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 The former IOPS vs. Latency plots also used in that review has been superseded by the far superior Percentile method (on the next page).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4KB random, yet the outdated Web Server workload applies nearly half (45%) of its workload at those 'wrong' sizes.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

9100-4k.png

3700-4k.png

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

9100-8k.png

3700-8k.png

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

9100-128k.png

3700-128k.png

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.

« PreviousNext »