alistair23-linux/tools/perf/util/metricgroup.c

810 lines
19 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
/*
* Copyright (c) 2017, Intel Corporation.
*/
/* Manage metrics and groups of metrics from JSON files */
#include "metricgroup.h"
#include "debug.h"
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
#include "evlist.h"
#include "evsel.h"
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
#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>
#include <linux/ctype.h>
#include <linux/string.h>
#include <linux/zalloc.h>
#include <subcmd/parse-options.h>
#include <api/fs/fs.h>
#include "util.h"
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
struct metric_event *metricgroup__lookup(struct rblist *metric_events,
struct evsel *evsel,
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
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 14:43:00 -07:00
if (!metric_events)
return NULL;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
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 metric_event_delete(struct rblist *rblist __maybe_unused,
struct rb_node *rb_node)
{
struct metric_event *me = container_of(rb_node, struct metric_event, nd);
struct metric_expr *expr, *tmp;
list_for_each_entry_safe(expr, tmp, &me->head, nd) {
free(expr);
}
free(me);
}
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
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;
metric_events->node_delete = metric_event_delete;
}
void metricgroup__rblist_exit(struct rblist *metric_events)
{
rblist__exit(metric_events);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
}
struct egroup {
struct list_head nd;
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
struct expr_parse_ctx pctx;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
const char *metric_name;
const char *metric_expr;
const char *metric_unit;
perf metricgroups: Enhance JSON/metric infrastructure to handle "?" Patch enhances current metric infrastructure to handle "?" in the metric expression. The "?" can be use for parameters whose value not known while creating metric events and which can be replace later at runtime to the proper value. It also add flexibility to create multiple events out of single metric event added in JSON file. Patch adds function 'arch_get_runtimeparam' which is a arch specific function, returns the count of metric events need to be created. By default it return 1. This infrastructure needed for hv_24x7 socket/chip level events. "hv_24x7" chip level events needs specific chip-id to which the data is requested. Function 'arch_get_runtimeparam' implemented in header.c which extract number of sockets from sysfs file "sockets" under "/sys/devices/hv_24x7/interface/". With this patch basically we are trying to create as many metric events as define by runtime_param. For that one loop is added in function 'metricgroup__add_metric', which create multiple events at run time depend on return value of 'arch_get_runtimeparam' and merge that event in 'group_list'. To achieve that we are actually passing this parameter value as part of `expr__find_other` function and changing "?" present in metric expression with this value. As in our JSON file, there gonna be single metric event, and out of which we are creating multiple events. To understand which data count belongs to which parameter value, we also printing param value in generic_metric function. For example, command:# ./perf stat -M PowerBUS_Frequency -C 0 -I 1000 1.000101867 9,356,933 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 1.000101867 9,366,134 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 2.000314878 9,365,868 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 2.000314878 9,366,092 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 So, here _0 and _1 after PowerBUS_Frequency specify parameter value. Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@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: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Joe Mario <jmario@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lore.kernel.org/lkml/20200401203340.31402-5-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-04-01 14:33:37 -06:00
int runtime;
bool has_constraint;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
};
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
/**
* Find a group of events in perf_evlist that correpond to those from a parsed
* metric expression. Note, as find_evsel_group is called in the same order as
* perf_evlist was constructed, metric_no_merge doesn't need to test for
* underfilling a group.
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
* @perf_evlist: a list of events something like: {metric1 leader, metric1
* sibling, metric1 sibling}:W,duration_time,{metric2 leader, metric2 sibling,
* metric2 sibling}:W,duration_time
* @pctx: the parse context for the metric expression.
* @metric_no_merge: don't attempt to share events for the metric with other
* metrics.
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
* @has_constraint: is there a contraint on the group of events? In which case
* the events won't be grouped.
* @metric_events: out argument, null terminated array of evsel's associated
* with the metric.
* @evlist_used: in/out argument, bitmap tracking which evlist events are used.
* @return the first metric event or NULL on failure.
*/
static struct evsel *find_evsel_group(struct evlist *perf_evlist,
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
struct expr_parse_ctx *pctx,
bool metric_no_merge,
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
bool has_constraint,
perf metricgroup: Fix printing event names of metric group with multiple events incase of overlapping 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 incase we try to run multiple metric groups with overlapping event. With current upstream version, incase of overlapping metric events issue is, we always start our comparision logic from start. So, the events which already matched with some metric group also take part in comparision logic. Because of that when we have overlapping events, we end up matching current metric group event with already matched one. For example, in skylake machine we have metric event CoreIPC and Instructions. Both of them need 'inst_retired.any' event value. As events in Instructions is subset of events in CoreIPC, they endup in pointing to same 'inst_retired.any' value. In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 1,254,992,790 inst_retired.any # 1254992790.0 Instructions # 1.3 CoreIPC 977,172,805 cycles 1,254,992,756 inst_retired.any 1.000802596 seconds time elapsed command:# sudo ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 948,650 uops_retired.retire_slots 866,182 inst_retired.any # 0.7 IPC 866,182 inst_retired.any 1,175,671 cpu_clk_unhalted.thread Patch fixes the issue by adding a new bool pointer 'evlist_used' to keep track of events which already matched with some group by setting it true. So, we skip all used events in list when we start comparision logic. Patch also make some changes in comparision logic, incase we get a match miss, we discard the whole match and start again with first event id in metric event. With this patch: In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 3,348,415 inst_retired.any # 0.3 CoreIPC 11,779,026 cycles 3,348,381 inst_retired.any # 3348381.0 Instructions 1.001649056 seconds time elapsed command:# ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 1,023,148 uops_retired.retire_slots # 1.1 UPI 924,976 inst_retired.any 924,976 inst_retired.any # 0.6 IPC 1,489,414 cpu_clk_unhalted.thread 1.003064672 seconds time elapsed Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> 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: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Link: http://lore.kernel.org/lkml/20200221101121.28920-1-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-21 03:11:21 -07:00
struct evsel **metric_events,
unsigned long *evlist_used)
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
{
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
struct evsel *ev, *current_leader = NULL;
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
double *val_ptr;
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
int i = 0, matched_events = 0, events_to_match;
const int idnum = (int)hashmap__size(&pctx->ids);
/* duration_time is grouped separately. */
if (!has_constraint &&
hashmap__find(&pctx->ids, "duration_time", (void **)&val_ptr))
events_to_match = idnum - 1;
else
events_to_match = idnum;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
evlist__for_each_entry (perf_evlist, ev) {
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
/*
* Events with a constraint aren't grouped and match the first
* events available.
*/
if (has_constraint && ev->weak_group)
perf metricgroup: Fix printing event names of metric group with multiple events incase of overlapping 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 incase we try to run multiple metric groups with overlapping event. With current upstream version, incase of overlapping metric events issue is, we always start our comparision logic from start. So, the events which already matched with some metric group also take part in comparision logic. Because of that when we have overlapping events, we end up matching current metric group event with already matched one. For example, in skylake machine we have metric event CoreIPC and Instructions. Both of them need 'inst_retired.any' event value. As events in Instructions is subset of events in CoreIPC, they endup in pointing to same 'inst_retired.any' value. In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 1,254,992,790 inst_retired.any # 1254992790.0 Instructions # 1.3 CoreIPC 977,172,805 cycles 1,254,992,756 inst_retired.any 1.000802596 seconds time elapsed command:# sudo ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 948,650 uops_retired.retire_slots 866,182 inst_retired.any # 0.7 IPC 866,182 inst_retired.any 1,175,671 cpu_clk_unhalted.thread Patch fixes the issue by adding a new bool pointer 'evlist_used' to keep track of events which already matched with some group by setting it true. So, we skip all used events in list when we start comparision logic. Patch also make some changes in comparision logic, incase we get a match miss, we discard the whole match and start again with first event id in metric event. With this patch: In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 3,348,415 inst_retired.any # 0.3 CoreIPC 11,779,026 cycles 3,348,381 inst_retired.any # 3348381.0 Instructions 1.001649056 seconds time elapsed command:# ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 1,023,148 uops_retired.retire_slots # 1.1 UPI 924,976 inst_retired.any 924,976 inst_retired.any # 0.6 IPC 1,489,414 cpu_clk_unhalted.thread 1.003064672 seconds time elapsed Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> 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: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Link: http://lore.kernel.org/lkml/20200221101121.28920-1-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-21 03:11:21 -07:00
continue;
/* Ignore event if already used and merging is disabled. */
if (metric_no_merge && test_bit(ev->idx, evlist_used))
continue;
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
if (!has_constraint && ev->leader != current_leader) {
/*
* Start of a new group, discard the whole match and
* start again.
*/
matched_events = 0;
perf metricgroup: Fix printing event names of metric group with multiple events incase of overlapping 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 incase we try to run multiple metric groups with overlapping event. With current upstream version, incase of overlapping metric events issue is, we always start our comparision logic from start. So, the events which already matched with some metric group also take part in comparision logic. Because of that when we have overlapping events, we end up matching current metric group event with already matched one. For example, in skylake machine we have metric event CoreIPC and Instructions. Both of them need 'inst_retired.any' event value. As events in Instructions is subset of events in CoreIPC, they endup in pointing to same 'inst_retired.any' value. In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 1,254,992,790 inst_retired.any # 1254992790.0 Instructions # 1.3 CoreIPC 977,172,805 cycles 1,254,992,756 inst_retired.any 1.000802596 seconds time elapsed command:# sudo ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 948,650 uops_retired.retire_slots 866,182 inst_retired.any # 0.7 IPC 866,182 inst_retired.any 1,175,671 cpu_clk_unhalted.thread Patch fixes the issue by adding a new bool pointer 'evlist_used' to keep track of events which already matched with some group by setting it true. So, we skip all used events in list when we start comparision logic. Patch also make some changes in comparision logic, incase we get a match miss, we discard the whole match and start again with first event id in metric event. With this patch: In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 3,348,415 inst_retired.any # 0.3 CoreIPC 11,779,026 cycles 3,348,381 inst_retired.any # 3348381.0 Instructions 1.001649056 seconds time elapsed command:# ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 1,023,148 uops_retired.retire_slots # 1.1 UPI 924,976 inst_retired.any 924,976 inst_retired.any # 0.6 IPC 1,489,414 cpu_clk_unhalted.thread 1.003064672 seconds time elapsed Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> 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: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Link: http://lore.kernel.org/lkml/20200221101121.28920-1-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-21 03:11:21 -07:00
memset(metric_events, 0,
sizeof(struct evsel *) * idnum);
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
current_leader = ev->leader;
}
if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr)) {
if (has_constraint) {
/*
* Events aren't grouped, ensure the same event
* isn't matched from two groups.
*/
for (i = 0; i < matched_events; i++) {
if (!strcmp(ev->name,
metric_events[i]->name)) {
break;
}
}
if (i != matched_events)
continue;
}
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
metric_events[matched_events++] = ev;
}
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
if (matched_events == events_to_match)
break;
}
if (events_to_match != idnum) {
/* Add the first duration_time. */
evlist__for_each_entry(perf_evlist, ev) {
if (!strcmp(ev->name, "duration_time")) {
metric_events[matched_events++] = ev;
break;
}
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
}
}
perf metricgroup: Support multiple events for metricgroup Some uncore metrics don't work as expected. For example, on cascadelakex: root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_BANDWIDTH.TOTAL -a -- sleep 1 Performance counter stats for 'system wide': 1841092 unc_m_pmm_rpq_inserts 3680816 unc_m_pmm_wpq_inserts 1.001775055 seconds time elapsed root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_READ_LATENCY -a -- sleep 1 Performance counter stats for 'system wide': 860649746 unc_m_pmm_rpq_occupancy.all 1840557 unc_m_pmm_rpq_inserts 12790627455 unc_m_clockticks 1.001773348 seconds time elapsed No metrics 'UNC_M_PMM_BANDWIDTH.TOTAL' or 'UNC_M_PMM_READ_LATENCY' are reported. The issue is, the case of an alias expanding to mulitple events is not supported, typically the uncore events. (see comments in find_evsel_group()). For UNC_M_PMM_BANDWIDTH.TOTAL in above example, the expanded event group is '{unc_m_pmm_rpq_inserts,unc_m_pmm_wpq_inserts}:W', but the actual events passed to find_evsel_group are: unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts For this multiple events case, it's not supported well. This patch introduces a new field 'metric_leader' in struct evsel. The first event is considered as a metric leader. For the rest of same events, they point to the first event via it's metric_leader field in struct evsel. This design is for adding the counting results of all same events to the first event in group (the metric_leader). With this patch, root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_BANDWIDTH.TOTAL -a -- sleep 1 Performance counter stats for 'system wide': 1842108 unc_m_pmm_rpq_inserts # 337.2 MB/sec UNC_M_PMM_BANDWIDTH.TOTAL 3682209 unc_m_pmm_wpq_inserts 1.001819706 seconds time elapsed root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_READ_LATENCY -a -- sleep 1 Performance counter stats for 'system wide': 861970685 unc_m_pmm_rpq_occupancy.all # 219.4 ns UNC_M_PMM_READ_LATENCY 1842772 unc_m_pmm_rpq_inserts 12790196356 unc_m_clockticks 1.001749103 seconds time elapsed Now we can see the correct metrics 'UNC_M_PMM_BANDWIDTH.TOTAL' and '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/20190828055932.8269-5-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-27 23:59:32 -06:00
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
if (matched_events != idnum) {
perf metricgroup: Support multiple events for metricgroup Some uncore metrics don't work as expected. For example, on cascadelakex: root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_BANDWIDTH.TOTAL -a -- sleep 1 Performance counter stats for 'system wide': 1841092 unc_m_pmm_rpq_inserts 3680816 unc_m_pmm_wpq_inserts 1.001775055 seconds time elapsed root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_READ_LATENCY -a -- sleep 1 Performance counter stats for 'system wide': 860649746 unc_m_pmm_rpq_occupancy.all 1840557 unc_m_pmm_rpq_inserts 12790627455 unc_m_clockticks 1.001773348 seconds time elapsed No metrics 'UNC_M_PMM_BANDWIDTH.TOTAL' or 'UNC_M_PMM_READ_LATENCY' are reported. The issue is, the case of an alias expanding to mulitple events is not supported, typically the uncore events. (see comments in find_evsel_group()). For UNC_M_PMM_BANDWIDTH.TOTAL in above example, the expanded event group is '{unc_m_pmm_rpq_inserts,unc_m_pmm_wpq_inserts}:W', but the actual events passed to find_evsel_group are: unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts For this multiple events case, it's not supported well. This patch introduces a new field 'metric_leader' in struct evsel. The first event is considered as a metric leader. For the rest of same events, they point to the first event via it's metric_leader field in struct evsel. This design is for adding the counting results of all same events to the first event in group (the metric_leader). With this patch, root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_BANDWIDTH.TOTAL -a -- sleep 1 Performance counter stats for 'system wide': 1842108 unc_m_pmm_rpq_inserts # 337.2 MB/sec UNC_M_PMM_BANDWIDTH.TOTAL 3682209 unc_m_pmm_wpq_inserts 1.001819706 seconds time elapsed root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_READ_LATENCY -a -- sleep 1 Performance counter stats for 'system wide': 861970685 unc_m_pmm_rpq_occupancy.all # 219.4 ns UNC_M_PMM_READ_LATENCY 1842772 unc_m_pmm_rpq_inserts 12790196356 unc_m_clockticks 1.001749103 seconds time elapsed Now we can see the correct metrics 'UNC_M_PMM_BANDWIDTH.TOTAL' and '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/20190828055932.8269-5-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-27 23:59:32 -06:00
/* Not whole match */
return NULL;
}
metric_events[idnum] = NULL;
for (i = 0; i < idnum; i++) {
perf metricgroup: Fix printing event names of metric group with multiple events incase of overlapping 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 incase we try to run multiple metric groups with overlapping event. With current upstream version, incase of overlapping metric events issue is, we always start our comparision logic from start. So, the events which already matched with some metric group also take part in comparision logic. Because of that when we have overlapping events, we end up matching current metric group event with already matched one. For example, in skylake machine we have metric event CoreIPC and Instructions. Both of them need 'inst_retired.any' event value. As events in Instructions is subset of events in CoreIPC, they endup in pointing to same 'inst_retired.any' value. In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 1,254,992,790 inst_retired.any # 1254992790.0 Instructions # 1.3 CoreIPC 977,172,805 cycles 1,254,992,756 inst_retired.any 1.000802596 seconds time elapsed command:# sudo ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 948,650 uops_retired.retire_slots 866,182 inst_retired.any # 0.7 IPC 866,182 inst_retired.any 1,175,671 cpu_clk_unhalted.thread Patch fixes the issue by adding a new bool pointer 'evlist_used' to keep track of events which already matched with some group by setting it true. So, we skip all used events in list when we start comparision logic. Patch also make some changes in comparision logic, incase we get a match miss, we discard the whole match and start again with first event id in metric event. With this patch: In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 3,348,415 inst_retired.any # 0.3 CoreIPC 11,779,026 cycles 3,348,381 inst_retired.any # 3348381.0 Instructions 1.001649056 seconds time elapsed command:# ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 1,023,148 uops_retired.retire_slots # 1.1 UPI 924,976 inst_retired.any 924,976 inst_retired.any # 0.6 IPC 1,489,414 cpu_clk_unhalted.thread 1.003064672 seconds time elapsed Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> 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: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Link: http://lore.kernel.org/lkml/20200221101121.28920-1-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-21 03:11:21 -07:00
ev = metric_events[i];
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
ev->metric_leader = ev;
set_bit(ev->idx, evlist_used);
perf metricgroup: Support multiple events for metricgroup Some uncore metrics don't work as expected. For example, on cascadelakex: root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_BANDWIDTH.TOTAL -a -- sleep 1 Performance counter stats for 'system wide': 1841092 unc_m_pmm_rpq_inserts 3680816 unc_m_pmm_wpq_inserts 1.001775055 seconds time elapsed root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_READ_LATENCY -a -- sleep 1 Performance counter stats for 'system wide': 860649746 unc_m_pmm_rpq_occupancy.all 1840557 unc_m_pmm_rpq_inserts 12790627455 unc_m_clockticks 1.001773348 seconds time elapsed No metrics 'UNC_M_PMM_BANDWIDTH.TOTAL' or 'UNC_M_PMM_READ_LATENCY' are reported. The issue is, the case of an alias expanding to mulitple events is not supported, typically the uncore events. (see comments in find_evsel_group()). For UNC_M_PMM_BANDWIDTH.TOTAL in above example, the expanded event group is '{unc_m_pmm_rpq_inserts,unc_m_pmm_wpq_inserts}:W', but the actual events passed to find_evsel_group are: unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_rpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts unc_m_pmm_wpq_inserts For this multiple events case, it's not supported well. This patch introduces a new field 'metric_leader' in struct evsel. The first event is considered as a metric leader. For the rest of same events, they point to the first event via it's metric_leader field in struct evsel. This design is for adding the counting results of all same events to the first event in group (the metric_leader). With this patch, root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_BANDWIDTH.TOTAL -a -- sleep 1 Performance counter stats for 'system wide': 1842108 unc_m_pmm_rpq_inserts # 337.2 MB/sec UNC_M_PMM_BANDWIDTH.TOTAL 3682209 unc_m_pmm_wpq_inserts 1.001819706 seconds time elapsed root@lkp-csl-2sp2:~# perf stat -M UNC_M_PMM_READ_LATENCY -a -- sleep 1 Performance counter stats for 'system wide': 861970685 unc_m_pmm_rpq_occupancy.all # 219.4 ns UNC_M_PMM_READ_LATENCY 1842772 unc_m_pmm_rpq_inserts 12790196356 unc_m_clockticks 1.001749103 seconds time elapsed Now we can see the correct metrics 'UNC_M_PMM_BANDWIDTH.TOTAL' and '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/20190828055932.8269-5-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-27 23:59:32 -06:00
}
return metric_events[0];
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
}
static int metricgroup__setup_events(struct list_head *groups,
bool metric_no_merge,
struct evlist *perf_evlist,
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
struct rblist *metric_events_list)
{
struct metric_event *me;
struct metric_expr *expr;
int i = 0;
int ret = 0;
struct egroup *eg;
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
struct evsel *evsel, *tmp;
unsigned long *evlist_used;
perf metricgroup: Fix printing event names of metric group with multiple events incase of overlapping 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 incase we try to run multiple metric groups with overlapping event. With current upstream version, incase of overlapping metric events issue is, we always start our comparision logic from start. So, the events which already matched with some metric group also take part in comparision logic. Because of that when we have overlapping events, we end up matching current metric group event with already matched one. For example, in skylake machine we have metric event CoreIPC and Instructions. Both of them need 'inst_retired.any' event value. As events in Instructions is subset of events in CoreIPC, they endup in pointing to same 'inst_retired.any' value. In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 1,254,992,790 inst_retired.any # 1254992790.0 Instructions # 1.3 CoreIPC 977,172,805 cycles 1,254,992,756 inst_retired.any 1.000802596 seconds time elapsed command:# sudo ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 948,650 uops_retired.retire_slots 866,182 inst_retired.any # 0.7 IPC 866,182 inst_retired.any 1,175,671 cpu_clk_unhalted.thread Patch fixes the issue by adding a new bool pointer 'evlist_used' to keep track of events which already matched with some group by setting it true. So, we skip all used events in list when we start comparision logic. Patch also make some changes in comparision logic, incase we get a match miss, we discard the whole match and start again with first event id in metric event. With this patch: In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 3,348,415 inst_retired.any # 0.3 CoreIPC 11,779,026 cycles 3,348,381 inst_retired.any # 3348381.0 Instructions 1.001649056 seconds time elapsed command:# ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 1,023,148 uops_retired.retire_slots # 1.1 UPI 924,976 inst_retired.any 924,976 inst_retired.any # 0.6 IPC 1,489,414 cpu_clk_unhalted.thread 1.003064672 seconds time elapsed Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> 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: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Link: http://lore.kernel.org/lkml/20200221101121.28920-1-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-21 03:11:21 -07:00
evlist_used = bitmap_alloc(perf_evlist->core.nr_entries);
if (!evlist_used)
return -ENOMEM;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
list_for_each_entry (eg, groups, nd) {
struct evsel **metric_events;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
metric_events = calloc(sizeof(void *),
hashmap__size(&eg->pctx.ids) + 1);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
if (!metric_events) {
ret = -ENOMEM;
break;
}
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
evsel = find_evsel_group(perf_evlist, &eg->pctx,
metric_no_merge,
eg->has_constraint, metric_events,
evlist_used);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
if (!evsel) {
pr_debug("Cannot resolve %s: %s\n",
eg->metric_name, eg->metric_expr);
free(metric_events);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
continue;
}
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
for (i = 0; metric_events[i]; i++)
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
metric_events[i]->collect_stat = true;
me = metricgroup__lookup(metric_events_list, evsel, true);
if (!me) {
ret = -ENOMEM;
free(metric_events);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
break;
}
expr = malloc(sizeof(struct metric_expr));
if (!expr) {
ret = -ENOMEM;
free(metric_events);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
break;
}
expr->metric_expr = eg->metric_expr;
expr->metric_name = eg->metric_name;
expr->metric_unit = eg->metric_unit;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
expr->metric_events = metric_events;
perf metricgroups: Enhance JSON/metric infrastructure to handle "?" Patch enhances current metric infrastructure to handle "?" in the metric expression. The "?" can be use for parameters whose value not known while creating metric events and which can be replace later at runtime to the proper value. It also add flexibility to create multiple events out of single metric event added in JSON file. Patch adds function 'arch_get_runtimeparam' which is a arch specific function, returns the count of metric events need to be created. By default it return 1. This infrastructure needed for hv_24x7 socket/chip level events. "hv_24x7" chip level events needs specific chip-id to which the data is requested. Function 'arch_get_runtimeparam' implemented in header.c which extract number of sockets from sysfs file "sockets" under "/sys/devices/hv_24x7/interface/". With this patch basically we are trying to create as many metric events as define by runtime_param. For that one loop is added in function 'metricgroup__add_metric', which create multiple events at run time depend on return value of 'arch_get_runtimeparam' and merge that event in 'group_list'. To achieve that we are actually passing this parameter value as part of `expr__find_other` function and changing "?" present in metric expression with this value. As in our JSON file, there gonna be single metric event, and out of which we are creating multiple events. To understand which data count belongs to which parameter value, we also printing param value in generic_metric function. For example, command:# ./perf stat -M PowerBUS_Frequency -C 0 -I 1000 1.000101867 9,356,933 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 1.000101867 9,366,134 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 2.000314878 9,365,868 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 2.000314878 9,366,092 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 So, here _0 and _1 after PowerBUS_Frequency specify parameter value. Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@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: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Joe Mario <jmario@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lore.kernel.org/lkml/20200401203340.31402-5-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-04-01 14:33:37 -06:00
expr->runtime = eg->runtime;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
list_add(&expr->nd, &me->head);
}
perf metricgroup: Fix printing event names of metric group with multiple events incase of overlapping 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 incase we try to run multiple metric groups with overlapping event. With current upstream version, incase of overlapping metric events issue is, we always start our comparision logic from start. So, the events which already matched with some metric group also take part in comparision logic. Because of that when we have overlapping events, we end up matching current metric group event with already matched one. For example, in skylake machine we have metric event CoreIPC and Instructions. Both of them need 'inst_retired.any' event value. As events in Instructions is subset of events in CoreIPC, they endup in pointing to same 'inst_retired.any' value. In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 1,254,992,790 inst_retired.any # 1254992790.0 Instructions # 1.3 CoreIPC 977,172,805 cycles 1,254,992,756 inst_retired.any 1.000802596 seconds time elapsed command:# sudo ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 948,650 uops_retired.retire_slots 866,182 inst_retired.any # 0.7 IPC 866,182 inst_retired.any 1,175,671 cpu_clk_unhalted.thread Patch fixes the issue by adding a new bool pointer 'evlist_used' to keep track of events which already matched with some group by setting it true. So, we skip all used events in list when we start comparision logic. Patch also make some changes in comparision logic, incase we get a match miss, we discard the whole match and start again with first event id in metric event. With this patch: In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 3,348,415 inst_retired.any # 0.3 CoreIPC 11,779,026 cycles 3,348,381 inst_retired.any # 3348381.0 Instructions 1.001649056 seconds time elapsed command:# ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 1,023,148 uops_retired.retire_slots # 1.1 UPI 924,976 inst_retired.any 924,976 inst_retired.any # 0.6 IPC 1,489,414 cpu_clk_unhalted.thread 1.003064672 seconds time elapsed Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> 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: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Link: http://lore.kernel.org/lkml/20200221101121.28920-1-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-21 03:11:21 -07:00
perf metricgroup: Remove duped metric group events A metric group contains multiple metrics. These metrics may use the same events. If metrics use separate events then it leads to more multiplexing and overall metric counts fail to sum to 100%. Modify how metrics are associated with events so that if the events in an earlier group satisfy the current metric, the same events are used. A record of used events is kept and at the end of processing unnecessary events are eliminated. Before: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 920,211,343 uops_issued.any # 0.5 Backend_Bound (16.56%) 1,977,733,128 idq_uops_not_delivered.core (16.56%) 51,668,510 int_misc.recovery_cycles (16.56%) 732,305,692 uops_retired.retire_slots (16.56%) 1,497,621,849 cycles (16.56%) 721,098,274 uops_issued.any # 0.1 Bad_Speculation (16.79%) 1,332,681,791 cycles (16.79%) 552,475,482 uops_retired.retire_slots (16.79%) 47,708,340 int_misc.recovery_cycles (16.79%) 1,383,713,292 cycles # 0.4 Frontend_Bound (16.76%) 2,013,757,701 idq_uops_not_delivered.core (16.76%) 1,373,363,790 cycles # 0.1 Retiring (33.54%) 577,302,589 uops_retired.retire_slots (33.54%) 392,766,987 inst_retired.any # 0.3 IPC (50.24%) 1,351,873,350 cpu_clk_unhalted.thread (50.24%) 1,332,510,318 cycles # 5330041272.0 SLOTS (49.90%) 1.006336145 seconds time elapsed After: $ perf stat -a -M TopDownL1 sleep 1 Performance counter stats for 'system wide': 765,949,145 uops_issued.any # 0.1 Bad_Speculation # 0.5 Backend_Bound (50.09%) 1,883,830,591 idq_uops_not_delivered.core # 0.3 Frontend_Bound (50.09%) 48,237,080 int_misc.recovery_cycles (50.09%) 581,798,385 uops_retired.retire_slots # 0.1 Retiring (50.09%) 1,361,628,527 cycles # 5446514108.0 SLOTS (50.09%) 391,415,714 inst_retired.any # 0.3 IPC (49.91%) 1,336,486,781 cpu_clk_unhalted.thread (49.91%) 1.005469298 seconds time elapsed Note: Bad_Speculation + Backend_Bound + Frontend_Bound + Retiring = 100% after, where as before it is 110%. After there are 2 groups, whereas before there are 6. After the cycles event appears once, before it appeared 5 times. Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200520182011.32236-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-20 12:20:09 -06:00
evlist__for_each_entry_safe(perf_evlist, tmp, evsel) {
if (!test_bit(evsel->idx, evlist_used)) {
evlist__remove(perf_evlist, evsel);
evsel__delete(evsel);
}
}
bitmap_free(evlist_used);
perf metricgroup: Fix printing event names of metric group with multiple events incase of overlapping 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 incase we try to run multiple metric groups with overlapping event. With current upstream version, incase of overlapping metric events issue is, we always start our comparision logic from start. So, the events which already matched with some metric group also take part in comparision logic. Because of that when we have overlapping events, we end up matching current metric group event with already matched one. For example, in skylake machine we have metric event CoreIPC and Instructions. Both of them need 'inst_retired.any' event value. As events in Instructions is subset of events in CoreIPC, they endup in pointing to same 'inst_retired.any' value. In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 1,254,992,790 inst_retired.any # 1254992790.0 Instructions # 1.3 CoreIPC 977,172,805 cycles 1,254,992,756 inst_retired.any 1.000802596 seconds time elapsed command:# sudo ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 948,650 uops_retired.retire_slots 866,182 inst_retired.any # 0.7 IPC 866,182 inst_retired.any 1,175,671 cpu_clk_unhalted.thread Patch fixes the issue by adding a new bool pointer 'evlist_used' to keep track of events which already matched with some group by setting it true. So, we skip all used events in list when we start comparision logic. Patch also make some changes in comparision logic, incase we get a match miss, we discard the whole match and start again with first event id in metric event. With this patch: In skylake platform: command:# ./perf stat -M CoreIPC,Instructions -C 0 sleep 1 Performance counter stats for 'CPU(s) 0': 3,348,415 inst_retired.any # 0.3 CoreIPC 11,779,026 cycles 3,348,381 inst_retired.any # 3348381.0 Instructions 1.001649056 seconds time elapsed command:# ./perf stat -M UPI,IPC sleep 1 Performance counter stats for 'sleep 1': 1,023,148 uops_retired.retire_slots # 1.1 UPI 924,976 inst_retired.any 924,976 inst_retired.any # 0.6 IPC 1,489,414 cpu_clk_unhalted.thread 1.003064672 seconds time elapsed Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> 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: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Link: http://lore.kernel.org/lkml/20200221101121.28920-1-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-21 03:11:21 -07:00
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
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;
}
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:
zfree(&me->name);
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);
zfree(&me->name);
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,
bool raw, bool details)
{
struct pmu_events_map *map = perf_pmu__find_map(NULL);
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;
g = skip_spaces(g);
if (*g == 0)
g = "No_group";
if (filter && !strstr(g, filter))
continue;
if (raw)
s = (char *)pe->metric_name;
else {
if (asprintf(&s, "%s\n%*s%s]",
pe->metric_name, 8, "[", pe->desc) < 0)
return;
if (details) {
if (asprintf(&s, "%s\n%*s%s]",
s, 8, "[", pe->metric_expr) < 0)
return;
}
}
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");
for (node = rb_first_cached(&groups.entries); node; node = next) {
struct mep *me = container_of(node, struct mep, nd);
if (metricgroups)
printf("%s%s%s", me->name, metrics && !raw ? ":" : "", raw ? " " : "\n");
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);
}
static void metricgroup__add_metric_weak_group(struct strbuf *events,
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
struct expr_parse_ctx *ctx)
{
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
struct hashmap_entry *cur;
size_t bkt;
bool no_group = true, has_duration = false;
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
hashmap__for_each_entry((&ctx->ids), cur, bkt) {
pr_debug("found event %s\n", (const char *)cur->key);
/*
* Duration time maps to a software event and can make
* groups not count. Always use it outside a
* group.
*/
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
if (!strcmp(cur->key, "duration_time")) {
has_duration = true;
continue;
}
strbuf_addf(events, "%s%s",
no_group ? "{" : ",",
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
(const char *)cur->key);
no_group = false;
}
if (!no_group) {
strbuf_addf(events, "}:W");
if (has_duration)
strbuf_addf(events, ",duration_time");
} else if (has_duration)
strbuf_addf(events, "duration_time");
}
static void metricgroup__add_metric_non_group(struct strbuf *events,
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
struct expr_parse_ctx *ctx)
{
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
struct hashmap_entry *cur;
size_t bkt;
bool first = true;
hashmap__for_each_entry((&ctx->ids), cur, bkt) {
if (!first)
strbuf_addf(events, ",");
strbuf_addf(events, "%s", (const char *)cur->key);
first = false;
}
}
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;
}
perf metricgroups: Enhance JSON/metric infrastructure to handle "?" Patch enhances current metric infrastructure to handle "?" in the metric expression. The "?" can be use for parameters whose value not known while creating metric events and which can be replace later at runtime to the proper value. It also add flexibility to create multiple events out of single metric event added in JSON file. Patch adds function 'arch_get_runtimeparam' which is a arch specific function, returns the count of metric events need to be created. By default it return 1. This infrastructure needed for hv_24x7 socket/chip level events. "hv_24x7" chip level events needs specific chip-id to which the data is requested. Function 'arch_get_runtimeparam' implemented in header.c which extract number of sockets from sysfs file "sockets" under "/sys/devices/hv_24x7/interface/". With this patch basically we are trying to create as many metric events as define by runtime_param. For that one loop is added in function 'metricgroup__add_metric', which create multiple events at run time depend on return value of 'arch_get_runtimeparam' and merge that event in 'group_list'. To achieve that we are actually passing this parameter value as part of `expr__find_other` function and changing "?" present in metric expression with this value. As in our JSON file, there gonna be single metric event, and out of which we are creating multiple events. To understand which data count belongs to which parameter value, we also printing param value in generic_metric function. For example, command:# ./perf stat -M PowerBUS_Frequency -C 0 -I 1000 1.000101867 9,356,933 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 1.000101867 9,366,134 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 2.000314878 9,365,868 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 2.000314878 9,366,092 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 So, here _0 and _1 after PowerBUS_Frequency specify parameter value. Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@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: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Joe Mario <jmario@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lore.kernel.org/lkml/20200401203340.31402-5-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-04-01 14:33:37 -06:00
int __weak arch_get_runtimeparam(void)
{
return 1;
}
static int __metricgroup__add_metric(struct list_head *group_list,
struct pmu_event *pe,
bool metric_no_group,
int runtime)
{
struct egroup *eg;
eg = malloc(sizeof(*eg));
if (!eg)
return -ENOMEM;
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
expr__ctx_init(&eg->pctx);
eg->metric_name = pe->metric_name;
eg->metric_expr = pe->metric_expr;
eg->metric_unit = pe->unit;
perf metricgroups: Enhance JSON/metric infrastructure to handle "?" Patch enhances current metric infrastructure to handle "?" in the metric expression. The "?" can be use for parameters whose value not known while creating metric events and which can be replace later at runtime to the proper value. It also add flexibility to create multiple events out of single metric event added in JSON file. Patch adds function 'arch_get_runtimeparam' which is a arch specific function, returns the count of metric events need to be created. By default it return 1. This infrastructure needed for hv_24x7 socket/chip level events. "hv_24x7" chip level events needs specific chip-id to which the data is requested. Function 'arch_get_runtimeparam' implemented in header.c which extract number of sockets from sysfs file "sockets" under "/sys/devices/hv_24x7/interface/". With this patch basically we are trying to create as many metric events as define by runtime_param. For that one loop is added in function 'metricgroup__add_metric', which create multiple events at run time depend on return value of 'arch_get_runtimeparam' and merge that event in 'group_list'. To achieve that we are actually passing this parameter value as part of `expr__find_other` function and changing "?" present in metric expression with this value. As in our JSON file, there gonna be single metric event, and out of which we are creating multiple events. To understand which data count belongs to which parameter value, we also printing param value in generic_metric function. For example, command:# ./perf stat -M PowerBUS_Frequency -C 0 -I 1000 1.000101867 9,356,933 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 1.000101867 9,366,134 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 2.000314878 9,365,868 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 2.000314878 9,366,092 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 So, here _0 and _1 after PowerBUS_Frequency specify parameter value. Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@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: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Joe Mario <jmario@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lore.kernel.org/lkml/20200401203340.31402-5-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-04-01 14:33:37 -06:00
eg->runtime = runtime;
eg->has_constraint = metric_no_group || metricgroup__has_constraint(pe);
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
if (expr__find_other(pe->metric_expr, NULL, &eg->pctx, runtime) < 0) {
expr__ctx_clear(&eg->pctx);
free(eg);
return -EINVAL;
}
if (list_empty(group_list))
list_add(&eg->nd, group_list);
else {
struct list_head *pos;
/* Place the largest groups at the front. */
list_for_each_prev(pos, group_list) {
struct egroup *old = list_entry(pos, struct egroup, nd);
if (hashmap__size(&eg->pctx.ids) <=
hashmap__size(&old->pctx.ids))
break;
}
list_add(&eg->nd, pos);
}
return 0;
}
static int metricgroup__add_metric(const char *metric, bool metric_no_group,
struct strbuf *events,
struct list_head *group_list,
struct pmu_events_map *map)
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
{
struct pmu_event *pe;
struct egroup *eg;
int i, ret;
bool has_match = false;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
for (i = 0; ; i++) {
pe = &map->table[i];
if (!pe->name && !pe->metric_group && !pe->metric_name) {
/* End of pmu events. */
if (!has_match)
return -EINVAL;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
break;
}
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
if (!pe->metric_expr)
continue;
if (match_metric(pe->metric_group, metric) ||
match_metric(pe->metric_name, metric)) {
has_match = true;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
perf metricgroups: Enhance JSON/metric infrastructure to handle "?" Patch enhances current metric infrastructure to handle "?" in the metric expression. The "?" can be use for parameters whose value not known while creating metric events and which can be replace later at runtime to the proper value. It also add flexibility to create multiple events out of single metric event added in JSON file. Patch adds function 'arch_get_runtimeparam' which is a arch specific function, returns the count of metric events need to be created. By default it return 1. This infrastructure needed for hv_24x7 socket/chip level events. "hv_24x7" chip level events needs specific chip-id to which the data is requested. Function 'arch_get_runtimeparam' implemented in header.c which extract number of sockets from sysfs file "sockets" under "/sys/devices/hv_24x7/interface/". With this patch basically we are trying to create as many metric events as define by runtime_param. For that one loop is added in function 'metricgroup__add_metric', which create multiple events at run time depend on return value of 'arch_get_runtimeparam' and merge that event in 'group_list'. To achieve that we are actually passing this parameter value as part of `expr__find_other` function and changing "?" present in metric expression with this value. As in our JSON file, there gonna be single metric event, and out of which we are creating multiple events. To understand which data count belongs to which parameter value, we also printing param value in generic_metric function. For example, command:# ./perf stat -M PowerBUS_Frequency -C 0 -I 1000 1.000101867 9,356,933 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 1.000101867 9,366,134 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 2.000314878 9,365,868 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 2.000314878 9,366,092 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 So, here _0 and _1 after PowerBUS_Frequency specify parameter value. Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@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: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Joe Mario <jmario@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lore.kernel.org/lkml/20200401203340.31402-5-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-04-01 14:33:37 -06:00
if (!strstr(pe->metric_expr, "?")) {
ret = __metricgroup__add_metric(group_list,
pe,
metric_no_group,
1);
if (ret)
return ret;
perf metricgroups: Enhance JSON/metric infrastructure to handle "?" Patch enhances current metric infrastructure to handle "?" in the metric expression. The "?" can be use for parameters whose value not known while creating metric events and which can be replace later at runtime to the proper value. It also add flexibility to create multiple events out of single metric event added in JSON file. Patch adds function 'arch_get_runtimeparam' which is a arch specific function, returns the count of metric events need to be created. By default it return 1. This infrastructure needed for hv_24x7 socket/chip level events. "hv_24x7" chip level events needs specific chip-id to which the data is requested. Function 'arch_get_runtimeparam' implemented in header.c which extract number of sockets from sysfs file "sockets" under "/sys/devices/hv_24x7/interface/". With this patch basically we are trying to create as many metric events as define by runtime_param. For that one loop is added in function 'metricgroup__add_metric', which create multiple events at run time depend on return value of 'arch_get_runtimeparam' and merge that event in 'group_list'. To achieve that we are actually passing this parameter value as part of `expr__find_other` function and changing "?" present in metric expression with this value. As in our JSON file, there gonna be single metric event, and out of which we are creating multiple events. To understand which data count belongs to which parameter value, we also printing param value in generic_metric function. For example, command:# ./perf stat -M PowerBUS_Frequency -C 0 -I 1000 1.000101867 9,356,933 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 1.000101867 9,366,134 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 2.000314878 9,365,868 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 2.000314878 9,366,092 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 So, here _0 and _1 after PowerBUS_Frequency specify parameter value. Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@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: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Joe Mario <jmario@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lore.kernel.org/lkml/20200401203340.31402-5-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-04-01 14:33:37 -06:00
} else {
int j, count;
count = arch_get_runtimeparam();
/* This loop is added to create multiple
* events depend on count value and add
* those events to group_list.
*/
for (j = 0; j < count; j++) {
ret = __metricgroup__add_metric(
group_list, pe,
metric_no_group, j);
if (ret)
return ret;
}
perf metricgroups: Enhance JSON/metric infrastructure to handle "?" Patch enhances current metric infrastructure to handle "?" in the metric expression. The "?" can be use for parameters whose value not known while creating metric events and which can be replace later at runtime to the proper value. It also add flexibility to create multiple events out of single metric event added in JSON file. Patch adds function 'arch_get_runtimeparam' which is a arch specific function, returns the count of metric events need to be created. By default it return 1. This infrastructure needed for hv_24x7 socket/chip level events. "hv_24x7" chip level events needs specific chip-id to which the data is requested. Function 'arch_get_runtimeparam' implemented in header.c which extract number of sockets from sysfs file "sockets" under "/sys/devices/hv_24x7/interface/". With this patch basically we are trying to create as many metric events as define by runtime_param. For that one loop is added in function 'metricgroup__add_metric', which create multiple events at run time depend on return value of 'arch_get_runtimeparam' and merge that event in 'group_list'. To achieve that we are actually passing this parameter value as part of `expr__find_other` function and changing "?" present in metric expression with this value. As in our JSON file, there gonna be single metric event, and out of which we are creating multiple events. To understand which data count belongs to which parameter value, we also printing param value in generic_metric function. For example, command:# ./perf stat -M PowerBUS_Frequency -C 0 -I 1000 1.000101867 9,356,933 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 1.000101867 9,366,134 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 2.000314878 9,365,868 hv_24x7/pm_pb_cyc,chip=0/ # 2.3 GHz PowerBUS_Frequency_0 2.000314878 9,366,092 hv_24x7/pm_pb_cyc,chip=1/ # 2.3 GHz PowerBUS_Frequency_1 So, here _0 and _1 after PowerBUS_Frequency specify parameter value. Signed-off-by: Kajol Jain <kjain@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@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: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Joe Mario <jmario@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lore.kernel.org/lkml/20200401203340.31402-5-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-04-01 14:33:37 -06:00
}
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
}
}
list_for_each_entry(eg, group_list, nd) {
if (events->len > 0)
strbuf_addf(events, ",");
if (eg->has_constraint) {
metricgroup__add_metric_non_group(events,
&eg->pctx);
} else {
metricgroup__add_metric_weak_group(events,
&eg->pctx);
}
}
return 0;
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
}
static int metricgroup__add_metric_list(const char *list, bool metric_no_group,
struct strbuf *events,
struct list_head *group_list,
struct pmu_events_map *map)
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
{
char *llist, *nlist, *p;
int ret = -EINVAL;
nlist = strdup(list);
if (!nlist)
return -ENOMEM;
llist = nlist;
strbuf_init(events, 100);
strbuf_addf(events, "%s", "");
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
while ((p = strsep(&llist, ",")) != NULL) {
ret = metricgroup__add_metric(p, metric_no_group, events,
group_list, map);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
if (ret == -EINVAL) {
fprintf(stderr, "Cannot find metric or group `%s'\n",
p);
break;
}
}
free(nlist);
if (!ret)
metricgroup___watchdog_constraint_hint(NULL, true);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
return ret;
}
static void metricgroup__free_egroups(struct list_head *group_list)
{
struct egroup *eg, *egtmp;
list_for_each_entry_safe (eg, egtmp, group_list, nd) {
perf expr: Migrate expr ids table to a hashmap Use a hashmap between a char* string and a double* value. While bpf's hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >= sizeof(double). Avoid a memory allocation when gathering ids by making 0.0 a special value encoded as NULL. Original map suggestion by Andi Kleen: https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/ and seconded by Jiri Olsa: https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/ Committer notes: There are fixes that need to land upstream before we can use libbpf's headers, for now use our copy unconditionally, since the data structures at this point are exactly the same, no problem. When the fixes for libbpf's hashmap land upstream, we can fix this up. Testing it: Building with LIBBPF=1, i.e. the default: $ perf -vv | grep -i bpf bpf: [ on ] # HAVE_LIBBPF_SUPPORT $ nm ~/bin/perf | grep -i libbpf_ | wc -l 39 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 17 $ Explicitely building without LIBBPF: $ perf -vv | grep -i bpf bpf: [ OFF ] # HAVE_LIBBPF_SUPPORT $ $ nm ~/bin/perf | grep -i libbpf_ | wc -l 0 $ nm ~/bin/perf | grep -i hashmap_ | wc -l 9 $ 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: Alexei Starovoitov <ast@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: kp singh <kpsingh@chromium.org> Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-15 16:17:32 -06:00
expr__ctx_clear(&eg->pctx);
list_del_init(&eg->nd);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
free(eg);
}
}
static int parse_groups(struct evlist *perf_evlist, const char *str,
bool metric_no_group,
bool metric_no_merge,
struct perf_pmu *fake_pmu,
struct rblist *metric_events,
struct pmu_events_map *map)
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
{
struct parse_events_error parse_error;
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, metric_no_group,
&extra_events, &group_list, map);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
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 00:46:52 -07:00
bzero(&parse_error, sizeof(parse_error));
ret = __parse_events(perf_evlist, extra_events.buf, &parse_error, fake_pmu);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
if (ret) {
parse_events_print_error(&parse_error, extra_events.buf);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
goto out;
}
strbuf_release(&extra_events);
ret = metricgroup__setup_events(&group_list, metric_no_merge,
perf_evlist, metric_events);
perf stat: Support JSON metrics in perf stat Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name. We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once. Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified. Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c The actual JSON metrics are in a separate pull request. % perf stat -M Summary --metric-only -a sleep 1 Performance counter stats for 'system wide': Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1 1.001497549 seconds time elapsed % perf stat -M GFLOPs flops Performance counter stats for 'flops': 3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%) 14 fp_comp_ops_exe.sse_scalar_double (66.65%) 0 fp_comp_ops_exe.sse_packed_double (66.67%) 0 fp_comp_ops_exe.sse_packed_single (66.70%) 0 simd_fp_256.packed_double (66.70%) 0 simd_fp_256.packed_single (66.67%) 0 duration_time 3.238372845 seconds time elapsed v2: Add missing header file v3: Move find_map to pmu.c Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170831194036.30146-7-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 13:40:31 -06:00
out:
metricgroup__free_egroups(&group_list);
return ret;
}
int metricgroup__parse_groups(const struct option *opt,
const char *str,
bool metric_no_group,
bool metric_no_merge,
struct rblist *metric_events)
{
struct evlist *perf_evlist = *(struct evlist **)opt->value;
struct pmu_events_map *map = perf_pmu__find_map(NULL);
if (!map)
return 0;
return parse_groups(perf_evlist, str, metric_no_group,
metric_no_merge, NULL, metric_events, map);
}
int metricgroup__parse_groups_test(struct evlist *evlist,
struct pmu_events_map *map,
const char *str,
bool metric_no_group,
bool metric_no_merge,
struct rblist *metric_events)
{
return parse_groups(evlist, str, metric_no_group,
metric_no_merge, &perf_pmu__fake, metric_events, map);
}
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;
}