lkml.org 
[lkml]   [2013]   [Jan]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v5 14/18] perf tools: add new mem command for memory access profiling
Date
This new command is a wrapper on top of perf record and
perf report to make it easier to configure for memory
access profiling.

To record loads:
$ perf mem -t load rec .....

To record stores:
$ perf mem -t store rec .....

To get the report:
$ perf mem -t load rep

Signed-off-by: Stephane Eranian <eranian@google.com>
---
tools/perf/Documentation/perf-mem.txt | 48 +++++++
tools/perf/Makefile | 1 +
tools/perf/builtin-mem.c | 238 +++++++++++++++++++++++++++++++++
tools/perf/builtin.h | 1 +
tools/perf/command-list.txt | 1 +
tools/perf/perf.c | 1 +
tools/perf/util/hist.c | 1 +
7 files changed, 291 insertions(+)
create mode 100644 tools/perf/Documentation/perf-mem.txt
create mode 100644 tools/perf/builtin-mem.c

diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
new file mode 100644
index 0000000..888d511
--- /dev/null
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -0,0 +1,48 @@
+perf-mem(1)
+===========
+
+NAME
+----
+perf-mem - Profile memory accesses
+
+SYNOPSIS
+--------
+[verse]
+'perf mem' [<options>] (record [<command>] | report)
+
+DESCRIPTION
+-----------
+"perf mem -t <TYPE> record" runs a command and gathers memory operation data
+from it, into perf.data. Perf record options are accepted and are passed through.
+
+"perf mem -t <TYPE> report" displays the result. It invokes perf report with the
+right set of options to display a memory access profile.
+
+OPTIONS
+-------
+<command>...::
+ Any command you can specify in a shell.
+
+-t::
+--type=::
+ Select the memory operation type: load or store (default: load)
+
+-D::
+--dump-raw-samples=::
+ Dump the raw decoded samples on the screen in a format that is easy to parse with
+ one sample per line.
+
+-x::
+--field-separator::
+ Specify the field separator used when dump raw samples (-D option). By default,
+ The separator is the space character.
+
+-C::
+--cpu-list::
+ Restrict dump of raw samples to those provided via this option. Note that the same
+ option can be passed in record mode. It will be interpreted the same way as perf
+ record.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 994f0f6..be8f4697 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -505,6 +505,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-lock.o
BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o
BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o
+BUILTIN_OBJS += $(OUTPUT)builtin-mem.o

PERFLIBS = $(LIB_FILE) $(LIBTRACEEVENT)

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
new file mode 100644
index 0000000..c2980b8
--- /dev/null
+++ b/tools/perf/builtin-mem.c
@@ -0,0 +1,238 @@
+#include "builtin.h"
+#include "perf.h"
+
+#include "util/parse-options.h"
+#include "util/trace-event.h"
+#include "util/tool.h"
+#include "util/session.h"
+
+#define MEM_OPERATION_LOAD "load"
+#define MEM_OPERATION_STORE "store"
+
+static const char *mem_operation = MEM_OPERATION_LOAD;
+
+struct perf_mem {
+ struct perf_tool tool;
+ char const *input_name;
+ symbol_filter_t annotate_init;
+ bool hide_unresolved;
+ bool dump_raw;
+ const char *cpu_list;
+ DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+};
+
+static const char * const mem_usage[] = {
+ "perf mem [<options>] {record <command> |report}",
+ NULL
+};
+
+static int __cmd_record(int argc, const char **argv)
+{
+ int rec_argc, i = 0, j;
+ const char **rec_argv;
+ char event[64];
+ int ret;
+
+ rec_argc = argc + 4;
+ rec_argv = calloc(rec_argc + 1, sizeof(char *));
+ if (!rec_argv)
+ return -1;
+
+ rec_argv[i++] = strdup("record");
+ if (!strcmp(mem_operation, MEM_OPERATION_LOAD))
+ rec_argv[i++] = strdup("-l");
+ rec_argv[i++] = strdup("-d");
+ rec_argv[i++] = strdup("-e");
+
+ if (strcmp(mem_operation, MEM_OPERATION_LOAD))
+ sprintf(event, "cpu/mem-stores/pp");
+ else
+ sprintf(event, "cpu/mem-loads/pp");
+
+ rec_argv[i++] = strdup(event);
+ for (j = 1; j < argc; j++, i++)
+ rec_argv[i] = argv[j];
+
+ ret = cmd_record(i, rec_argv, NULL);
+ free(rec_argv);
+ return ret;
+}
+
+static int
+dump_raw_samples(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel __maybe_unused,
+ struct machine *machine)
+{
+ struct perf_mem *mem = container_of(tool, struct perf_mem, tool);
+ struct addr_location al;
+ const char *fmt;
+
+ if (perf_event__preprocess_sample(event, machine, &al, sample,
+ mem->annotate_init) < 0) {
+ fprintf(stderr, "problem processing %d event, skipping it.\n",
+ event->header.type);
+ return -1;
+ }
+
+ if (al.filtered || (mem->hide_unresolved && al.sym == NULL))
+ return 0;
+
+ if (al.map != NULL)
+ al.map->dso->hit = 1;
+
+ if (symbol_conf.field_sep) {
+ fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
+ "%s0x%"PRIx64"%s%s:%s\n";
+ } else {
+ fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+ "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
+ symbol_conf.field_sep = " ";
+ }
+
+ printf( fmt,
+ sample->pid,
+ symbol_conf.field_sep,
+ sample->tid,
+ symbol_conf.field_sep,
+ event->ip.ip,
+ symbol_conf.field_sep,
+ sample->addr,
+ symbol_conf.field_sep,
+ sample->weight,
+ symbol_conf.field_sep,
+ sample->dsrc,
+ symbol_conf.field_sep,
+ al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+ al.sym ? al.sym->name : "???");
+
+ return 0;
+}
+
+static int process_sample_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct machine *machine)
+{
+ return dump_raw_samples(tool, event, sample, evsel, machine);
+}
+
+static int report_raw_events(struct perf_mem *mem)
+{
+ int err = -EINVAL;
+ int ret;
+ struct perf_session *session = perf_session__new(input_name, O_RDONLY,
+ 0, false, &mem->tool);
+
+ if (session == NULL)
+ return -ENOMEM;
+
+ if (mem->cpu_list) {
+ ret = perf_session__cpu_bitmap(session, mem->cpu_list,
+ mem->cpu_bitmap);
+ if (ret)
+ goto out_delete;
+ }
+
+ if (symbol__init() < 0)
+ return -1;
+
+ printf("# PID, TID, IP, ADDR, COST, DSRC, SYMBOL\n");
+
+ err = perf_session__process_events(session, &mem->tool);
+ if (err)
+ return err;
+
+ return 0;
+
+out_delete:
+ perf_session__delete(session);
+ return err;
+}
+
+static int report_events(int argc, const char **argv, struct perf_mem *mem)
+{
+ const char **rep_argv;
+ int ret, i = 0, j, rep_argc;
+
+ if (mem->dump_raw)
+ return report_raw_events(mem);
+
+ rep_argc = argc + 3;
+ rep_argv = calloc(rep_argc + 1, sizeof(char *));
+ if (!rep_argv)
+ return -1;
+
+ rep_argv[i++] = strdup("report");
+ rep_argv[i++] = strdup("--mem-mode");
+ rep_argv[i++] = strdup("-n"); /* display number of samples */
+
+ /*
+ * there is no cost associated with stores, so don't print
+ * the column
+ */
+ if (strcmp(mem_operation, MEM_OPERATION_LOAD))
+ rep_argv[i++] = strdup("--sort=mem,sym,dso,symbol_daddr,dso_daddr,tlb,locked");
+
+ for (j = 1; j < argc; j++, i++)
+ rep_argv[i] = argv[j];
+
+ ret = cmd_report(i, rep_argv, NULL);
+ free(rep_argv);
+ return ret;
+}
+
+int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+ struct stat st;
+ struct perf_mem mem = {
+ .tool = {
+ .sample = process_sample_event,
+ .mmap = perf_event__process_mmap,
+ .comm = perf_event__process_comm,
+ .lost = perf_event__process_lost,
+ .fork = perf_event__process_fork,
+ .build_id = perf_event__process_build_id,
+ .ordered_samples= true,
+ },
+ .input_name = "perf.data",
+ };
+ const struct option mem_options[] = {
+ OPT_STRING('t', "type", &mem_operation,
+ "type", "memory operations(load/store)"),
+ OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw,
+ "dump raw samples in ASCII"),
+ OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved,
+ "Only display entries resolved to a symbol"),
+ OPT_STRING('i', "input", &input_name, "file", "input file name"),
+ OPT_STRING('C', "cpu", &mem.cpu_list, "cpu", "list of cpus to profile"),
+ OPT_STRING('x', "field-separator", &symbol_conf.field_sep, "separator",
+ "separator for columns, no spaces will be added between "
+ "columns '.' is reserved."),
+ OPT_END()
+ };
+
+ argc = parse_options(argc, argv, mem_options, mem_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+
+ if (!argc || !(strncmp(argv[0], "rec", 3) || mem_operation))
+ usage_with_options(mem_usage, mem_options);
+
+ if (!mem.input_name || !strlen(mem.input_name)) {
+ if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
+ mem.input_name = "-";
+ else
+ mem.input_name = "perf.data";
+ }
+
+ if (!strncmp(argv[0], "rec", 3))
+ return __cmd_record(argc, argv);
+ else if (!strncmp(argv[0], "rep", 3))
+ return report_events(argc, argv, &mem);
+ else
+ usage_with_options(mem_usage, mem_options);
+
+ return 0;
+}
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 08143bd..b210d62 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -36,6 +36,7 @@ extern int cmd_kvm(int argc, const char **argv, const char *prefix);
extern int cmd_test(int argc, const char **argv, const char *prefix);
extern int cmd_trace(int argc, const char **argv, const char *prefix);
extern int cmd_inject(int argc, const char **argv, const char *prefix);
+extern int cmd_mem(int argc, const char **argv, const char *prefix);

extern int find_scripts(char **scripts_array, char **scripts_path_array);
#endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 3e86bbd..2c5b621 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -24,3 +24,4 @@ perf-kmem mainporcelain common
perf-lock mainporcelain common
perf-kvm mainporcelain common
perf-test mainporcelain common
+perf-mem mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 0f661fb..682340e 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -60,6 +60,7 @@ static struct cmd_struct commands[] = {
{ "trace", cmd_trace, 0 },
#endif
{ "inject", cmd_inject, 0 },
+ { "mem", cmd_mem, 0 },
};

struct pager_config {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 8570d90..7034500 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -477,6 +477,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
void hist_entry__free(struct hist_entry *he)
{
free(he->branch_info);
+ free(he->mem_info);
free(he);
}

--
1.7.9.5


\
 
 \ /
  Last update: 2013-01-07 21:41    [W:0.144 / U:0.048 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site