AnandTech Storage Bench - Light

Our Light storage test has relatively more sequential accesses and lower queue depths than The Destroyer or the Heavy test, and it's by far the shortest test overall. It's based largely on applications that aren't highly dependent on storage performance, so this is a test more of application launch times and file load times. This test can be seen as the sum of all the little delays in daily usage, but with the idle times trimmed to 25ms it takes less than half an hour to run. Details of the Light test can be found here. As with the ATSB Heavy test, this test is run with the drive both freshly erased and empty, and after filling the drive with sequential writes.

ATSB - Light (Data Rate)

The Light test allows the flash-based SSDs to make the most of their write caching throughout the test, so even the 900p is surpassed by the Samsung NVMe SSDs while the 800p ranks with the budget NVMe drives. When the drives are full and the flash-based SSDs get bogged down with garbage collection, the 900p comes out ahead but the 800p still trails behind the Samsung 960 PRO. The VROC configuration look especially poor in terms of average data rate, and the RAID-5 performance is surprisingly low.

ATSB - Light (Average Latency)ATSB - Light (99th Percentile Latency)

The Optane SSD 800p scores in the middle tier of SSDs for average latency on the Light test, and VROC RAID is no help here. VROC does help with the 99th percentile latencies, but without it the 800p looks like a low-end drive that merely doesn't have garbage collection problems.

ATSB - Light (Average Read Latency)ATSB - Light (Average Write Latency)

The average read latencies from the 800p are almost twice as high as those from the 900p, and VROC's overhead only makes it worse. The average write latencies of the 900p aren't as good as the best flash-based SSDs, and the write latency of the 800p is well over twice that of the 900p.

ATSB - Light (99th Percentile Read Latency)ATSB - Light (99th Percentile Write Latency)

The 99th percentile latency scores from the 800p are not great, but at least the drives perform just as well when full. Small flash-based drives are the most heavily affected when constant garbage collection becomes necessary.

ATSB - Light (Power)

The Light test is a fairly short run with any of these drives, but the 800p still manages to return extremely good power usage numbers that are well ahead of any flash-based NVMe SSD.

AnandTech Storage Bench - Heavy Random Performance
POST A COMMENT

116 Comments

View All Comments

  • AnnonymousCoward - Wednesday, March 14, 2018 - link

    No. My understanding is that most load times are CPU bound, and there's a negligible difference from most 500MB/s SATA III drives vs the Samsung 950/960 vs Optane. That makes it completely pointless for almost all users. Reply
  • emvonline - Friday, March 16, 2018 - link

    so any reasonable calculation says chip can be cycled 7-10k times (mlc nand is specd at 10k). And total tbw is less than most of the competion 960 pro ssds. is this true? so its around enterprise mlc in endurance??? Reply
  • mkozakewich - Sunday, March 18, 2018 - link

    Why is everyone so bad at figuring out when to use things? This would be great in any environment where you're prioritizing low-queue-depth transfers. Obviously it's not going to replace your computer's SSD. Reply
  • MDD1963 - Friday, March 23, 2018 - link

    When these things cost less than and/or exceed the performance of the 960 EVO, perhaps then they will begin to sell.... Reply
  • DocNo - Thursday, April 12, 2018 - link

    Use this as L2 cache with PrimoCache and prepared to be amazed. I have the 64GB Optane paired with Primocache and the performance difference is notable - even with my primary drive being a Samsung M2 Pro series SSD drive. If I wasn't so happy with my current setup I'd be all over this new drive as an L2 cache. And unlike Intel's caching software for Optane, Primocache is trivial to install with no special requirements for BIOS or partitioning.

    http://www.romexsoftware.com/en-us/primo-cache/ind...

    Primocache is also the most inexpensive way I have found to accelerate Windows server too. I'm a huge fan!
    Reply
  • Chongsboy - Monday, August 27, 2018 - link

    Not sure where you guys work, or what you have against optane is, but under server conditions, a new mb design, would be wonderful for servers, ie: cloud servers. Where workers are a fricken arm and a leg, hardware costs is not that much of an issue, especially special discounts intel will give to big players. I feel that most ppl here commenting negatively dont actually run real life servers, dealing with thousands, maybe not even hundred requests per minute. Reliability amd speed trumps prices for these servers as if you dont realize aws and all cloud providers are ripping people off, and thats why these c rooked companies are earning billions. Anyways, i deal with these cloud systems in my work. I for one expect all large companies to mov to optane, because it's just that fast, and reliable: ie facebook, aws, azure, what not. Dunno why people are going nuts... we got intel haters galore here... Reply

Log in

Don't have an account? Sign up now