kernel/linux.git/tools/perf/builtin-stat.c, branch v6.19.11

perf stat: Improve handling of termination by signal

2025-12-04T23:44:39+00:00

When interrupting perf stat in repeat mode with a signal the signal is passed to the child process but the repeat doesn't terminate: ``` $ perf stat -v --null --repeat 10 sleep 1 Control descriptor is not initialized [ perf stat: executing run #1 ... ] [ perf stat: executing run #2 ... ] ^Csleep: Interrupt [ perf stat: executing run #3 ... ] [ perf stat: executing run #4 ... ] [ perf stat: executing run #5 ... ] [ perf stat: executing run #6 ... ] [ perf stat: executing run #7 ... ] [ perf stat: executing run #8 ... ] [ perf stat: executing run #9 ... ] [ perf stat: executing run #10 ... ] Performance counter stats for 'sleep 1' (10 runs): 0.9500 +- 0.0512 seconds time elapsed ( +- 5.39% ) 0.01user 0.02system 0:09.53elapsed 0%CPU (0avgtext+0avgdata 18940maxresident)k 29944inputs+0outputs (0major+2629minor)pagefaults 0swaps ``` Terminate the repeated run and give a reasonable exit value: ``` $ perf stat -v --null --repeat 10 sleep 1 Control descriptor is not initialized [ perf stat: executing run #1 ... ] [ perf stat: executing run #2 ... ] [ perf stat: executing run #3 ... ] ^Csleep: Interrupt Performance counter stats for 'sleep 1' (10 runs): 0.680 +- 0.321 seconds time elapsed ( +- 47.16% ) Command exited with non-zero status 130 0.00user 0.01system 0:02.05elapsed 0%CPU (0avgtext+0avgdata 70688maxresident)k 0inputs+0outputs (0major+5002minor)pagefaults 0swaps ``` Note, this also changes the exit value for non-repeat runs when interrupted by a signal. Reported-by: Ingo Molnar Closes: https://lore.kernel.org/lkml/aS5wjmbAM9ka3M2g@gmail.com/ Signed-off-by: Ian Rogers Tested-by: Thomas Richter Signed-off-by: Namhyung Kim

perf stat: When no events, don't report an error if there is none

2025-12-04T08:36:14+00:00

Events may fail to open as no supported CPUs were specified on the command line. In this case a confusing "error" message of "success" can be reported. Let's skip the error in that case. Before: ``` $ perf stat -C2048 -e cycles -- true WARNING: A requested CPU in '2048' is not supported by PMU 'cpu' (CPUs 0-7) for event 'cycles' Error: No supported events found. The sys_perf_event_open() syscall returned with 0 (Success) for event (cpu/unknown-hardware/). "dmesg | grep -i perf" may provide additional information. ``` After: ``` $ perf stat -C2048 -e cycles -- true WARNING: A requested CPU in '2048' is not supported by PMU 'cpu' (CPUs 0-7) for event 'cycles' Error: No supported events found. ``` Signed-off-by: Ian Rogers Tested-by: Thomas Richter Signed-off-by: Namhyung Kim

perf stat: Allow no events to open if this is a "--null" run

2025-12-04T08:36:14+00:00

It is intended that a "--null" run doesn't open any events. Fixes: 2cc7aa995ce9 ("perf stat: Refactor retry/skip/fatal error handling") Tested-by: Ingo Molnar Signed-off-by: Ian Rogers Tested-by: Thomas Richter Signed-off-by: Namhyung Kim

perf stat: Read tool events last

2025-11-19T04:32:41+00:00

When reading a metric like memory bandwidth on multiple sockets, the additional sockets will be on CPUS > 0. Because of the affinity reading, the counters are read on CPU 0 along with the time, then the later sockets are read. This can lead to the later sockets having a bandwidth larger than is possible for the period of time. To avoid this move the reading of tool events to occur after all other events are read. Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim

perf stat: Reduce scope of walltime_nsecs_stats

2025-11-18T02:43:09+00:00

walltime_nsecs_stats is no longer used for counter values, move into that stat_config where it controls certain things like noise measurement. Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim

perf stat: Reduce scope of ru_stats

2025-11-18T02:43:09+00:00

The ru_stats are used to capture user and system time stats when a process exits. These are then applied to user and system time tool events if their reads fail due to the process terminating. Reduce the scope now the metric code no longer reads these values. Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim

perf tool_pmu: Use old_count when computing count values for time events

2025-11-18T02:43:08+00:00

When running in interval mode every third count of a time event isn't showing properly: ``` $ perf stat -e duration_time -a -I 1000 1.001082862 1,002,290,425 duration_time 2.004264262 1,003,183,516 duration_time 3.007381401 duration_time 4.011160141 1,003,705,631 duration_time 5.014515385 1,003,290,110 duration_time 6.018539680 duration_time 7.022065321 1,003,591,720 duration_time ``` The regression came in with a different fix, found through bisection, commit 68cb1567439f ("perf tool_pmu: Fix aggregation on duration_time"). The issue is caused by the enabled and running time of the event matching the old_count's and creating a delta of 0, which is indicative of an error. Fixes: 68cb1567439f ("perf tool_pmu: Fix aggregation on duration_time") Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim

perf stat: Sort default events/metrics

2025-11-12T00:48:35+00:00

To improve the readability of default events/metrics, sort the evsels after the Default metric groups have be parsed. Before: ``` $ perf stat -a sleep 1 Performance counter stats for 'system wide': 22,087 context-switches # nan cs/sec cs_per_second TopdownL1 (cpu_core) # 10.3 % tma_bad_speculation # 25.8 % tma_frontend_bound # 34.5 % tma_backend_bound # 29.3 % tma_retiring 7,829 page-faults # nan faults/sec page_faults_per_second 880,144,270 cpu_atom/cpu-cycles/ # nan GHz cycles_frequency (50.10%) 1,693,081,235 cpu_core/cpu-cycles/ # nan GHz cycles_frequency TopdownL1 (cpu_atom) # 20.5 % tma_bad_speculation # 13.8 % tma_retiring (50.26%) # 34.6 % tma_frontend_bound (50.23%) 89,326,916 cpu_atom/branches/ # nan M/sec branch_frequency (60.19%) 538,123,088 cpu_core/branches/ # nan M/sec branch_frequency 1,368 cpu-migrations # nan migrations/sec migrations_per_second # 31.1 % tma_backend_bound (60.19%) 0.00 msec cpu-clock # 0.0 CPUs CPUs_utilized 485,744,856 cpu_atom/instructions/ # 0.6 instructions insn_per_cycle (59.87%) 3,093,112,283 cpu_core/instructions/ # 1.8 instructions insn_per_cycle 4,939,427 cpu_atom/branch-misses/ # 5.0 % branch_miss_rate (49.77%) 7,632,248 cpu_core/branch-misses/ # 1.4 % branch_miss_rate 1.005084693 seconds time elapsed ``` After: ``` $ perf stat -a sleep 1 Performance counter stats for 'system wide': 22,165 context-switches # nan cs/sec cs_per_second 0.00 msec cpu-clock # 0.0 CPUs CPUs_utilized 2,260 cpu-migrations # nan migrations/sec migrations_per_second 20,476 page-faults # nan faults/sec page_faults_per_second 17,052,357 cpu_core/branch-misses/ # 1.5 % branch_miss_rate 1,120,090,590 cpu_core/branches/ # nan M/sec branch_frequency 3,402,892,275 cpu_core/cpu-cycles/ # nan GHz cycles_frequency 6,129,236,701 cpu_core/instructions/ # 1.8 instructions insn_per_cycle 6,159,523 cpu_atom/branch-misses/ # 3.1 % branch_miss_rate (49.86%) 222,158,812 cpu_atom/branches/ # nan M/sec branch_frequency (50.25%) 1,547,610,244 cpu_atom/cpu-cycles/ # nan GHz cycles_frequency (50.40%) 1,304,901,260 cpu_atom/instructions/ # 0.8 instructions insn_per_cycle (50.41%) TopdownL1 (cpu_core) # 13.7 % tma_bad_speculation # 23.5 % tma_frontend_bound # 33.3 % tma_backend_bound # 29.6 % tma_retiring TopdownL1 (cpu_atom) # 32.1 % tma_backend_bound (59.65%) # 30.1 % tma_frontend_bound (59.51%) # 22.3 % tma_bad_speculation # 15.5 % tma_retiring (59.53%) 1.008405429 seconds time elapsed ``` Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim

perf stat: Add detail -d,-dd,-ddd metrics

2025-11-12T00:48:35+00:00

Add metrics for the stat-shadow -d, -dd and -ddd events and hard coded metrics. Remove the events as these now come from the metrics. Following this change a detailed perf stat output looks like: ``` $ perf stat -a -ddd -- sleep 1 Performance counter stats for 'system wide': 21,089 context-switches # nan cs/sec cs_per_second TopdownL1 (cpu_core) # 14.1 % tma_bad_speculation # 27.3 % tma_frontend_bound (30.56%) TopdownL1 (cpu_core) # 31.5 % tma_backend_bound # 27.2 % tma_retiring (30.56%) 6,302 page-faults # nan faults/sec page_faults_per_second 928,495,163 cpu_atom/cpu-cycles/ # nan GHz cycles_frequency (28.41%) 1,841,409,834 cpu_core/cpu-cycles/ # nan GHz cycles_frequency (38.51%) # 14.5 % tma_bad_speculation # 16.0 % tma_retiring (28.41%) # 36.8 % tma_frontend_bound (35.57%) 100,859,118 cpu_atom/branches/ # nan M/sec branch_frequency (42.73%) 572,657,734 cpu_core/branches/ # nan M/sec branch_frequency (54.43%) 1,527 cpu-migrations # nan migrations/sec migrations_per_second # 32.7 % tma_backend_bound (42.73%) 0.00 msec cpu-clock # 0.000 CPUs utilized # 0.0 CPUs CPUs_utilized 498,668,509 cpu_atom/instructions/ # 0.57 insn per cycle # 0.6 instructions insn_per_cycle (42.97%) 3,281,762,225 cpu_core/instructions/ # 1.84 insn per cycle # 1.8 instructions insn_per_cycle (62.20%) 4,919,511 cpu_atom/branch-misses/ # 5.43% of all branches # 5.4 % branch_miss_rate (35.80%) 7,431,776 cpu_core/branch-misses/ # 1.39% of all branches # 1.4 % branch_miss_rate (62.20%) 2,517,007 cpu_atom/LLC-loads/ # 0.1 % llc_miss_rate (28.62%) 3,931,318 cpu_core/LLC-loads/ # 40.4 % llc_miss_rate (45.98%) 14,918,674 cpu_core/L1-dcache-load-misses/ # 2.25% of all L1-dcache accesses # nan % l1d_miss_rate (37.80%) 27,067,264 cpu_atom/L1-icache-load-misses/ # 15.92% of all L1-icache accesses # 15.9 % l1i_miss_rate (21.47%) 116,848,994 cpu_atom/dTLB-loads/ # 0.8 % dtlb_miss_rate (21.47%) 764,870,407 cpu_core/dTLB-loads/ # 0.1 % dtlb_miss_rate (15.12%) 1.006181526 seconds time elapsed ``` Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim

perf jevents: Add metric DefaultShowEvents

2025-11-12T00:48:35+00:00

Some Default group metrics require their events showing for consistency with perf's previous behavior. Add a flag to indicate when this is the case and use it in stat-display. As events are coming from Default metrics remove that default hardware and software events from perf stat. Following this change the default perf stat output on an alderlake looks like: ``` $ perf stat -a -- sleep 1 Performance counter stats for 'system wide': 20,550 context-switches # nan cs/sec cs_per_second TopdownL1 (cpu_core) # 9.0 % tma_bad_speculation # 28.1 % tma_frontend_bound TopdownL1 (cpu_core) # 29.2 % tma_backend_bound # 33.7 % tma_retiring 6,685 page-faults # nan faults/sec page_faults_per_second 790,091,064 cpu_atom/cpu-cycles/ # nan GHz cycles_frequency (49.83%) 2,563,918,366 cpu_core/cpu-cycles/ # nan GHz cycles_frequency # 12.3 % tma_bad_speculation # 14.5 % tma_retiring (50.20%) # 33.8 % tma_frontend_bound (50.24%) 76,390,322 cpu_atom/branches/ # nan M/sec branch_frequency (60.20%) 1,015,173,047 cpu_core/branches/ # nan M/sec branch_frequency 1,325 cpu-migrations # nan migrations/sec migrations_per_second # 39.3 % tma_backend_bound (60.17%) 0.00 msec cpu-clock # 0.000 CPUs utilized # 0.0 CPUs CPUs_utilized 554,347,072 cpu_atom/instructions/ # 0.64 insn per cycle # 0.6 instructions insn_per_cycle (60.14%) 5,228,931,991 cpu_core/instructions/ # 2.04 insn per cycle # 2.0 instructions insn_per_cycle 4,308,874 cpu_atom/branch-misses/ # 5.65% of all branches # 5.6 % branch_miss_rate (49.76%) 9,890,606 cpu_core/branch-misses/ # 0.97% of all branches # 1.0 % branch_miss_rate 1.005477803 seconds time elapsed ``` Signed-off-by: Ian Rogers Signed-off-by: Namhyung Kim