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

  • FunBunny2 - Wednesday, May 16, 2018 - link

    one of the distinguishing points, so to speak, of XPoint is its byte-addressable protocol. but I've found nothing about the advantages, or whether (it seems so) OS has to be (heavily?) modified to support such files. anyone know?
  • Billy Tallis - Wednesday, May 16, 2018 - link

    The byte-addressability doesn't provide any direct advantages when the memory is put behind a block-oriented storage protocol like NVMe. But it does simplify the internal management the SSD needs to do, because modifying a chunk of data doesn't require re-writing other stuff that isn't changing. NVDIMMs will provide a more direct interface to 3D XPoint, and that's where the OS and applications need to be heavily modified.
  • zodiacfml - Friday, May 18, 2018 - link

    Quite impressive but for 32GB Optane drive, I can have a 250 GB SSD.

    The Optane might improve performance for fractions of a second over SSDs for applications but it won't help during program/driver installations or Windows updates which needs more speed.

    I'd reconsider it for a 64 GB Optane as a boot drive for the current price of the 32GB.
  • RagnarAntonisen - Sunday, May 20, 2018 - link

    You've got to feel for Intel. They spend a tonne of cash on projects like Larrabee, Itanium and Optane and the market and tech reviewers mostly respond with a shrug.

    And then everyone complains they're being complacent when it comes to CPU design. Mind you they clearly were - CPU performances increased at a glacial rate until AMD released a competitive product and then there was a big jump from 4 cores to 6 in mainstream CPUs with Coffee Lake. Still if the competition was so far behind you can afford to direct to R&D dollars to other areas.

    Still it all seems a bit unfair - Intel get criticised when they try something new and when they don't.

    And Itanium, Larrabee and Optane all looked like good ideas on paper. It was only when they had a product that it became clear that it wasn't competitive.
  • Adramtech - Sunday, May 20, 2018 - link

    since when is a 1st or 2nd Gen product competitive? I'm sure if they don't have a path to reach competitiveness, the project will be scrapped.
  • Keljian - Tuesday, May 29, 2018 - link

    While I don't doubt the tests are valid, I would really like to see a test with say PrimoCache - with the blocksize set to 4k. I have found in my own testing that Optane (with PrimoCache using optane as an L2 @ 4k) is very worthwhile even for my Samsung 950 pro.
  • Keljian - Tuesday, May 29, 2018 - link

    https://hardforum.com/threads/intel-900p-optane-wo... - Here are my benchmark findings for the 850 evo and 950 pro using the 32gb optane as L2 cache. You'll notice the 4k speeds stand out.
  • denywinarto - Tuesday, May 29, 2018 - link

    Thinking of using this with 12 tb hgst for a gamedisk drive for a ISCSI-based server, the data read is usually the same as they only game files. But occasionally new game gets added. Would it be a better option compared to raid? SSD are too expensive.
  • Lolimaster - Monday, October 1, 2018 - link

    Nice to use the 16GB as pagefile, chrome/firefox profile/cache
  • Lolimaster - Tuesday, October 2, 2018 - link

    It's better to use them as extra ram/pagefile or scratch disk.

Log in

Don't have an account? Sign up now