4K Random Read/Write
We precondition the CloudSpeed 500 for 18,000 seconds, or five hours, receiving reports on several parameters of workload performance every second. We then plot this data to illustrate the drives' descent into steady state.
This chart consists of 36,000 data points. This is a dual-axis chart with the IOPS on the left and the latency on the right. The red dots signify IOPS during the test, and light brown dots are latency measurements during the test period. We place latency data in a logarithmic scale to bring it into comparison range. The lines through the data scatter are the average during the test. This type of testing presents standard deviation and maximum/minimum I/O in a visual manner.
Note that the IOPS and Latency figures are nearly mirror images of each other. This illustrates the point that high-granularity testing can give our readers a good feel for the latency distribution by viewing IOPS at one-second intervals. This should be in mind when viewing our test results below.
We provide histograms for further latency granularity below. This downward slope of performance happens very few times in the lifetime of the device, typically during the first few hours of life, and we present the precondition results only to confirm steady state convergence.
Each QD for every parameter tested includes 300 data points (five minutes of one second reports) to illustrate the degree of performance variability. The line for each QD represents the average speed reported during the five-minute interval.
4K random speed measurements are an important metric when comparing drive performance, as the hardest type of file access for any storage solution to master is small-file random. One of the most sought-after performance specifications, 4K random performance is a heavily marketed figure.
The CloudSpeed 500 provides 49,000 IOPS at QD256, and the SM843 averages 69,654 IOPS in random 4K read speed at QD256. The SM843 performs well in read-centric environments, and provides much higher performance.
Garbage collection routines are more pronounced in heavy write workloads. This leads to more variability in performance, and the CloudSpeed 500 has a wide range of performance in this test, averaging 25,560 IOPS in 4K write speed at QD256. The Samsung SM843 averages 12,313 IOPS. While the CloudSpeed 500 does suffer from more pronounced variability than the SM843, its performance in a heavy random write workload is higher.
Our write percentage testing illustrates the varying performance of each solution with mixed workloads. The 100% column to the right is a pure write workload of the 4K file size, and 0% represents a pure 4K read workload.
The CloudSpeed 500 has a reduction in performance from 49,000 IOPS in 4K read to 25,560 IOPS with a pure 4K random write workload.
The SM843 provides steady performance from the 10% to 60% range, but then falls to an average of 13,000 IOPS at a 100% 4k write workload. We can observe that in pure 4K read workloads the SM843 is hard to beat, but once we apply a 10% write workload, it falls quickly.
The CloudSpeed 500 has 3,474,579 I/O's (44.9%) fall into the 4-6ms range, and 4,078,199 I/O's (52.7%) fall into the 10-20ms range.
The CloudSpeed features a tighter latency range than the SM843 in the heavy write workload testing. The SM843 is optimized for read-heavy workloads, so this distribution is not entirely unexpected.
We record the power consumption measurements during our precondition run. We calculate the stated average results during the last five minutes of the test, after the device has settled into steady state.
The CloudSpeed 500 is higher than the SM843, with an average of 3.7 Watts. The SM843 averages 2.79 Watts.
IOPS to Watts measurements are generated from data recorded during our precondition run, and the stated average is from the last five minutes of the test. The CloudSpeed 500 with an advantage in the 4K random write workload at 6,994 IOPS per Watt.