Plextor M5 Pro (256GB) Review
by Kristian Vättö on August 31, 2012 11:32 AM ESTRandom Read/Write Speed
The four corners of SSD performance are as follows: random read, random write, sequential read and sequential write speed. Random accesses are generally small in size, while sequential accesses tend to be larger and thus we have the four Iometer tests we use in all of our reviews. Our first test writes 4KB in a completely random pattern over an 8GB space of the drive to simulate the sort of random access that you'd see on an OS drive (even this is more stressful than a normal desktop user would see).
We perform three concurrent IOs and run the test for 3 minutes. The results reported are in average MB/s over the entire time. We use both standard pseudo randomly generated data for each write as well as fully random data to show you both the maximum and minimum performance offered by SandForce based drives in these tests. The average performance of SF drives will likely be somewhere in between the two values for each drive you see in the graphs. For an understanding of why this matters, read our original SandForce article.
Random read performance is excellent. The M3/Pro already had great random read performance to begin with but M5 Pro takes that one step further. We are looking at figures similar to Vertex 4 here.
At queue depth of 3, the M5 Pro is noticeably faster than its predecessors. The difference is 30MB/s (~18% on average), although Plextor still cannot match the performance of SandForce or Indilinx Everest 2.
Increasing the queue depth to 32 yields great results. Performance has significantly improved since the M3/Pro. The M5 Pro is on par with SandForce and Everest 2 based SSDs here.
Sequential Read/Write Speed
To measure sequential performance we ran a one minute long 128KB sequential test over the entire span of the drive at a queue depth of 1. The results reported are in average MB/s over the entire test length.
Sequential read performance remains unchanged from M3 Pro.
Sequential write is up when compared to M3 Pro, but for some reason, the M3 is still even faster than the M5 Pro.
Facebook
Twitter
RSS
37 Comments
View All Comments
scottwilkins - Friday, August 31, 2012 - link
@bji: while not "immature", SSD is stil much younger than Winchester drive technology.@sheh: I wouldn't keep data on a Winchester longer than I would on an SSD. IMHO.
B3an - Friday, August 31, 2012 - link
Irrelevant. You'll get many years out of any SSD, enough for any consumer. The people who buy these sort of performance SSD's usually upgrade again within 2 or 3 years anyway. I upgrade every 18 months.Neutron bomb - Sunday, September 9, 2012 - link
Yes, flash memory loses its charge eventually, but eventually may be a very long way off. Does anyone know just how long it takes before flash memory begins to lose its charge?Beenthere - Friday, August 31, 2012 - link
Actually SSD tech is very IMMATURE TECH and this is proven weekly with the need for frequent firmware updates, compatibility and reliability issues, lost data, lost drive capacity, frequent RMAs, missing TRIM function, etc.Just because half-baked SSDs have been sold for a number of years doesn't mean that the tech is sorted, reliable or standardised. In fact the tech changes almost monthly and has proven to be quite unreliable/incompatible.
Anand himself stated about a year ago that SSD tech was "immature" and that statement is still true today. He suggested back then to wait 6-12 months from the time an SSD was released to see how it pans out.
Unfortunately the same advice is still appropriate today - to wait 6-12 months as the SSD makers are rushing half-baked crap to market for undeserved profits instead of conducting thorough validation of their products. It doesn't matter what the brand, they are all shipping half-baked SSD products in one form or another and consumers have no means to know what to expect from any given product.
kyuu - Friday, August 31, 2012 - link
Yeah... what a bunch of bull. Please show me any reputable source showing that late-model SSDs have failure/return rates higher than any other electronic good. You're behind the times; SSDs have gotten cheaper, and the issues have mostly been sorted. The major issues were pretty much isolated to Sandforce drives anyway.No, SSDs aren't perfect, but nothing is. HDDs go bad, have issues, are DoA as well, just like any consumer electronic. Your propoganda aimed at scaring people away from SSDs is disingenuous at best.
mura - Friday, August 31, 2012 - link
I have been using SSD extensively for the last two years - and (knock on wood) none of them has failed me yet. (4 x Intel X25V, 2 x Samsung 470, 2 x Samsung 830, Kingston V200+, Intel X18M, just to name a few - I don't remember the others exactly).They work in desktop computers, workstations and notebooks, and even in my office server. These machines FLY.
Oh, and to mention, almost all of these were bought, because some HDD has started producing bad sectors(mostly within the warranty period, but I did not want another slow and crappy product).
cosminmcm - Friday, August 31, 2012 - link
Come on guys, this is beenthere, why do you even bother?waldojim42 - Sunday, September 2, 2012 - link
As an owner of a Plextor M3 256GB drive (no S or P - this was made before then) I suffer none of the issues you commented about. I have never touched the firmware, it has been perfectly reliable, lost no data, and has yet to make me even consider an RMA. This is why people like me are willing to pay more for a quality product.When you talk about the immature drives, remember to differentiate a bit. The CHEAP drives are immature. Intel, Samsung, and Plextor all make top notch drives that easily rival the die hard 15K SCSI drives.
poccsx - Friday, August 31, 2012 - link
A-men to thatdishayu - Friday, August 31, 2012 - link
This is my first SSD for sure! Thanks for the review, although it took so much more time than expected.