Skip to main content

Upgrade Advice: Does Your Fast SSD Really Need SATA 6Gb/s?

More Background On Our Benchmarks

4 KB Random

Our Storage Bench v1.0 mixes random and sequential operations. However, it's still important to isolate 4 KB random performance because that's such a large portion of what you're doing on a day-to-day basis. Right after Storage Bench v1.0, we subject the drives to Iometer to test random 4 KB performance. But why specifically 4 KB?

When you open Firefox, browse multiple Web pages, and write a few documents, you're mostly performing small random read and write operations. The chart above comes from analyzing Storage Bench v1.0, but it epitomizes what you'll see when you analyze any trace from a desktop computer. Notice that close to 70% of all of our accesses are eight sectors in size (512 bytes per sector, thus 4 KB).

We're restricting Iometer to test an LBA space of 16 GB because a fresh install of a 64-bit version of Windows 7 takes up nearly that amount of space. In a way, this examines the performance that you would see from accessing various scattered file dependencies, caches, and temporary files.

If you're a typical PC user, it's important to examine performance at a queue depth of one, because this is where the majority of your accesses are going to fall on a machine that isn't being hammered by I/O commands.

Before we get to the numbers, note that we're presenting random performance in MB/s instead of IOPS. There is a direct relationship between these two units, as average transfer size * IOPS = MB/s. Most workloads tend to be a mixture of different transfer sizes, which is why the networking ninjas in IT prefer IOPS. It reflects the number of transactions that occur per second. Since we're only testing with a single transfer size, it's more relevant to look at MB/s (it's also more intuitive for "the rest of us"). If you want to convert back to IOPS, just take the MB/s figure and divide by .004096 MB (remember your units) for the 4 KB transfer size.

128 KB Sequential

SSD manufacturers often want to stress random performance because it's a clear case where they decimate conventional hard drives. Sequential performance is a little different, but still represents an important aspect of performance to examine.

But how pervasive is sequential performance for the average user? Take a look at the graph below; it shows the distribution of all the seek distances from one of our traces.

The first thing you'll notice is that there's a preponderance of activity zero sectors away, which means that our trace is made mostly of back-to-back requests, or sequential I/O. If the trace was 100% random, none of the accesses would be zero sectors away.

More and more of your data is becoming sequential in nature, especially if you're watching movies and listening to music. Consider that most webpages contain less than 1 MB worth of data and most emails less than 16 KB. Office productivity isn't particularly disk intensive, but that workload pales in comparison to multimedia, as a two minute movie transfer can easily exceed 200 MB.

Of course, this doesn't even touch the subject of gaming. We've traced six games now and except in the case of MMORPGs, we've found gameplay related data to be mostly sequential. First person shooter games like Crysis 2 are particularly data heavy, as only 20 minutes of gameplay involves reading and writing over 1 GB of data.

  • compton
    Buying the best drive rather than the perceived fastest is good advice. I have fast drives and slow drives, but I prize the reliable ones. The good news is that there are drives which are both fast and reliable, so don't buy a drive just because of its Vantage score or simply because of the speed with which it handles 0-fill data.
    Reply
  • compton
    Which FW is the 830 using? The Test Setup and Benchmarks page lists it as CXM0. There are currently 3 FWs, CXM01,02,03]B1Q. The page simply lists CXM0.
    Reply
  • phamhlam
    Crucial m4, Samsung 830, and Intel 320 are all good drives. 128GB drives go for $180. They are the best value.

    I find it interesting that SATA 3 doesn't make a difference in file copy. Most SATA 3 drives cost the same as a SATA 2 so no need to save a few dollars.
    Reply
  • SteelCity1981
    So basiucly what this is saying is even thought SATA 3 looks impressive on paper, when it comes to actual real world results it's really not any faster than SATA 2 in performaning everyday real world task.
    Reply
  • dark_knight33
    I think I wrote you an email asking for this article when I was looking to buy my SSD a few weeks/months ago. Even though your article came after I purchased mine, thanks for addressing it. I'm rocking a Vertex III 240GB on my Sata II x58 MB and I don't regret it one bit.
    Reply
  • a4mula
    I can say this. I'm running 2x OCZ Solid first gen SSDs off SATA 3Gb/s ICH10R. When new they benched at about 300/100 sequential read/write. Compared to current generation drives this is pretty slow. When researching my current build I asked a friend that just put together a rig with a 64GB M4 on Intel 6Gb/s if I could give it a spin. While his machine boots faster w/o a doubt, I attest most of this to the RAID verification I face when I boot. Inside Win7 I couldn't tell a difference at all. While I'm sure his system is faster, it just wasn't obvious or noticeable in my opinion.
    Reply
  • sincreator
    What about quality? Is there any way to stress them till they start to fail? It just seems that if there isn't much difference in the drives in real world applications, then the next logical thing a buyer would want to know would be how much average data particuar drives can read/write before a failure. Like actual stress testing in a controlled environment. Come on Tom's, don't you want to destroy a few perfectly good SSD's? lol. These are things i would like to know more than anything else so I could make a very informed decision before a purchase.

    I asked before but no one answered. Anyway here goes... If SSD's are supposed to be more reliable than spinning drives, why are most warranties for 3 years instead of the usual 5 years on high end conventional spinning drives? It seems like the companies are not to confident in their products to me, and that's why I ask this question and the one that preceded it. It would be nice to get some honest answers......
    Reply
  • compton
    sincreatorWhat about quality? Is there any way to stress them till they start to fail? It just seems that if there isn't much difference in the drives in real world applications, then the next logical thing a buyer would want to know would be how much average data particuar drives can read/write before a failure. Like actual stress testing in a controlled environment. Come on Tom's, don't you want to destroy a few perfectly good SSD's? lol. These are things i would like to know more than anything else so I could make a very informed decision before a purchase. I asked before but no one answered. Anyway here goes... If SSD's are supposed to be more reliable than spinning drives, why are most warranties for 3 years instead of the usual 5 years on high end conventional spinning drives? It seems like the companies are not to confident in their products to me, and that's why I ask this question and the one that preceded it. It would be nice to get some honest answers......
    Well, the warranties are mostly 3 years, but some drives like Intel's 320s and Plextor's M3S drives do have 5 years of coverage.

    As for stress testing... well... some have taken this matter in their own hands to answer that very question. So far, it's far more than anyone could imagine. And for complex reasons, a drive only writing 10GB might not wear out it's NAND in over a century. A drive's endurance is typically way underestimated. No one is going to wear out any 3xnm or 2xnm NAND in 5 years, except in the most extreme cases. Most drives die from firmware problems, or physical damage to the PCB or components, or some other unknown phenomenon. Only the factory could do a proper autopsy, and since the FW, FTL, controller, etc. are usually trade secrets or covered under NDA, no one in the know is going to volunteer.

    There is an SSD endurance thread on the XtremeSystems forum:

    http://www.xtremesystems.org/forums/showthread.php?271063-SSD-Write-Endurance-25nm-Vs-34nm/page1
    Reply
  • heezdeadjim
    You probably aren't going to see much of a difference in speed while on the desktop from one SSD to another. It's when loading programs and game levels that you might see a real difference in.

    I know when I first got my 1st gen OCZ Vertex nearly when it first came out, I was always the first person on the map for Counter Strike. While other players were still loading the level, I would rush in from the side and lob a grenade and take a few people out because they didn't think anyone could get there so fast (now with more people with SSD's, it's not quite so funny anymore).

    I do appreciate being able to open PS CS5 in less than 2 seconds (for quick photo re-edits) and opening Premiere a lot faster too. Transferring large RAW photo folders (think 50+GBs total) to and from backup HDD's, I could use the extra MB's from these new 6Gb/s versions.
    Reply
  • cmcghee358
    I've read this article entirely too many times. Except this time it looks much better than the version I saw. Good job Mr. Angelini!
    Reply