OLD | NEW |
(Empty) | |
| 1 AUTHOR = "David Sharp <dhsharp@google.com>" |
| 2 NAME = "Tracing microbenchmark" |
| 3 TIME = "SHORT" |
| 4 TEST_CATEGORY = "Benchmark" |
| 5 TEST_CLASS = "Kernel" |
| 6 TEST_TYPE = "client" |
| 7 |
| 8 DOC = """ |
| 9 A simple benchmark of kernel tracers such as ftrace. Enables tracepoints in |
| 10 sys_getuid and makes 100,000 calls to getuid with tracing on and off to measure |
| 11 the overhead of enabling tracing. The intent for this benchmark is to not |
| 12 overflow the ring buffer, so the buffer is generously sized. |
| 13 |
| 14 |
| 15 tracer: tracepoint enabled |
| 16 ------ |
| 17 off: n/a |
| 18 ftrace: syscalls:sys_enter_getuid |
| 19 |
| 20 Args: |
| 21 tracer: see table above. |
| 22 buffer_size_kb: Set the tracing ring buffer to this size (per-cpu). |
| 23 calls: Set the number of calls to make to getuid. |
| 24 """ |
| 25 |
| 26 |
| 27 job.run_test('tracing_microbenchmark', tracer='off', tag='off', iterations=10) |
| 28 job.run_test('tracing_microbenchmark', tracer='ftrace', tag='ftrace', iterations
=10) |
OLD | NEW |