolfman
August 21, 2007 11:10:18 PM

mgr said:
But when I look at the chart, the Average and the Maximum write speeds are much faster than the fastest hard drive in the list, no?

I just found this in the article:

Quote: Using two SanDisk SSD 5000 drives for a RAID 0 configuration almost doubles the read transfer rate to approximately 122 MB/s. The sequential write performance is 70-76 MB/s, which is often inferior to that of conventional hard drives.


Conventional being 3.5" hard disk drives.
August 22, 2007 4:24:49 AM

gwolfman said:
I just found this in the article:

Quote: Using two SanDisk SSD 5000 drives for a RAID 0 configuration almost doubles the read transfer rate to approximately 122 MB/s. The sequential write performance is 70-76 MB/s, which is often inferior to that of conventional hard drives.


Conventional being 3.5" hard disk drives.


OK, that clears it up for me finally, thank you. Damn shame though. The idea of an SSD that reads AND writes at many times the speed of a hard disk is a nice dream. I guess a RAID-0 pair still makes sense for C:, with perhaps two fast disks for storage/swapfiles, one for the OS swap, and the other for the PShop or video editor swap, so they're not competing over the same drive. Does that sound like a best-solution-for-now?

I do appreciate your taking the extra time to get me clear on the SSD shortcomings.

!