perf ftrace latency: Add --max-latency option

This patch adds a max-latency option as discussed, in case the number of
buckets is more than 22, we don't observe the setting (for now, let's
say).

By default or if 0 is passed, the value is automatically determined
based on the number of buckets, range and minimum, so that we fill all
available buffers (equivalent to the behaviour before this patch).

We now get something like this:

  # perf ftrace latency --bucket-range=20 \
			--min-latency 10 \
			--max-latency=100 \
			-T switch_mm_irqs_off -a sleep 2
  #   DURATION     |      COUNT | GRAPH             |
       0 -   10 us |       1731 | ################  |
      10 -   30 us |          1 |                   |
      30 -   50 us |          0 |                   |
      50 -   70 us |          0 |                   |
      70 -   90 us |          0 |                   |
      90 -  100 us |          0 |                   |
     100 -  ... us |          0 |                   |

Note the maximum is observed also if it doesn't cover completely a full
range (the second to last range is 10us long to let the last start at
100 sharp), this looks to me more sensible and eases the computations,
since we don't need to account for the range while filling the buckets.

Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20241112181214.1171244-5-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
index 82219e4262c73bc21115aff3dfb2fc8ec591881d..eccc0483f7faecadbc0b80bd031ebb264b60c3ed 100644 (file)
--- a/tools/perf/Documentation/perf-ftrace.txt
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -155,6 +155,10 @@ OPTIONS for 'perf ftrace latency'
        Minimum latency for the start of the first bucket, in ms or ns (according to
        -n/--use-nsec).
 
+--max-latency=::
+       Maximum latency for the start of the last bucket, in ms or ns (according to
+       -n/--use-nsec). The setting is ignored if the value results in more than
+       22 buckets.
 
 OPTIONS for 'perf ftrace profile'
 ---------------------------------

diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index d9fbe7a329268572522240a40c3f3a6230f348a6..cea7bc284f2f90775c493faa2a93aa95580b04d5 100644 (file)
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -730,6 +730,7 @@ static void make_histogram(struct perf_ftrace *ftrace, int buckets[],
                           char *buf, size_t len, char *linebuf)
 {
        int min_latency = ftrace->min_latency;
+       int max_latency = ftrace->max_latency;
        char *p, *q;
        char *unit;
        double num;
@@ -794,7 +795,7 @@ static void make_histogram(struct perf_ftrace *ftrace, int buckets[],
                        if (num > 0) // 1st entry: [ 1 unit .. bucket_range units ]
                                i = num / ftrace->bucket_range + 1;
                }
-               if (i >= NUM_BUCKET)
+               if (i >= NUM_BUCKET || num >= max_latency - min_latency)
                        i = NUM_BUCKET - 1;
 
 do_inc:
@@ -837,7 +838,7 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[])
               buckets[0], bar_len, bar, bar_total - bar_len, "");
 
        for (i = 1; i < NUM_BUCKET - 1; i++) {
-               int start, stop;
+               unsigned int start, stop;
                const char *unit = use_nsec ? "ns" : "us";
 
                if (!ftrace->bucket_range) {
@@ -853,6 +854,11 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[])
                        start = (i - 1) * ftrace->bucket_range + min_latency;
                        stop  = i * ftrace->bucket_range + min_latency;
 
+                       if (start >= ftrace->max_latency)
+                               break;
+                       if (stop > ftrace->max_latency)
+                               stop = ftrace->max_latency;
+
                        if (start >= 1000) {
                                double dstart = start / 1000.0,
                                       dstop  = stop / 1000.0;
@@ -873,7 +879,9 @@ 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 + min_latency;
+               unsigned int upper_outlier = (NUM_BUCKET - 2) * ftrace->bucket_range + min_latency;
+               if (upper_outlier > ftrace->max_latency)
+                       upper_outlier = ftrace->max_latency;
 
                if (upper_outlier >= 1000) {
                        double dstart = upper_outlier / 1000.0;
@@ -1609,6 +1617,8 @@ int cmd_ftrace(int argc, const char **argv)
                    "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_UINTEGER(0, "max-latency", &ftrace.max_latency,
+                   "Maximum latency (last bucket). Works only with --bucket-range and total buckets less than 22."),
        OPT_PARENT(common_options),
        };
        const struct option profile_options[] = {
@@ -1715,6 +1725,18 @@ int cmd_ftrace(int argc, const char **argv)
                        /* default min latency should be the bucket range */
                        ftrace.min_latency = ftrace.bucket_range;
                }
+               if (!ftrace.bucket_range && ftrace.max_latency) {
+                       pr_err("--max-latency works only with --bucket-range\n");
+                       parse_options_usage(ftrace_usage, options,
+                                           "max-latency", /*short_opt=*/false);
+                       ret = -EINVAL;
+                       goto out_delete_filters;
+               }
+               if (!ftrace.max_latency) {
+                       /* default max latency should depend on bucket range and num_buckets */
+                       ftrace.max_latency = (NUM_BUCKET - 2) * ftrace.bucket_range +
+                                               ftrace.min_latency;
+               }
                cmd_func = __cmd_latency;
                break;
        case PERF_FTRACE_PROFILE:

diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c
index a89d2b4c38174c033ae2a2cc9fa5505b6a765a7b..50ae153bf26e7a131857c170fd7932eb7a04eb0e 100644 (file)
--- a/tools/perf/util/bpf_skel/func_latency.bpf.c
+++ b/tools/perf/util/bpf_skel/func_latency.bpf.c
@@ -43,6 +43,7 @@ const volatile int has_task = 0;
 const volatile int use_nsec = 0;
 const volatile unsigned int bucket_range;
 const volatile unsigned int min_latency;
+const volatile unsigned int max_latency;
 
 SEC("kprobe/func")
 int BPF_PROG(func_begin)
@@ -116,7 +117,8 @@ int BPF_PROG(func_end)
                        // than the min latency desired.
                        if (delta > 0) { // 1st entry: [ 1 unit .. bucket_range units )
                                key = delta / bucket_range + 1;
-                               if (key >= NUM_BUCKET)
+                               if (key >= NUM_BUCKET ||
+                                       delta >= max_latency - min_latency)
                                        key = NUM_BUCKET - 1;
                        }
                        goto do_lookup;

diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h
index 78d7745d497a8988fcfcc62df76c0d34a87161b6..f218703063f74786781b16b700daf342cebfff73 100644 (file)
--- a/tools/perf/util/ftrace.h
+++ b/tools/perf/util/ftrace.h
@@ -22,6 +22,7 @@ struct perf_ftrace {
        bool                    use_nsec;
        unsigned int            bucket_range;
        unsigned int            min_latency;
+       unsigned int            max_latency;
        int                     graph_depth;
        int                     func_stack_trace;
        int                     func_irq_info;