Random Read/Write Speed

The four corners of SSD performance are as follows: random read, random write, sequential read and sequential write speed. Random accesses are generally small in size, while sequential accesses tend to be larger and thus we have the four Iometer tests we use in all of our reviews.

Our first test writes 4KB in a completely random pattern over an 8GB space of the drive to simulate the sort of random access that you'd see on an OS drive (even this is more stressful than a normal desktop user would see). I perform three concurrent IOs and run the test for 3 minutes. The results reported are in average MB/s over the entire time. We use both standard pseudo randomly generated data for each write as well as fully random data to show you both the maximum and minimum performance offered by SandForce based drives in these tests. The average performance of SF drives will likely be somewhere in between the two values for each drive you see in the graphs. For an understanding of why this matters, read our original SandForce article.

Iometer - 4KB Random Write, 8GB LBA Space, QD=3

Peak performance on the 120GB Vertex 3 is just as impressive as the 240GB pre-production sample as well as the m4 we just tested. Write incompressible data and you'll see the downside to having fewer active die, the 120GB drive now delivers 84% of the performance of the 240GB drive. In 3Gbps mode the 240 and 120GB drives are identical.

Many of you have asked for random write performance at higher queue depths. What I have below is our 4KB random write test performed at a queue depth of 32 instead of 3. While the vast majority of desktop usage models experience queue depths of 0 - 5, higher depths are possible in heavy I/O (and multi-user) workloads:

Iometer - 4KB Random Write, 8GB LBA Space, QD=32

At high queue depths the gap between the 120 and 240GB Vertex 3s grows a little bit when we're looking at incompressible data.

Iometer - 4KB Random Read, QD=3

Random read performance is what suffered the most with the transition from 240GB to 120GB. The 120GB Vertex 3 is slower than the 120GB Corsair Force F120 (SF-1200, similar to the Vertex 2) in our random read test. The Vertex 3 is actually about the same speed as the old Indilinx based Nova V128 here. I'm curious to see how this plays out in our real world tests.

Sequential Read/Write Speed

To measure sequential performance I ran a 1 minute long 128KB sequential test over the entire span of the drive at a queue depth of 1. The results reported are in average MB/s over the entire test length.

Iometer - 128KB Sequential Write

Highly compressible sequential write speed is identical to the 240GB drive, but use incompressible data and the picture changes dramatically. The 120GB has far fewer NAND die to write to in parallel and in this case manages 76% of the performance of the 240GB drive.

Iometer - 128KB Sequential Read

Sequential read speed is also lower than the 240GB drive. Compared to the SF-1200 drives there's still a big improvement as long as you've got a 6Gbps controller.

The Vertex 3 120GB AnandTech Storage Bench 2011
POST A COMMENT

154 Comments

View All Comments

  • mpx999 - Sunday, April 10, 2011 - link

    That's a big limitation for number of total I/Os. Eg. in 300MB/s SATA-II you'd be limited to ~37.5k IOPS with 8kB transfers, less than some SSDs are capable of, while the limit with 4kB clusters is 2 times higher, which is still beyond current SSDs for random transfers.

    4kB clusters are a perfect match for x86 processors that use hardware 4kB page size, as each page size is one block on disk. This is especially important for pagefile reads, which tend to be random by nature, rather than pagefile writes that are mostly sequential dumps of memory content. Some Unix systems may use 8kB disc block sizes because it's a default page size for SPARC and Itanium processors. For Power and ARM 4kB is the default but also 64kB can be used. So I'd advice against using large (larger than hw. page size) block sizes on a system/boot partition.

    8kB disk block sizes can be useful on partitions dedicated for SQL Server as default database blocks are 8kB for SQL Server, so it's doing 8kB transfers anyway. Oracle supports multiple page sizes and their advice is:

    http://www.dba-oracle.com/t_multiple_blocksizes_su...

    "Oracle recommends smaller Oracle Database block sizes (2 KB or 4 KB) for online transaction processing (OLTP) or mixed workload environments and larger block sizes (8 KB, 16 KB, or 32 KB) for decision support system (DSS) workload environments."

    32kB cluster sizes are a default value on flash cards for digital cameras, as sequential writes of large prictures are done on them.

    BTW. The slow speed of both Hynix and Intel 25nm versions of Vertex 2 may be because it's aging controller cannot deal with 8kB flash pages.
    Reply
  • martixy - Monday, April 11, 2011 - link

    So... the SSD market is shaping up to the just about the most confusing and volatile market out there.
    At least that's the impression I get from the articles here. I mean you'd probably need your very own market research team if you want to get a good deal on an SSD.
    Meh...
    Reply
  • gixxer - Monday, April 11, 2011 - link

    So if you have read all the comments up to this point with the OCZ verus Intel debate.

    Where would you spend your money?

    A vertex 3, Intel 320, or Intel 510
    Reply
  • MamiyaOtaru - Tuesday, April 12, 2011 - link

    it's not scientific, but after looking at the newegg user review averages, not touching anything other than intel Reply
  • tech6 - Monday, April 11, 2011 - link

    Thank you Anand - you're a real asset to the tech community!

    While OCZ has a potentially great product, they are really proving to be their own worst enemy. Until they demonstrate some maturity I will choose an Intel 320 instead. It may not be the newest or fastest but the G1/G2/G3 series drives have so far proven to be reasonably reliable and perform as advertised.
    Reply
  • ClagMaster - Monday, April 11, 2011 - link

    Seems to me the Intel 510 offers better mainstream performance than the Vertex 3.

    And I also think Intel does a better job with balancing firmware with memory technology, and has better configuration control of what memory is used for their SSD's.

    I think suffering a 20% risk of getting a Vertex 3 SSD with slower memory is too high for what I pay for such a device
    Reply
  • qax - Wednesday, April 13, 2011 - link

    This sort of commitment can make me wanna buy OCZ next time, thats for sure.
    Although they shipped slow drives, they accept the responsability, and thats a big thing in my world.
    I´ve totaly stopped buying som vendors that are too cheap, resulting in useless/nonexisting support.
    Same reason why i allways buy from a psysical shop and never from internetshops.
    I need psysical adress not too far from my own adress, where i can turn in a faulty product.
    For me an SSD driver will allways be used for OS, programs and games. For space i would have HDD.
    So space on SSD is no concern.
    Reply
  • javishd - Wednesday, April 13, 2011 - link

    I think I'm not alone here. Waiting to buy after some real comparisons of the $300 120gb range. We look to you for help with the decision! Thanks for your long term commitment to ssd. I've been on board since the x25 g1, and I really appreciate all the info from you guys. I'll keep checking every day hoping.... Reply
  • alexb1 - Wednesday, April 13, 2011 - link

    Anand, THANK YOU VERY VERY MUCH!

    Honestly, there is NO ONE ELSE in the IT industry advocating for enthusiast consumers like you... kudos!

    I am A VICTIM of OCZ Marketing of Vertex2, and got a 80GB recently that basically does EXTREMELY POOR compared to ALL benchmarks. To top it all off, it is NOT part of the *recall* drives as its size hasn't been affected with the 25nm transition... so I am just about to return and take a 15% restocking fee.

    Now, my question is... should I even bother looking for a 34nm drive, or one of the newer 25nm drives would just do ok as boot drive in Win7? My MOST CONCERN is reliability and longevity.

    I can either get a F60-A (25nm), F60 (34nm), or OCZ Vertex2 (25nm)... The 25nm being $30-40 CHEAPER!
    Reply
  • faster - Thursday, April 14, 2011 - link

    Today the Intel 510 250GB drive mentioned in these benchamarks can be had at newegg for $615 (-$40 off promo until 4/19, $575).

    The Egg also has the Revo Drive X2 240GB at $570 (was $680).

    So we as consumers have the new 250 GB 6Gbps SATA3 SSD drives vs. the 240GB PCIE X4 integrated bootable RAID 0 card within $5 of the same price point.

    Certainly a bootable add in card is not a straight comparison to a single SSD drive, but at the same price point, in the cutting edge overpriced enthusiast level, it is a sensible comparison.

    Anandtech should put the RevoX2 in these benchmark charts to show how they measure up. It would be more interesting than comparing a WD Raptor represented by tiny slivers on the performance comparisons. I believe, generally speaking, that the Revo would come away with faster read speeds and be neck in neck with fastest SSD drives on write speeds. AnandTech had or has a RevoDrive that they reviewed in the past. Is that thing still laying around?
    Reply

Log in

Don't have an account? Sign up now