Skip to contentSkip to conversation

perf stat: Enable BPF counter with --for-each-cgroup

PATCH In review Namhyung Kim 2 participants 2 messages Jul 1, 2021 – Jul 2, 2021 perf events

lore
Share & tools
lore

Namhyung Kim

author maintainer
#0 lore raw

PATCH v5 1/1 perf stat: Enable BPF counter with --for-each-cgroup

Recently bperf was added to use BPF to count perf events for various purposes. This is an extension for the approach and targetting to cgroup usages.

Unlike the other bperf, it doesn't share the events with other processes but it'd reduce unnecessary events (and the overhead of multiplexing) for each monitored cgroup within the perf session.

When --for-each-cgroup is used with --bpf-counters, it will open cgroup-switches event per cpu internally and attach the new BPF program to read given perf_events and to aggregate the results for cgroups. It's only called when task is switched to a task in a different cgroup.

---
* fix build errors
* update copyright year
* call bperf_cgrp__sync_counters during enable
* change warning when trigger reading failed

 tools/perf/Makefile.perf                    |  17 +-
 tools/perf/util/Build                       |   1 +
 tools/perf/util/bpf_counter.c               |   5 +
 tools/perf/util/bpf_counter_cgroup.c        | 307 ++++++++++++++++++++
 tools/perf/util/bpf_skel/bperf_cgroup.bpf.c | 191 ++++++++++++
 tools/perf/util/cgroup.c                    |   2 +
 tools/perf/util/cgroup.h                    |   1 +
 7 files changed, 523 insertions(+), 1 deletion(-)
 create mode 100644 tools/perf/util/bpf_counter_cgroup.c
 create mode 100644 tools/perf/util/bpf_skel/bperf_cgroup.bpf.c
tools/perf/Makefile.perf +16 -1
index e47f04e5b51e..c63f91409195 100644
@@ -1015,6 +1015,7 @@ SKEL_OUT := $(abspath $(OUTPUT)util/bpf_skel)
 SKEL_TMP_OUT := $(abspath $(SKEL_OUT)/.tmp)
 SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h
 SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h
+SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h
 
 ifdef BUILD_BPF_SKEL
 BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool
@@ -1028,7 +1029,21 @@ $(BPFTOOL): | $(SKEL_TMP_OUT)
 	CFLAGS= $(MAKE) -C ../bpf/bpftool \
 		OUTPUT=$(SKEL_TMP_OUT)/ bootstrap
 
-$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT)
+VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
+		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
+		     ../../vmlinux					\
+		     /sys/kernel/btf/vmlinux				\
+		     /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+
+$(SKEL_OUT)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL)
+ifeq ($(VMLINUX_H),)
+	$(QUIET_GEN)$(BPFTOOL) btf dump file $< format c > $@
+else
+	$(Q)cp "$(VMLINUX_H)" $@
+endif
+
+$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) $(SKEL_OUT)/vmlinux.h | $(SKEL_TMP_OUT)
 	$(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \
 	  -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@
 
tools/perf/util/Build +1 -0
index 95e15d1035ab..700d635448ff 100644
@@ -140,6 +140,7 @@ perf-y += clockid.o
 perf-$(CONFIG_LIBBPF) += bpf-loader.o
 perf-$(CONFIG_LIBBPF) += bpf_map.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o
+perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o
 perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
 perf-$(CONFIG_LIBELF) += symbol-elf.o
 perf-$(CONFIG_LIBELF) += probe-file.o
tools/perf/util/bpf_counter.c +5 -0
index 21c8e71162b1..1d0b9742f727 100644
@@ -18,6 +18,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "target.h"
+#include "cgroup.h"
 #include "cpumap.h"
 #include "thread_map.h"
 
@@ -742,6 +743,8 @@ struct bpf_counter_ops bperf_ops = {
 	.destroy    = bperf__destroy,
 };
 
+extern struct bpf_counter_ops bperf_cgrp_ops;
+
 static inline bool bpf_counter_skip(struct evsel *evsel)
 {
 	return list_empty(&evsel->bpf_counter_list) &&
@@ -759,6 +762,8 @@ int bpf_counter__load(struct evsel *evsel, struct target *target)
 {
 	if (target->bpf_str)
 		evsel->bpf_counter_ops = &bpf_program_profiler_ops;
+	else if (cgrp_event_expanded && target->use_bpf)
+		evsel->bpf_counter_ops = &bperf_cgrp_ops;
 	else if (target->use_bpf || evsel->bpf_counter ||
 		 evsel__match_bpf_counter_events(evsel->name))
 		evsel->bpf_counter_ops = &bperf_ops;
tools/perf/util/bpf_counter_cgroup.c new file +307 -0

307 lines not on this page · raw message

tools/perf/util/bpf_skel/bperf_cgroup.bpf.c new file +191 -0

191 lines not on this page · raw message

tools/perf/util/cgroup.c +2 -0
index e819a4f30fc2..851531102fd6 100644
@@ -18,6 +18,7 @@
 #include <regex.h>
 
 int nr_cgroups;
+bool cgrp_event_expanded;
 
 /* used to match cgroup name with patterns */
 struct cgroup_name {
@@ -484,6 +485,7 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str,
 	}
 
 	ret = 0;
+	cgrp_event_expanded = true;
 
 out_err:
 	evlist__delete(orig_list);
tools/perf/util/cgroup.h +1 -0
index 13f4ea7dfe4c..87bd417d55ab 100644
@@ -17,6 +17,7 @@ struct cgroup {
 };
 
 extern int nr_cgroups; /* number of explicit cgroups defined */
+extern bool cgrp_event_expanded;
 
 struct cgroup *cgroup__get(struct cgroup *cgroup);
 void cgroup__put(struct cgroup *cgroup);
Signature · 1 line
2.32.0.93.g670b81a890-goog
Acked-by on v5 1/1
#1 lore raw
Quoted 12 lines · Namhyung Kim

Recently bperf was added to use BPF to count perf events for various purposes. This is an extension for the approach and targetting to cgroup usages.

Unlike the other bperf, it doesn't share the events with other processes but it'd reduce unnecessary events (and the overhead of multiplexing) for each monitored cgroup within the perf session.

Quoted 8 lines

When --for-each-cgroup is used with --bpf-counters, it will open cgroup-switches event per cpu internally and attach the new BPF program to read given perf_events and to aggregate the results for cgroups. It's only called when task is switched to a task in a different cgroup.