summaryrefslogtreecommitdiff
path: root/tools/perf/util
diff options
context:
space:
mode:
authorAdrian Hunter <adrian.hunter@intel.com>2019-05-10 15:41:41 +0300
committerArnaldo Carvalho de Melo <acme@redhat.com>2019-05-16 14:17:23 -0300
commit7ba8fa20e26eb3c0c04d747f7fd2223694eac4d5 (patch)
tree50ae8c6322f69a8c9b18f82846a9552d127351a8 /tools/perf/util
parent6466ec14aaf44ff14a05369dcf0929d0f01171c6 (diff)
perf intel-pt: Fix instructions sampling rate
The timestamp used to determine if an instruction sample is made, is an estimate based on the number of instructions since the last known timestamp. A consequence is that it might go backwards, which results in extra samples. Change it so that a sample is only made when the timestamp goes forwards. Note this does not affect a sampling period of 0 or sampling periods specified as a count of instructions. Example: Before: $ perf script --itrace=i10us ls 13812 [003] 2167315.222583: 3270 instructions:u: 7fac71e2e494 __GI___tunables_init+0xf4 (/lib/x86_64-linux-gnu/ld-2.28.so) ls 13812 [003] 2167315.222667: 30902 instructions:u: 7fac71e2da0f _dl_cache_libcmp+0x2f (/lib/x86_64-linux-gnu/ld-2.28.so) ls 13812 [003] 2167315.222667: 10 instructions:u: 7fac71e2d9ff _dl_cache_libcmp+0x1f (/lib/x86_64-linux-gnu/ld-2.28.so) ls 13812 [003] 2167315.222667: 8 instructions:u: 7fac71e2d9ea _dl_cache_libcmp+0xa (/lib/x86_64-linux-gnu/ld-2.28.so) ls 13812 [003] 2167315.222667: 14 instructions:u: 7fac71e2d9ea _dl_cache_libcmp+0xa (/lib/x86_64-linux-gnu/ld-2.28.so) ls 13812 [003] 2167315.222667: 6 instructions:u: 7fac71e2d9ff _dl_cache_libcmp+0x1f (/lib/x86_64-linux-gnu/ld-2.28.so) ls 13812 [003] 2167315.222667: 14 instructions:u: 7fac71e2d9ff _dl_cache_libcmp+0x1f (/lib/x86_64-linux-gnu/ld-2.28.so) ls 13812 [003] 2167315.222667: 4 instructions:u: 7fac71e2dab2 _dl_cache_libcmp+0xd2 (/lib/x86_64-linux-gnu/ld-2.28.so) ls 13812 [003] 2167315.222728: 16423 instructions:u: 7fac71e2477a _dl_map_object_deps+0x1ba (/lib/x86_64-linux-gnu/ld-2.28.so) ls 13812 [003] 2167315.222734: 12731 instructions:u: 7fac71e27938 _dl_name_match_p+0x68 (/lib/x86_64-linux-gnu/ld-2.28.so) ... After: $ perf script --itrace=i10us ls 13812 [003] 2167315.222583: 3270 instructions:u: 7fac71e2e494 __GI___tunables_init+0xf4 (/lib/x86_64-linux-gnu/ld-2.28.so) ls 13812 [003] 2167315.222667: 30902 instructions:u: 7fac71e2da0f _dl_cache_libcmp+0x2f (/lib/x86_64-linux-gnu/ld-2.28.so) ls 13812 [003] 2167315.222728: 16479 instructions:u: 7fac71e2477a _dl_map_object_deps+0x1ba (/lib/x86_64-linux-gnu/ld-2.28.so) ... Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: stable@vger.kernel.org Fixes: f4aa081949e7b ("perf tools: Add Intel PT decoder") Link: http://lkml.kernel.org/r/20190510124143.27054-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/util')
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-decoder.c13
1 files changed, 10 insertions, 3 deletions
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 872fab163585..26dbf11e071a 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -888,16 +888,20 @@ static uint64_t intel_pt_next_period(struct intel_pt_decoder *decoder)
timestamp = decoder->timestamp + decoder->timestamp_insn_cnt;
masked_timestamp = timestamp & decoder->period_mask;
if (decoder->continuous_period) {
- if (masked_timestamp != decoder->last_masked_timestamp)
+ if (masked_timestamp > decoder->last_masked_timestamp)
return 1;
} else {
timestamp += 1;
masked_timestamp = timestamp & decoder->period_mask;
- if (masked_timestamp != decoder->last_masked_timestamp) {
+ if (masked_timestamp > decoder->last_masked_timestamp) {
decoder->last_masked_timestamp = masked_timestamp;
decoder->continuous_period = true;
}
}
+
+ if (masked_timestamp < decoder->last_masked_timestamp)
+ return decoder->period_ticks;
+
return decoder->period_ticks - (timestamp - masked_timestamp);
}
@@ -926,7 +930,10 @@ static void intel_pt_sample_insn(struct intel_pt_decoder *decoder)
case INTEL_PT_PERIOD_TICKS:
timestamp = decoder->timestamp + decoder->timestamp_insn_cnt;
masked_timestamp = timestamp & decoder->period_mask;
- decoder->last_masked_timestamp = masked_timestamp;
+ if (masked_timestamp > decoder->last_masked_timestamp)
+ decoder->last_masked_timestamp = masked_timestamp;
+ else
+ decoder->last_masked_timestamp += decoder->period_ticks;
break;
case INTEL_PT_PERIOD_NONE:
case INTEL_PT_PERIOD_MTC: