diff options
| -rw-r--r-- | tools/perf/Documentation/perf-ftrace.txt | 4 | ||||
| -rw-r--r-- | tools/perf/builtin-ftrace.c | 32 | ||||
| -rw-r--r-- | tools/perf/util/bpf_ftrace.c | 1 | ||||
| -rw-r--r-- | tools/perf/util/bpf_skel/func_latency.bpf.c | 12 | ||||
| -rw-r--r-- | tools/perf/util/ftrace.h | 1 |
5 files changed, 43 insertions, 7 deletions
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index e8cc8208e29f..82219e4262c7 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -151,6 +151,10 @@ OPTIONS for 'perf ftrace latency' --bucket-range=:: Bucket range in ms or ns (according to -n/--use-nsec), default is log2() mode. +--min-latency=:: + Minimum latency for the start of the first bucket, in ms or ns (according to + -n/--use-nsec). + OPTIONS for 'perf ftrace profile' --------------------------------- diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index e047e5dcda26..d9fbe7a32926 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -729,6 +729,7 @@ out: static void make_histogram(struct perf_ftrace *ftrace, int buckets[], char *buf, size_t len, char *linebuf) { + int min_latency = ftrace->min_latency; char *p, *q; char *unit; double num; @@ -777,6 +778,12 @@ static void make_histogram(struct perf_ftrace *ftrace, int buckets[], if (ftrace->use_nsec) num *= 1000; + i = 0; + if (num < min_latency) + goto do_inc; + + num -= min_latency; + if (!ftrace->bucket_range) { i = log2(num); if (i < 0) @@ -784,13 +791,13 @@ static void make_histogram(struct perf_ftrace *ftrace, int buckets[], } else { // Less than 1 unit (ms or ns), or, in the future, // than the min latency desired. - i = 0; if (num > 0) // 1st entry: [ 1 unit .. bucket_range units ] i = num / ftrace->bucket_range + 1; } if (i >= NUM_BUCKET) i = NUM_BUCKET - 1; +do_inc: buckets[i]++; next: @@ -804,6 +811,7 @@ next: static void display_histogram(struct perf_ftrace *ftrace, int buckets[]) { + int min_latency = ftrace->min_latency; bool use_nsec = ftrace->use_nsec; int i; int total = 0; @@ -825,7 +833,8 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[]) bar_len = buckets[0] * bar_total / total; printf(" %4d - %4d %s | %10d | %.*s%*s |\n", - 0, 1, use_nsec ? "ns" : "us", buckets[0], bar_len, bar, bar_total - bar_len, ""); + 0, min_latency, use_nsec ? "ns" : "us", + buckets[0], bar_len, bar, bar_total - bar_len, ""); for (i = 1; i < NUM_BUCKET - 1; i++) { int start, stop; @@ -841,8 +850,8 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[]) unit = use_nsec ? "us" : "ms"; } } else { - start = (i - 1) * ftrace->bucket_range + 1; - stop = i * ftrace->bucket_range + 1; + start = (i - 1) * ftrace->bucket_range + min_latency; + stop = i * ftrace->bucket_range + min_latency; if (start >= 1000) { double dstart = start / 1000.0, @@ -864,7 +873,7 @@ print_bucket_info: if (!ftrace->bucket_range) { printf(" %4d - %-4s %s", 1, "...", use_nsec ? "ms" : "s "); } else { - int upper_outlier = (NUM_BUCKET - 2) * ftrace->bucket_range; + int upper_outlier = (NUM_BUCKET - 2) * ftrace->bucket_range + min_latency; if (upper_outlier >= 1000) { double dstart = upper_outlier / 1000.0; @@ -1598,6 +1607,8 @@ int cmd_ftrace(int argc, const char **argv) "Use nano-second histogram"), OPT_UINTEGER(0, "bucket-range", &ftrace.bucket_range, "Bucket range in ms or ns (-n/--use-nsec), default is log2() mode"), + OPT_UINTEGER(0, "min-latency", &ftrace.min_latency, + "Minimum latency (1st bucket). Works only with --bucket-range."), OPT_PARENT(common_options), }; const struct option profile_options[] = { @@ -1693,6 +1704,17 @@ int cmd_ftrace(int argc, const char **argv) ret = -EINVAL; goto out_delete_filters; } + if (!ftrace.bucket_range && ftrace.min_latency) { + pr_err("--min-latency works only with --bucket-range\n"); + parse_options_usage(ftrace_usage, options, + "min-latency", /*short_opt=*/false); + ret = -EINVAL; + goto out_delete_filters; + } + if (!ftrace.min_latency) { + /* default min latency should be the bucket range */ + ftrace.min_latency = ftrace.bucket_range; + } cmd_func = __cmd_latency; break; case PERF_FTRACE_PROFILE: diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c index b3cb68295e56..bc484e65fb8f 100644 --- a/tools/perf/util/bpf_ftrace.c +++ b/tools/perf/util/bpf_ftrace.c @@ -37,6 +37,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) } skel->rodata->bucket_range = ftrace->bucket_range; + skel->rodata->min_latency = ftrace->min_latency; /* don't need to set cpu filter for system-wide mode */ if (ftrace->target.cpu_list) { diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c index 00a340ca1543..a89d2b4c3817 100644 --- a/tools/perf/util/bpf_skel/func_latency.bpf.c +++ b/tools/perf/util/bpf_skel/func_latency.bpf.c @@ -42,6 +42,7 @@ const volatile int has_cpu = 0; const volatile int has_task = 0; const volatile int use_nsec = 0; const volatile unsigned int bucket_range; +const volatile unsigned int min_latency; SEC("kprobe/func") int BPF_PROG(func_begin) @@ -93,7 +94,7 @@ int BPF_PROG(func_end) start = bpf_map_lookup_elem(&functime, &tid); if (start) { __s64 delta = bpf_ktime_get_ns() - *start; - __u32 key; + __u32 key = 0; __u64 *hist; bpf_map_delete_elem(&functime, &tid); @@ -103,9 +104,16 @@ int BPF_PROG(func_end) if (bucket_range != 0) { delta /= cmp_base; + + if (min_latency > 0) { + if (delta > min_latency) + delta -= min_latency; + else + goto do_lookup; + } + // Less than 1 unit (ms or ns), or, in the future, // than the min latency desired. - key = 0; if (delta > 0) { // 1st entry: [ 1 unit .. bucket_range units ) key = delta / bucket_range + 1; if (key >= NUM_BUCKET) diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h index 6ac136484349..78d7745d497a 100644 --- a/tools/perf/util/ftrace.h +++ b/tools/perf/util/ftrace.h @@ -21,6 +21,7 @@ struct perf_ftrace { bool inherit; bool use_nsec; unsigned int bucket_range; + unsigned int min_latency; int graph_depth; int func_stack_trace; int func_irq_info; |