For some events it's useful to weight sample with a hardware provided number. This expresses how expensive the action the sample represent was. This allows the profiler to scale the samples to be more informative to the programmer. There is already the period which is used similarly, but it means something different, so I chose to not overload it. Instead a new sample type for WEIGHT is added. Can be used for multiple things. Initially it is used for TSX abort costs and profiling by memory latencies (so to make expensive load appear higher up in the histograms). The concept is quite generic and can be extended to many other kinds of events or architectures, as long as the hardware provides suitable auxillary values. In principle it could be also used for software tracepoints. This adds the generic glue. A new optional sample format for a 64-bit weight value.
Showing the changes to include/uapi/linux (1 of 3 files). Show all
Unified · Split
| @@ -132,8 +132,10 @@ enum perf_event_sample_format { · 131 unmodified lines | ||
| 132 | 132 | PERF_SAMPLE_BRANCH_STACK = 1U << 11, |
| 133 | 133 | PERF_SAMPLE_REGS_USER = 1U << 12, |
| 134 | 134 | PERF_SAMPLE_STACK_USER = 1U << 13, |
| 135 | + PERF_SAMPLE_WEIGHT = 1U << 14, | |
| 136 | + | |
| 137 | + PERF_SAMPLE_MAX = 1U << 15, /* non-ABI */ | |
| 135 | 138 | |
| 136 | − PERF_SAMPLE_MAX = 1U << 14, /* non-ABI */ | |
| 137 | 139 | }; |
| 138 | 140 | |
| 139 | 141 | /* |
| @@ -588,6 +590,8 @@ enum perf_event_type { · 448 unmodified lines | ||
| 588 | 590 | * { u64 size; |
| 589 | 591 | * char data[size]; |
| 590 | 592 | * u64 dyn_size; } && PERF_SAMPLE_STACK_USER |
| 593 | + * | |
| 594 | + * { u64 weight; } && PERF_SAMPLE_WEIGHT | |
| 591 | 595 | * }; |
| 592 | 596 | */ |
| 593 | 597 | PERF_RECORD_SAMPLE = 9, |