AnandTech Storage Bench 2011

Last year we introduced our AnandTech Storage Bench, a suite of benchmarks that took traces of real OS/application usage and played them back in a repeatable manner. Anand assembled the traces out of frustration with the majority of what we have today in terms of SSD benchmarks.

Although the AnandTech Storage Bench tests did a good job of characterizing SSD performance, they weren't stressful enough. All of the tests performed less than 10GB of reads/writes and typically involved only 4GB of writes specifically. That's not even enough exceed the spare area on most SSDs. Most canned SSD benchmarks don't even come close to writing a single gigabyte of data, but that doesn't mean that simply writing 4GB is acceptable.

Originally we kept the benchmarks short enough that they wouldn't be a burden to run (~30 minutes) but long enough that they were representative of what a power user might do with their system. Later, however, we created what we refer to as the Mother of All SSD Benchmarks (MOASB). Rather than only writing 4GB of data to the drive, this benchmark writes 106.32GB. This represents the load you'd put on a drive after nearly two weeks of constant usage. And it takes a long time to run.

1) The MOASB, officially called AnandTech Storage Bench 2011—Heavy Workload, mainly focuses on the times when your I/O activity is the highest. There is a lot of downloading and application installing that happens during the course of this test. Our thinking was that it's during application installs, file copies, downloading, and multitasking with all of this that you can really notice performance differences between drives.

2) We tried to cover as many bases as possible with the software incorporated into this test. There's a lot of photo editing in Photoshop, HTML editing in Dreamweaver, web browsing, game playing/level loading (Starcraft II and WoW are both a part of the test), as well as general use stuff (application installing, virus scanning). We included a large amount of email downloading, document creation, and editing as well. To top it all off we even use Visual Studio 2008 to build Chromium during the test.

The test has 2,168,893 read operations and 1,783,447 write operations. The IO breakdown is as follows:

AnandTech Storage Bench 2011—Heavy Workload IO Breakdown
IO Size % of Total
4KB 28%
16KB 10%
32KB 10%
64KB 4%

Only 42% of all operations are sequential; the rest ranges from pseudo to fully random (with most falling in the pseudo-random category). Average queue depth is 4.625 IOs, with 59% of operations taking place in an IO queue of 1.

Many of you have asked for a better way to really characterize performance. Simply looking at IOPS doesn't really say much. As a result we're going to be presenting Storage Bench 2011 data in a slightly different way. We'll have performance represented as Average MB/s, with higher numbers being better. At the same time we'll be reporting how long the SSD was busy while running this test. These disk busy graphs will show you exactly how much time was shaved off by using a faster drive vs. a slower one during the course of this test. Finally, we will also break out performance into reads, writes, and combined. The reason we do this is to help balance out the fact that this test is unusually write intensive, which can often hide the benefits of a drive with good read performance.

There's also a new light workload for 2011. This is a far more reasonable, typical every day use case benchmark. It has lots of web browsing, photo editing (but with a greater focus on photo consumption), video playback, as well as some application installs and gaming. This test isn't nearly as write intensive as the MOASB but it's still multiple times more write intensive than what we were running last year.

We don't believe that these two benchmarks alone are enough to characterize the performance of a drive, but hopefully along with the rest of our tests they will help provide a better idea. The testbed for Storage Bench 2011 has changed as well. We're now using a Sandy Bridge platform with full 6Gbps support for these tests.

AnandTech Storage Bench 2011 - Heavy Workload

We'll start out by looking at average data rate throughout our new heavy workload test:

Heavy Workload 2011 - Average Data Rate

The SX900 is slightly faster than the Vertex 3 and Force GT here, which is most likely due to the newer firmware as I noted in the incompressible sequential read/write speed section. I asked Anand to test a 120GB ADATA S511, which is based on the same SF-2281 controller and utilizes 25nm Intel MLC NAND. The SX900 and S511 should be as similar as possible; however, they don't share the same firmware version. The SX900 is reported to have firmware version 5.0.1 in Device Manager, whereas the S511 Anand tested was running 3.2.2. That's the most current firmware for the S511 and it dates back to November 2011, so this is likely the reason for the difference in performance.

Heavy Workload 2011 - Average Read Speed

Heavy Workload 2011 - Average Write Speed

The next three charts just represent the same data, but in a different manner. Instead of looking at average data rate, we're looking at how long the disk was busy for during this entire test. Note that disk busy time excludes any and all idles, this is just how long the SSD was busy doing something:

Heavy Workload 2011 - Disk Busy Time

Heavy Workload 2011 - Disk Busy Time (Reads)

Heavy Workload 2011 - Disk Busy Time (Writes)

AS-SSD Incompressible Sequential Performance AnandTech Storage Bench 2011 - Light Workload


View All Comments

  • stotticus - Friday, June 8, 2012 - link

    I was about to spring for the 256 GB Samsung 830 for my Late 2011 MBP for use as my system drive, based on this site and others' recommendations.

    On Newegg this drive is cheaper and this review is encouraging. Does anyone have any recommendations for me, as far as this drive being a good choice? My head is spinning trying to wrap around all the tech specs.
  • iceman98343 - Friday, June 8, 2012 - link

    where is your review on new vertex 4 fw? Reply
  • vectorm12 - Friday, June 8, 2012 - link

    However I'd really love a comparison between the different SSD controllers concerning write-amplification with uncompressible data.

    I'm particularly interested in this as I'm constantly evaluating drives for RAIDs aimed at RAIDs. Having a benchmark for write-amplification would really help me estimate lifespan for RAID-volumes based on SSDs.
  • TheJian - Friday, June 8, 2012 - link

    Not sure why you're not using google to get pricing which gives you the best out there. Amazon is selling the 256GB M4 for $205 (shipping included) and the 128GB for $119 (with a good 10 vendors at this price!). That's a pretty awesome price on the 256. These are not the cheapest either (with an ebay guy showing $198 - I'd still buy at amazon though). B&H has the 256 for $205 also. So multiple choices at that price. This engine heads off to newegg where you get screwed (and if you're buying an HD you also get to deal with their wonderful shipping - followed by an RMA because they can't pack a drive to save their life). Amazon and frustration free shipping FTW! :)

    I'm not going to bother checking the others as I'm only interested in the M4 or Samsung 830. I consider the rest problems (except for Intel, but they are ridiculously priced). Sandforce can go fly a kite with their firmware sucking so bad.

    Just an FYI people. GOOGLE your product and hit shopping results on the left side of the screen. Hit compare for the one that shows the most results and then total price (sort). Done.
  • TheJian - Saturday, June 9, 2012 - link

    One more comment I forgot. All your newegg hits serve to set their AUTO PRICING engine off in high gear. Which after so many hits raises the price. It's currently sitting at $144 for the 128GB Samsung 830 which you show $130 for. So all the hits in the last few hours probably drove this up $14.

    I've watched this happen on a cpu that was rising throughout the day (back when the E8400 came out). I was trying to figure out if I could afford it and just watched it rise. Luckily not many knew it was a xeon 3110 also :) Which I picked up for $20 less and with better thermals :)

    Note newegg doesn't work like this for just hits in the list, such as searching for a GTX680 or something and getting a whole list. But an actual viewing of their product page will cause the hit (for any particular product).

    Here's hoping you get your SSD for the cheapest possible! As Seagate/WD have been screwing us since the flood. Seagates profits quadrupled (140mil to 563mil) and they shipped 8% fewer drives (overcharging a bit?). How do you QUADRUPLE your profits in a catastrophe? Fabricate the catastrophe, then charge more for everything you ship...LOL. FREAKING QUADRUPLE PROFITS! They did this while shorting your warranty (which will raise the profits even more over the next few years since there will be less they replace with shorter warranty). Seagate shipped 47mil drives (vs. 51 mil previously - not much of a catastrophe). Revenues were 3.2bil (again for 8% fewer drives) vs. 2.8bil before.

    Sept 2011 (pre flood) had WD at 239mil income (53.5mil drives shipped). After flood Dec 2011, $145mil (28.5mil shipped drives, with 4Bil in cash, so $199mil for recovery is nothing to them). March 2012, once WD started screwing the customers too they posted 483mil income on 44.2mil drives shipped. So Thailand flooding is a great business for WD. They shipped roughly 10mil less drives in the first 3 months this year compared to sept 2011 pre flood and yet DOUBLED their income from 239mil in that sept PRE FLOOD quarter. So you ship 20% fewer drives (roughly) and double your profits (note that extra 244mil they made this quarter covers ALL flood costs). So this quarter WD will just collect FLOOD PROFITS. Flooding is apparently GOOD for everyone's business. To top that off they are now FULLY recovered and are shipping drives at full capacity now (as of end of May). I wouldn't be surprised to see them top 500mil by cashing in on us. There is NO reason for drives to not be at PRE FLOOD levels for pricing from EITHER company. Sorry about grammar or spelling I've been up all night...LOL

    Worse, we now have 1/2 the competition, and idiot reporters are saying pricing won't come down until 2014...UMM...WHY? They're both making money on the flood and eliminated competition. It's been a great year for WD and Seagate...WTF?

    The only way to stop them, is to CLOSE YOUR WALLET until pre flood pricing returns! For the love of GOD (or whoever...LOL), quit buying drives! Buy a bluray and a 100 blanks (25TB of storage!) and burn something. Buy an SSD. Just don't buy a stinking hard drive. :)
  • TheJian - Saturday, June 9, 2012 - link

    2.5TB..LOL. No edit...bah. Reply
  • CeriseCogburn - Sunday, June 10, 2012 - link

    Thank you for that post TheJian Reply
  • TheJian - Sunday, June 10, 2012 - link

    You're very welcome. I hope it either saves you some money or at least closes your wallet to WD and Seagate for a while :)

    I say that as I have a blu-ray burner (LG WH12LS39-sata burner) and 100 blanks in my cart at amazon... :) The blanks are Optical Quantum (shiny, I hate the white's that bleed paint all over themselves making your drives work harder to read them through the 'fog' so to speak). 100 4x BD-R discs so I can dump a good 2.5TB for $75 ($37x2 50packs), and the drive is $85. Discount shockwave has the drive for $79 but it can take 10 days to get to you and I'm out of space so went for amazon who should have it here in 3 days or so.

    Taking my own advice; I hereby close my wallet to seagate until pre-flood (I want that 2TB 2 platter version for $70 like before - they sell a 2 and 3 platter version 4heads vs 6heads until all out of the 3platters I guess). The wallet has been closed to WD for a long while. As a tech in IT I saw too many die (ran hot in dell SFF's which killed them more frequently than seagates/samsung/hitachi) and watched us switch to seagate/hitachi for our stock replacement drives. Of note, WD only had 1% enterprise marketshare until buying Hitachi (not completed yet but will go through no doubt) who has 27% of the enterprise market. Seagate has like 63% of the enterprise share.
    Jan2012 article. That one shows Hitachi at 24% but they added a few since (can't remember where I got the 27% but it's the latest info - it was a merger article like the one above but an update on proceedings to may or so). We will feel the pain of these two mergers for some time. Of course global HD shares are quite different where WD does very well (equal split with seagate pretty much). Enterprise is getting raped by these guys as they HAVE to replace dead drives. Whereas I can go blu-ray to get buy for a while :) I'm saying a prayer that ALL of you on this board seeking drives go blu-ray (with 50-100blanks) or SSD to get you all by :) And it's been a while since I prayed...LOL.
    ***promptly gets down on knees and prays, nay, begs, pleads and just plain kisses GOD's ARSE to get people to stop buying Seagate/WD for a while***
  • CeriseCogburn - Monday, June 11, 2012 - link

    Thank you again TheJian, for the further information.

    A good friend of mine determined the price scalping by general human experience, and it was great to see this, check it out and show him.

    I've avoided the spindle drive hike completely and I've been buying SSD's like mad since the spring price drop, so in a sense I've been doing my part to stick it right back to them. :-)
  • TheJian - Monday, June 11, 2012 - link

    You're welcome :)

    I still can't believe the profits, but it's easy to verify on any stock site. For anyone wanting verification just google stock:stx and hit enter, or stock:wdc and look at their quarterly reports which you can usually view the last 3-4 quarters side by side, check net profits. The top result with show 6-7 news outlets anyone can look at (google finance, yahoo, cnbc, etc).

    CeriseCogburn - Thanks for doing your part! :)

    That was a bit of typing before, though I had most of the info at the ready. I follow a more than a few tech's, pile up on NVDA and by xmas you'll get some drives for free on them :) - 2/3rd's of their stock price is in cash now...LOL. Easy money by Q1 with Kepler and Tegra3 just taking off (love or hate NV, money is MONEY! I own a radeon 8850 btw...LOL). Unfortunately only a few people will probably see these posts and the raping will continue :(

    Kristian?...Could we get an small article on WD and Seagate's profits, and the mass spanking these two are giving us on their drives? I'm guessing if a big site like anandtech did a little diddy on these bozos perhaps these "research" outfits would quit saying they expect no recovery until 2014! That's complete BS as WD has already said they're back to full production (seagate already was, only 8% drop anyway - hardly a catastrophe on their end, hence the quad profits from nowhere). Anandtech could take the bull by the horns and affect world wide pricing. If the ripoff article hit mainstream news media (TV, cnbc?...etc), I'm guessing they'd have to explain something or drop prices. Is this collusion? Price fixing? Even the IHS guy says they won't start a price war and will keep it this way as long as possible with 2 fewer competitors. Collusion?

    Most people just don't follow the stocks or realize this is happening. Until you look at profits, you may actually believe they're hurting (especially if you listen to them or their IHS SUPPLY SHILLS - he SHOULD have said drives should drop): This quarter they'll ship more drives than pre-flood. So what if Dell/HP etc signed long term contracts above flood levels. What does that have to do with MY price in the store? Why are all externals still cheap? Why didn't they go up? Surely an anti-hard drive raping article would be quite popular in this crap economy. Artificially keeping pricing high in a down economy should have consequences (at least a bit of bad publicity??).

    Anyway, thanks for doing SSD articles Kristian (and Anandtech in general). At least I'm fairly educated on my next pc part purchase (xmas SSD FTW!). Blu-ray and blanks until then...ROFL. AMEN!

Log in

Don't have an account? Sign up now