summaryrefslogtreecommitdiffstats
path: root/tools/perf/builtin-diff.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-10-17 11:47:46 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-10-17 11:47:46 -0700
commit9d9af1007bc08971953ae915d88dc9bb21344b53 (patch)
tree02090da0b271c31f19d58d80f4cff19c8ef89971 /tools/perf/builtin-diff.c
parenta1e16bc7d5f7ca3599d8a7f061841c93a563665e (diff)
parent744aec4df2c5b4d12af26a57d8858af2f59ef3d0 (diff)
downloadlinux-9d9af1007bc08971953ae915d88dc9bb21344b53.tar.bz2
Merge tag 'perf-tools-for-v5.10-2020-10-15' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux
Pull perf tools updates from Arnaldo Carvalho de Melo: - cgroup improvements for 'perf stat', allowing for compact specification of events and cgroups in the command line. - Support per thread topdown metrics in 'perf stat'. - Support sample-read topdown metric group in 'perf record' - Show start of latency in addition to its start in 'perf sched latency'. - Add min, max to 'perf script' futex-contention output, in addition to avg. - Allow usage of 'perf_event_attr->exclusive' attribute via the new ':e' event modifier. - Add 'snapshot' command to 'perf record --control', using it with Intel PT. - Support FIFO file names as alternative options to 'perf record --control'. - Introduce branch history "streams", to compare 'perf record' runs with 'perf diff' based on branch records and report hot streams. - Support PE executable symbol tables using libbfd, to profile, for instance, wine binaries. - Add filter support for option 'perf ftrace -F/--funcs'. - Allow configuring the 'disassembler_style' 'perf annotate' knob via 'perf config' - Update CascadelakeX and SkylakeX JSON vendor events files. - Add support for parsing perchip/percore JSON vendor events. - Add power9 hv_24x7 core level metric events. - Add L2 prefetch, ITLB instruction fetch hits JSON events for AMD zen1. - Enable Family 19h users by matching Zen2 AMD vendor events. - Use debuginfod in 'perf probe' when required debug files not found locally. - Display negative tid in non-sample events in 'perf script'. - Make GTK2 support opt-in - Add build test with GTK+ - Add missing -lzstd to the fast path feature detection - Add scripts to auto generate 'mmap', 'mremap' string<->id tables for use in 'perf trace'. - Show python test script in verbose mode. - Fix uncore metric expressions - Msan uninitialized use fixes. - Use condition variables in 'perf bench numa' - Autodetect python3 binary in systems without python2. - Support md5 build ids in addition to sha1. - Add build id 'perf test' regression test. - Fix printable strings in python3 scripts. - Fix off by ones in 'perf trace' in arches using libaudit. - Fix JSON event code for events referencing std arch events. - Introduce 'perf test' shell script for Arm CoreSight testing. - Add rdtsc() for Arm64 for used in the PERF_RECORD_TIME_CONV metadata event and in 'perf test tsc'. - 'perf c2c' improvements: Add "RMT Load Hit" metric, "Total Stores", fixes and documentation update. - Fix usage of reloc_sym in 'perf probe' when using both kallsyms and debuginfo files. - Do not print 'Metric Groups:' unnecessarily in 'perf list' - Refcounting fixes in the event parsing code. - Add expand cgroup event 'perf test' entry. - Fix out of bounds CPU map access when handling armv8_pmu events in 'perf stat'. - Add build-id injection 'perf bench' benchmark. - Enter namespace when reading build-id in 'perf inject'. - Do not load map/dso when injecting build-id speeding up the 'perf inject' process. - Add --buildid-all option to avoid processing all samples, just the mmap metadata events. - Add feature test to check if libbfd has buildid support - Add 'perf test' entry for PE binary format support. - Fix typos in power8 PMU vendor events JSON files. - Hide libtraceevent non API functions. * tag 'perf-tools-for-v5.10-2020-10-15' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (113 commits) perf c2c: Update documentation for metrics reorganization perf c2c: Add metrics "RMT Load Hit" perf c2c: Correct LLC load hit metrics perf c2c: Change header for LLC local hit perf c2c: Use more explicit headers for HITM perf c2c: Change header from "LLC Load Hitm" to "Load Hitm" perf c2c: Organize metrics based on memory hierarchy perf c2c: Display "Total Stores" as a standalone metrics perf c2c: Display the total numbers continuously perf bench: Use condition variables in numa. perf jevents: Fix event code for events referencing std arch events perf diff: Support hot streams comparison perf streams: Report hot streams perf streams: Calculate the sum of total streams hits perf streams: Link stream pair perf streams: Compare two streams perf streams: Get the evsel_streams by evsel_idx perf streams: Introduce branch history "streams" perf intel-pt: Improve PT documentation slightly perf tools: Add support for exclusive groups/events ...
Diffstat (limited to 'tools/perf/builtin-diff.c')
-rw-r--r--tools/perf/builtin-diff.c119
1 files changed, 106 insertions, 13 deletions
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index f8c9bdd8269a..584e2e1a3793 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -25,6 +25,7 @@
#include "util/map.h"
#include "util/spark.h"
#include "util/block-info.h"
+#include "util/stream.h"
#include <linux/err.h>
#include <linux/zalloc.h>
#include <subcmd/pager.h>
@@ -42,6 +43,7 @@ struct perf_diff {
int range_size;
int range_num;
bool has_br_stack;
+ bool stream;
};
/* Diff command specific HPP columns. */
@@ -72,6 +74,7 @@ struct data__file {
struct perf_data data;
int idx;
struct hists *hists;
+ struct evlist_streams *evlist_streams;
struct diff_hpp_fmt fmt[PERF_HPP_DIFF__MAX_INDEX];
};
@@ -106,6 +109,7 @@ enum {
COMPUTE_DELTA_ABS,
COMPUTE_CYCLES,
COMPUTE_MAX,
+ COMPUTE_STREAM, /* After COMPUTE_MAX to avoid use current compute arrays */
};
const char *compute_names[COMPUTE_MAX] = {
@@ -393,6 +397,11 @@ static int diff__process_sample_event(struct perf_tool *tool,
struct perf_diff *pdiff = container_of(tool, struct perf_diff, tool);
struct addr_location al;
struct hists *hists = evsel__hists(evsel);
+ struct hist_entry_iter iter = {
+ .evsel = evsel,
+ .sample = sample,
+ .ops = &hist_iter_normal,
+ };
int ret = -1;
if (perf_time__ranges_skip_sample(pdiff->ptime_range, pdiff->range_num,
@@ -411,14 +420,8 @@ static int diff__process_sample_event(struct perf_tool *tool,
goto out_put;
}
- if (compute != COMPUTE_CYCLES) {
- if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample,
- true)) {
- pr_warning("problem incrementing symbol period, "
- "skipping event\n");
- goto out_put;
- }
- } else {
+ switch (compute) {
+ case COMPUTE_CYCLES:
if (!hists__add_entry_ops(hists, &block_hist_ops, &al, NULL,
NULL, NULL, sample, true)) {
pr_warning("problem incrementing symbol period, "
@@ -428,6 +431,23 @@ static int diff__process_sample_event(struct perf_tool *tool,
hist__account_cycles(sample->branch_stack, &al, sample, false,
NULL);
+ break;
+
+ case COMPUTE_STREAM:
+ if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+ NULL)) {
+ pr_debug("problem adding hist entry, skipping event\n");
+ goto out_put;
+ }
+ break;
+
+ default:
+ if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample,
+ true)) {
+ pr_warning("problem incrementing symbol period, "
+ "skipping event\n");
+ goto out_put;
+ }
}
/*
@@ -996,10 +1016,55 @@ static void data_process(void)
}
}
+static int process_base_stream(struct data__file *data_base,
+ struct data__file *data_pair,
+ const char *title __maybe_unused)
+{
+ struct evlist *evlist_base = data_base->session->evlist;
+ struct evlist *evlist_pair = data_pair->session->evlist;
+ struct evsel *evsel_base, *evsel_pair;
+ struct evsel_streams *es_base, *es_pair;
+
+ evlist__for_each_entry(evlist_base, evsel_base) {
+ evsel_pair = evsel_match(evsel_base, evlist_pair);
+ if (!evsel_pair)
+ continue;
+
+ es_base = evsel_streams__entry(data_base->evlist_streams,
+ evsel_base->idx);
+ if (!es_base)
+ return -1;
+
+ es_pair = evsel_streams__entry(data_pair->evlist_streams,
+ evsel_pair->idx);
+ if (!es_pair)
+ return -1;
+
+ evsel_streams__match(es_base, es_pair);
+ evsel_streams__report(es_base, es_pair);
+ }
+
+ return 0;
+}
+
+static void stream_process(void)
+{
+ /*
+ * Stream comparison only supports two data files.
+ * perf.data.old and perf.data. data__files[0] is perf.data.old,
+ * data__files[1] is perf.data.
+ */
+ process_base_stream(&data__files[0], &data__files[1],
+ "# Output based on old perf data:\n#\n");
+}
+
static void data__free(struct data__file *d)
{
int col;
+ if (d->evlist_streams)
+ evlist_streams__delete(d->evlist_streams);
+
for (col = 0; col < PERF_HPP_DIFF__MAX_INDEX; col++) {
struct diff_hpp_fmt *fmt = &d->fmt[col];
@@ -1153,9 +1218,19 @@ static int __cmd_diff(void)
if (pdiff.ptime_range)
zfree(&pdiff.ptime_range);
+
+ if (compute == COMPUTE_STREAM) {
+ d->evlist_streams = evlist__create_streams(
+ d->session->evlist, 5);
+ if (!d->evlist_streams)
+ goto out_delete;
+ }
}
- data_process();
+ if (compute == COMPUTE_STREAM)
+ stream_process();
+ else
+ data_process();
out_delete:
data__for_each_file(i, d) {
@@ -1228,6 +1303,8 @@ static const struct option options[] = {
"only consider symbols in these pids"),
OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
"only consider symbols in these tids"),
+ OPT_BOOLEAN(0, "stream", &pdiff.stream,
+ "Enable hot streams comparison."),
OPT_END()
};
@@ -1887,6 +1964,9 @@ int cmd_diff(int argc, const char **argv)
if (cycles_hist && (compute != COMPUTE_CYCLES))
usage_with_options(diff_usage, options);
+ if (pdiff.stream)
+ compute = COMPUTE_STREAM;
+
symbol__annotation_init();
if (symbol__init(NULL) < 0)
@@ -1898,13 +1978,26 @@ int cmd_diff(int argc, const char **argv)
if (check_file_brstack() < 0)
return -1;
- if (compute == COMPUTE_CYCLES && !pdiff.has_br_stack)
+ if ((compute == COMPUTE_CYCLES || compute == COMPUTE_STREAM)
+ && !pdiff.has_br_stack) {
return -1;
+ }
- if (ui_init() < 0)
- return -1;
+ if (compute == COMPUTE_STREAM) {
+ symbol_conf.show_branchflag_count = true;
+ symbol_conf.disable_add2line_warn = true;
+ callchain_param.mode = CHAIN_FLAT;
+ callchain_param.key = CCKEY_SRCLINE;
+ callchain_param.branch_callstack = 1;
+ symbol_conf.use_callchain = true;
+ callchain_register_param(&callchain_param);
+ sort_order = "srcline,symbol,dso";
+ } else {
+ if (ui_init() < 0)
+ return -1;
- sort__mode = SORT_MODE__DIFF;
+ sort__mode = SORT_MODE__DIFF;
+ }
if (setup_sorting(NULL) < 0)
usage_with_options(diff_usage, options);
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-27 08:52:51 +0000