Performance consistency tells us a lot about the architecture of these SSDs and how they handle internal fragmentation. The reason we do not have consistent IO latency with SSDs is because inevitably all controllers have to do some amount of defragmentation or garbage collection in order to continue operating at high speeds. When and how an SSD decides to run its defrag or cleanup routines directly impacts the user experience as inconsistent performance results in application slowdowns.
To test IO consistency, we fill a secure erased SSD with sequential data to ensure that all user accessible LBAs (Logical Block Addresses) have data associated with them. Next we kick off a 4KB random write workload across all LBAs at a queue depth of 32 using incompressible data. The test is run for just over half an hour and we record instantaneous IOPS every second.
We are also testing drives with added over-provisioning by limiting the LBA range. This gives us a look into the drive’s behavior with varying levels of empty space, which is frankly a more realistic approach for client workloads.
Each of the three graphs has its own purpose. The first one is of the whole duration of the test in log scale. The second and third one zoom into the beginning of steady-state operation (t=1400s) but on different scales: the second one uses log scale for easy comparison whereas the third one uses linear scale for better visualization of differences between drives. Click the dropdown selections below each graph to switch the source data.
For more detailed description of the test and why performance consistency matters, read our original Intel SSD DC S3700 article.
Default
25% Over-Provisioning
Despite the use of newer and slightly lower performance 16nm NAND, Reactor's performance consistency is actually marginally better than the other SM2246EN based SSDs we have tested. It's still worse than most of the other drives, but at least the increase in capacity didn't negatively impact the consistency, which happens with some drives.
Default
25% Over-Provisioning
Default
25% Over-Provisioning
TRIM Validation
To test TRIM, I filled the drive with sequential 128KB data and proceeded with a 30-minute random 4KB write (QD32) workload to put the drive into steady-state. After that I TRIM'ed the drive by issuing a quick format in Windows and ran HD Tach to produce the graph below.
That's because SSDs are old and antiquated. NAND should be right on the DIMMs with DRAM, sharing the same bus, the same memory controller, as much of the same hardware as possbile. It should have started 3 years ago and by now we should have had 4GB DRAM + 64GB NAND DIMMs for $120 a pair and 8GB + 128GB for $200 a pair.
I think: Lack of Chipset support, require most recent OSes, lack of boot support, competing standards -> general consumer confusion (SATA Express vs M.2), Rarity of motherboards with M.2, cost.
There is not one specific reason holding back, but I guess you can just say with all new tech adoption will be low at first, and this would be the explanation.
"That said, if the prices go up to $450 again, the Reactor will become a better choice because despite the performance and features I don't find the 850 EVO to be worth $60 more."
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
69 Comments
View All Comments
Shadowmaster625 - Friday, February 13, 2015 - link
That's because SSDs are old and antiquated. NAND should be right on the DIMMs with DRAM, sharing the same bus, the same memory controller, as much of the same hardware as possbile. It should have started 3 years ago and by now we should have had 4GB DRAM + 64GB NAND DIMMs for $120 a pair and 8GB + 128GB for $200 a pair.akrobet - Monday, February 9, 2015 - link
What is holding back the adoption of NVMe M.2 drives?AnnihilatorX - Monday, February 9, 2015 - link
I think: Lack of Chipset support, require most recent OSes, lack of boot support, competing standards -> general consumer confusion (SATA Express vs M.2), Rarity of motherboards with M.2, cost.There is not one specific reason holding back, but I guess you can just say with all new tech adoption will be low at first, and this would be the explanation.
galta - Monday, February 9, 2015 - link
I boot with my Plextor M.2dgingeri - Monday, February 9, 2015 - link
The M6e doesn't do NVMe. It's AHCI, which restricts performance somewhat.BillyONeal - Monday, February 9, 2015 - link
The article says that you don't think the 850 EVO is worth 60 dollars more; but in the list they're the same price. Typo?Kristian Vättö - Monday, February 9, 2015 - link
Read the full sentence."That said, if the prices go up to $450 again, the Reactor will become a better choice because despite the performance and features I don't find the 850 EVO to be worth $60 more."
Kristian Vättö - Monday, February 9, 2015 - link
I also edited it to be more clear now.BillyONeal - Monday, February 9, 2015 - link
Makes sense. Thanks!Andy Chow - Monday, February 9, 2015 - link
A 1TB drive with 144 TB endurance? No thanks!