diff options
| -rw-r--r-- | tools/perf/Documentation/perf-record.txt | 9 | ||||
| -rw-r--r-- | tools/perf/builtin-record.c | 26 | ||||
| -rw-r--r-- | tools/perf/util/bpf_off_cpu.c | 3 | ||||
| -rw-r--r-- | tools/perf/util/bpf_skel/off_cpu.bpf.c | 2 | ||||
| -rw-r--r-- | tools/perf/util/off_cpu.h | 1 | ||||
| -rw-r--r-- | tools/perf/util/record.h | 1 |
6 files changed, 41 insertions, 1 deletions
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index c59f1e79f2b4..612612fa2d80 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -842,6 +842,15 @@ filtered through the mask provided by -C option. only, as of now. So the applications built without the frame pointer might see bogus addresses. + off-cpu profiling consists two types of samples: direct samples, which + share the same behavior as regular samples, and the accumulated + samples, stored in BPF stack trace map, presented after all the regular + samples. + +--off-cpu-thresh:: + Once a task's off-cpu time reaches this threshold (in milliseconds), it + generates a direct off-cpu sample. The default is 500ms. + --setup-filter=<action>:: Prepare BPF filter to be used by regular users. The action should be either "pin" or "unpin". The filter can be used after it's pinned. diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 4194ea5ac729..8898357325cf 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -3162,6 +3162,28 @@ out_free: return ret; } +static int record__parse_off_cpu_thresh(const struct option *opt, + const char *str, + int unset __maybe_unused) +{ + struct record_opts *opts = opt->value; + char *endptr; + u64 off_cpu_thresh_ms; + + if (!str) + return -EINVAL; + + off_cpu_thresh_ms = strtoull(str, &endptr, 10); + + /* the threshold isn't string "0", yet strtoull() returns 0, parsing failed */ + if (*endptr || (off_cpu_thresh_ms == 0 && strcmp(str, "0"))) + return -EINVAL; + else + opts->off_cpu_thresh_ns = off_cpu_thresh_ms * NSEC_PER_MSEC; + + return 0; +} + void __weak arch__add_leaf_frame_record_opts(struct record_opts *opts __maybe_unused) { } @@ -3355,6 +3377,7 @@ static struct record record = { .ctl_fd = -1, .ctl_fd_ack = -1, .synth = PERF_SYNTH_ALL, + .off_cpu_thresh_ns = OFFCPU_THRESH, }, }; @@ -3582,6 +3605,9 @@ static struct option __record_options[] = { OPT_BOOLEAN(0, "off-cpu", &record.off_cpu, "Enable off-cpu analysis"), OPT_STRING(0, "setup-filter", &record.filter_action, "pin|unpin", "BPF filter action"), + OPT_CALLBACK(0, "off-cpu-thresh", &record.opts, "ms", + "Dump off-cpu samples if off-cpu time exceeds this threshold (in milliseconds). (Default: 500ms)", + record__parse_off_cpu_thresh), OPT_END() }; diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c index c7fde66bb8f9..c367fefe6ecb 100644 --- a/tools/perf/util/bpf_off_cpu.c +++ b/tools/perf/util/bpf_off_cpu.c @@ -14,6 +14,7 @@ #include "util/strlist.h" #include <bpf/bpf.h> #include <internal/xyarray.h> +#include <linux/time64.h> #include "bpf_skel/off_cpu.skel.h" @@ -292,6 +293,8 @@ int off_cpu_prepare(struct evlist *evlist, struct target *target, } } + skel->bss->offcpu_thresh_ns = opts->off_cpu_thresh_ns; + err = off_cpu_bpf__attach(skel); if (err) { pr_err("Failed to attach off-cpu BPF skeleton\n"); diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c index 14cd8881f8bb..72763bb8d1de 100644 --- a/tools/perf/util/bpf_skel/off_cpu.bpf.c +++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c @@ -124,7 +124,7 @@ const volatile bool uses_cgroup_v1 = false; int perf_subsys_id = -1; -__u64 offcpu_thresh_ns = 500000000ull; +__u64 offcpu_thresh_ns; /* * Old kernel used to call it task_struct->state and now it's '__state'. diff --git a/tools/perf/util/off_cpu.h b/tools/perf/util/off_cpu.h index 2a4b7f9b2c4c..64bf763ddf50 100644 --- a/tools/perf/util/off_cpu.h +++ b/tools/perf/util/off_cpu.h @@ -16,6 +16,7 @@ struct record_opts; PERF_SAMPLE_PERIOD | PERF_SAMPLE_RAW | \ PERF_SAMPLE_CGROUP) +#define OFFCPU_THRESH 500000000ULL #ifdef HAVE_BPF_SKEL int off_cpu_prepare(struct evlist *evlist, struct target *target, diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index f1956c4db319..ea3a6c4657ee 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -80,6 +80,7 @@ struct record_opts { int synth; int threads_spec; const char *threads_user_spec; + u64 off_cpu_thresh_ns; }; extern const char * const *record_usage; |