Review Index:
Feedback

The Micron 9100 MAX 2.4TB U.2 Enterprise SSD Review - P3700 Killer

Subject: Storage
Manufacturer: Micron
Tagged: U.2, ssd, pro, pcie, NVMe, micron, MAX, HHHL, 9100

Saturated IOPS Performance - 4KB, 8KB Random, 128K Sequential

I'm carrying over the IOPS vs. % Read charts from my P3608 review. The former IOPS vs. Latency plots also used in that review has been superseded by the far superior Percentile method (on the next page). With sweeps of R/W in 10% increments and all Queue Depths covered, there's a lot of data on each chart, so here I have listed the charts sequentially but matched the scales of each pair for easier A/B comparison.

Note that since we are plotting a Read/Write percentage spread, we no longer need to include other specific workloads (OLTP, Database, etc), as those workloads are included as a part of the below charts. For reference, here is the IO distribution of typical purpose-specific workloads:

  • Database / OLTP: 8KB 67/33 (or 70/30)
  • Email Server: 8KB 50/50
  • File Server: 80/20 of the following:
    • 10% 512B, 5% 1KB, 5% 2KB *
    • 60% 4KB, 2% 8KB, 4% 16KB, 4% 32KB, 10% 64KB
  • Web Server: 100/0 (read only) of the following:
    • 22% 512B, 15% 1KB, 8% 2KB *
    • 23% 4KB, 15% 8KB, 2% 16KB, 6% 32KB, 7% 64KB, 1% 128KB, 1% 512KB

* We have discontinued the File Server and Web Server tests currently used by many other sites, as they employ legacy workloads that are 16 years old (yes, in the year 2000) and are simply no longer representative of modern technology. Specifically, modern enterprise SSDs are no longer optimized for <4KB random, yet the outdated Web Server workload applies nearly half (45%) of its workload at those 'wrong' sizes. While it makes for an interesting spread in the results showing artificial penalties with SSDs optimized for 4KB, those results are just no longer meaningful in modern day enterprise use.

4KB Random

View Full Size

View Full Size

The 9100 MAX turns in nearly twice the random read performance and over 3x the random write performance at a 4KB random workload. That said, the 9100 MAX does 'dip' by a larger amount while passing through the 50/50 and 70/30 points at moderate queue depths. I just want to focus on that upper right data point for a second - that is 3GB/s of *random access* taking place there (nearly the sequential speed of the drive)!

8KB Random

View Full Size

View Full Size

Similar story here as it was with 4KB, with the increased write bandwidth of the 9100 MAX giving us a 3x improvement in random writes. The P3700 was able to stretch its legs a bit more in reads, and it actually beats the 9100 at the QD=8 data point. The 9100 MAX is the ultimate winner here, though, once again reaching a full 3 GB/s *worth of random access*, nearly saturating its interface.

128KB Sequential

View Full Size

View Full Size

No real surprises here, though this time the situation flips and we see the P3700 dipping across the center of the R/W span. It does make up for it a bit by finally being able to show its ultimate write speeds (left), throughput figures that were previously a small fraction of what was shown in 4K and 8K random.


July 6, 2016 | 06:56 PM - Posted by madison214

Allyn:

Are you sure these are bootable? Thought I read somewhere Micron claimed "you are on your own" if you try and boot to the 9100's...

July 6, 2016 | 07:55 PM - Posted by Allyn Malventano

There's no reason they shouldn't be really, but the system needs to support NVMe boot. Micron isn't on the hook to support it if it doesn't work, though. 

July 7, 2016 | 07:20 PM - Posted by jtAJ (not verified)

pretty good performing drive. just to mention one thing however, p3700 was out few yrs ago.. so with this drive being out, we'd probably see intel doing some xpoint nand soon no?

July 13, 2016 | 11:44 AM - Posted by anonymous (not verified)

DC really is an entirely different universe from consumer. Price point comparison isn't pertinent seeing as how DC customers typically have quotes dependant on Quantity of order and specifications needed, not to mention the hand tailoring for the customer Device to interface with the solution.

July 6, 2016 | 10:09 PM - Posted by Pixy Misa (not verified)

That's a pretty impressive bit of hardware. Can't wait to see the 3D-NAND versions in the future, which should be even better.

At work we were paying $7/GB for enterprise SSDs just a few years ago, and they had about 10% of the performance of this one.

July 10, 2016 | 07:03 PM - Posted by Anonymous (not verified)

Allyn,

The last page reads:

"Conclusion, Pricing, RSTe, and Final Thoughts"

Were you going to write something about RSTe too?

MRFS

July 19, 2016 | 12:36 AM - Posted by Allyn Malventano

Oops. It was late :). Fixed, and thanks!

July 22, 2016 | 05:46 PM - Posted by Anonymous (not verified)

WANT AD:
Allyn Malventano Cloning Device
Must reproduce all DNA sequences exactly.
Minimum quantity: 1,000 (initially)
for BETA testing. Larger volume orders
to follow after CERTIFICATION.
Inquire within.
MRFS
lol :)

August 1, 2016 | 12:58 PM - Posted by Allyn Malventano

Actually, I'll take 5!

Post new comment

The content of this field is kept private and will not be shown publicly.
  • Lines and paragraphs break automatically.
  • Allowed HTML tags: <a> <em> <strong> <cite> <code> <ul> <ol> <li> <dl> <dt> <dd> <blockquote><p><br>
  • Web page addresses and e-mail addresses turn into links automatically.

More information about formatting options

CAPTCHA
This question is for testing whether you are a human visitor and to prevent automated spam submissions.