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
The 850 EVO presents a healthy increase in IO consistency. The 840 EVO wasn't exactly inconsistent in the first place, but the 850 EVO takes the steady-state IOPS from ~3,000-5,000 IOPS to 5,000-8,000 IOPS, which is actually nearly on par with the 850 Pro. The 850 EVO has without a doubt one of the highest performance consistencies out of the value/mainstream drives we have tested.
Default
25% Over-Provisioning
Default
25% Over-Provisioning
TRIM Validation
To test TRIM, I filled a 120GB 850 EVO 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.
They do seem a little low but we just got out of a major sale spree. During the Black Friday/Cyber Monday shopping fest the 480 GB Intel 730 was going for $200. I would have picked up one up myself at that price but they ran out of stock.
OCZ's firmware for the Barefoot3 series of chips the ARC100 uses has a less then stellar reputation. Things like unexpected power loss have been known to put it into a state of progressive corruption only recoverable by secure erase. There have been patches that claim to fix this on my Vector (that probably got applied to the ARC out the door), but I haven't seen anyone test if they're working.
It's because of TurboWrite. Iometer is a time based tool and the sequential tests are run for one minute, which means that the TurboWrite buffer will be filled and thus the performance goes down as data is written to the TLC array. AS-SSD, on the other hand, only writes a gigabyte of data so it all gets written to the fast SLC cache.
I saw the 840 EVO 500gb going for $180 over the black Friday - cyber Monday period. It'll interesting to see if Samsung keep the 840 EVO on the market as a the low end, so the 850 EVO can fill the mid-range portion of the market while the 850 Pro serves the high end.
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
97 Comments
View All Comments
Kevin G - Monday, December 8, 2014 - link
They do seem a little low but we just got out of a major sale spree. During the Black Friday/Cyber Monday shopping fest the 480 GB Intel 730 was going for $200. I would have picked up one up myself at that price but they ran out of stock.HisDivineOrder - Wednesday, December 10, 2014 - link
You'd have been better served with the Sandisk Extreme Pro 480GB for $185.davolfman - Monday, December 8, 2014 - link
OCZ's firmware for the Barefoot3 series of chips the ARC100 uses has a less then stellar reputation. Things like unexpected power loss have been known to put it into a state of progressive corruption only recoverable by secure erase. There have been patches that claim to fix this on my Vector (that probably got applied to the ARC out the door), but I haven't seen anyone test if they're working.Oxford Guy - Wednesday, December 31, 2014 - link
Up to its old tricks, then.Kristian Vättö - Tuesday, December 9, 2014 - link
As listed on the table, the prices were taken on December 7 and were accurate at the time.sheh - Monday, December 8, 2014 - link
Can anyone explain the large discrepancy (not only in this case) in sequential speed between Iometer and AS-SSD?Kristian Vättö - Tuesday, December 9, 2014 - link
It's because of TurboWrite. Iometer is a time based tool and the sequential tests are run for one minute, which means that the TurboWrite buffer will be filled and thus the performance goes down as data is written to the TLC array. AS-SSD, on the other hand, only writes a gigabyte of data so it all gets written to the fast SLC cache.sheh - Friday, December 12, 2014 - link
Thanks. I'll have to reread older reviews, but I think there's a similar behavior also on other drives that do not have a fast temporary buffer?maecenas - Monday, December 8, 2014 - link
I saw the 840 EVO 500gb going for $180 over the black Friday - cyber Monday period. It'll interesting to see if Samsung keep the 840 EVO on the market as a the low end, so the 850 EVO can fill the mid-range portion of the market while the 850 Pro serves the high end.Laststop311 - Monday, December 8, 2014 - link
Prices are kinda crappy. Why go with an 850 evo when u can spend 20-30 dollars more and get an 850 pro?