From: tip-bot for Stephane Eranian <tipbot@zytor.com>
To: linux-tip-commits@vger.kernel.org
Cc: acme@redhat.com, linux-kernel@vger.kernel.org,
eranian@google.com, hpa@zytor.com, mingo@kernel.org,
peterz@infradead.org, namhyung.kim@lge.com, jolsa@redhat.com,
ak@linux.intel.com, tglx@linutronix.de, mingo@elte.hu
Subject: [tip:perf/core] perf report: Add support for mem access profiling
Date: Tue, 2 Apr 2013 02:53:08 -0700 [thread overview]
Message-ID: <tip-f4f7e28d0e813ddb997f49ae718ddf98db972292@git.kernel.org> (raw)
In-Reply-To: <1359040242-8269-13-git-send-email-eranian@google.com>
Commit-ID: f4f7e28d0e813ddb997f49ae718ddf98db972292
Gitweb: http://git.kernel.org/tip/f4f7e28d0e813ddb997f49ae718ddf98db972292
Author: Stephane Eranian <eranian@google.com>
AuthorDate: Thu, 24 Jan 2013 16:10:36 +0100
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 1 Apr 2013 12:21:28 -0300
perf report: Add support for mem access profiling
This patch adds the --mem-mode option to perf report.
This mode requires a perf.data file created with memory access samples.
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1359040242-8269-13-git-send-email-eranian@google.com
[ Removed duplicates in the --sort help, man page needs updating,
Fixed minor conflict with 328ccda "perf report: Add --no-demangle option" ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-report.c | 135 ++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 131 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index e31f070..a20550c 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -46,6 +46,7 @@ struct perf_report {
bool show_full_info;
bool show_threads;
bool inverted_callchain;
+ bool mem_mode;
struct perf_read_values show_threads_values;
const char *pretty_printing_style;
symbol_filter_t annotate_init;
@@ -64,6 +65,99 @@ static int perf_report_config(const char *var, const char *value, void *cb)
return perf_default_config(var, value, cb);
}
+static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
+ struct addr_location *al,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct machine *machine,
+ union perf_event *event)
+{
+ struct perf_report *rep = container_of(tool, struct perf_report, tool);
+ struct symbol *parent = NULL;
+ u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+ int err = 0;
+ struct hist_entry *he;
+ struct mem_info *mi, *mx;
+ uint64_t cost;
+
+ if ((sort__has_parent || symbol_conf.use_callchain) &&
+ sample->callchain) {
+ err = machine__resolve_callchain(machine, evsel, al->thread,
+ sample, &parent);
+ if (err)
+ return err;
+ }
+
+ mi = machine__resolve_mem(machine, al->thread, sample, cpumode);
+ if (!mi)
+ return -ENOMEM;
+
+ if (rep->hide_unresolved && !al->sym)
+ return 0;
+
+ cost = sample->weight;
+ if (!cost)
+ cost = 1;
+
+ /*
+ * must pass period=weight in order to get the correct
+ * sorting from hists__collapse_resort() which is solely
+ * based on periods. We want sorting be done on nr_events * weight
+ * and this is indirectly achieved by passing period=weight here
+ * and the he_stat__add_period() function.
+ */
+ he = __hists__add_mem_entry(&evsel->hists, al, parent, mi, cost, cost);
+ if (!he)
+ return -ENOMEM;
+
+ /*
+ * In the newt browser, we are doing integrated annotation,
+ * so we don't allocate the extra space needed because the stdio
+ * code will not use it.
+ */
+ if (sort__has_sym && he->ms.sym && use_browser > 0) {
+ struct annotation *notes = symbol__annotation(he->ms.sym);
+
+ assert(evsel != NULL);
+
+ if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
+ goto out;
+
+ err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+ if (err)
+ goto out;
+ }
+
+ if (sort__has_sym && he->mem_info->daddr.sym && use_browser > 0) {
+ struct annotation *notes;
+
+ mx = he->mem_info;
+
+ notes = symbol__annotation(mx->daddr.sym);
+ if (notes->src == NULL && symbol__alloc_hist(mx->daddr.sym) < 0)
+ goto out;
+
+ err = symbol__inc_addr_samples(mx->daddr.sym,
+ mx->daddr.map,
+ evsel->idx,
+ mx->daddr.al_addr);
+ if (err)
+ goto out;
+ }
+
+ evsel->hists.stats.total_period += cost;
+ hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+ err = 0;
+
+ if (symbol_conf.use_callchain) {
+ err = callchain_append(he->callchain,
+ &callchain_cursor,
+ sample->period);
+ }
+out:
+ return err;
+}
+
static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
struct addr_location *al,
struct perf_sample *sample,
@@ -220,6 +314,12 @@ static int process_sample_event(struct perf_tool *tool,
pr_debug("problem adding lbr entry, skipping event\n");
return -1;
}
+ } else if (rep->mem_mode == 1) {
+ if (perf_report__add_mem_hist_entry(tool, &al, sample,
+ evsel, machine, event)) {
+ pr_debug("problem adding mem entry, skipping event\n");
+ return -1;
+ }
} else {
if (al.map != NULL)
al.map->dso->hit = 1;
@@ -303,7 +403,8 @@ static void sig_handler(int sig __maybe_unused)
session_done = 1;
}
-static size_t hists__fprintf_nr_sample_events(struct hists *self,
+static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
+ struct hists *self,
const char *evname, FILE *fp)
{
size_t ret;
@@ -331,7 +432,11 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self,
if (evname != NULL)
ret += fprintf(fp, " of event '%s'", evname);
- ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
+ if (rep->mem_mode) {
+ ret += fprintf(fp, "\n# Total weight : %" PRIu64, nr_events);
+ ret += fprintf(fp, "\n# Sort order : %s", sort_order);
+ } else
+ ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
return ret + fprintf(fp, "\n#\n");
}
@@ -349,7 +454,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
!perf_evsel__is_group_leader(pos))
continue;
- hists__fprintf_nr_sample_events(hists, evname, stdout);
+ hists__fprintf_nr_sample_events(rep, hists, evname, stdout);
hists__fprintf(hists, true, 0, 0, stdout);
fprintf(stdout, "\n\n");
}
@@ -646,7 +751,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
"sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
" dso_to, dso_from, symbol_to, symbol_from, mispredict,"
- " weight, local_weight"),
+ " weight, local_weight, mem, symbol_daddr, dso_daddr, tlb, "
+ "snoop, locked"),
OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
"Show sample percentage for different cpu modes"),
OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -696,6 +802,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
"objdump binary to use for disassembly and annotations"),
OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
"Disable symbol demangling"),
+ OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
OPT_END()
};
@@ -753,6 +860,18 @@ repeat:
"dso_to,symbol_to";
}
+ if (report.mem_mode) {
+ if (sort__branch_mode == 1) {
+ fprintf(stderr, "branch and mem mode incompatible\n");
+ goto error;
+ }
+ /*
+ * if no sort_order is provided, then specify
+ * branch-mode specific order
+ */
+ if (sort_order == default_sort_order)
+ sort_order = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
+ }
if (setup_sorting() < 0)
usage_with_options(report_usage, options);
@@ -818,6 +937,14 @@ repeat:
sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout);
sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout);
} else {
+ if (report.mem_mode) {
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "symbol_daddr", stdout);
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso_daddr", stdout);
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "mem", stdout);
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "local_weight", stdout);
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "tlb", stdout);
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "snoop", stdout);
+ }
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
}
next prev parent reply other threads:[~2013-04-02 9:53 UTC|newest]
Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-24 15:10 [PATCH v7 00/18] perf: add memory access sampling support Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 01/18] perf, x86: Support CPU specific sysfs events Stephane Eranian
2013-01-25 12:16 ` [tip:perf/x86] perf/x86: " tip-bot for Andi Kleen
2013-04-02 9:38 ` [tip:perf/core] " tip-bot for Andi Kleen
2013-01-24 15:10 ` [PATCH v7 02/18] perf/x86: improve sysfs event mapping with event string Stephane Eranian
2013-01-25 12:17 ` [tip:perf/x86] perf/x86: Improve " tip-bot for Stephane Eranian
2013-04-02 9:39 ` [tip:perf/core] " tip-bot for Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 03/18] perf/x86: add flags to event constraints Stephane Eranian
2013-01-25 12:18 ` [tip:perf/x86] perf/x86: Add " tip-bot for Stephane Eranian
2013-04-02 9:40 ` [tip:perf/core] " tip-bot for Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 04/18] perf, core: Add a concept of a weightened sample v2 Stephane Eranian
2013-01-25 12:20 ` [tip:perf/x86] perf/core: Add weighted samples tip-bot for Andi Kleen
2013-04-02 9:42 ` [tip:perf/core] " tip-bot for Andi Kleen
2013-01-24 15:10 ` [PATCH v7 05/18] perf, tools: Add support for weight v7 (modified) Stephane Eranian
2013-04-02 9:49 ` [tip:perf/core] perf " tip-bot for Andi Kleen
2013-01-24 15:10 ` [PATCH v7 06/18] perf: add support for PERF_SAMPLE_ADDR in dump_sampple() Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 07/18] perf: add generic memory sampling interface Stephane Eranian
2013-01-25 9:01 ` Ingo Molnar
2013-01-25 15:30 ` Stephane Eranian
2013-01-29 10:37 ` Michael Ellerman
2013-02-15 19:46 ` Sukadev Bhattiprolu
2013-02-16 2:45 ` Benjamin Herrenschmidt
2013-02-16 8:41 ` Ingo Molnar
2013-02-16 14:14 ` Stephane Eranian
2013-01-25 12:21 ` [tip:perf/x86] perf: Add " tip-bot for Stephane Eranian
2013-04-02 9:43 ` [tip:perf/core] " tip-bot for Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 08/18] perf/x86: add memory profiling via PEBS Load Latency Stephane Eranian
2013-01-25 12:22 ` [tip:perf/x86] perf/x86: Add " tip-bot for Stephane Eranian
2013-04-02 9:44 ` [tip:perf/core] " tip-bot for Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 09/18] perf/x86: export PEBS load latency threshold register to sysfs Stephane Eranian
2013-01-25 12:23 ` [tip:perf/x86] perf/x86: Export " tip-bot for Stephane Eranian
2013-04-02 9:45 ` [tip:perf/core] " tip-bot for Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 10/18] perf/x86: add support for PEBS Precise Store Stephane Eranian
2013-01-25 12:24 ` [tip:perf/x86] perf/x86: Add " tip-bot for Stephane Eranian
2013-04-02 9:47 ` [tip:perf/core] " tip-bot for Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 11/18] perf tools: add mem access sampling core support Stephane Eranian
2013-03-27 14:14 ` Jiri Olsa
2013-03-27 14:20 ` Peter Zijlstra
2013-03-27 14:34 ` Jiri Olsa
2013-03-27 14:48 ` Stephane Eranian
2013-03-27 16:56 ` Arnaldo Carvalho de Melo
2013-03-28 14:24 ` Stephane Eranian
2013-03-28 15:00 ` Arnaldo Carvalho de Melo
2013-03-28 15:06 ` Stephane Eranian
2013-03-28 15:12 ` Arnaldo Carvalho de Melo
2013-03-28 15:15 ` Stephane Eranian
2013-03-27 14:23 ` Jiri Olsa
2013-04-02 9:50 ` [tip:perf/core] perf tools: Add " tip-bot for Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 12/18] perf report: add support for mem access profiling Stephane Eranian
2013-04-02 9:53 ` tip-bot for Stephane Eranian [this message]
2013-01-24 15:10 ` [PATCH v7 13/18] perf record: " Stephane Eranian
2013-04-02 9:51 ` [tip:perf/core] perf record: Add " tip-bot for Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 14/18] perf tools: add new mem command for memory " Stephane Eranian
2013-04-02 9:55 ` [tip:perf/core] perf tools: Add " tip-bot for Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 15/18] perf: add PERF_RECORD_MISC_MMAP_DATA to RECORD_MMAP Stephane Eranian
2013-01-25 12:25 ` [tip:perf/x86] perf: Add " tip-bot for Stephane Eranian
2013-04-02 9:48 ` [tip:perf/core] " tip-bot for Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 16/18] perf tools: detect data vs. text mappings Stephane Eranian
2013-04-02 9:57 ` [tip:perf/core] perf machine: Detect " tip-bot for Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 17/18] perf tools: Ignore ABS symbols when loading data maps Stephane Eranian
2013-01-24 15:10 ` [PATCH v7 18/18] perf tools: Fix output of symbol_daddr offset Stephane Eranian
2013-04-02 9:58 ` [tip:perf/core] " tip-bot for Namhyung Kim
2013-01-25 8:55 ` [PATCH v7 00/18] perf: add memory access sampling support Ingo Molnar
2013-01-25 15:28 ` Stephane Eranian
2013-01-25 10:38 ` Ingo Molnar
2013-02-05 13:03 ` Stephane Eranian
2013-02-05 15:35 ` Arnaldo Carvalho de Melo
2013-02-06 13:24 ` Ingo Molnar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=tip-f4f7e28d0e813ddb997f49ae718ddf98db972292@git.kernel.org \
--to=tipbot@zytor.com \
--cc=acme@redhat.com \
--cc=ak@linux.intel.com \
--cc=eranian@google.com \
--cc=hpa@zytor.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=mingo@kernel.org \
--cc=namhyung.kim@lge.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).