Mixed Random Read/Write Performance

Mixed read/write tests are also a new addition to our test suite. In real world applications a significant portion of workloads are mixed, meaning that there are both read and write IOs. Our Storage Bench benchmarks already illustrate mixed workloads by being based on actual real world IO traces, but until now we haven't had a proper synthetic way to measure mixed performance. 

The benchmark is divided into two tests. The first one tests mixed performance with 4KB random IOs at six different read/write distributions starting at 100% reads and adding 20% of writes in each phase. Because we are dealing with a mixed workload that contains reads, the drive is first filled with 128KB sequential data to ensure valid results. Similarly, because the IO pattern is random, I've limited the LBA span to 16GB to ensure that the results aren't affected by IO consistency. The queue depth of the 4KB random test is three.

Again, for the sake of readability, I provide both an average based bar graph as well as a line graph with the full data on it. The bar graph represents an average of all six read/write distribution data rates for quick comparison, whereas the line graph includes a separate data point for each tested distribution. 

Iometer - Mixed 4KB Random Read/Write

The Vector 180 does better in mixed 4KB random IO than the 850 Pro, but it's a bit slower than the rest of the drives.

Iometer - Mixed 4KB Random Read/Write (Power)

Fortunately the power consumption is still excellent.

Samsung SM951 512GB

Vector 180's problem is its low random read performance because the performance gets better as more writes are thrown into the mix. 

Mixed Sequential Read/Write Performance

The sequential mixed workload tests are also tested with a full drive, but I've not limited the LBA range as that's not needed with sequential data patterns. The queue depth for the tests is one.

Iometer - Mixed 128KB Sequential Read/Write

In mixed sequential tests the Vector 180 does slightly better in the sense that the difference between drives in the order of 10% when excluding the 850 Pro.

Iometer - Mixed 128KB Sequential Read/Write (Power)

Similar to what we saw in the sequential tests, the write power consumption is fairly high, which also increases the average power consumption and the Vector 180 no longer enjoys an advantage over the other drives.

Samsung SM951 512GB

Vector 180's "bathtub" curve is pretty average, but as we can see here the power scales as soon as the portion of writes is increased, which isn't unique but for instance the 850 Pro and Extreme Pro don't exhibit such behavior.

Sequential Performance ATTO & AS-SSD
Comments Locked

89 Comments

View All Comments

  • KAlmquist - Tuesday, March 24, 2015 - link

    Vector 180 vx. MX 100:

    I think that the Crucial MX 100 will be a bit faster than the Vector 180 under typical usage, though the Vector 180 does outperform the MX 100 on some benchmarks. Both drives have partial power loss protection. The Vector 180 has a 5 year warranty vs. the 3 year warranty on the MX 100, but a lot of people will be looking to upgrade from SATA to PCIe SSD's before the 3 year warranty expires. In short, I don't see any reason to pay a premium price for the Vector 180.
  • MrCommunistGen - Tuesday, March 24, 2015 - link

    If only HIPM+DIPM worked (yes I know its a hardware limitation of the platform) this looks like it'd be a great laptop SSD due to such low power consumption in the various workloads measured here.
  • djsvetljo - Tuesday, March 24, 2015 - link

    Two dead OCZ drives - there will never be a 3rd one. One of the drives was from the era of the bitcoins boom ( when they were easy to mine). Lost 150 coins there ( that's over $50 000). They stupid thing locked up due to power issues ( too many power cycles).

    STAY AWAY FROM OCZ
  • Antronman - Wednesday, March 25, 2015 - link

    Well the thing is, the internals are drastically different right now.

    I've been in the market for a good SSD for a while. These drives seem to perform well. Sadly outperformed by the 850 Pro drives, but I do think that the enclosure is actually very aesthetically pleasing. If the cost could be driven down a lot, I'd be very interested in the 180.
  • mapesdhs - Wednesday, March 25, 2015 - link

    You're right, they need to have a price advantage with the 180 to pull people in. Also,
    availability needs to be good - in the past it's been rather sketchy with the 150, which
    means prices tend to creep up from a small number of suppliers.

    Ian.
  • mapesdhs - Wednesday, March 25, 2015 - link

    More than 30 OCZ drives, all working fine. Some had bad luck, others used Marvell ports
    and blame OCZ. It varies.

    As for coins, well boohoo, not real money unless they're converted back to $.

    Ian.
  • ocztosh - Monday, March 30, 2015 - link

    Hi mapesdhs, thank you for your feedback and great to hear the drives are working well for you. We greatly appreciate both your business and support.
  • FalcomPSX - Tuesday, March 24, 2015 - link

    I've owned i think three OCZ drives in the past, they've all bricked on me within about a year. Never again will I purchase their shoddy products. While i was able to get warranty replacments each time, and the customer service is decent, the product itself is just not reliable in any way. I don't know if the new ones are improved at all, but i'm not risking MY data to find out.
  • ocztosh - Wednesday, March 25, 2015 - link

    Hello FalcomPSX, thank you for your comments and sorry to hear that you has a problem with previous drives. We are a new organization under Toshiba and have made significant changes to everything from processes to production. We understand how you feel and hope that one day we will have the opportunity to demonstrate the reliability of our current products. Thank you again for your feedback
  • NeatOman - Wednesday, March 25, 2015 - link

    Battery backup should be built into the PSU for workstations and servers, google does this for their data centers.. why shouldn't servers and workstations. All you need is 1 minute for the average workstation to go into hibernation until power is back on IMO.

Log in

Don't have an account? Sign up now