Previewing Maxiotek's MK8115 SSD Controller: Can DRAM-less Drives Make The Cut?
by Billy Tallis on May 9, 2017 8:00 AM ESTMixed Random Read/Write Performance
The mixed random I/O benchmark starts with a pure read test and gradually increases the proportion of writes, finishing with pure writes. The queue depth is 3 for the entire test and each subtest lasts for 3 minutes, for a total test duration of 18 minutes. As with the pure random write test, this test is restricted to a 16GB span of the drive, which is empty save for the 16GB test file.
The MK8115 struggled with both random reads and random writes, so it's no surprise to see them turn in the lowest performance scores for the mixed random workload test. The MLC drive is only ahead of the TLC drive by a hair, and the next slowest drive is faster by a third.
The MK8115 with TLC ends up using less power to deliver almost exactly the same performance, so the TLC drive scores a minor win for efficiency. They're both still beat by a wide range of mainstream SSDs.
 |
|||||||||
Both MK8115 drives show a normal spike in performance at the end of the test when the workload shifts to pure writes. During the rest of the test, performance is mostly constant instead of the more usual pattern of growing steadily with the proportion of writes in the workload. The TLC drive is substantially faster than the MLC drive in the initial all-reads phase of the test, but it is slightly slower through the middle of the test and that gives it the slower overall average.
Mixed Sequential Read/Write Performance
The mixed sequential access test covers the entire span of the drive and uses a queue depth of one. It starts with a pure read test and gradually increases the proportion of writes, finishing with pure writes. Each subtest lasts for 3 minutes, for a total test duration of 18 minutes. The drive is filled before the test starts.
The MK8115 drive with MLC has much higher average performance on the mixed sequential workload test than its TLC counterpart, which is quite clearly the slowest drive. The MLC manages to outperform two TLC drives, but doesn't come close to matching the next slowest MLC drive on this test.
Both MK8115 drives draw about the same amount of power during the mixed sequential workload test. The MLC drive requires slightly more power but is substantially more efficient due to its higher performance, and it actually beats the Crucial MX300 for efficiency here.
 |
|||||||||
The MLC drive's performance curve across the mixed sequential test is the U shape that is normal for mainstream SSDs, though the minimum performance of around 150MB/s is a bit on the low side. The TLC drive by contrast slows down steadily as more writes are added, and doesn't recover any performance near the end of the test.
Facebook
Twitter
RSS
60 Comments
View All Comments
MajGenRelativity - Tuesday, May 9, 2017 - link
samevladx - Tuesday, May 9, 2017 - link
It will take until Q2 2018 for prices to start going down again.milli - Tuesday, May 9, 2017 - link
You should have included other DRAM-less drives.Billy Tallis - Tuesday, May 9, 2017 - link
I would have, if I had any on hand to test. Nobody's offered one up for review in quite a while, and I've asked a few vendors for a Phison S11 drive but they're not interested.vladx - Tuesday, May 9, 2017 - link
It's pretty obvious why, at least Maxiotek has some guts.bortiz - Tuesday, May 9, 2017 - link
My problem with dram-less ssd is the durability of the drive. How does the life-expectancy of this drive compare to other SSD drives. The DRAM in current SSD drives groups data accesses together, reducing the data array access. This increases performance and array durability. Array durability is proportional to the number of array accesses. I don't think this is a good idea and I would like to see if someone can prove to me that this will have a decent life span (5 years???)vladx - Tuesday, May 9, 2017 - link
Whether a SSD IS DRAM-less or not doesn't influence life expectancy.Billy Tallis - Tuesday, May 9, 2017 - link
SSDs that have external DRAM usually don't use it as a write cache for user data; it's just for caching the mapping metadata. A DRAMless controller like MK8115 can do pretty much the same amount of write combining and wear leveling that a mainstream controller can. There may be a slight increase in write amplification from the controller having to flush metadata updates to the flash more often, but mainstream drives don't want to buffer those writes too much either, for the same safety reasons they don't put user data in the DRAM.Remember that write operations are the only ones that significantly affect drive lifetime. DRAMless controllers need to do more flash reads, but read disturb errors are still too rare for that to matter to drive reliability.
CrazyElf - Tuesday, May 9, 2017 - link
It is difficult for it to make the cut with a low 4k random read and write test like this SSD has.I think that the DRAM cache is well worth it.
I think it is best to hold off on SSDs for now.
rocky12345 - Tuesday, May 9, 2017 - link
Yea no thanks if this is what DRAM-less drives are like I think I will stick to SSD's that can maintain their performance a lot better. I don't care if these drives are a bit cheaper if you end up swearing at your computer because the SSD is lagging then for peace of mind just spend the extra cash on a real SSD.I just sold a gaming system to a customer that had a SSD installed as the windows drive. Yep it booted fast and was pretty peppy but if you tried to work the system it seemed like the SSD would bog right down to a crawl so I would assume it was a DRAM-Less SSD. When I sold the customer on the system I was going off of my own SSD usage on my gaming laptop & gaming desktop options which would never bog down like that. I guess the good news was the customer did come back a few days later and said the system was great and so fast that he never had to wait for stuff to load like he did before on his older setup so he was a happy camper I guess.