Home
last modified time | relevance | path

Searched refs:sampled (Results 1 – 9 of 9) sorted by relevance

/tools/testing/selftests/bpf/benchs/
Dbench_ringbufs.c17 bool sampled; member
25 .sampled = false,
66 args.sampled = true; in parse_arg()
150 if (args.sampled) in ringbuf_setup_skeleton()
411 if (args.sampled) { in perfbuf_libbpf_setup()
Drun_bench_ringbufs.sh46 summarize $b-sampled "$($RUN_BENCH --rb-sampled --rb-b2b $b)"
/tools/perf/Documentation/
Dperf-evlist.txt15 This command displays the names of events sampled in a perf.data file.
Dperf-report.txt111 - code_page_size: the code page size of sampled code address (ip)
141 sampled IPC in this function. IPC means Instruction Per Cycle. If it's low,
367 Use the addresses of sampled taken branches instead of the instruction
376 Add the addresses of sampled taken branches to the callstack.
493 When multiple events are sampled, it may not be needed to collect
568 'Sampled Cycles%' - block sampled cycles aggregation / total sampled cycles
569 'Sampled Cycles' - block sampled cycles aggregation
570 'Avg Cycles%' - block average sampled cycles / sum of total block average
571 sampled cycles
572 'Avg Cycles' - block average sampled cycles
Dperf-mem.txt20 and stores are sampled. Use the -t option to limit to loads or stores.
Dperf-record.txt272 when sampled. Default size of the stack dump is 8192 (bytes).
297 Record the sampled data address data page size.
300 Record the sampled code address (ip) page size
364 Enable taken branch stack sampling. Any type of taken branch may be sampled.
394 is enabled for all the sampling events. The sampled branch type is the same for all events.
Dperf-top.txt234 Enable taken branch stack sampling. Any type of taken branch may be sampled.
249 is enabled for all the sampling events. The sampled branch type is the same for all events.
Dperf-list.txt152 Events on these PMUs generally cannot be sampled, but only counted globally
Dperf-intel-pt.txt168 presently sampled, so IPC values for them do not appear e.g. a CYC packet with a
690 for executables for all addresses sampled. Deliberately, Intel PT is not