Plextor Updates The Firmware on M5 Pro: Promises Increased Performance, We Test It

46 Comments

View All Comments

• JonnyDough - Monday, December 10, 2012 - link

  I'm a bit sad the Intel 520 isn't represented here.

• Kristian Vättö - Monday, December 10, 2012 - link

  I only included Intel SSD 335 240GB because it's newer and actually a bit faster. You can always use our Bench tool to compare any SSD, here's M5 Pro versus 520:
  
  http://www.anandtech.com/bench/Product/731?vs=529

• JonnyDough - Monday, December 10, 2012 - link

  I got a 240GB drive from a forum guy for $160 shipped. Seemed like a great deal on a solid drive. Besides, I thought that a lot of people have the 520.

• mckirkus - Monday, December 10, 2012 - link

  This drive scores well in the Anandtech Storage Benchmarks. So my question is whether it means your test doesn't measure impact of IO consistency or if it simply doesn't matter in the real world?

• Kristian Vättö - Monday, December 10, 2012 - link

  Our Storage Suites are run on an empty drive, whereas in the IO consistency test the drive is first filled with sequential data before being hammered by 4KB random writes. The Storage Suites also consist of various IOs with different transfer sizes, queue depths and data patterns and as we have shown before, sequential writes recover performance with most SSDs. The SSD is also not being subjected to IO load all of the time, there are lots of idle periods where the SSD can do GC to recover performance.
  
  So, our Storage Suites don't fully ignore IO consistency but it's hard to say how much of an impact the M5 Pro's IO consistency has on its scores.

• TemjinGold - Monday, December 10, 2012 - link

  Curious as to why this metric HASN'T been reviewed yet? I'm sure a lot of us would be curious as to how all the major SSDs do in this.

• skytrench - Monday, December 10, 2012 - link

  The test is hitting the drive so hard, that cleanup operations don't have time to improve matters. More testing is needed. Few usage patterns would resemble indefinite 4KB random writes.

• jwilliams4200 - Monday, December 10, 2012 - link

  You need to examine the latency for this SSD to see what it is doing. Like you, I was surprised when I first saw the M5P dropping down to such low IOPS under sustained heavy load. Basically, the M5P is rapidly switching between two modes -- a slow throughput mode (presumably doing GC) and a high throughput mode. It certainly does not look pretty when you plot it out.
  
  But there are two (possibly) mitigating factors:
  
  1) The average throughput isn't terrible, especially with at least 20% OP. The more OP, the greater percentage of time the SSD spends in the high throughput mode, thus raising the average throughput. The average throughput still is not as good as the Vector, Neutron, or 840 Pro, but it is not as bad as it looks on the graph.
  
  M5P with 0% OP (avg 7MB/s):
  http://i.imgur.com/30ZDE.png
  
  M5P with 20% OP (avg 75MB/s):
  http://i.imgur.com/yj0cF.png
  
  2) Importantly, Plextor appears to put an ABSOLUTE cap on worst-case latency. I have never seen the latency go over 500ms, no matter what you throw at it. For comparison, with the Samsung 840 Pro, with no OP and a very heavy load, the latency will, very occasionally, go over even 1000ms. You can easily see the bimodal distribution of latencies for the Plextor if you look at the normal probability scale CDF plot. It seems that Plextor has tuned the firmware so that whenever it is in the slow mode doing GC, it has an absolute limit of 500ms before any IO returns. I guess the price to be paid for that absolute latency cap is that the average and worst-case throughput is lower than the competition -- but not so much lower that nobody could consider it an acceptable trade-off in order to gain the absolute cap on worst-case latency.
  
  M5P with 0% OP, worst-case latency 500ms:
  http://i.imgur.com/pVmWQ.png
  
  Samsung 840 Pro with 0% OP, worst-case latency >1000ms:
  http://i.imgur.com/fjA7N.png
  
  Personally, I would still choose the 840 Pro over the Plextor for sustained heavy workloads (I would overprovision either SSD by at least 20%) because the 840 Pro has much better average latency. But I can imagine that some applications might benefit from the absolute 500ms cap on worst-case latency that the Plextor provides.
  
  Note that none of this really matters for the consumer workloads most people would put an SSD under. Under most consumer workloads, neither the Plextor nor any of the others would have performance drops anywhere near as bad as shown in these sustained heavy workload conditions.

• Kevin G - Monday, December 10, 2012 - link

  This makes me wonder Plextor has optimized their firmware for more consumer oriented loads. They typically have a lower queue depth

• ckevin1 - Tuesday, December 11, 2012 - link

  Great analysis, thank you!
  
  The max latency constraint is very clear from the graphs you generated. It's not that the firmware is "bad" necessarily, it is just optimizing for a different performance measurement, one that Anandtech doesn't cover.
  
  I think an analysis of whether max latency is ever important than max throughput would be interesting, along with some data on how the Plextor compares to other drives in this alternate metric.