By using "make TCMALLOC=1" you can enable perf to be build
for usage with libtcmalloc.so (gperftools).
Get heap profile (tools/perf directory):
$ <install gperftools>
$ make TCMALLOC=1 DEBUG=1
$ HEAPPROFILE=/tmp/heapprof ./perf ...
$ pprof ./perf /tmp/heapprof.000*
(pprof) top
Total: 2335.5 MB
1735.1 74.3% 74.3% 1735.1 74.3% memdup
402.0 17.2% 91.5% 402.0 17.2% zalloc
140.2 6.0% 97.5% 145.8 6.2% map__new
33.6 1.4% 98.9% 33.6 1.4% symbol__new
12.4 0.5% 99.5% 12.4 0.5% alloc_event
6.2 0.3% 99.7% 6.2 0.3% nsinfo__new
5.5 0.2% 100.0% 5.5 0.2% nsinfo__copy
0.3 0.0% 100.0% 0.3 0.0% dso__new
0.1 0.0% 100.0% 0.1 0.0% do_read_string
0.0 0.0% 100.0% 0.0 0.0% __GI__IO_file_doallocate
See callstack:
$ pprof --pdf ./perf /tmp/heapprof.00* > callstack.pdf
$ pprof --web ./perf /tmp/heapprof.00*
Link: http://lkml.kernel.org/n/tip-qyo3c7z69dysk10sr3pf5...@git.kernel.org
Signed-off-by: Jiri Olsa <jo...@kernel.org>
---
tools/perf/Makefile.config | 5 +++++
tools/perf/Makefile.perf | 2 ++
2 files changed, 7 insertions(+)
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 063202c53b64..1783427da9b0 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -265,6 +265,11 @@ LDFLAGS += -Wl,-z,noexecstack
EXTLIBS = -lpthread -lrt -lm -ldl
+ifneq ($(TCMALLOC),)
+ CFLAGS += -fno-builtin-malloc -fno-builtin-calloc -fno-builtin-realloc
-fno-builtin-free
+ EXTLIBS += -ltcmalloc
+endif
+
ifeq ($(FEATURES_DUMP),)
include $(srctree)/tools/build/Makefile.feature
else
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index a099a8a89447..8f1ba986d3bf 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -114,6 +114,8 @@ include ../scripts/utilities.mak
# Define NO_LIBZSTD if you do not want support of Zstandard based runtime
# trace compression in record mode.
#
+# Define TCMALLOC to enable tcmalloc heap profiling.
+#
# As per kernel Makefile, avoid funny character set dependencies
unexport LC_ALL
--
2.21.0
