Whole-Drive Fill

This test starts with a freshly-erased drive and fills it with 128kB sequential writes at queue depth 32, recording the write speed for each 1GB segment. This test is not representative of any ordinary client/consumer usage pattern, but it does allow us to observe transitions in the drive's behavior as it fills up. This can allow us to estimate the size of any SLC write cache, and get a sense for how much performance remains on the rare occasions where real-world usage keeps writing data after filling the cache.

The SLC write cache in the 1TB SK hynix Gold P31 runs out after just over 100GB of writes. After the SLC cache fills up, the Gold P31's sequential write performance becomes highly variable, ranging from about 1.4 to 2.3 GB/s with little change in character across the entire TLC filling phase. There are no obvious patterns of periodic garbage collection cycles visible at this scale.

Sustained 128kB Sequential Write (Power Efficiency)
Average Throughput for last 16 GB Overall Average Throughput

Despite the variability, the P31's long-term sustained write performance is excellent. It averages out to the best overall write throughput we've measured from a 1TB TLC drive, and in all that variation the performance never drops down to a disappointing level.

Working Set Size

Most mainstream SSDs have enough DRAM to store the entire mapping table that translates logical block addresses into physical flash memory addresses. DRAMless drives only have small buffers to cache a portion of this mapping information. Some NVMe SSDs support the Host Memory Buffer feature and can borrow a piece of the host system's DRAM for this cache rather needing lots of on-controller memory.

When accessing a logical block whose mapping is not cached, the drive needs to read the mapping from the full table stored on the flash memory before it can read the user data stored at that logical block. This adds extra latency to read operations and in the worst case may double random read latency.

We can see the effects of the size of any mapping buffer by performing random reads from different sized portions of the drive. When performing random reads from a small slice of the drive, we expect the mappings to all fit in the cache, and when performing random reads from the entire drive, we expect mostly cache misses.

When performing this test on mainstream drives with a full-sized DRAM cache, we expect performance to be generally constant regardless of the working set size, or for performance to drop only slightly as the working set size increases.

As expected for a drive with a full size DRAM buffer, the P31's random read latency is unaffected by spatial locality: reading across the whole drive is just as fast as reading from a narrow range. And the only other TLC drives that can match this read latency are the two Toshiba/Kioxia SSDs with 96L BiCS4 TLC NAND, but they can't maintain this performance across the entire test.

SK hynix Gold P31 1TB Review AnandTech Storage Bench
POST A COMMENT

80 Comments

View All Comments

  • Luminar - Tuesday, September 1, 2020 - link

    Kapton tape works better. Those small SSDs can get pretty hot and good Kapton tape won't leave residue. Reply
  • Luminar - Thursday, August 27, 2020 - link

    Why didn't the WD blue sn500 get included? Reply
  • Billy Tallis - Thursday, August 27, 2020 - link

    Mainly because I only have a 250GB sample of that, and that's not a particularly fair or relevant comparison against 1TB drives. If I had the 1TB SN550 I would definitely have included that. Reply
  • cfbcfb - Sunday, August 30, 2020 - link

    Not even in the ballpark. The read and especially write speeds are in the top 3 of ALL nvme SSD's, and this one uses half the power and makes half the heat, for just a few dollars more than the Blue. In fact, in most use cases, its faster than the WD Black for less money. Reply
  • DZor - Thursday, August 27, 2020 - link

    All this does not matter cause 1TB drives are for long time in USD 130 - 150 range. For PCIe 3. PCIe 4 is some USD 50 more expensive.
    Except for "hi end" once like 970 Pro.
    Reply
  • Gigaplex - Thursday, August 27, 2020 - link

    Why doesn't it matter? It's a good drive in this price range, and to many people it's pretty affordable. Reply
  • plopke - Thursday, August 27, 2020 - link

    I am curious to try SKHynix consumer drives out myself. But unless you are a OEM like dell there is no support software to check firmware or update firmware , so if there is ever an issues they have no framework at all to fix anything? This drive isn't even mentioned on their weird ssd webpage?

    I mean sandisk-WD/samsung/crucial/ADATA/Kingston , ALL OF THEM have a ssd manager client and software in place just in case firmware updates are needed?
    Reply
  • plopke - Thursday, August 27, 2020 - link

    PS I mean someone please proof me wrong , i actually was kinda interested in getting one of these but then I saw their product page and it was horrible and alarms bells started to ring when I couldn't find any support software at all. Reply
  • Billy Tallis - Thursday, August 27, 2020 - link

    Their consumer SSD site is definitely a work in progress, but that's not too surprising since they only have two retail products at the moment and no real history in this market.

    I wouldn't be too worried about software. Aside from firmware updates, there's really not much point in vendor-specific tools and I wish they would all just lobby Microsoft to make decent vendor-neutral storage admin tools.

    And I don't think firmware updates are as important as you seem to think. They're pretty uncommon these days and usually don't matter much unless your system has a weird incompatibility that a SSD firmware update can fix. If SK hynix does need to push out an update for this drive, I'm sure they'll be able to come up with a delivery method. Running an extra application to give you a firmware update notification on the outside chance you ever need such a notification is a bit silly.
    Reply
  • damianrobertjones - Thursday, August 27, 2020 - link

    Well, I'm not a copy editor, but i could prove you wrong if I tried. Reply

Log in

Don't have an account? Sign up now