Plextor M5S 256GB Review
by Kristian Vättö on July 18, 2012 3:00 AM ESTPerformance Over Time & TRIM
Plextor's M3 and M3 Pro performed well in our torture testing. After 20 minutes of torture their performance was still bearable, which is what matters for consumer workloads (although even that is very extreme). Plextor relies on idle time garbage collection, so the performance restores when the drive is doing nothing. Plextor has always promoted their "True Speed" technology and I can see why. In fact, dirty state performance is one of the key features of the M5S as shown on Plextor's website.
I was excited to see if M5S brought even better garbage colletion as Plextor is advertising it so heavily. To begin testing, I ran HD Tach on a secure erased drive to get the baseline performance:
Next I tortured the drive by filling it with sequential data and then exposed it to 20 minutes of 4KB random writes (QD=32, LBA 100%):
Write performance drops to as low as 50MB/s for the first LBAs but the average write speed is up by 10MB/s compared to the M3.
I let the drive sit idle for 30 minutes and reran HD Tach:
Performance is over 90% of clean state performance, which is very good. With more idle time and sequential writes, performance shhould get even closer to clean state numbers.
Since 20 minutes of torture is not enough to put the M5S in its worst possible state, I secure erased the drive, filled it with sequential data and ran our torture test for 60 minutes:
And performance drops significantly as expected.
I again let the drive idle for 30 minutes and reran HD Tach after that:
This is pleasant news. The M5S came from worst state to over 70% of clean state performance in only 30 minutes. For comparison, the M3 Pro only restored to 46% of clean state performance and it was idling for nearly two hours.
Finally, I secure erased the drive one more time, filled it with sequential data and tortured for 60 minutes. After that, I formatted the drive in Disk Management to see if TRIM works properly (and it does):
Write Amplification
Write amplification has been reduced dramatically. The M3 Pro had relatively high worst case write amplification, although it was still acceptable. The M5S takes write amplification down to the level of most other non-SandForce drives.
Conclusion
I'm pleased that Plextor has paid extra attention to the garbage collection in the M5S. The garbage collection in the M3 and M3 Pro was already good, but not perfect. The garbage collection in M5S is very aggressive if the drive is put into an extremely dirty state, which is good news because the most noticeable difference in performance comes when the drive is at its worst state.
I'm even happier about the fact that better garbage collection did not come at the expense of write amplification. In fact, the M5S almost halved estimated worst case write amplification compared to the M3 Pro. Aggressive garbage collection can come with serious downsides if not applied correctly. Plextor's approach has improved both garbage collection and write amplification, which is the optimal way when looking at the big picture.
Facebook
Twitter
RSS
43 Comments
View All Comments
Kristian Vättö - Wednesday, July 18, 2012 - link
The prices were taken two days ago on July 16th, so some may have changed already. The idea is to provide some kind of idea of pricing, that's all. As you noticed already, prices change all the time so the table is only useful for a few days, hence I don't see a point in making a Europe table as well.Rick83 - Wednesday, July 18, 2012 - link
While geizhals/skinflint is a convenient tool, outside of Germany things usually get much more expensive.Occasionally a good deal in the UK, but component prices in France are often 10% higher, making even the 15 euro shipping appear attractive in some cases....
scbdpa - Wednesday, July 18, 2012 - link
So would you recommend the m3pro or m5s to a user looking to buy a plextor ssd (128gb)?Kristian Vättö - Wednesday, July 18, 2012 - link
If price is not a concern, the M3 Pro. It's noticeably faster and carries a 5-year warranty.scbdpa - Wednesday, July 18, 2012 - link
price is not the problem. What about if the machine doesn't support TRIM (a standalone audio recorder)?still get the 3pro, or get the m5s with the better garbage collection?
Thanks
name99 - Thursday, July 19, 2012 - link
Depending on what you're doing, an EXTREMELY important characteristic is power. Not idle power, but peak power (which is usually hit during sustained writes). In spite of what some people think, this number, for current SSDs, is usually substantially higher than the equivalent number for a 2.5" HD.So I'd say figure out what's the max sustained power your audio recorder can provide and use that to make your decision. If you don't know, anything below 2.5W (which is what USB-2 provides, and what most 2.5" HDs target) is safe, anything above that and you may be setting yourself up for random crashes.
kmmatney - Wednesday, July 18, 2012 - link
I don't see why one would buy this over the Crucial M4. If I understand correctly, they They both use the same NAND and a similar marvell controller. It looks liek the Plextor firmware is tweaked for better performance, but I don't think there would be any real-life difference. FYI - I have both a Samsung and a Crucial 256GB SSD in my laptop (2 bays) and I can say for certain that their real-life performance is identical.sheh - Wednesday, July 18, 2012 - link
How do you estimate the write amplification?shodanshok - Wednesday, July 18, 2012 - link
Quote, I'm interested on this.Moreover, it is a very pleasant surprise that Plextor managed to both deliver better write amplification and more aggressive garbage collector, as they are usually mutually exclusive.
Thanks.
Kristian Vättö - Wednesday, July 18, 2012 - link
I can't disclose our testing methods (they are kind of like our "trade secrets") but the basic formula for calculating WA is data written to the flash divided by data written by host. For example, if you go and copy a 1GB folder to the SSD and and the SSD ends up writing 3GB, WA would be 3x.Keep in mind that our WA estimation is a worst case scenario, not average WA.