Learn how to read Sysbench test results
The cpu test is one of the most simple benchmarks in SysBench. In this mode each request consists in calculation of prime numbers up to a value specified by the --cpu-max-primes option. All calculations are performed using 64-bit integers. Each thread executes the requests concurrently until either the total number of requests or the total execution time exceed the limits specified with the common command line options.
| Test Name | total_time | per_request_avg | per_request_p95 | events_rate |
|---|---|---|---|---|
| Multithreaded | 30.00 s | 1.24 ms | 2.61 ms | 3230 ops/sec |
| Single Thread | 30.00 s | 0.61 ms | 0.63 ms | 1634 ops/sec |
This test mode can be used to produce various kinds of file I/O workloads. At the prepare stage Sysbench
creates a specified number of files with a specified total size, then at the run stage, each thread
performs specified I/O operations on this set of files.
Sysbench fileio tests are run in synchronous mode, all operations are buffered. All tests are run
with a number of threads that matches the number of vCPUs found in the instance with a minimum of 4.
| Test Name | read_transfer_rate | write_transfer_rate | avg_latency | p95_latency |
|---|---|---|---|---|
| Random Read 4k (clear cache) | 54.01 MiB/s | 0 MiB/s | 0.29 ms | 0.57 ms |
| Random Read-Write 4k | 16.47 MiB/s | 10.98 MiB/s | 0.25 ms | 0.73 ms |
| Random Write 4k | 0 MiB/s | 16.79 MiB/s | 0.41 ms | 1.44 ms |
| Sequential Read 128k (clear cache) | 829.21 MiB/s | 0 MiB/s | 0.60 ms | 1.04 ms |
| Sequential Write 128k | 0 MiB/s | 513.15 MiB/s | 0.43 ms | 1.58 ms |
Memory allocation and transfer speed.
| Test Name | total_time | transfer_rate | operations_rate |
|---|---|---|---|
| Read | 19.93 s | 10.03 GiB/sec | 10520433 ops/sec |
| Read 1MB | 10.33 s | 96.78 GiB/sec | 99101 ops/sec |
| Write | 21.05 s | 4.75 GiB/sec | 4979835 ops/sec |
| Write 1MB | 13.77 s | 29.05 GiB/sec | 29746 ops/sec |