The Performance Degradation Problem

When Intel first released the X25-M, Allyn Malventano discovered a nasty corner case where the drive would no longer be able to run at its full potential. You basically had to hammer on the drive with tons of random writes for at least 20 minutes, but eventually the drive would be stuck at a point of no return. Performance would remain low until you secure erased the drive.

Although it shouldn't appear in real world use, the worry was that over time a similar set of conditions could align resulting in the X25-M performing slower than it should. Intel, having had much experience with similar types of problems (e.g. FDIV, Pentium III 1.13GHz), immediately began working on a fix and released the fix a couple of months after launch. The fix was nondestructive although you saw much better performance if you secure erased your drive first.

SandForce has a similar problem and I have you all and bit-tech to thank for pointing it out. In bit-tech's SandForce SSD reviews they test TRIM functionality by filling a drive with actual data (from a 500GB source including a Windows install, pictures, movies, documents, etc...). The drive is then TRIMed, and performance is measured.

If you look at bit-tech's charts you'll notice that after going through this process, the SandForce drives no longer recover their performance after TRIM. They are stuck in a lower performance state making the drives much slower when writing incompressible data.

You can actually duplicate the bit-tech results without going through all of that trouble. All you need to do is write incompressible data to all pages of a SandForce drive (user accessible LBAs + spare area), TRIM the drive and then measure performance. You'll get virtually the same results as bit-tech:

AS-SSD Incompressible Write Speed
  Clean Performance Dirty (All Blocks + Spare Area Filled) After TRIM
SandForce SF-1200 (120GB) 131.7MB/s 70.3MB/s 71MB/s

The question is why.

I spoke with SandForce about the issue late last year. To understand the cause we need to remember how SSDs work. When you go to write to an SSD, the controller must first determine where to write. When a drive is completely empty, this decision is pretty easy to make. When a drive is not completely full to the end user but all NAND pages are occupied (e.g. in a very well used state), the controller must first supply a clean/empty block for you to write to.

When you fill a SF drive with incompressible data, you're filling all user addressable LBAs as well as all of the drive's spare area. When the SF controller gets a request to overwrite one of these LBAs the drive has to first clean a block and then write to it. It's the block recycling path that causes the aforementioned problem.

In the SF-1200 SandForce can only clean/recycle blocks at a rate of around 80MB/s. Typically this isn't an issue because you won't be in a situation where you're writing to a completely full drive (all user LBAs + spare area occupied with incompressible data). However if you do create an environment where all blocks have data in them (which can happen over time) and then attempt to write incompressible data, the SF-1200 will be limited by its block recycling path.

So why doesn't TRIMing the entire drive restore performance?

Remember what TRIM does. The TRIM command simply tells the controller what LBAs are no longer needed by the OS. It doesn't physically remove data from the SSD, it just tells the controller that it can remove the aforementioned data at its own convenience and in accordance with its own algorithms.

The best drives clean dirty blocks as late as possible without impacting performance. Aggressive garbage collection only increases write amplification and wear on the NAND, which we've already established SandForce doesn't really do. Pair a conservative garbage collection/block recycling algorithm with you attempting to write an already full drive with tons of incompressible data and you'll back yourself into a corner where the SF-1200 continues to be bottlenecked by the block recycling path. The only way to restore performance at this point is to secure erase the drive.

This is a real world performance issue on SF-1200 drives. Over time you'll find that when you go to copy a highly compressed file (e.g. H264 video) that your performance will drop to around 80MB/s. However, the rest of your performance will remain as high as always. This issue only impacts data that can't be further compressed/deduped by the SF controller. While SandForce has attempted to alleviate it in the SF-1200, I haven't seen any real improvements with the latest firmware updates. If you're using your SSD primarily to copy and store highly compressed files, you'll want to consider another drive.

Luckily for SandForce, the SF-2500 controller alleviates the problem. Here I'm running the same test as above. Filling all blocks of the Vertex 3 Pro with incompressible data and then measuring sequential write speed. There's a performance drop, but it's no where near as significant as what we saw with the SF-1200:

AS-SSD Incompressible Write Speed
  Clean Performance Dirty (All Blocks + Spare Area Filled) After TRIM
SandForce SF-1200 (120GB) 131.7 MB/s 70.3 MB/s 71 MB/s
SandForce SF-2500 (200GB) 229.5 MB/s 230.0 MB/s 198.2 MB/s

It looks like SandForce has increased the speed of its block recycling engine among other things, resulting in a much more respectable worst case scenario of ~200MB/s.

Verifying the Fix

I was concerned that perhaps SandForce simply optimized for the manner in which AS-SSD and Iometer write incompressible data. In order to verify the results I took a 6.6GB 720p H.264 movie and copied it from an Intel X25-M G2 SSD to one of two SF drives. The first was a SF-1200 based Corsair Force F120, and the second was an OCZ Vertex 3 Pro (SF-2500).

I measured both clean performance as well as performance after I'd filled all blocks on the drive. The results are below:

6.6GB 720p H.264 File Copy (X25-M G2 Source to Destination)
  Clean Performance Dirty (All Blocks + Spare Area Filled) After TRIM
SandForce SF-1200 (120GB) 138.6 MB/s 78.5 MB/s 81.7 MB/s
SandForce SF-2500 (200GB) 157.5 MB/s 158.2 MB/s 157.8 MB/s

As expected the SF-1200 drive drops from 138MB/s down to 81MB/s. The drive is bottlenecked by its block recycling path and performance never goes up beyond 81MB/s.

The SF-2000 however doesn't drop in performance. Brand new performance is at 157MB/s and post-torture it's still at 157MB/s. What's interesting however is that the incompressible file copy performance here is lower than what Iometer and AS-SSD would have you believe. Iometer warns that even its fully random data pattern can be defeated by drives with good data deduplication algorithms. Unless there's another bottleneck at work here, it looks like the SF-2000 is still reducing the data that Iometer is writing to the drive. The AS-SSD comparison actually makes a bit more sense since AS-SSD runs at a queue depth of 32 and this simple file copy is mostly at a queue depth of 1. Higher queue depths will make better use of parallel NAND channels and result in better performance.

Sequential Read/Write Speed AnandTech Storage Bench 2011: Much Heavier
POST A COMMENT

144 Comments

View All Comments

  • slickr - Thursday, February 17, 2011 - link

    Now this is what I'm talking about about reviews/previews. Tons of benchmarks at various settings and loads. You can really make a difference now and see how the drives perform.

    I would also like a good old fashion test with Starcraft 2, how long it takes to load a 5-6mb custom map.

    I would also like another test where you select 30 files and open them at the same time and see how much time it takes to open all. I'm talking about selecting few 3-5mb images, few MP4 360p videos, few H.264 720p videos, dozen office documents from 500kb up to 3mb, several applications like GPU-z, skype, Live, Xfire, firefox etc... and opening few highly compressed script files.
    Reply
  • MamiyaOtaru - Thursday, February 17, 2011 - link

    smaller process, less reliability, and higher price? We've been waiting for years fr prices to become reasonable next to magnetic storage but there's been barely a drop at all, and the drops that do come (smaller processes, supposedly) reduce reliability. At this point I don't see myself ever getting one for my desktop.

    Laptops sure, hard drives die there all the time, and I don't use them as my primary machine. Smaller storage requirements + hard drives dying far more often in laptops makes SSDs the better choice for me there.
    Reply
  • Chloiber - Thursday, February 17, 2011 - link

    I do generally agree. I don't want faster drives, I want cheaper drives. They are already very fast. Of course, faster is always better but at the moment I prefer low price and reliabilty over speed. Reply
  • seapeople - Friday, February 18, 2011 - link

    Seriously... I don't need a brand new controller that might or might not be reliable and is so fast that it would still seem fast if I taped myself using the computer and replayed it in slow motion. What I want is an x25m-like drive at 160 GB for under $200. Still extremely fast, legendary (for SSD's) reliability, and make it affordable.

    The reason I don't buy Ferrari's right now is not because I don't think they're fast enough, it's because they COST too much.
    Reply
  • RU482 - Thursday, February 17, 2011 - link

    this might be the problem with OCZ. They are an SSD marketing company with a manufacturing division Reply
  • TimK - Thursday, February 17, 2011 - link

    Damn, Anand, so this is what an engineering degree will get you, not to mention some heavy duty skill at writing. Comprehensive and comprehensible. Thanks very much. At your recommendation I bought an early Vertex 30GB SSD for my unibody MacBook. From time to time I take it out, thinking to have everything in one place on a bigger drive, but I just can't let go of the speed. It's still working great. Reply
  • dlang1234 - Thursday, February 17, 2011 - link

    The Samsung 470 seems to be in a lot of the benchmarks but not all, and seems to do well in every one that it is listed in.

    I can't seem to find a review of it here, but would be interested in it possibly.
    Reply
  • markjx1 - Thursday, February 17, 2011 - link

    No mention of the fact this thing was originally slated with the SF-2000 controller, which proved to be plagued with problems in the lab and the dirty little secret no vendor would discuss at CES which was why no one had anything SF-2000 based up and running. And now OCZ had to resort to slapping Sandforce's enterprise class SF-2500 controller on it.

    Great except its going to be hella expensive and not cost competitive with the Crucial C400 unless OCZ bleeds margin, and given they took a $25 million bank loan recently, well let's just say OCZ isn't a company I'd rely on to fulfill a warranty replacement a couple years down the road when your drive dies.

    Lastly, notice the "hardware isn't final" disclaimers all over the article. This is nothing more than OCZ trying to get some buzz, and have painted themselves into a corner now if they go switching back to the SF-2000 since they've already set expectations high.
    Reply
  • jwilliams4200 - Thursday, February 17, 2011 - link

    I thought the article was fairly well done. The only problem I have with it is a passing mention to the SSD being unusuable on a Macbook Pro, and yet not a single benchmark shows any problems with the SSD. It seems the benchmark suite Anand is using needs to have some more components added. Perhaps a latency test? Reply
  • Anand Lal Shimpi - Sunday, February 20, 2011 - link

    Check back on the site by the end of the week ;)

    Take care,
    Anand
    Reply

Log in

Don't have an account? Sign up now