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 The former IOPS vs. Latency plots also used in that review has been superseded by the far superior Percentile method (on the next page).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4KB random, yet the outdated Web Server workload applies nearly half (45%) of its workload at those 'wrong' sizes.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.
Alright, starting out with 4KB random performance, we see a very linear response between some very impressive numbers here. Anything over QD=8 turns into that saturation blob at the top line there. I've never seen anything ramp up on IOPS so quickly. Lets put this in a bit more perspective by adding in the Intel P3700 and Micron 9100 MAX:
Holy crap! The P3700 (green) and 9100 MAX (gold) are literally wiping up the floor at these lower queue depths, while the P4800X just walks all over them – even its QD=1 performance is higher than the other two at QD=4 nearly across the board! Let's look out to the longer queue depths here to see if they can catch up:
Ok, so singling out reads, writes, and a 70/30 mix, only the Micron 9100 MAX is able to beat the P4800X in 4KB random performance, but in order to do so it must operate at a QD of nearly 128 to reach the same level seen by the P4800X at 1/10th the Queue Depth!
8KB random performance is very much the same story as it was with 4KB, the only exception being the P3700 gaining a tad more ground but still falling short overall.
I've marked the 'meager' 2GB/s / 2.2GB/s specs obtained from the P4800X specification leak, ghosted here as I'm not considering them final specs (and we were not provided the specification for this review). Note that the P4800X takes just a single step at QD=1 before reaching its saturation throughput at QD=2. Insanity! (The second data line you see is actually all other QDs results overlapped.)
Even though Micron's 9100 MAX can reach higher sequentials, it requires very high queue depths to do so. While the P4800X may not climb as high as the others, it gets there at the lower queue depths, which is where it really counts.