Skip to main content

OCZ Vector 150 SSD Review: A New Flagship With 19 nm Flash

Results: Tom's Hardware Storage Bench

Storage Bench v1.0 (Background Info)

Our Storage Bench incorporates all of the I/O from a trace recorded over two weeks. The process of replaying this sequence to capture performance gives us a bunch of numbers that aren't really intuitive at first glance. Most idle time gets expunged, leaving only the time that each benchmarked drive was actually busy working on host commands. So, by taking the ratio of that busy time and the the amount of data exchanged during the trace, we arrive at an average data rate (in MB/s) metric we can use to compare drives.

It's not quite a perfect system. The original trace captures the TRIM command in transit, but since the trace is played on a drive without a file system, TRIM wouldn't work even if it were sent during the trace replay (which, sadly, it isn't). Still, trace testing is a great way to capture periods of actual storage activity, a great companion to synthetic testing like Iometer.

Incompressible Data and Storage Bench v1.0

Also worth noting is the fact that our trace testing pushes incompressible data through the system's buffers to the drive getting benchmarked. So, when the trace replay plays back write activity, it's writing largely incompressible data. If we run our storage bench on a SandForce-based SSD, we can monitor the SMART attributes for a bit more insight.

Mushkin Chronos Deluxe 120 GBSMART AttributesRAW Value Increase
#242 Host Reads (in GB)84 GB
#241 Host Writes (in GB)142 GB
#233 Compressed NAND Writes (in GB)149 GB

Host reads are greatly outstripped by host writes to be sure. That's all baked into the trace. But with SandForce's inline deduplication/compression, you'd expect that the amount of information written to flash would be less than the host writes (unless the data is mostly incompressible, of course). For every 1 GB the host asked to be written, Mushkin's drive is forced to write 1.05 GB.

If our trace replay was just writing easy-to-compress zeros out of the buffer, we'd see writes to NAND as a fraction of host writes. This puts the tested drives on a more equal footing, regardless of the controller's ability to compress data on the fly.

Average Data Rate

The Storage Bench trace generates more than 140 GB worth of writes during testing. Obviously, this tends to penalize drives smaller than 180 GB and reward those with more than 256 GB of capacity.

Not to sound like a broken record, but the same trend continues as we look at average data rate results. The original Vector earns its top billing, while the newer Vector 150 takes fourth place. OCZ's Vertex 450 lands in sixth place, which is a an altogether respectable finish.

The Vector 150 does end up closer to the Vertex 450 than the original Vector, despite (or perhaps because of) its 19 nm Toggle-mode flash and the Vector's Barefoot 3 silicon. I personally put more stock in mean service time as a measure of storage performance though, for reasons outlined on the next page. So, let's check out that metric.

  • Amdlova
    time to upgrade from vertex 4 to 150
    Reply
  • CommentariesAnd More
    It looks pretty good and it does perform pretty good.
    Reply
  • enihcam
    Will Toshiba buy OCZ?
    Reply
  • jimmysmitty
    11918040 said:
    time to upgrade from vertex 4 to 150

    I just hope the quality increased. Only because at my last job we had used Vertex 3s for all of our work stations and they one by one started having random issues, from not being detected to wiping the partitions.

    I like OCZ because they help lower the price of SSDs but there has to be quality behind the price as well.
    Reply
  • Sakkura
    Some of the numbers in the bottom diagram on page 4 seem to be off. Look at the Intel 520 180GB for example; the random write bar is longer than the random read bar, but the actual IOPS numbers are the other way around.
    Reply
  • Sakkura
    11918340 said:
    11918040 said:
    time to upgrade from vertex 4 to 150

    I just hope the quality increased. Only because at my last job we had used Vertex 3s for all of our work stations and they one by one started having random issues, from not being detected to wiping the partitions.

    I like OCZ because they help lower the price of SSDs but there has to be quality behind the price as well.
    My impression is that OCZ was hit hard by the Sandforce issues, partially as a result of being an early adopter. Their newer drives seem to be reliable.
    Reply
  • cryan
    11918441 said:
    Some of the numbers in the bottom diagram on page 4 seem to be off. Look at the Intel 520 180GB for example; the random write bar is longer than the random read bar, but the actual IOPS numbers are the other way around.

    Awesome catch! The 520 seems to have the right bar length, but the label from the Intel 510. I'll sort that out, but that's a genuine not-my-fault problem. One of the very few. I can blame Excel 2013 with confidence, but kudos for the eagle eye.

    The random write bar is correct though; the SandForce-based 520, 525, and Intel 530 each pull down more random write IOps than read with incompressible data.



    Regards,
    CR
    Reply
  • kancaras
    TOM!!! you gotta unswap PCMARK 7 graph with PCMARK vantage graph!
    Reply
  • Amdlova
    I got two SSD vertex 4 128gb on my computer 3770k and on my girlfriend 3470 I never get an single error on this SSD. raid 0 or normal configs. run solid!
    Reply
  • ssdpro
    11918455 said:
    My impression is that OCZ was hit hard by the Sandforce issues, partially as a result of being an early adopter. Their newer drives seem to be reliable.

    Early on yes, but the 2nd gen SF drives really are pretty darn stable now. OCZ has had solid top tier releases since the Vertex 4. I own Vertex 4 and Vector, will probably get a 150. Hands down the worst thing they ever did was try budget/value offerings like the Petrol. I don't think there is any reason for fanboism, I own Samsung and OCZ drives and all work happily together.

    Reply