2019-05-29 14:18:02 +00:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
2017-08-31 19:40:31 +00:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2017, Intel Corporation.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* Manage metrics and groups of metrics from JSON files */
|
|
|
|
|
|
|
|
#include "metricgroup.h"
|
2019-08-29 18:56:40 +00:00
|
|
|
#include "debug.h"
|
2017-08-31 19:40:31 +00:00
|
|
|
#include "evlist.h"
|
2019-08-21 13:54:14 +00:00
|
|
|
#include "evsel.h"
|
2017-08-31 19:40:31 +00:00
|
|
|
#include "strbuf.h"
|
|
|
|
#include "pmu.h"
|
|
|
|
#include "expr.h"
|
|
|
|
#include "rblist.h"
|
|
|
|
#include <string.h>
|
|
|
|
#include <errno.h>
|
|
|
|
#include "pmu-events/pmu-events.h"
|
|
|
|
#include "strlist.h"
|
|
|
|
#include <assert.h>
|
2019-06-26 00:13:51 +00:00
|
|
|
#include <linux/ctype.h>
|
2019-08-29 18:56:40 +00:00
|
|
|
#include <linux/string.h>
|
2019-07-04 15:06:20 +00:00
|
|
|
#include <linux/zalloc.h>
|
2019-08-21 13:54:14 +00:00
|
|
|
#include <subcmd/parse-options.h>
|
perf metricgroup: Support metric constraint
Some metric groups have metric constraints. A metric group can be
scheduled as a group only when some constraints are applied. For
example, Page_Walks_Utilization has a metric constraint,
"NO_NMI_WATCHDOG".
When NMI watchdog is disabled, the metric group can be scheduled as a
group. Otherwise, splitting the metric group into standalone metrics.
Add a new function, metricgroup__has_constraint(), to check whether all
constraints are applied. If not, splitting the metric group into
standalone metrics.
Currently, only one constraint, "NO_NMI_WATCHDOG", is checked. Print a
warning for the metric group with the constraint, when NMI WATCHDOG is
enabled.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Link: http://lore.kernel.org/lkml/1582581564-184429-5-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-24 21:59:23 +00:00
|
|
|
#include <api/fs/fs.h>
|
|
|
|
#include "util.h"
|
2017-08-31 19:40:31 +00:00
|
|
|
|
|
|
|
struct metric_event *metricgroup__lookup(struct rblist *metric_events,
|
2019-07-21 11:23:51 +00:00
|
|
|
struct evsel *evsel,
|
2017-08-31 19:40:31 +00:00
|
|
|
bool create)
|
|
|
|
{
|
|
|
|
struct rb_node *nd;
|
|
|
|
struct metric_event me = {
|
|
|
|
.evsel = evsel
|
|
|
|
};
|
perf script: Allow computing 'perf stat' style metrics
Add support for computing 'perf stat' style metrics in 'perf script'.
When using leader sampling we can get metrics for each sampling period
by computing formulas over the values of the different group members.
This allows things like fine grained IPC tracking through sampling, much
more fine grained than with 'perf stat'.
The metric is still averaged over the sampling period, it is not just
for the sampling point.
This patch adds a new metric output field for 'perf script' that uses
the existing 'perf stat' metrics infrastructure to compute any metrics
supported by 'perf stat'.
For example to sample IPC:
$ perf record -e '{ref-cycles,cycles,instructions}:S' -a sleep 1
$ perf script -F metric,ip,sym,time,cpu,comm
...
alsa-sink-ALC32 [000] 42815.856074: 7fd65937d6cc [unknown]
alsa-sink-ALC32 [000] 42815.856074: 7fd65937d6cc [unknown]
alsa-sink-ALC32 [000] 42815.856074: 7fd65937d6cc [unknown]
alsa-sink-ALC32 [000] 42815.856074: metric: 0.13 insn per cycle
swapper [000] 42815.857961: ffffffff81655df0 __schedule
swapper [000] 42815.857961: ffffffff81655df0 __schedule
swapper [000] 42815.857961: ffffffff81655df0 __schedule
swapper [000] 42815.857961: metric: 0.23 insn per cycle
qemu-system-x86 [000] 42815.858130: ffffffff8165ad0e _raw_spin_unlock_irqrestore
qemu-system-x86 [000] 42815.858130: ffffffff8165ad0e _raw_spin_unlock_irqrestore
qemu-system-x86 [000] 42815.858130: ffffffff8165ad0e _raw_spin_unlock_irqrestore
qemu-system-x86 [000] 42815.858130: metric: 0.46 insn per cycle
:4972 [000] 42815.858312: ffffffffa080e5f2 vmx_vcpu_run
:4972 [000] 42815.858312: ffffffffa080e5f2 vmx_vcpu_run
:4972 [000] 42815.858312: ffffffffa080e5f2 vmx_vcpu_run
:4972 [000] 42815.858312: metric: 0.45 insn per cycle
TopDown:
This requires disabling SMT if you have it enabled, because SMT would
require sampling per core, which is not supported.
$ perf record -e '{ref-cycles,topdown-fetch-bubbles,\
topdown-recovery-bubbles,\
topdown-slots-retired,topdown-total-slots,\
topdown-slots-issued}:S' -a sleep 1
$ perf script --header -I -F cpu,ip,sym,event,metric,period
...
[000] 121108 ref-cycles: ffffffff8165222e copy_user_enhanced_fast_string
[000] 190350 topdown-fetch-bubbles: ffffffff8165222e copy_user_enhanced_fast_string
[000] 2055 topdown-recovery-bubbles: ffffffff8165222e copy_user_enhanced_fast_string
[000] 148729 topdown-slots-retired: ffffffff8165222e copy_user_enhanced_fast_string
[000] 144324 topdown-total-slots: ffffffff8165222e copy_user_enhanced_fast_string
[000] 160852 topdown-slots-issued: ffffffff8165222e copy_user_enhanced_fast_string
[000] metric: 33.0% frontend bound
[000] metric: 3.5% bad speculation
[000] metric: 25.8% retiring
[000] metric: 37.7% backend bound
[000] 112112 ref-cycles: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 357222 topdown-fetch-bubbles: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 3325 topdown-recovery-bubbles: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 323553 topdown-slots-retired: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 270507 topdown-total-slots: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 341226 topdown-slots-issued: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] metric: 33.0% frontend bound
[000] metric: 2.9% bad speculation
[000] metric: 29.9% retiring
[000] metric: 34.2% backend bound
...
v2:
Use evsel->priv for new fields
Port to new base line, support fp output.
Handle stats in ->stats, not ->priv
Minor cleanups
Extra explanation about the use of the term 'averaging', from Andi in the
thread in the Link: tag below:
<quote Andi>
The current samples contains the sum of event counts for a sampling period.
EventA-1 EventA-2 EventA-3 EventA-4
EventB-1 EventB-2 EventC-3
gap with no events overflow
|-----------------------------------------------------------------|
period-start period-end
^ ^
| |
previous sample current sample
So EventA = 4 and EventB = 3 at the sample point
I generate a metric, let's say EventA / EventB. It applies to the whole period.
But the metric is over a longer time which does not have the same behavior. For
example the gap above doesn't have any events, while they are clustered at the
beginning and end of the sample period.
But we're summing everything together. The metric doesn't know that the gap is
different than the busy period.
That's what I'm trying to express with averaging.
</quote>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20171117214300.32746-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-11-17 21:43:00 +00:00
|
|
|
|
|
|
|
if (!metric_events)
|
|
|
|
return NULL;
|
|
|
|
|
2017-08-31 19:40:31 +00:00
|
|
|
nd = rblist__find(metric_events, &me);
|
|
|
|
if (nd)
|
|
|
|
return container_of(nd, struct metric_event, nd);
|
|
|
|
if (create) {
|
|
|
|
rblist__add_node(metric_events, &me);
|
|
|
|
nd = rblist__find(metric_events, &me);
|
|
|
|
if (nd)
|
|
|
|
return container_of(nd, struct metric_event, nd);
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int metric_event_cmp(struct rb_node *rb_node, const void *entry)
|
|
|
|
{
|
|
|
|
struct metric_event *a = container_of(rb_node,
|
|
|
|
struct metric_event,
|
|
|
|
nd);
|
|
|
|
const struct metric_event *b = entry;
|
|
|
|
|
|
|
|
if (a->evsel == b->evsel)
|
|
|
|
return 0;
|
|
|
|
if ((char *)a->evsel < (char *)b->evsel)
|
|
|
|
return -1;
|
|
|
|
return +1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct rb_node *metric_event_new(struct rblist *rblist __maybe_unused,
|
|
|
|
const void *entry)
|
|
|
|
{
|
|
|
|
struct metric_event *me = malloc(sizeof(struct metric_event));
|
|
|
|
|
|
|
|
if (!me)
|
|
|
|
return NULL;
|
|
|
|
memcpy(me, entry, sizeof(struct metric_event));
|
|
|
|
me->evsel = ((struct metric_event *)entry)->evsel;
|
|
|
|
INIT_LIST_HEAD(&me->head);
|
|
|
|
return &me->nd;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void metricgroup__rblist_init(struct rblist *metric_events)
|
|
|
|
{
|
|
|
|
rblist__init(metric_events);
|
|
|
|
metric_events->node_cmp = metric_event_cmp;
|
|
|
|
metric_events->node_new = metric_event_new;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct egroup {
|
|
|
|
struct list_head nd;
|
|
|
|
int idnum;
|
|
|
|
const char **ids;
|
|
|
|
const char *metric_name;
|
|
|
|
const char *metric_expr;
|
perf metricgroup: Scale the metric result
Some metrics define the scale unit, such as
{
"BriefDescription": "Intel Optane DC persistent memory read latency (ns). Derived from unc_m_pmm_rpq_occupancy.all",
"Counter": "0,1,2,3",
"EventCode": "0xE0",
"EventName": "UNC_M_PMM_READ_LATENCY",
"MetricExpr": "UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS / UNC_M_CLOCKTICKS",
"MetricName": "UNC_M_PMM_READ_LATENCY",
"PerPkg": "1",
"ScaleUnit": "6000000000ns",
"UMask": "0x1",
"Unit": "iMC"
},
For above example, the ratio should be,
ratio = (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS / UNC_M_CLOCKTICKS) * 6000000000
But in current code, the ratio is not scaled ( * 6000000000)
With this patch, the ratio is scaled and the unit (ns) is printed.
For example,
# 219.4 ns UNC_M_PMM_READ_LATENCY
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20190828055932.8269-4-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-28 05:59:31 +00:00
|
|
|
const char *metric_unit;
|
2017-08-31 19:40:31 +00:00
|
|
|
};
|
|
|
|
|
2019-07-21 11:23:52 +00:00
|
|
|
static struct evsel *find_evsel_group(struct evlist *perf_evlist,
|
2019-07-21 11:23:51 +00:00
|
|
|
const char **ids,
|
|
|
|
int idnum,
|
|
|
|
struct evsel **metric_events)
|
2017-08-31 19:40:31 +00:00
|
|
|
{
|
2019-08-28 05:59:32 +00:00
|
|
|
struct evsel *ev;
|
|
|
|
int i = 0;
|
|
|
|
bool leader_found;
|
2017-08-31 19:40:31 +00:00
|
|
|
|
|
|
|
evlist__for_each_entry (perf_evlist, ev) {
|
2019-08-28 05:59:32 +00:00
|
|
|
if (!strcmp(ev->name, ids[i])) {
|
|
|
|
if (!metric_events[i])
|
|
|
|
metric_events[i] = ev;
|
perf metricgroup: Fix printing event names of metric group with multiple events
Commit f01642e4912b ("perf metricgroup: Support multiple events for
metricgroup") introduced support for multiple events in a metric group.
But with the current upstream, metric events names are not printed
properly
In power9 platform:
command:# ./perf stat --metric-only -M translation -C 0 -I 1000 sleep 2
1.000208486
2.000368863
2.001400558
Similarly in skylake platform:
command:./perf stat --metric-only -M Power -I 1000
1.000579994
2.002189493
With current upstream version, issue is with event name comparison logic
in find_evsel_group(). Current logic is to compare events belonging to a
metric group to the events in perf_evlist. Since the break statement is
missing in the loop used for comparison between metric group and
perf_evlist events, the loop continues to execute even after getting a
pattern match, and end up in discarding the matches.
Incase of single metric event belongs to metric group, its working fine,
because in case of single event once it compare all events it reaches to
end of perf_evlist.
Example for single metric event in power9 platform:
command:# ./perf stat --metric-only -M branches_per_inst -I 1000 sleep 1
1.000094653 0.2
1.001337059 0.0
This patch fixes the issue by making sure once we found all events
belongs to that metric event matched in find_evsel_group(), we
successfully break from that loop by adding corresponding condition.
With this patch:
In power9 platform:
command:# ./perf stat --metric-only -M translation -C 0 -I 1000 sleep 2
result:#
time derat_4k_miss_rate_percent derat_4k_miss_ratio derat_miss_ratio derat_64k_miss_rate_percent derat_64k_miss_ratio dslb_miss_rate_percent islb_miss_rate_percent
1.000135672 0.0 0.3 1.0 0.0 0.2 0.0 0.0
2.000380617 0.0 0.0 0.0 0.0 0.0 0.0 0.0
command:# ./perf stat --metric-only -M Power -I 1000
Similarly in skylake platform:
result:#
time Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.000563580 0.3 0.0 2.6 44.2 21.9 0.0 0.0 0.0
2.002235027 0.4 0.0 2.7 43.0 20.7 0.0 0.0 0.0
Committer testing:
Before:
[root@seventh ~]# perf stat --metric-only -M Power -I 1000
# time
1.000383223
2.001168182
3.001968545
4.002741200
5.003442022
^C 5.777687244
[root@seventh ~]#
After the patch:
[root@seventh ~]# perf stat --metric-only -M Power -I 1000
# time Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.000406577 0.4 0.1 1.4 97.0 0.0 0.0 0.0 0.0
2.001481572 0.3 0.0 0.6 97.9 0.0 0.0 0.0 0.0
3.002332585 0.2 0.0 1.0 97.5 0.0 0.0 0.0 0.0
4.003196624 0.2 0.0 0.3 98.6 0.0 0.0 0.0 0.0
5.004063851 0.3 0.0 0.7 97.7 0.0 0.0 0.0 0.0
^C 5.471260276 0.2 0.0 0.5 49.3 0.0 0.0 0.0 0.0
[root@seventh ~]#
[root@seventh ~]# dmesg | grep -i skylake
[ 0.187807] Performance Events: PEBS fmt3+, Skylake events, 32-deep LBR, full-width counters, Intel PMU driver.
[root@seventh ~]#
Fixes: f01642e4912b ("perf metricgroup: Support multiple events for metricgroup")
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Reviewed-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Anju T Sudhakar <anju@linux.vnet.ibm.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20191120084059.24458-1-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-20 08:40:59 +00:00
|
|
|
i++;
|
|
|
|
if (i == idnum)
|
|
|
|
break;
|
2017-08-31 19:40:31 +00:00
|
|
|
} else {
|
perf metricgroup: Fix printing event names of metric group with multiple events
Commit f01642e4912b ("perf metricgroup: Support multiple events for
metricgroup") introduced support for multiple events in a metric group.
But with the current upstream, metric events names are not printed
properly
In power9 platform:
command:# ./perf stat --metric-only -M translation -C 0 -I 1000 sleep 2
1.000208486
2.000368863
2.001400558
Similarly in skylake platform:
command:./perf stat --metric-only -M Power -I 1000
1.000579994
2.002189493
With current upstream version, issue is with event name comparison logic
in find_evsel_group(). Current logic is to compare events belonging to a
metric group to the events in perf_evlist. Since the break statement is
missing in the loop used for comparison between metric group and
perf_evlist events, the loop continues to execute even after getting a
pattern match, and end up in discarding the matches.
Incase of single metric event belongs to metric group, its working fine,
because in case of single event once it compare all events it reaches to
end of perf_evlist.
Example for single metric event in power9 platform:
command:# ./perf stat --metric-only -M branches_per_inst -I 1000 sleep 1
1.000094653 0.2
1.001337059 0.0
This patch fixes the issue by making sure once we found all events
belongs to that metric event matched in find_evsel_group(), we
successfully break from that loop by adding corresponding condition.
With this patch:
In power9 platform:
command:# ./perf stat --metric-only -M translation -C 0 -I 1000 sleep 2
result:#
time derat_4k_miss_rate_percent derat_4k_miss_ratio derat_miss_ratio derat_64k_miss_rate_percent derat_64k_miss_ratio dslb_miss_rate_percent islb_miss_rate_percent
1.000135672 0.0 0.3 1.0 0.0 0.2 0.0 0.0
2.000380617 0.0 0.0 0.0 0.0 0.0 0.0 0.0
command:# ./perf stat --metric-only -M Power -I 1000
Similarly in skylake platform:
result:#
time Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.000563580 0.3 0.0 2.6 44.2 21.9 0.0 0.0 0.0
2.002235027 0.4 0.0 2.7 43.0 20.7 0.0 0.0 0.0
Committer testing:
Before:
[root@seventh ~]# perf stat --metric-only -M Power -I 1000
# time
1.000383223
2.001168182
3.001968545
4.002741200
5.003442022
^C 5.777687244
[root@seventh ~]#
After the patch:
[root@seventh ~]# perf stat --metric-only -M Power -I 1000
# time Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.000406577 0.4 0.1 1.4 97.0 0.0 0.0 0.0 0.0
2.001481572 0.3 0.0 0.6 97.9 0.0 0.0 0.0 0.0
3.002332585 0.2 0.0 1.0 97.5 0.0 0.0 0.0 0.0
4.003196624 0.2 0.0 0.3 98.6 0.0 0.0 0.0 0.0
5.004063851 0.3 0.0 0.7 97.7 0.0 0.0 0.0 0.0
^C 5.471260276 0.2 0.0 0.5 49.3 0.0 0.0 0.0 0.0
[root@seventh ~]#
[root@seventh ~]# dmesg | grep -i skylake
[ 0.187807] Performance Events: PEBS fmt3+, Skylake events, 32-deep LBR, full-width counters, Intel PMU driver.
[root@seventh ~]#
Fixes: f01642e4912b ("perf metricgroup: Support multiple events for metricgroup")
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Reviewed-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Anju T Sudhakar <anju@linux.vnet.ibm.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20191120084059.24458-1-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-20 08:40:59 +00:00
|
|
|
if (i + 1 == idnum) {
|
2019-08-28 05:59:32 +00:00
|
|
|
/* Discard the whole match and start again */
|
|
|
|
i = 0;
|
|
|
|
memset(metric_events, 0,
|
|
|
|
sizeof(struct evsel *) * idnum);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!strcmp(ev->name, ids[i]))
|
|
|
|
metric_events[i] = ev;
|
|
|
|
else {
|
|
|
|
/* Discard the whole match and start again */
|
|
|
|
i = 0;
|
|
|
|
memset(metric_events, 0,
|
|
|
|
sizeof(struct evsel *) * idnum);
|
|
|
|
continue;
|
perf stat: Fix group lookup for metric group
The metric group code tries to find a group it added earlier in the
evlist. Fix the lookup to handle groups with partially overlaps
correctly. When a sub string match fails and we reset the match, we have
to compare the first element again.
I also renamed the find_evsel function to find_evsel_group to make its
purpose clearer.
With the earlier changes this fixes:
Before:
% perf stat -M UPI,IPC sleep 1
...
1,032,922 uops_retired.retire_slots # 1.1 UPI
1,896,096 inst_retired.any
1,896,096 inst_retired.any
1,177,254 cpu_clk_unhalted.thread
After:
% perf stat -M UPI,IPC sleep 1
...
1,013,193 uops_retired.retire_slots # 1.1 UPI
932,033 inst_retired.any
932,033 inst_retired.any # 0.9 IPC
1,091,245 cpu_clk_unhalted.thread
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Fixes: b18f3e365019 ("perf stat: Support JSON metrics in perf stat")
Link: http://lkml.kernel.org/r/20190624193711.35241-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-24 19:37:10 +00:00
|
|
|
}
|
2017-08-31 19:40:31 +00:00
|
|
|
}
|
|
|
|
}
|
2019-08-28 05:59:32 +00:00
|
|
|
|
perf metricgroup: Fix printing event names of metric group with multiple events
Commit f01642e4912b ("perf metricgroup: Support multiple events for
metricgroup") introduced support for multiple events in a metric group.
But with the current upstream, metric events names are not printed
properly
In power9 platform:
command:# ./perf stat --metric-only -M translation -C 0 -I 1000 sleep 2
1.000208486
2.000368863
2.001400558
Similarly in skylake platform:
command:./perf stat --metric-only -M Power -I 1000
1.000579994
2.002189493
With current upstream version, issue is with event name comparison logic
in find_evsel_group(). Current logic is to compare events belonging to a
metric group to the events in perf_evlist. Since the break statement is
missing in the loop used for comparison between metric group and
perf_evlist events, the loop continues to execute even after getting a
pattern match, and end up in discarding the matches.
Incase of single metric event belongs to metric group, its working fine,
because in case of single event once it compare all events it reaches to
end of perf_evlist.
Example for single metric event in power9 platform:
command:# ./perf stat --metric-only -M branches_per_inst -I 1000 sleep 1
1.000094653 0.2
1.001337059 0.0
This patch fixes the issue by making sure once we found all events
belongs to that metric event matched in find_evsel_group(), we
successfully break from that loop by adding corresponding condition.
With this patch:
In power9 platform:
command:# ./perf stat --metric-only -M translation -C 0 -I 1000 sleep 2
result:#
time derat_4k_miss_rate_percent derat_4k_miss_ratio derat_miss_ratio derat_64k_miss_rate_percent derat_64k_miss_ratio dslb_miss_rate_percent islb_miss_rate_percent
1.000135672 0.0 0.3 1.0 0.0 0.2 0.0 0.0
2.000380617 0.0 0.0 0.0 0.0 0.0 0.0 0.0
command:# ./perf stat --metric-only -M Power -I 1000
Similarly in skylake platform:
result:#
time Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.000563580 0.3 0.0 2.6 44.2 21.9 0.0 0.0 0.0
2.002235027 0.4 0.0 2.7 43.0 20.7 0.0 0.0 0.0
Committer testing:
Before:
[root@seventh ~]# perf stat --metric-only -M Power -I 1000
# time
1.000383223
2.001168182
3.001968545
4.002741200
5.003442022
^C 5.777687244
[root@seventh ~]#
After the patch:
[root@seventh ~]# perf stat --metric-only -M Power -I 1000
# time Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.000406577 0.4 0.1 1.4 97.0 0.0 0.0 0.0 0.0
2.001481572 0.3 0.0 0.6 97.9 0.0 0.0 0.0 0.0
3.002332585 0.2 0.0 1.0 97.5 0.0 0.0 0.0 0.0
4.003196624 0.2 0.0 0.3 98.6 0.0 0.0 0.0 0.0
5.004063851 0.3 0.0 0.7 97.7 0.0 0.0 0.0 0.0
^C 5.471260276 0.2 0.0 0.5 49.3 0.0 0.0 0.0 0.0
[root@seventh ~]#
[root@seventh ~]# dmesg | grep -i skylake
[ 0.187807] Performance Events: PEBS fmt3+, Skylake events, 32-deep LBR, full-width counters, Intel PMU driver.
[root@seventh ~]#
Fixes: f01642e4912b ("perf metricgroup: Support multiple events for metricgroup")
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Reviewed-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Anju T Sudhakar <anju@linux.vnet.ibm.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20191120084059.24458-1-kjain@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-20 08:40:59 +00:00
|
|
|
if (i != idnum) {
|
2019-08-28 05:59:32 +00:00
|
|
|
/* Not whole match */
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
metric_events[idnum] = NULL;
|
|
|
|
|
|
|
|
for (i = 0; i < idnum; i++) {
|
|
|
|
leader_found = false;
|
|
|
|
evlist__for_each_entry(perf_evlist, ev) {
|
|
|
|
if (!leader_found && (ev == metric_events[i]))
|
|
|
|
leader_found = true;
|
|
|
|
|
|
|
|
if (leader_found &&
|
|
|
|
!strcmp(ev->name, metric_events[i]->name)) {
|
|
|
|
ev->metric_leader = metric_events[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return metric_events[0];
|
2017-08-31 19:40:31 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static int metricgroup__setup_events(struct list_head *groups,
|
2019-07-21 11:23:52 +00:00
|
|
|
struct evlist *perf_evlist,
|
2017-08-31 19:40:31 +00:00
|
|
|
struct rblist *metric_events_list)
|
|
|
|
{
|
|
|
|
struct metric_event *me;
|
|
|
|
struct metric_expr *expr;
|
|
|
|
int i = 0;
|
|
|
|
int ret = 0;
|
|
|
|
struct egroup *eg;
|
2019-07-21 11:23:51 +00:00
|
|
|
struct evsel *evsel;
|
2017-08-31 19:40:31 +00:00
|
|
|
|
|
|
|
list_for_each_entry (eg, groups, nd) {
|
2019-07-21 11:23:51 +00:00
|
|
|
struct evsel **metric_events;
|
2017-08-31 19:40:31 +00:00
|
|
|
|
|
|
|
metric_events = calloc(sizeof(void *), eg->idnum + 1);
|
|
|
|
if (!metric_events) {
|
|
|
|
ret = -ENOMEM;
|
|
|
|
break;
|
|
|
|
}
|
perf stat: Fix group lookup for metric group
The metric group code tries to find a group it added earlier in the
evlist. Fix the lookup to handle groups with partially overlaps
correctly. When a sub string match fails and we reset the match, we have
to compare the first element again.
I also renamed the find_evsel function to find_evsel_group to make its
purpose clearer.
With the earlier changes this fixes:
Before:
% perf stat -M UPI,IPC sleep 1
...
1,032,922 uops_retired.retire_slots # 1.1 UPI
1,896,096 inst_retired.any
1,896,096 inst_retired.any
1,177,254 cpu_clk_unhalted.thread
After:
% perf stat -M UPI,IPC sleep 1
...
1,013,193 uops_retired.retire_slots # 1.1 UPI
932,033 inst_retired.any
932,033 inst_retired.any # 0.9 IPC
1,091,245 cpu_clk_unhalted.thread
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Fixes: b18f3e365019 ("perf stat: Support JSON metrics in perf stat")
Link: http://lkml.kernel.org/r/20190624193711.35241-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-24 19:37:10 +00:00
|
|
|
evsel = find_evsel_group(perf_evlist, eg->ids, eg->idnum,
|
|
|
|
metric_events);
|
2017-08-31 19:40:31 +00:00
|
|
|
if (!evsel) {
|
|
|
|
pr_debug("Cannot resolve %s: %s\n",
|
|
|
|
eg->metric_name, eg->metric_expr);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
for (i = 0; i < eg->idnum; i++)
|
|
|
|
metric_events[i]->collect_stat = true;
|
|
|
|
me = metricgroup__lookup(metric_events_list, evsel, true);
|
|
|
|
if (!me) {
|
|
|
|
ret = -ENOMEM;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
expr = malloc(sizeof(struct metric_expr));
|
|
|
|
if (!expr) {
|
|
|
|
ret = -ENOMEM;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
expr->metric_expr = eg->metric_expr;
|
|
|
|
expr->metric_name = eg->metric_name;
|
perf metricgroup: Scale the metric result
Some metrics define the scale unit, such as
{
"BriefDescription": "Intel Optane DC persistent memory read latency (ns). Derived from unc_m_pmm_rpq_occupancy.all",
"Counter": "0,1,2,3",
"EventCode": "0xE0",
"EventName": "UNC_M_PMM_READ_LATENCY",
"MetricExpr": "UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS / UNC_M_CLOCKTICKS",
"MetricName": "UNC_M_PMM_READ_LATENCY",
"PerPkg": "1",
"ScaleUnit": "6000000000ns",
"UMask": "0x1",
"Unit": "iMC"
},
For above example, the ratio should be,
ratio = (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS / UNC_M_CLOCKTICKS) * 6000000000
But in current code, the ratio is not scaled ( * 6000000000)
With this patch, the ratio is scaled and the unit (ns) is printed.
For example,
# 219.4 ns UNC_M_PMM_READ_LATENCY
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20190828055932.8269-4-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-28 05:59:31 +00:00
|
|
|
expr->metric_unit = eg->metric_unit;
|
2017-08-31 19:40:31 +00:00
|
|
|
expr->metric_events = metric_events;
|
|
|
|
list_add(&expr->nd, &me->head);
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool match_metric(const char *n, const char *list)
|
|
|
|
{
|
|
|
|
int len;
|
|
|
|
char *m;
|
|
|
|
|
|
|
|
if (!list)
|
|
|
|
return false;
|
|
|
|
if (!strcmp(list, "all"))
|
|
|
|
return true;
|
|
|
|
if (!n)
|
|
|
|
return !strcasecmp(list, "No_group");
|
|
|
|
len = strlen(list);
|
|
|
|
m = strcasestr(n, list);
|
|
|
|
if (!m)
|
|
|
|
return false;
|
|
|
|
if ((m == n || m[-1] == ';' || m[-1] == ' ') &&
|
|
|
|
(m[len] == 0 || m[len] == ';'))
|
|
|
|
return true;
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2017-08-31 19:40:32 +00:00
|
|
|
struct mep {
|
|
|
|
struct rb_node nd;
|
|
|
|
const char *name;
|
|
|
|
struct strlist *metrics;
|
|
|
|
};
|
|
|
|
|
|
|
|
static int mep_cmp(struct rb_node *rb_node, const void *entry)
|
|
|
|
{
|
|
|
|
struct mep *a = container_of(rb_node, struct mep, nd);
|
|
|
|
struct mep *b = (struct mep *)entry;
|
|
|
|
|
|
|
|
return strcmp(a->name, b->name);
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct rb_node *mep_new(struct rblist *rl __maybe_unused,
|
|
|
|
const void *entry)
|
|
|
|
{
|
|
|
|
struct mep *me = malloc(sizeof(struct mep));
|
|
|
|
|
|
|
|
if (!me)
|
|
|
|
return NULL;
|
|
|
|
memcpy(me, entry, sizeof(struct mep));
|
|
|
|
me->name = strdup(me->name);
|
|
|
|
if (!me->name)
|
|
|
|
goto out_me;
|
|
|
|
me->metrics = strlist__new(NULL, NULL);
|
|
|
|
if (!me->metrics)
|
|
|
|
goto out_name;
|
|
|
|
return &me->nd;
|
|
|
|
out_name:
|
2019-07-04 15:06:20 +00:00
|
|
|
zfree(&me->name);
|
2017-08-31 19:40:32 +00:00
|
|
|
out_me:
|
|
|
|
free(me);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct mep *mep_lookup(struct rblist *groups, const char *name)
|
|
|
|
{
|
|
|
|
struct rb_node *nd;
|
|
|
|
struct mep me = {
|
|
|
|
.name = name
|
|
|
|
};
|
|
|
|
nd = rblist__find(groups, &me);
|
|
|
|
if (nd)
|
|
|
|
return container_of(nd, struct mep, nd);
|
|
|
|
rblist__add_node(groups, &me);
|
|
|
|
nd = rblist__find(groups, &me);
|
|
|
|
if (nd)
|
|
|
|
return container_of(nd, struct mep, nd);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void mep_delete(struct rblist *rl __maybe_unused,
|
|
|
|
struct rb_node *nd)
|
|
|
|
{
|
|
|
|
struct mep *me = container_of(nd, struct mep, nd);
|
|
|
|
|
|
|
|
strlist__delete(me->metrics);
|
2019-07-04 15:06:20 +00:00
|
|
|
zfree(&me->name);
|
2017-08-31 19:40:32 +00:00
|
|
|
free(me);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void metricgroup__print_strlist(struct strlist *metrics, bool raw)
|
|
|
|
{
|
|
|
|
struct str_node *sn;
|
|
|
|
int n = 0;
|
|
|
|
|
|
|
|
strlist__for_each_entry (sn, metrics) {
|
|
|
|
if (raw)
|
|
|
|
printf("%s%s", n > 0 ? " " : "", sn->s);
|
|
|
|
else
|
|
|
|
printf(" %s\n", sn->s);
|
|
|
|
n++;
|
|
|
|
}
|
|
|
|
if (raw)
|
|
|
|
putchar('\n');
|
|
|
|
}
|
|
|
|
|
|
|
|
void metricgroup__print(bool metrics, bool metricgroups, char *filter,
|
2019-02-13 12:32:41 +00:00
|
|
|
bool raw, bool details)
|
2017-08-31 19:40:32 +00:00
|
|
|
{
|
2017-10-16 18:32:18 +00:00
|
|
|
struct pmu_events_map *map = perf_pmu__find_map(NULL);
|
2017-08-31 19:40:32 +00:00
|
|
|
struct pmu_event *pe;
|
|
|
|
int i;
|
|
|
|
struct rblist groups;
|
|
|
|
struct rb_node *node, *next;
|
|
|
|
struct strlist *metriclist = NULL;
|
|
|
|
|
|
|
|
if (!map)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (!metricgroups) {
|
|
|
|
metriclist = strlist__new(NULL, NULL);
|
|
|
|
if (!metriclist)
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
rblist__init(&groups);
|
|
|
|
groups.node_new = mep_new;
|
|
|
|
groups.node_cmp = mep_cmp;
|
|
|
|
groups.node_delete = mep_delete;
|
|
|
|
for (i = 0; ; i++) {
|
|
|
|
const char *g;
|
|
|
|
pe = &map->table[i];
|
|
|
|
|
|
|
|
if (!pe->name && !pe->metric_group && !pe->metric_name)
|
|
|
|
break;
|
|
|
|
if (!pe->metric_expr)
|
|
|
|
continue;
|
|
|
|
g = pe->metric_group;
|
|
|
|
if (!g && pe->metric_name) {
|
|
|
|
if (pe->name)
|
|
|
|
continue;
|
|
|
|
g = "No_group";
|
|
|
|
}
|
|
|
|
if (g) {
|
|
|
|
char *omg;
|
|
|
|
char *mg = strdup(g);
|
|
|
|
|
|
|
|
if (!mg)
|
|
|
|
return;
|
|
|
|
omg = mg;
|
|
|
|
while ((g = strsep(&mg, ";")) != NULL) {
|
|
|
|
struct mep *me;
|
|
|
|
char *s;
|
|
|
|
|
2019-06-26 14:21:47 +00:00
|
|
|
g = skip_spaces(g);
|
2017-08-31 19:40:32 +00:00
|
|
|
if (*g == 0)
|
|
|
|
g = "No_group";
|
|
|
|
if (filter && !strstr(g, filter))
|
|
|
|
continue;
|
|
|
|
if (raw)
|
|
|
|
s = (char *)pe->metric_name;
|
|
|
|
else {
|
2018-07-30 21:35:04 +00:00
|
|
|
if (asprintf(&s, "%s\n%*s%s]",
|
|
|
|
pe->metric_name, 8, "[", pe->desc) < 0)
|
2017-08-31 19:40:32 +00:00
|
|
|
return;
|
2019-02-13 12:32:41 +00:00
|
|
|
|
|
|
|
if (details) {
|
|
|
|
if (asprintf(&s, "%s\n%*s%s]",
|
|
|
|
s, 8, "[", pe->metric_expr) < 0)
|
|
|
|
return;
|
|
|
|
}
|
2017-08-31 19:40:32 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
if (!s)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
if (!metricgroups) {
|
|
|
|
strlist__add(metriclist, s);
|
|
|
|
} else {
|
|
|
|
me = mep_lookup(&groups, g);
|
|
|
|
if (!me)
|
|
|
|
continue;
|
|
|
|
strlist__add(me->metrics, s);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
free(omg);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (metricgroups && !raw)
|
|
|
|
printf("\nMetric Groups:\n\n");
|
|
|
|
else if (metrics && !raw)
|
|
|
|
printf("\nMetrics:\n\n");
|
|
|
|
|
2018-12-06 19:18:16 +00:00
|
|
|
for (node = rb_first_cached(&groups.entries); node; node = next) {
|
2017-08-31 19:40:32 +00:00
|
|
|
struct mep *me = container_of(node, struct mep, nd);
|
|
|
|
|
|
|
|
if (metricgroups)
|
2019-06-28 22:07:36 +00:00
|
|
|
printf("%s%s%s", me->name, metrics && !raw ? ":" : "", raw ? " " : "\n");
|
2017-08-31 19:40:32 +00:00
|
|
|
if (metrics)
|
|
|
|
metricgroup__print_strlist(me->metrics, raw);
|
|
|
|
next = rb_next(node);
|
|
|
|
rblist__remove_node(&groups, node);
|
|
|
|
}
|
|
|
|
if (!metricgroups)
|
|
|
|
metricgroup__print_strlist(metriclist, raw);
|
|
|
|
strlist__delete(metriclist);
|
|
|
|
}
|
|
|
|
|
2020-02-24 21:59:21 +00:00
|
|
|
static void metricgroup__add_metric_weak_group(struct strbuf *events,
|
|
|
|
const char **ids,
|
|
|
|
int idnum)
|
|
|
|
{
|
|
|
|
bool no_group = false;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < idnum; i++) {
|
|
|
|
pr_debug("found event %s\n", ids[i]);
|
|
|
|
/*
|
|
|
|
* Duration time maps to a software event and can make
|
|
|
|
* groups not count. Always use it outside a
|
|
|
|
* group.
|
|
|
|
*/
|
|
|
|
if (!strcmp(ids[i], "duration_time")) {
|
|
|
|
if (i > 0)
|
|
|
|
strbuf_addf(events, "}:W,");
|
|
|
|
strbuf_addf(events, "duration_time");
|
|
|
|
no_group = true;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
strbuf_addf(events, "%s%s",
|
|
|
|
i == 0 || no_group ? "{" : ",",
|
|
|
|
ids[i]);
|
|
|
|
no_group = false;
|
|
|
|
}
|
|
|
|
if (!no_group)
|
|
|
|
strbuf_addf(events, "}:W");
|
|
|
|
}
|
|
|
|
|
perf metricgroup: Support metric constraint
Some metric groups have metric constraints. A metric group can be
scheduled as a group only when some constraints are applied. For
example, Page_Walks_Utilization has a metric constraint,
"NO_NMI_WATCHDOG".
When NMI watchdog is disabled, the metric group can be scheduled as a
group. Otherwise, splitting the metric group into standalone metrics.
Add a new function, metricgroup__has_constraint(), to check whether all
constraints are applied. If not, splitting the metric group into
standalone metrics.
Currently, only one constraint, "NO_NMI_WATCHDOG", is checked. Print a
warning for the metric group with the constraint, when NMI WATCHDOG is
enabled.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Link: http://lore.kernel.org/lkml/1582581564-184429-5-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-24 21:59:23 +00:00
|
|
|
static void metricgroup__add_metric_non_group(struct strbuf *events,
|
|
|
|
const char **ids,
|
|
|
|
int idnum)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < idnum; i++)
|
|
|
|
strbuf_addf(events, ",%s", ids[i]);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void metricgroup___watchdog_constraint_hint(const char *name, bool foot)
|
|
|
|
{
|
|
|
|
static bool violate_nmi_constraint;
|
|
|
|
|
|
|
|
if (!foot) {
|
|
|
|
pr_warning("Splitting metric group %s into standalone metrics.\n", name);
|
|
|
|
violate_nmi_constraint = true;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!violate_nmi_constraint)
|
|
|
|
return;
|
|
|
|
|
|
|
|
pr_warning("Try disabling the NMI watchdog to comply NO_NMI_WATCHDOG metric constraint:\n"
|
|
|
|
" echo 0 > /proc/sys/kernel/nmi_watchdog\n"
|
|
|
|
" perf stat ...\n"
|
|
|
|
" echo 1 > /proc/sys/kernel/nmi_watchdog\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool metricgroup__has_constraint(struct pmu_event *pe)
|
|
|
|
{
|
|
|
|
if (!pe->metric_constraint)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
if (!strcmp(pe->metric_constraint, "NO_NMI_WATCHDOG") &&
|
|
|
|
sysctl__nmi_watchdog_enabled()) {
|
|
|
|
metricgroup___watchdog_constraint_hint(pe->metric_name, false);
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2017-08-31 19:40:31 +00:00
|
|
|
static int metricgroup__add_metric(const char *metric, struct strbuf *events,
|
|
|
|
struct list_head *group_list)
|
|
|
|
{
|
2017-10-16 18:32:18 +00:00
|
|
|
struct pmu_events_map *map = perf_pmu__find_map(NULL);
|
2017-08-31 19:40:31 +00:00
|
|
|
struct pmu_event *pe;
|
2020-02-24 21:59:21 +00:00
|
|
|
int i, ret = -EINVAL;
|
2017-08-31 19:40:31 +00:00
|
|
|
|
|
|
|
if (!map)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
for (i = 0; ; i++) {
|
|
|
|
pe = &map->table[i];
|
|
|
|
|
|
|
|
if (!pe->name && !pe->metric_group && !pe->metric_name)
|
|
|
|
break;
|
|
|
|
if (!pe->metric_expr)
|
|
|
|
continue;
|
|
|
|
if (match_metric(pe->metric_group, metric) ||
|
|
|
|
match_metric(pe->metric_name, metric)) {
|
|
|
|
const char **ids;
|
|
|
|
int idnum;
|
|
|
|
struct egroup *eg;
|
|
|
|
|
|
|
|
pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
|
|
|
|
|
|
|
|
if (expr__find_other(pe->metric_expr,
|
|
|
|
NULL, &ids, &idnum) < 0)
|
|
|
|
continue;
|
|
|
|
if (events->len > 0)
|
|
|
|
strbuf_addf(events, ",");
|
2020-02-24 21:59:21 +00:00
|
|
|
|
perf metricgroup: Support metric constraint
Some metric groups have metric constraints. A metric group can be
scheduled as a group only when some constraints are applied. For
example, Page_Walks_Utilization has a metric constraint,
"NO_NMI_WATCHDOG".
When NMI watchdog is disabled, the metric group can be scheduled as a
group. Otherwise, splitting the metric group into standalone metrics.
Add a new function, metricgroup__has_constraint(), to check whether all
constraints are applied. If not, splitting the metric group into
standalone metrics.
Currently, only one constraint, "NO_NMI_WATCHDOG", is checked. Print a
warning for the metric group with the constraint, when NMI WATCHDOG is
enabled.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Link: http://lore.kernel.org/lkml/1582581564-184429-5-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-24 21:59:23 +00:00
|
|
|
if (metricgroup__has_constraint(pe))
|
|
|
|
metricgroup__add_metric_non_group(events, ids, idnum);
|
|
|
|
else
|
|
|
|
metricgroup__add_metric_weak_group(events, ids, idnum);
|
2017-08-31 19:40:31 +00:00
|
|
|
|
|
|
|
eg = malloc(sizeof(struct egroup));
|
|
|
|
if (!eg) {
|
|
|
|
ret = -ENOMEM;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
eg->ids = ids;
|
|
|
|
eg->idnum = idnum;
|
|
|
|
eg->metric_name = pe->metric_name;
|
|
|
|
eg->metric_expr = pe->metric_expr;
|
perf metricgroup: Scale the metric result
Some metrics define the scale unit, such as
{
"BriefDescription": "Intel Optane DC persistent memory read latency (ns). Derived from unc_m_pmm_rpq_occupancy.all",
"Counter": "0,1,2,3",
"EventCode": "0xE0",
"EventName": "UNC_M_PMM_READ_LATENCY",
"MetricExpr": "UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS / UNC_M_CLOCKTICKS",
"MetricName": "UNC_M_PMM_READ_LATENCY",
"PerPkg": "1",
"ScaleUnit": "6000000000ns",
"UMask": "0x1",
"Unit": "iMC"
},
For above example, the ratio should be,
ratio = (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS / UNC_M_CLOCKTICKS) * 6000000000
But in current code, the ratio is not scaled ( * 6000000000)
With this patch, the ratio is scaled and the unit (ns) is printed.
For example,
# 219.4 ns UNC_M_PMM_READ_LATENCY
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20190828055932.8269-4-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-28 05:59:31 +00:00
|
|
|
eg->metric_unit = pe->unit;
|
2017-08-31 19:40:31 +00:00
|
|
|
list_add_tail(&eg->nd, group_list);
|
|
|
|
ret = 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
|
|
|
|
struct list_head *group_list)
|
|
|
|
{
|
|
|
|
char *llist, *nlist, *p;
|
|
|
|
int ret = -EINVAL;
|
|
|
|
|
|
|
|
nlist = strdup(list);
|
|
|
|
if (!nlist)
|
|
|
|
return -ENOMEM;
|
|
|
|
llist = nlist;
|
2017-09-14 20:57:35 +00:00
|
|
|
|
|
|
|
strbuf_init(events, 100);
|
|
|
|
strbuf_addf(events, "%s", "");
|
|
|
|
|
2017-08-31 19:40:31 +00:00
|
|
|
while ((p = strsep(&llist, ",")) != NULL) {
|
|
|
|
ret = metricgroup__add_metric(p, events, group_list);
|
|
|
|
if (ret == -EINVAL) {
|
|
|
|
fprintf(stderr, "Cannot find metric or group `%s'\n",
|
|
|
|
p);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
free(nlist);
|
perf metricgroup: Support metric constraint
Some metric groups have metric constraints. A metric group can be
scheduled as a group only when some constraints are applied. For
example, Page_Walks_Utilization has a metric constraint,
"NO_NMI_WATCHDOG".
When NMI watchdog is disabled, the metric group can be scheduled as a
group. Otherwise, splitting the metric group into standalone metrics.
Add a new function, metricgroup__has_constraint(), to check whether all
constraints are applied. If not, splitting the metric group into
standalone metrics.
Currently, only one constraint, "NO_NMI_WATCHDOG", is checked. Print a
warning for the metric group with the constraint, when NMI WATCHDOG is
enabled.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Link: http://lore.kernel.org/lkml/1582581564-184429-5-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-24 21:59:23 +00:00
|
|
|
|
|
|
|
if (!ret)
|
|
|
|
metricgroup___watchdog_constraint_hint(NULL, true);
|
|
|
|
|
2017-08-31 19:40:31 +00:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void metricgroup__free_egroups(struct list_head *group_list)
|
|
|
|
{
|
|
|
|
struct egroup *eg, *egtmp;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
list_for_each_entry_safe (eg, egtmp, group_list, nd) {
|
|
|
|
for (i = 0; i < eg->idnum; i++)
|
2019-07-04 15:06:20 +00:00
|
|
|
zfree(&eg->ids[i]);
|
|
|
|
zfree(&eg->ids);
|
2019-07-04 15:20:21 +00:00
|
|
|
list_del_init(&eg->nd);
|
2017-08-31 19:40:31 +00:00
|
|
|
free(eg);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
int metricgroup__parse_groups(const struct option *opt,
|
|
|
|
const char *str,
|
|
|
|
struct rblist *metric_events)
|
|
|
|
{
|
|
|
|
struct parse_events_error parse_error;
|
2019-07-21 11:23:52 +00:00
|
|
|
struct evlist *perf_evlist = *(struct evlist **)opt->value;
|
2017-08-31 19:40:31 +00:00
|
|
|
struct strbuf extra_events;
|
|
|
|
LIST_HEAD(group_list);
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (metric_events->nr_entries == 0)
|
|
|
|
metricgroup__rblist_init(metric_events);
|
|
|
|
ret = metricgroup__add_metric_list(str, &extra_events, &group_list);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
pr_debug("adding %s\n", extra_events.buf);
|
perf parse: Report initial event parsing error
Record the first event parsing error and report. Implementing feedback
from Jiri Olsa:
https://lkml.org/lkml/2019/10/28/680
An example error is:
$ tools/perf/perf stat -e c/c/
WARNING: multiple event parsing errors
event syntax error: 'c/c/'
\___ unknown term
valid terms: event,filter_rem,filter_opc0,edge,filter_isoc,filter_tid,filter_loc,filter_nc,inv,umask,filter_opc1,tid_en,thresh,filter_all_op,filter_not_nm,filter_state,filter_nm,config,config1,config2,name,period,percore
Initial error:
event syntax error: 'c/c/'
\___ Cannot find PMU `c'. Missing kernel support?
Run 'perf list' for a list of valid events
Usage: perf stat [<options>] [<command>]
-e, --event <event> event selector. use 'perf list' to list available events
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Allison Randal <allison@lohutok.net>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Anju T Sudhakar <anju@linux.vnet.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: http://lore.kernel.org/lkml/20191116074652.9960-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-16 07:46:52 +00:00
|
|
|
bzero(&parse_error, sizeof(parse_error));
|
2017-08-31 19:40:31 +00:00
|
|
|
ret = parse_events(perf_evlist, extra_events.buf, &parse_error);
|
|
|
|
if (ret) {
|
2017-09-13 21:50:06 +00:00
|
|
|
parse_events_print_error(&parse_error, extra_events.buf);
|
2017-08-31 19:40:31 +00:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
strbuf_release(&extra_events);
|
|
|
|
ret = metricgroup__setup_events(&group_list, perf_evlist,
|
|
|
|
metric_events);
|
|
|
|
out:
|
|
|
|
metricgroup__free_egroups(&group_list);
|
|
|
|
return ret;
|
|
|
|
}
|
2018-06-26 07:17:01 +00:00
|
|
|
|
|
|
|
bool metricgroup__has_metric(const char *metric)
|
|
|
|
{
|
|
|
|
struct pmu_events_map *map = perf_pmu__find_map(NULL);
|
|
|
|
struct pmu_event *pe;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (!map)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
for (i = 0; ; i++) {
|
|
|
|
pe = &map->table[i];
|
|
|
|
|
|
|
|
if (!pe->name && !pe->metric_group && !pe->metric_name)
|
|
|
|
break;
|
|
|
|
if (!pe->metric_expr)
|
|
|
|
continue;
|
|
|
|
if (match_metric(pe->metric_name, metric))
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|