Results: 4 KB Random Performance And Latency
With a specification claiming 145,000 random read IOPS, we hoped we were in for a treat. Needless to say, the SSD800MM delivered. Achieving almost 150,000 IOPS, it almost doubled the SSD DC S3700's performance. When we moved it to a 6 Gb/s connection, the SSD800MM still delivered 110,000 random read IIOPS, clearly smoking the SSD DC S3700. In fact, that number is also higher than other SAS-based enterprise SSDs, such as the Smart Optimus, which top out at nearly 100,000 IOPS.
Finally, we tested Intel's SSD DC S3700 on both the LSI SAS 9300-8e and our system's built-in SATA ports. As you can see, the 6 Gb/s drive fares almost the same, regardless of where it's plugged in.
As we saw in our random read test, the SSD800MM out-muscles Intel's SSD DC S3700 at every queue depth. Although we didn't quite hit the 70,000 IOPS specified by HGST, 66,000 IOPS still comes very close to doubling the SSD DC S3700's performance. Stepping up to 12 Gb/s doesn't get us much in this random write test. Even though 66,000 IOPS is a large number, it wouldn't overwhelm a 6 Gb/s interface.
We did observe more consistent performance from the SAS 9300-8e at lower queue depths, but once you hit a queue depth of 64, the advantage disappears. Also, LSI's SAS 9300-8e falls a little behind Intel's on-board SATA controller, as the green line edges above the blue. Fortunately, the difference is less than 2% at most queue depths.
A look at average response times shows us that these results correspond well with the line charts. The SSD800MM performs slightly better on the SAS 9300-8e, while X79 Express chipset edges out the add-in 12 Gb/s HBA. In both cases, those advantages are a scant 10 μs.
In our maximum response time test, the SSD DC S3700 attains a rare victory. The differences are so minor, though, that they're hardly significant. To truly determine performance consistency, we need to look at latency over time.
