Comparing Two 1TB NVMe Drives with Same NAND, Same Controller: XPG SX8200 Pro vs HP EX950
by Billy Tallis on February 6, 2019 11:30 AM ESTAnandTech 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.
When the Light test is run on an empty drive, the SM2262EN SSDs offer excellent performance, but it's not meaningfully better than what last year's models did with the original SM2262 controller. What's changed is that full-drive performance is much worse, and the gap between empty and full drive performance is much larger for the Light test than for the Heavy test.
The average and 99th percentile latency scores for the SM2262EN drives are barely slower than the Samsung 970 EVO Plus when the Light test is run on an empty drive, but the full-drive average latency is about as bad as a mainstream SATA drive, and the 99th percentile latencies are worse.
The average read and write latency scores for the SM2262EN drives are within a few microseconds of the fastest drives when the Light test is run on an empty drive, but when the drives are full the read latency ends up in SATA territory and the write latency comes close to that.
The 99th percentile read and write latency scores again show no problem for the SM2262EN drives when the Light test is run on an empty drive, but the full-drive performance is a problem. In this case, the 99th percentile read latency is especially bad, with the retail SM2262EN drives scoring worse than the engineering sample and providing tail latencies several times higher than the Crucial MX500 SATA drive.
The SM2262EN drives again show significantly higher energy requirements when the test is run on a full drive rather than an empty drive. The ADATA SXP SX8200 Pro's efficiency advantage over the HP EX950 means the former's efficiency is still decent by NVMe standards even for the full-drive test run.
Facebook
Twitter
RSS
42 Comments
View All Comments
cassiohui - Thursday, February 7, 2019 - link
Hi Billy, just wondering, why is the 970 pro not in the graphs when even the 900p is?Death666Angel - Thursday, February 7, 2019 - link
They have stated on Twitter and in the comments before that they did not receive a 970 Pro review sample.cassiohui - Thursday, February 7, 2019 - link
960 pro maybe?mapesdhs - Thursday, February 7, 2019 - link
Pity they don't just buy them in themselves to do the tests anyway. I'd put more faith in data thathasn't come from free samples. :)
Billy Tallis - Thursday, February 7, 2019 - link
CPU, GPU and DRAM vendors can in theory sample chips that will overclock better than the average retail item, but there's no easy way for SSD vendors to cheat on performance with careful sampling. And the number of drives that don't survive my testing strongly suggests that they aren't doing any sort of extra QA before sending samples to me.jahid - Thursday, February 7, 2019 - link
Thanks for your valuable writing. HP some model availble in https://www.startech.com.bd/component/SSD-Hard-Dis...ballsystemlord - Thursday, February 7, 2019 - link
Well, I will not be purchasing an EX950. That is for sure. I'm bound to run the SLC down quite a bit and then performance will tank.KAlmquist - Sunday, February 10, 2019 - link
These drives are mostly of interest to people who need odd sized drives. For example, if you need a 600GB drive, you probably have to buy a 1TB drive and only use 600GB of it. Either of the 1TB drives should perform reasonably in this scenario. You might still have to tweak the power saving settings to avoid putting the drive to sleep too frequently (due to the huge wakeup time), but the active idle power is less that one watt.dromoxen - Wednesday, February 20, 2019 - link
For me , anything over 500Gb is going to be used for mass storage, so HDD rulez. But ssd would be better on speed, noise and (possibly) reliability. I dont need ultra speeds, just something cheap enough, and faster than HDD. A long way off, still .Why couldn't ADATA offer two versions of the drive, or at least two firmwares, one for Boy racers, one for commercial use? if you can get a chandelier on your ram sticks ....well?
upvts - Monday, July 29, 2019 - link
How full is full? 100%? And is there a noticeable cliff in the performance, or is there a general decline? Or both (gradual decline in performance until the drives are filled to some threshold amount, after which the performance drops off a cliff)? If we were to leave enough space empty on the drive, could we avoid this hypothetical cliff?