Latency vs. Bandwidth: What to Look for in a SSD

It took me months to get my head wrapped around it, but I think I finally get it. We often talk about the concepts of bandwidth and latency but rarely are they as tangible as they are here today.

When I speak of latency I’m talking about how long it takes to complete a request, or fetch a block of data. When I mention bandwidth, I’m talking about how much you can read/write at once. Think of latency as the speed limit and bandwidth as the number of lanes on a high way.

If you’re the only car on the highway, you’re going to notice the impact of latency more than bandwidth. A speed limit of 70 mph instead of 35 is going to impact you much more than if you added more lanes to the road.

If you’re a city planner however and your only concern is getting as many people to work and back, you’re going to notice the impact of bandwidth more than latency. It doesn’t matter how fast a single car can move, what matters is how many cars you can move during rush hour traffic.

I’d argue that if you’re a desktop user and you’re using an SSD as a boot/application drive, what will matter most is latency. After you’ve got your machine setup the way you want it, the majority of accesses are going to be sequential reads and random reads/writes of very small file sizes. Things like updating file tables, scanning individual files for viruses, writing your web browser cache. What influences these tasks is latency, not bandwidth.

If you were constantly moving large multi-gigabyte files to and from your disk then total bandwidth would be more important. SSDs are still fairly limited in size and I don’t think you’ll be backing up many Blu-ray discs to them given their high cost per GB. It’s latency that matters here.

Obviously I’ll be testing both latency and bandwidth, but I wanted to spend a moment talking about the synthetic latency tests.

Iometer is a tool that can simulate any combination of disk accesses you can think of. If you know how an application or OS hits the disk, iometer can simulate it. While random disk accesses are the reason that desktop/notebook hard drives feel so slow, the accesses are generally confined to particular areas of the disk. For example, when you’re writing a file the OS needs to update a table mapping the file you’re writing to the LBAs it allocated for the file. The table that contains all of the LBA mapping is most likely located far away from the file you’re writing, thus the process of writing files to the same area can look like random writes to two different groups of LBAs. But the accesses aren’t spread out across the entire drive.

In my original X25-M article I ran a 4KB random write test over the entire span of the drive. That’s a bit more ridiculous than even the toughest user will be on his/her desktop. For this article I’m limiting the random write test to an 8GB space of the drive; it makes the benchmark a little more realistic for a desktop/notebook workload.

The other thing I’ve done is increased the number of outstanding IOs from 1 to 3. I’ve found that in a multitasking user environment Vista will generally have a maximum of 3 or 4 outstanding IOs (read/write requests).

The combination of the two results in a 100% random file write of 4KB files with 3 outstanding IOs to an 8GB portion of the drive for 3 minutes. That should be enough time to get a general idea of how well these drives will perform when it comes to random file write latency in a worst case, but realistic usage scenario.

The Verdict The Return of the JMicron based SSD
POST A COMMENT

250 Comments

View All Comments

  • siberx - Thursday, March 19, 2009 - link

    This is, very likely, the best article I have ever read, period. Online, in magazines, about any subject... this was an absolutely fantastic read. Suddenly, all smoke surrounding SSDs has cleared and the truth shines through in editorial brilliance. It's great to see that at least some computer news sites out there can still cut through the crap and get to the heart of the issue. My already high opinion of AnandTech has risen even further.

    Thank you for taking the immense time it must have taken to compile and assemble all this information - this article is now a must-read for *anybody* considering purchasing an SSD, and it's just about all the background you could need in one place.

    In addition to all the extremely useful general SSD information contained within, the detailing of the issues with the JMicron controllers as well as OCZ's efforts to address the concerns to produce the best product possible (despite the reduced marketability to the uninformed) is reassuring and comforting in a world where tech companies seem more concerned with how much they can deceive their customers instead of producing quality products.

    In short, the article is a win on all fronts, thank you greatly for posting it. When I purchase my first SSD (which I'm considering doing reasonably soon) this article, its information and suggestions, and OCZs actions to resolve the issues with its drives will definitely be at the forefront of my mind.
    Reply
  • jkua - Thursday, March 19, 2009 - link

    I have to say, I really appreciate the effort and throughness with which you have covered the state of the SSD market today. As an engineer and scientist, I applaud your methods in tracking down and reporting the major issues with SSDs. As a consumer, I really appreciate the timeliness of this article as I was just thinking of putting an SSD in a netbook for a robotics application where mechanical drives are not ideal.

    Cheers!
    Reply
  • jkua - Thursday, March 19, 2009 - link

    That said, one thing I would have like to have seen is some numbers on power consumption for these drives compared to average mechanical desktop and laptop drives. Reply
  • aamsel - Thursday, March 19, 2009 - link

    Anyone have a link to the Intel HDD ERASE program that Anand referred to? Reply
  • HolyFire - Thursday, March 19, 2009 - link

    http://www.ultimatebootcd.com/download.html">http://www.ultimatebootcd.com/download.html (includes HDD erase 3.1)

    http://cmrr.ucsd.edu/people/Hughes/SecureErase.sht...">http://cmrr.ucsd.edu/people/Hughes/SecureErase.sht... (version 4.0)
    Reply
  • AnnonymousCoward - Thursday, March 19, 2009 - link

    AWESOME ARTICLE.

    The huge difference in read/write flash performance looks a lot like this article: http://www.anandtech.com/memory/showdoc.aspx?i=257...">http://www.anandtech.com/memory/showdoc.aspx?i=257...
    Reply
  • wind glider - Thursday, March 19, 2009 - link

    Thanks for the orgasmic review. Reply
  • wicko - Wednesday, March 18, 2009 - link

    Had a really good read here, thanks for the history and info, Anand. The only thing I don't understand is what the importance of random write is? What kind of task would benefit from high random write speeds (maybe copying many files at once)? I'm tempted to pick up a vertex drive but it depends on whether or not random write will be important for me. But the price... whoa, pretty damn expensive here in Canada.. http://www.ncix.com/products/index.php?sku=36023&a...">http://www.ncix.com/products/index.php?...X120G&am... - $625 for a 120GB!!! I kind of want 2, for RAID0, I have a lot of games installed (steam folder alone is 100GB lol). Might even have to raid 3 of em.. but not for $1800 lol. Reply
  • strikeback03 - Thursday, March 19, 2009 - link

    As mentioned in the article, the OS in general makes lots of random writes. Send an IM, it writes to a log. Load a website, it caches some images. Reply
  • AnnonymousCoward - Thursday, March 19, 2009 - link

    >I'm tempted to pick up a vertex drive but it depends on
    >whether or not random write will be important for me.
    Keep in mind, its random write is twice as fast as mechanical HDs.

    >But the price...
    It's only $110USD/32GB.
    Reply

Log in

Don't have an account? Sign up now