From c4937a91ea56b546234b0608a413ebad90536d26 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Sun, 10 May 2015 15:13:15 -0400 Subject: perf tools: handle PERF_RECORD_LOST_SAMPLES This patch modifies the perf tool to handle the new RECORD type, PERF_RECORD_LOST_SAMPLES. The number of lost-sample events is stored in .nr_events[PERF_RECORD_LOST_SAMPLES]. The exact number of samples which the kernel dropped is stored in total_lost_samples. When the percentage of dropped samples is greater than 5%, a warning is printed. Here are some examples: Eg 1, Recording different frequently-occurring events is safe with the patch. Only a very low drop rate is associated with such actions. $ perf record -e '{cycles:p,instructions:p}' -c 20003 --no-time ~/tchain ~/tchain $ perf report -D | tail SAMPLE events: 120243 MMAP2 events: 5 LOST_SAMPLES events: 24 FINISHED_ROUND events: 15 cycles:p stats: TOTAL events: 59348 SAMPLE events: 59348 instructions:p stats: TOTAL events: 60895 SAMPLE events: 60895 $ perf report --stdio --group # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 24 # # Samples: 120K of event 'anon group { cycles:p, instructions:p }' # Event count (approx.): 24048600000 # # Overhead Command Shared Object Symbol # ................ ........... ................ .................................. # 99.74% 99.86% tchain_edit tchain_edit [.] f3 0.09% 0.02% tchain_edit tchain_edit [.] f2 0.04% 0.00% tchain_edit [kernel.vmlinux] [k] ixgbe_read_reg Eg 2, Recording the same thing multiple times can lead to high drop rate, but it is not a useful configuration. $ perf record -e '{cycles:p,cycles:p}' -c 20003 --no-time ~/tchain Warning: Processed 600592 samples and lost 99.73% samples! [perf record: Woken up 148 times to write data] [perf record: Captured and wrote 36.922 MB perf.data (1206322 samples)] [perf record: Woken up 1 times to write data] [perf record: Captured and wrote 0.121 MB perf.data (1629 samples)] Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@infradead.org Cc: eranian@google.com Link: http://lkml.kernel.org/r/1431285195-14269-9-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar --- tools/perf/util/event.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'tools/perf/util/event.h') diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 97179abc80a1..5dc51ada05df 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -52,6 +52,11 @@ struct lost_event { u64 lost; }; +struct lost_samples_event { + struct perf_event_header header; + u64 lost; +}; + /* * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID */ @@ -235,6 +240,12 @@ enum auxtrace_error_type { * total_lost tells exactly how many events the kernel in fact lost, i.e. it is * the sum of all struct lost_event.lost fields reported. * + * The kernel discards mixed up samples and sends the number in a + * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored + * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells + * exactly how many samples the kernel in fact dropped, i.e. it is the sum of + * all struct lost_samples_event.lost fields reported. + * * The total_period is needed because by default auto-freq is used, so * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get * the total number of low level events, it is necessary to to sum all struct @@ -244,6 +255,7 @@ struct events_stats { u64 total_period; u64 total_non_filtered_period; u64 total_lost; + u64 total_lost_samples; u64 total_invalid_chains; u32 nr_events[PERF_RECORD_HEADER_MAX]; u32 nr_non_filtered_samples; @@ -342,6 +354,7 @@ union perf_event { struct comm_event comm; struct fork_event fork; struct lost_event lost; + struct lost_samples_event lost_samples; struct read_event read; struct throttle_event throttle; struct sample_event sample; @@ -390,6 +403,10 @@ int perf_event__process_lost(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_lost_samples(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process_aux(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, -- cgit v1.2.3