Random Read Performance

One of the major changes in our 2015 test suite is the synthetic Iometer tests we run. In the past we used to test just one or two queue depths, but real world workloads always contain a mix of different queue depths as shown by our Storage Bench traces. To get the full scope in performance, I'm now testing various queue depths starting from one and going all the way to up to 32. I'm not testing every single queue depth, but merely how the throughput scales with the queue depth. I'm using exponential scaling, meaning that the tested queue depths increase in powers of two (i.e. 1, 2, 4, 8...). 

Read tests are conducted on a full drive because that is the only way to ensure that the results are valid (testing with an empty drive can substantially inflate the results and in reality the data you are reading is always valid rather than full of zeros). Each queue depth is tested for three minutes and there is no idle time between the tests. 

I'm also reporting two metrics now. For the bar graph, I've taken the average of QD1, QD2 and QD4 data rates, which are the most relevant queue depths for client workloads. This allows for easy and quick comparison between drives. In addition to the bar graph, I'm including a line graph, which shows the performance scaling across all queue depths. To keep the line graphs readable, each drive has its own graph, which can be selected from the drop-down menu.

I'm also plotting power for SATA drives and will be doing the same for PCIe drives as soon as I have the system set up properly. Our datalogging multimeter logs power consumption every second, so I report the average for every queue depth to see how the power scales with the queue depth and performance.

Iometer - 4KB Random Read

Random read performance at small queue depths has never been an area where the Vector 180 has excelled in. Given that these are one of the most common IOs, it's an area where I would like to see improvement on OCZ's behalf.

Iometer - 4KB Random Read (Power)

Power consumption, on the other hand, is excellent, which is partially explained by the lower performance. 

Samsung SM951 512GB

Having a closer look at the performance data across all queue depths reveals the reason for Vector 180's poor random read performance. For some reason, the performance only starts to scale properly after queue depth of 4, but even then the scaling isn't as aggressive as on some other drives. 

Random Write Performance

Write performance is tested in the same way as read performance, except that the drive is in a secure erased state and the LBA span is limited to 16GB. We already test performance consistency separately, so a secure erased drive and limited LBA span ensures that the results here represent peak performance rather than sustained performance.

Iometer - 4KB Random Write

In random write performance the Vector 180 does considerably better, although it's still not the fastest drive around. 

Iometer - 4KB Random Write (Power)

Even though the random write performance doesn't scale at all with capacity, the power consumption does. Still, the Vector 180 is quite power efficient compared to other drives.

Samsung SM951 512GB

The Vector 180 scales smoothly across all queue depths, but it could scale a bit more aggressively because especially the QD4 score is a bit low. On a positive side, the Vector 180 does very well at QD1, though.

AnandTech Storage Bench - Light Sequential Performance
POST A COMMENT

89 Comments

View All Comments

  • LB-ID - Thursday, March 26, 2015 - link

    Looks like an overpriced product that doesn't stack up against competition in the same price range. Given OCZ's extensive track record of failures and attempts to use their user base as unpaid beta testers I can understand their desire to include a feature to give more peace of mind, but in reality it's just not that useful and certainly insufficient to overcome years of accumulated ill will. Reply
  • serndipity - Thursday, March 26, 2015 - link

    The specifications say it all.

    On a $, performance, reliability, endurance, warranty basis, the OCZ 180 falls significantly short of even the consumer grade competition (e.g. Crucial or Samsung).

    Unfortunately, the OCZ story when from deceiving investors, to customers, ending in bankruptcy.

    Sadly, the same management etc., remains in place

    Be smart and avoid OCZ
    Reply
  • ocztosh - Monday, March 30, 2015 - link

    Hi LB-ID, thank you for your feedback. We have shipped countless Barefoot 3 based drives across multiple series products and never once had to rev silicon. We have made updates to firmware to continually improve our products. The addition of the PFM+ feature was a decision to support customers that are really on the edge of enthusiast and workstation. This is a required feature for many enterprise drives and we felt there was a value to including this feature into our Vector 180 Series. We agree that not every customer necessarily needs this feature, and for those customers across the client spectrum we have other BF3 based drives that do not include the additional circuitry, but for those customers that really would like that extra layer of protection we were able to integrate this feature without a price premium over our previous Vector 150 Series. We have already received a very positive response from some users but will continue to offer a range of drives to meet the needs of different user applications. Reply
  • voicequal - Friday, March 27, 2015 - link

    Wow, great review and a ton of new tests and data. The bathtub curve on the mixed sequential read/write performance will be very interesting to compare to forthcoming NVMe drives. I was surprised by how much the IOPS were reduced by commingling of sequential reads/writes. Seems to be room for improvement in this area. Reply
  • Ethos Evoss - Saturday, March 28, 2015 - link

    The worst company of SSD's some OCZ or OWC or PVC .. jeez trash.. it's been sold to toshiba anyway .. Reply
  • ocztosh - Monday, March 30, 2015 - link

    Hello Ethos Evoss. We are sorry that you feel this way and/or if you had a negative experience in the past. We are indeed now part of Toshiba and OCZ Storage Solutions is a very different organization as a subsidiary of Toshiba. Toshiba has provided the ability to vastly enhance resources for product development as well as given us complete access to their premium NAND. We certainly will continue to strive to meet the high expectations of you, our valued customers. Thank you again for your input. Reply
  • daerron - Tuesday, May 26, 2015 - link

    Nice in depth analysis Anandtech! Read the article as I'm receiving a new Vector 180 240GB drive this week as my original Vector bricked itself earlier this month after around 2 years of service. I have to say that I'm really impressed with OCZ's customer service as I couriered the drive last week and will be receiving a brand new and latest SSD in return this week. Fortunately I had my data backed up as it really just died without any warning. Based on the analysis I was also thinking this would be a killer laptop drive, till I saw the lack of slumber support which is a bit of a disappointment and opportunity missed. Still the PFM+ and low power usage is also most welcome in my workstation PC. We have regular power cuts in my country so its great to have that extra peace of mind. Reply
  • bogdan_kr - Thursday, December 17, 2015 - link

    Hello guys. I would like to ask how exactly this Storage Bench - Light is designed. The description says it is designed to be an accurate illustration of basic usage with Total IO Operations 832,339, Total GB Read 17.97 and Total GB Written 23.25.
    With its 23 GB of writes it should account for roughly two or three days of average usage (i.e. 7-11GB per day).

    How long (typically) does it take to finish this bench?
    Is it designed to last for few hours (which would account for a typical daily use) or is it designed to finish as fast as possible, in few minutes perhaps?
    Reply
  • bogdan_kr - Saturday, January 23, 2016 - link

    I am aware that most likely it is a rhetorical question but can anyone from AnandTech answer it, please? I just wanted to be sure about that benchmark. Reply

Log in

Don't have an account? Sign up now