perf stat: Basic support for TopDown in perf stat
Add basic plumbing for TopDown in perf stat
TopDown is intended to replace the frontend cycles idle/ backend cycles
idle metrics in standard perf stat output. These metrics are not
reliable in many workloads, due to out of order effects.
This implements a new --topdown mode in perf stat (similar to
--transaction) that measures the pipe line bottlenecks using
standardized formulas. The measurement can be all done with 5 counters
(one fixed counter)
The result are four metrics:
FrontendBound, BackendBound, BadSpeculation, Retiring
that describe the CPU pipeline behavior on a high level.
The full top down methology has many hierarchical metrics. This
implementation only supports level 1 which can be collected without
multiplexing. A full implementation of top down on top of perf is
available in pmu-tools toplev. (http://github.com/andikleen/pmu-tools)
The current version works on Intel Core CPUs starting with Sandy Bridge,
and Atom CPUs starting with Silvermont. In principle the generic
metrics should be also implementable on other out of order CPUs.
TopDown level 1 uses a set of abstracted metrics which are generic to
out of order CPU cores (although some CPUs may not implement all of
them):
topdown-total-slots Available slots in the pipeline
topdown-slots-issued Slots issued into the pipeline
topdown-slots-retired Slots successfully retired
topdown-fetch-bubbles Pipeline gaps in the frontend
topdown-recovery-bubbles Pipeline gaps during recovery
from misspeculation
These metrics then allow to compute four useful metrics:
FrontendBound, BackendBound, Retiring, BadSpeculation.
Add a new --topdown options to enable events. When --topdown is
specified set up events for all topdown events supported by the kernel.
Add topdown-* as a special case to the event parser, as is needed for
all events containing -.
The actual code to compute the metrics is in follow-on patches.
v2: Use standard sysctl read function.
v3: Move x86 specific code to arch/
v4: Enable --metric-only implicitly for topdown.
v5: Add --single-thread option to not force per core mode
v6: Fix output order of topdown metrics
v7: Allow combining with -d
v8: Remove --single-thread again
v9: Rename functions, adding arch_ and topdown_.
v10: Expand man page and describe TopDown better
Paste intro into commit description.
Print error when malloc fails.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1464119559-17203-1-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ee7ada7..fd76bb0 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -59,10 +59,13 @@
#include "util/thread.h"
#include "util/thread_map.h"
#include "util/counts.h"
+#include "util/group.h"
#include "util/session.h"
#include "util/tool.h"
+#include "util/group.h"
#include "asm/bug.h"
+#include <api/fs/fs.h>
#include <stdlib.h>
#include <sys/prctl.h>
#include <locale.h>
@@ -98,6 +101,15 @@
"}"
};
+static const char * topdown_attrs[] = {
+ "topdown-total-slots",
+ "topdown-slots-retired",
+ "topdown-recovery-bubbles",
+ "topdown-fetch-bubbles",
+ "topdown-slots-issued",
+ NULL,
+};
+
static struct perf_evlist *evsel_list;
static struct target target = {
@@ -112,6 +124,7 @@
static bool null_run = false;
static int detailed_run = 0;
static bool transaction_run;
+static bool topdown_run = false;
static bool big_num = true;
static int big_num_opt = -1;
static const char *csv_sep = NULL;
@@ -124,6 +137,7 @@
static unsigned int unit_width = 4; /* strlen("unit") */
static bool forever = false;
static bool metric_only = false;
+static bool force_metric_only = false;
static struct timespec ref_time;
static struct cpu_map *aggr_map;
static aggr_get_id_t aggr_get_id;
@@ -1520,6 +1534,14 @@
return 0;
}
+static int enable_metric_only(const struct option *opt __maybe_unused,
+ const char *s __maybe_unused, int unset)
+{
+ force_metric_only = true;
+ metric_only = !unset;
+ return 0;
+}
+
static const struct option stat_options[] = {
OPT_BOOLEAN('T', "transaction", &transaction_run,
"hardware transaction statistics"),
@@ -1578,8 +1600,10 @@
"aggregate counts per thread", AGGR_THREAD),
OPT_UINTEGER('D', "delay", &initial_delay,
"ms to wait before starting measurement after program start"),
- OPT_BOOLEAN(0, "metric-only", &metric_only,
- "Only print computed metrics. No raw values"),
+ OPT_CALLBACK_NOOPT(0, "metric-only", &metric_only, NULL,
+ "Only print computed metrics. No raw values", enable_metric_only),
+ OPT_BOOLEAN(0, "topdown", &topdown_run,
+ "measure topdown level 1 statistics"),
OPT_END()
};
@@ -1772,12 +1796,62 @@
return 0;
}
+static int topdown_filter_events(const char **attr, char **str, bool use_group)
+{
+ int off = 0;
+ int i;
+ int len = 0;
+ char *s;
+
+ for (i = 0; attr[i]; i++) {
+ if (pmu_have_event("cpu", attr[i])) {
+ len += strlen(attr[i]) + 1;
+ attr[i - off] = attr[i];
+ } else
+ off++;
+ }
+ attr[i - off] = NULL;
+
+ *str = malloc(len + 1 + 2);
+ if (!*str)
+ return -1;
+ s = *str;
+ if (i - off == 0) {
+ *s = 0;
+ return 0;
+ }
+ if (use_group)
+ *s++ = '{';
+ for (i = 0; attr[i]; i++) {
+ strcpy(s, attr[i]);
+ s += strlen(s);
+ *s++ = ',';
+ }
+ if (use_group) {
+ s[-1] = '}';
+ *s = 0;
+ } else
+ s[-1] = 0;
+ return 0;
+}
+
+__weak bool arch_topdown_check_group(bool *warn)
+{
+ *warn = false;
+ return false;
+}
+
+__weak void arch_topdown_group_warn(void)
+{
+}
+
/*
* Add default attributes, if there were no attributes specified or
* if -d/--detailed, -d -d or -d -d -d is used:
*/
static int add_default_attributes(void)
{
+ int err;
struct perf_event_attr default_attrs0[] = {
{ .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK },
@@ -1896,7 +1970,6 @@
return 0;
if (transaction_run) {
- int err;
if (pmu_have_event("cpu", "cycles-ct") &&
pmu_have_event("cpu", "el-start"))
err = parse_events(evsel_list, transaction_attrs, NULL);
@@ -1909,6 +1982,46 @@
return 0;
}
+ if (topdown_run) {
+ char *str = NULL;
+ bool warn = false;
+
+ if (stat_config.aggr_mode != AGGR_GLOBAL &&
+ stat_config.aggr_mode != AGGR_CORE) {
+ pr_err("top down event configuration requires --per-core mode\n");
+ return -1;
+ }
+ stat_config.aggr_mode = AGGR_CORE;
+ if (nr_cgroups || !target__has_cpu(&target)) {
+ pr_err("top down event configuration requires system-wide mode (-a)\n");
+ return -1;
+ }
+
+ if (!force_metric_only)
+ metric_only = true;
+ if (topdown_filter_events(topdown_attrs, &str,
+ arch_topdown_check_group(&warn)) < 0) {
+ pr_err("Out of memory\n");
+ return -1;
+ }
+ if (topdown_attrs[0] && str) {
+ if (warn)
+ arch_topdown_group_warn();
+ err = parse_events(evsel_list, str, NULL);
+ if (err) {
+ fprintf(stderr,
+ "Cannot set up top down events %s: %d\n",
+ str, err);
+ free(str);
+ return -1;
+ }
+ } else {
+ fprintf(stderr, "System does not support topdown\n");
+ return -1;
+ }
+ free(str);
+ }
+
if (!evsel_list->nr_entries) {
if (target__has_cpu(&target))
default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;