Random Read Performance

Our first test of random read performance uses very short bursts of operations issued one at a time with no queuing. The drives are given enough idle time between bursts to yield an overall duty cycle of 20%, so thermal throttling is impossible. Each burst consists of a total of 32MB of 4kB random reads, from a 16GB span of the disk. The total data read is 1GB.

Burst 4kB Random Read (Queue Depth 1)

The M.2 Optane modules offer the fastest burst random read speeds when tested as standalone drives, but Intel's caching system imposes substantial overhead. Even with that overhead, the random read performance is far above any solution that doesn't involve 3D XPoint memory. As in past reviews, we find that the Optane Memory/Optane SSD 800P has a slight advantage here over the top of the line Optane SSD 900P.

Our sustained random read performance is similar to the random read test from our 2015 test suite: queue depths from 1 to 32 are tested, and the average performance and power efficiency across QD1, QD2 and QD4 are reported as the primary scores. Each queue depth is tested for one minute or 32GB of data transferred, whichever is shorter. After each queue depth is tested, the drive is given up to one minute to cool off so that the higher queue depths are unlikely to be affected by accumulated heat build-up. The individual read operations are again 4kB, and cover a 64GB span of the drive.

Sustained 4kB Random Read

The sustained random read test covers a larger span of the drive, and the 32GB and 64GB modules are not large enough to cache the entire dataset plus the necessary cache management metadata, leaving them with performance close to that of the the hard drive. The 118GB cache is sufficient to contain the full data set for this test, and its performance is below that of the Optane drives tested as standalone drives, but still out of reach of flash-based storage.

The random read performance scaling of the Optane Memory and 800P drives is rather uneven at higher queue depths, but they do still reach very high throughput. The 118GB cache configuration doesn't scale to higher queue depths as well as the standalone SSD configuration, and the 900P hits a wall at a far lower performance level than it should based on our Linux benchmarking.

Random Write Performance

Our test of random write burst performance is structured similarly to the random read burst test, but each burst is only 4MB and the total test length is 128MB. The 4kB random write operations are distributed over a 16GB span of the drive, and the operations are issued one at a time with no queuing.

Burst 4kB Random Write (Queue Depth 1)

On the burst random write test, the larger two caching configurations perform far above what any standalone drive delivers under Windows. The 32GB Optane Memory module also scores better when used as a cache than as a standalone SSD. It is possible that Intel's caching software is also using a RAM cache and is lying to the benchmark software about whether the writes have actually made it onto non-volatile storage. However, the performance here is not actually beyond what NVMe SSDs deliver when we test them under Linux, so it's somewhat possible that there are simply some much-needed fast paths in Intel's drivers.

As with the sustained random read test, our sustained 4kB random write test runs for up to one minute or 32GB per queue depth, covering a 64GB span of the drive and giving the drive up to 1 minute of idle time between queue depths to allow for write caches to be flushed and for the drive to cool down.

Sustained 4kB Random Write

The sustained random write test covers more data than can be cached on the 64GB Optane Memory M10, so it and the 32GB cache module fall far behind mainstream SATA SSDs. The standalone Optane SSDs continue to offer great performance, and the 118GB Optane SSD 800P as a cache device tops the chart.

For the one configuration with a cache large enough to handle this test, performance scales up much sooner than in the standalone SSD configuration: QD2 gives almost the full random write speed. When the cache is too small, increasing queue depth just makes performance worse.

AnandTech Storage Bench - Light Sequential Performance
Comments Locked

96 Comments

View All Comments

  • Billy Tallis - Tuesday, May 15, 2018 - link

    Yes, but since my AMD system is a Threadripper, it won't actually represent any cost savings compared to the systems tested in this review.
  • evernessince - Wednesday, May 16, 2018 - link

    AdoredTV already did a video showing the performance improvements from StoreMi.

    https://www.youtube.com/watch?v=D3-SqJHYzC0

    AMD's solution works in the same way, in that as you run programs it stores data to the cache drive. The big difference is AMD's solution let's you use any SSD as a cache drive. This means it can be any size and it doesn't require an addition purpose. This is especially important, give the huge price tag of the larger optane drives.

    Speed wise though, assuming the Intel SSD is actually big enough to cache all your data, they are about equal. Of course, the AMD solution would be slower if you used a really low end SSD as your cache drive. It could also be much faster if you used a really good SSD though. The Intel optane drive has performance numbers similar to a 960 evo. The problem for Intel though are the small sizes and large prices. $200 for only 118GB of space is not a good solution. You could get double that space with a brand new 250GB 960 evo and it costs half as much. That's assuming you want to keep that drive for caching only, you could simply use your current SSD with the AMD solution and save $200+ altogether.

    I simply don't see a universe where Optane makes sense.
  • CheapSushi - Wednesday, May 16, 2018 - link

    You realize you can use Optane like any other SSD right? You can even use it with StorageMI.
  • MDD1963 - Tuesday, May 15, 2018 - link

    There will be no tiny Optane things inserted into/wasting an M.2 NVME slot making it SEEM like I have a 960/970; there will be a 960/970. :)
  • Valantar - Tuesday, May 15, 2018 - link

    Any chance you could test one of these drives with AMD's new caching solution? AFAIK the drives show up as regular NVME devices, so it should work in theory. Would be really interesting to see these solutions compared, and if Ryzen or Threadripper can make proper use of Optane caching through third-party software.
  • Billy Tallis - Tuesday, May 15, 2018 - link

    I'll be setting up a Threadripper system this week to test both caching and NVMe RAID.
  • Lolimaster - Tuesday, May 15, 2018 - link

    My only use for an optane drive would be for swap file, firefox/chrome cache/install/profiles and GTA5.

    But a 500GB 860EVO cost $169 with 300TB of endurance vs 365TB on optane, with the 860 offering 4x the storage... dunno.

    Their "low end" 118GB 800p needs to improve endurance to at least 1PB level to be a proper swapfile/browser/cache tool
  • evernessince - Wednesday, May 16, 2018 - link

    So what's the point of this when AMD is giving away StoreMi with it's X470 boards? From what I've seen from reviews of the product, it works exceptionally well. It also doesn't require you to buy another drive and it can use much larger SSDs as a cache.
  • CheapSushi - Wednesday, May 16, 2018 - link

    You can definitely ignore Intel's marketing pitch about these. But you can use ANY Optane drive, including ones mentioned here like ANY OTHER SSD out there. So you can make it work with StoreMi too. You have to decide which drive benefits your workload more and how and what your budget is. Optane has inherent benefits that beats out NAND is many ways. But again, just depends on what you want. The smaller GB ones are pretty damn cheap in my opinion. So worth just trying out.
  • Svend Tveskæg - Wednesday, May 16, 2018 - link

    Reminds me of back in the days, when you could buy a weird plastic screen, that claimed it would turn your black and white television into a color-TV....

Log in

Don't have an account? Sign up now