Both sequential and random read write performance are much better with the single SSD drive, but where you see the biggest difference is with random reads and writes with a queue depth of 32, which is more like most server workloads. We will probably start to see 12Gbps SATA become available over the next year or so.įigure 2 shows the results for two 15K SAS drives in a RAID 1 array. This particular drive is basically limited by the sequential bandwidth limits of the 6Gbps SATA III interface (which is about 550MB/sec). I have captured the test results for a high-performance consumer grade 6Gbps MLC SSD (the 256GBGB Samsung 840 Pro) in Figure 1, showing pretty impressive sequential and random I/O performance. You should test all of your logical drives with these tools before you install SQL Server. I like to do my first round of testing on each logical drive using CrystalDiskMark before I do more detailed, time-consuming testing with SQLIO. Using CrystalDiskMark should be a supplement to other disk benchmarking that you do. There are other disk benchmarks such as SQLIO that will do a much more thorough job of benchmarking your disk subsystem, but they are a little more difficult to work with. Random read and write performance for a 4K block size with a queue depth of 32.Random read and write performance for a 4K block size.Random read and write performance for a 512K block size.Sequential read and write performance in megabytes/second.
You can select the number of test runs, desired file size, desired test file type, and which logical drive you want to test.
CrystalDiskMark, which is available from Crystal Dew World is a fairly well-known disk subsystem benchmark.
For Day 10 of this series, I am going to talk a little bit about disk performance and one easy benchmark tool that you can use to quickly compare the performance of different types of disks and disk arrays.
0 kommentar(er)
