A Note on Real World Performance

The majority of our SSD test suite is focused on I/O bound tests. These are benchmarks that intentionally shift the bottleneck to the SSD and away from the CPU/GPU/memory subsystem in order to give us the best idea of which drives are the fastest. Unfortunately, as many of you correctly point out, these numbers don't always give you a good idea of how tangible the performance improvement is in the real world.

Some of them do. Our 128KB sequential read/write tests as well as the ATTO and AS-SSD results give you a good indication of large file copy performance. Our small file random read/write tests tell a portion of the story for things like web browser cache accesses, but those are difficult to directly relate to experiences in the real world.

So why not exclusively use real world performance tests? It turns out that although the move from a hard drive to a decent SSD is tremendous, finding differences between individual SSDs is harder to quantify in a single real world metric. Take application launch time for example. I stopped including that data in our reviews because the graphs ended up looking like this:

All of the SSDs performed the same. It's not just application launch times though. Here is data from our Chrome Build test timing how long it takes to compile the Chromium project:

Build Chrome

Even going back two generations of SSDs, at the same capacity nearly all of these drives perform within a couple of percent of one another. Note that the Vertex 3 is even a 6Gbps drive and doesn't even outperform its predecessor.

So do all SSDs perform the same then? The answer there is a little more complicated. As I mentioned at the start of this review, I do long term evaluation of all drives I recommend in my own personal system. If a drive is particularly well recommended I'll actually hand out drives for use in the systems of other AnandTech editors. For example, back when I wanted to measure actual write amplification on SandForce drives I sent three Vertex 2s to three different AnandTech editors. I had them use the drives normally for two - three months and then looked at the resulting wear on the NAND.

In doing these real world use tests I get a good feel for when a drive is actually faster or slower than another. My experiences typically track with the benchmark results but it's always important to feel it first hand. What I've noticed is that although single tasks perform very similarly on all SSDs, it's during periods of heavy I/O activity that you can feel the difference between drives. Unfortunately these periods of heavy I/O activity aren't easily measured, at least in a repeatable fashion. Getting file copies, compiles, web browsing, application launches, IM log updates and searches to all start at the same time while properly measuring overall performance is near impossible without some sort of automated tool. Unfortunately most system-wide benchmarks are more geared towards CPU or GPU performance and as a result try to minimize the impact of I/O.

The best we can offer is our Storage Bench suite. In those tests we are actually playing back the I/O requests captured of me using a PC over a long period of time. While all other bottlenecks are excluded from the performance measurement, the source of the workload is real world in nature.

What you have to keep in mind is that a performance advantage in our Storage Bench suite isn't going to translate linearly into the same overall performance impact on your system. Remember these are I/O bound tests, so a 20% increase in your Heavy 2011 score is going to mean that the drive you're looking at will be 20% faster in that particular type of heavy I/O bound workload. Most desktop PCs aren't under that sort of load constantly, so that 20% advantage may only be seen 20% of the time. The rest of the time your drive may be no quicker than a model from last year.

The point of our benchmarks isn't to tell you that only the newest SSDs are fast, but rather to show you the best performing drive at a given price point. The best values in SSDs are going to be last year's models without a doubt. I'd say that the 6Gbps drives are interesting mostly for the folks that do a lot of large file copies, but for most general use you're fine with an older drive. Almost any SSD is better than a hard drive (almost) and as long as you choose a good one you won't regret the jump.

I like the SF-2281 series because, despite things like the BSOD issues, SandForce has put a lot more development and validation time into this controller than its predecessor. Even Intel's SSD 320 is supposed to be more reliable than the X25-M G2 that came before it. Improvements do happen from one generation to the next but they're evolutionary - they just aren't going to be as dramatic as the jump from a hard drive to an SSD.

So use these numbers for what they tell you (which drive is the fastest) but keep in mind that a 20% advantage in an I/O bound scenario isn't going to mean that your system is 20% faster in all cases.

Patriot's Wildfire Random & Sequential Read/Write Speed
Comments Locked

112 Comments

View All Comments

  • PartEleven - Sunday, June 26, 2011 - link

    Anand, I'm hoping this question reaches you but I was wondering if you can comment on the Vertex 3 oem version, the V3LT-25SAT3-240G.oem. Official specs rate it as slightly slower than the retail Vertex 3, but when people asked about it on the ocz forums the mods there say it's because of different NAND. Supposedly this drive uses the same Toshiba 32nm toggle nand used as these MAX IOPS drives. Why is it then that the oem drives are slower than the MAX IOPS drives? I thought at first they might be using higher density chips so you have less NAND dies running in parallel, but you mention here that Toshiba's NAND only gets 4GB per die. What do you think is the cause for the performance difference? OCZ seems pretty reluctant to give a detailed answer.
  • cakeab - Sunday, June 26, 2011 - link


    --Something unexpected surprise--

    Hello. My friend

    === {{w w w }} {{be tter whole saler }} {{ u s }} ====

    Dedi cated service, the new style, believing you will love it!!!

    WE ACCEPT PYA PAL PAY MENT

    YOU MUST NOT MISS IT!!!

    thank you!!!

    -- w w w . jordan forworld . c o m -
  • aritai - Sunday, June 26, 2011 - link

    Has been working well (no bluescreens, no crashes, no hangs, no issues w/ sleep-resume or use of bitlocker on the drive) with a Thinkpad W520/4270CT since first week of April (W7ultimate+SP1, current w/ MS, NVIDIA and Lenovo patches and drivers).

    However on a restart (but not on a shutdown to power off followed by power back on) there's some SATA3/Intel/IBM BIOS issue that seems to hang on the SSD read - it eventually times out (after perhaps as long as a minute) and continues booting. Rather than wait, an option is to simply force a power off (hold power button for 5 seconds) followed by re-powering on. A minor nit given Lenovo has yet to announce support for 6gbyte/s SSDs, and other than this the 4core/8thread 16gbyte dram sandybridge machine is a developer's dream (I run a handful of VMs on a 2nd SSD in the media bay, can't even tell they're VMs).

    And with the 2nd-battery (that attaches on the bottom like a mini-dock), I can work all the way to Hong Kong (14+ hours) on batteries (a good thing, since there's no travel adapter yet - and may never be given they want to support 2 hour recharge and require 170W supply that no seat power can deliver. Which is a pity because the W520 automagically switches to integrated graphics and Intel turns off cores (so power meter shows < 8 watt average use in extended battery life mode). So even a 60 watt travel adapter world work save for Lenovo's BIOS doesn't / has yet to permit it.
  • danrichards - Tuesday, June 28, 2011 - link

    MTBF, Mean Time Between Failure. Frequently advertised at 2+million hours. What kind of claim is this?

    Does this mean I place the drive on the shelf for 200 years, put it in to an antique computer in 200 years and it should still work? Until otherwise proven, I think so...

    I bought 60GB Agility 2 for my laptop and a 120GB Vertex 3 for my desktop and both failed within two months. I'm in the process of returning one to Newegg and replacing another with OCZ (the Agility 2 for the 2nd time). The Vertex 3, I got a F4 BSOD at least twice daily (I didn't think it was possible to have 2 bad drives so I spent too many hours parting out my system and formatting it 3 times and trying different drivers to no success). Newegg was sympathetic and gave me a refund after the 30 refund period.

    By the way, when one of these drive fails, there is no getting out Stellar Phoenix and recovering your data, they just pop and your data is vaporized. Do not use a SSD unless you have a solid backup plan...and don't even think using an SSD will increase your productivity. If I added up the downtime from work, frustration time, and troubleshooting time I spend with my machines, I'll give that up for a fast HDD that lasts 3-5 years (and is recoverable) and takes 4-5 seconds longer to load my Outlook.

    I was extremely enthusiastic about SSDs and I'm disappointed to detail such a poor report.
  • PR3ACH3R - Wednesday, June 29, 2011 - link

    I must agree with everything you said, its sad it is up to small builders & forum members to set the record straight about the SSD situation.

    If theres anything you got wrong is the MTBF abbrev ..
    regarding SSDs it actually means: Mad Total Bork Freakshow.
  • jcompagner - Tuesday, June 28, 2011 - link

    I was one of the first here that had a 240GB V3. That had the initial firmware of 2.02, with that firmware installing on my Dell XPS17 (SandyBridge) notebook that was quite difficult to do.

    But after i find out about 2 things: 1 use the latest intel rapid store driver (else BSOD directly after install with the first boot) and after install make sure you disable the LPM settings (else you will get stutter) everything was pretty smooth i had no BSOD after that and it was quite solid.
    So the only problem with V3 was the install part on a laptop of Dell which is quite a high volume laptop out there. (and yes there are plenty other dell laptops that have the same problem because underneath they use pretty much the same stuff)

    What i don't get is why OCZ seems to test many things on desktop boards, i hear always Asus board X or Gigabyte board Y. But who is using that? SSD are the perfect things in laptops because there is where the most gain is, and i wonder who is using desktops anyway currently (i don't know them anymore)

    After that firmware 2.06 came out and then i made a mistake by upgrading to it (and let me say that the upgrade for a system drive what in a laptop almost always is the case....) is quite hard. But after that BSOD started happening.. 2.08 same stuff still BSOD, now with 2.09 BSOD stopped it is solid again, and i must say that my performance is still quite good. i don't notice in real life or with testing any real performance penalty.

    So now for me everything is quite good again. I never reinstalled or did a secure erase (that really cost a lot of time!) .

    But i wouldn't really recommend to none real technical users a OCZ drive at the moment. Installation, firmware updates are all quite hard and you really know what to do.
  • kaikaihhh - Tuesday, June 28, 2011 - link



    hello,welcome to www.voguecatch.us,there have more top goods,like hand bag,t shirt,sun glass and so

    on ,i hope everyone will like them,thanks
  • doodles - Sunday, July 10, 2011 - link

    You asked what I'd do if I won a Eee Pad Transformer or a Samsung Galaxy Tab 10.1...so many ideas came to mind that I felt my skull crack. I'd keep up with my husband's medicines, (lung cancer), set reminders, keep his appointment schedules, And it might even entertain me while I do that interminable waiting in the dr.'s office.
  • AeroJoe - Wednesday, July 13, 2011 - link

    Exactly which version of Iometer are you using these days to run your benchmarks? The latest version at www.iometer.org is many years old - or am I looking in the wrong spot?
  • Jphelps2630 - Monday, July 18, 2011 - link

    I'm one of the lucky owners of a Vertex 3 that has the BSOD problems. Just can't get it stable. Besides BSODs, it disappears from the BIOS and corrupts the file system so Windows and Office are trashed a couple of hours after loading. It's been upgraded to the latest 2.09 firmware which didn't help.

    Very disappointing product. Spent a lot of money and it just doesn't work. Waiting for help from OCZ. Will let you know what they say.

    I7 2600k on Asus p8z68 pro, 8gb Corsair RAM, Win7 64

Log in

Don't have an account? Sign up now