Benchmark operator delete

Added the microbenchmark for operator delete.
Also modified bench.h so that it can be used in C++.

Makefile.in

@@ -332,10 +332,15 @@ TESTS_STRESS := $(srcroot)test/stress/batch_alloc.c \
 	$(srcroot)test/stress/large_microbench.c \
 	$(srcroot)test/stress/mallctl.c \
 	$(srcroot)test/stress/microbench.c
+ifeq (@enable_cxx@, 1)
+TESTS_STRESS_CPP := $(srcroot)test/stress/cpp/microbench.cpp
+else
+TESTS_STRESS_CPP :=
+endif
 
 
 TESTS := $(TESTS_UNIT) $(TESTS_INTEGRATION) $(TESTS_INTEGRATION_CPP) \
-	$(TESTS_ANALYZE) $(TESTS_STRESS)
+	$(TESTS_ANALYZE) $(TESTS_STRESS) $(TESTS_STRESS_CPP)
 
 PRIVATE_NAMESPACE_HDRS := $(objroot)include/jemalloc/internal/private_namespace.h $(objroot)include/jemalloc/internal/private_namespace_jet.h
 PRIVATE_NAMESPACE_GEN_HDRS := $(PRIVATE_NAMESPACE_HDRS:%.h=%.gen.h)
@@ -362,9 +367,10 @@ TESTS_INTEGRATION_OBJS := $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%.$(O))
 TESTS_INTEGRATION_CPP_OBJS := $(TESTS_INTEGRATION_CPP:$(srcroot)%.cpp=$(objroot)%.$(O))
 TESTS_ANALYZE_OBJS := $(TESTS_ANALYZE:$(srcroot)%.c=$(objroot)%.$(O))
 TESTS_STRESS_OBJS := $(TESTS_STRESS:$(srcroot)%.c=$(objroot)%.$(O))
+TESTS_STRESS_CPP_OBJS := $(TESTS_STRESS_CPP:$(srcroot)%.cpp=$(objroot)%.$(O))
 TESTS_OBJS := $(TESTS_UNIT_OBJS) $(TESTS_INTEGRATION_OBJS) $(TESTS_ANALYZE_OBJS) \
 	$(TESTS_STRESS_OBJS)
-TESTS_CPP_OBJS := $(TESTS_INTEGRATION_CPP_OBJS)
+TESTS_CPP_OBJS := $(TESTS_INTEGRATION_CPP_OBJS) $(TESTS_STRESS_CPP_OBJS)
 
 .PHONY: all dist build_doc_html build_doc_man build_doc
 .PHONY: install_bin install_include install_lib
@@ -454,6 +460,7 @@ $(TESTS_INTEGRATION_OBJS): CPPFLAGS += -DJEMALLOC_INTEGRATION_TEST
 $(TESTS_INTEGRATION_CPP_OBJS): CPPFLAGS += -DJEMALLOC_INTEGRATION_CPP_TEST
 $(TESTS_ANALYZE_OBJS): CPPFLAGS += -DJEMALLOC_ANALYZE_TEST
 $(TESTS_STRESS_OBJS): CPPFLAGS += -DJEMALLOC_STRESS_TEST
+$(TESTS_STRESS_CPP_OBJS): CPPFLAGS += -DJEMALLOC_STRESS_CPP_TEST
 $(TESTS_OBJS): $(objroot)test/%.$(O): $(srcroot)test/%.c
 $(TESTS_CPP_OBJS): $(objroot)test/%.$(O): $(srcroot)test/%.cpp
 $(TESTS_OBJS): CPPFLAGS += -I$(srcroot)test/include -I$(objroot)test/include
@@ -474,7 +481,7 @@ $(TESTS_OBJS) $(TESTS_CPP_OBJS): $(objroot)test/include/test/jemalloc_test.h
 endif
 
 $(C_OBJS) $(CPP_OBJS) $(C_PIC_OBJS) $(CPP_PIC_OBJS) $(C_TESTLIB_INTEGRATION_OBJS) $(C_UTIL_INTEGRATION_OBJS) $(TESTS_INTEGRATION_OBJS) $(TESTS_INTEGRATION_CPP_OBJS): $(objroot)include/jemalloc/internal/private_namespace.h
-$(C_JET_OBJS) $(C_TESTLIB_UNIT_OBJS) $(C_TESTLIB_ANALYZE_OBJS) $(C_TESTLIB_STRESS_OBJS) $(TESTS_UNIT_OBJS) $(TESTS_ANALYZE_OBJS) $(TESTS_STRESS_OBJS): $(objroot)include/jemalloc/internal/private_namespace_jet.h
+$(C_JET_OBJS) $(C_TESTLIB_UNIT_OBJS) $(C_TESTLIB_ANALYZE_OBJS) $(C_TESTLIB_STRESS_OBJS) $(TESTS_UNIT_OBJS) $(TESTS_ANALYZE_OBJS) $(TESTS_STRESS_OBJS) $(TESTS_STRESS_CPP_OBJS): $(objroot)include/jemalloc/internal/private_namespace_jet.h
 
 $(C_SYM_OBJS) $(C_OBJS) $(C_PIC_OBJS) $(C_JET_SYM_OBJS) $(C_JET_OBJS) $(C_TESTLIB_OBJS) $(TESTS_OBJS): %.$(O):
 	@mkdir -p $(@D)
@@ -664,7 +671,7 @@ endif
 tests_unit: $(TESTS_UNIT:$(srcroot)%.c=$(objroot)%$(EXE))
 tests_integration: $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%$(EXE)) $(TESTS_INTEGRATION_CPP:$(srcroot)%.cpp=$(objroot)%$(EXE))
 tests_analyze: $(TESTS_ANALYZE:$(srcroot)%.c=$(objroot)%$(EXE))
-tests_stress: $(TESTS_STRESS:$(srcroot)%.c=$(objroot)%$(EXE))
+tests_stress: $(TESTS_STRESS:$(srcroot)%.c=$(objroot)%$(EXE)) $(TESTS_STRESS_CPP:$(srcroot)%.cpp=$(objroot)%$(EXE))
 tests: tests_unit tests_integration tests_analyze tests_stress
 
 check_unit_dir:
@@ -697,6 +704,7 @@ else
 endif
 stress: tests_stress stress_dir
 	$(SHELL) $(objroot)test/test.sh $(TESTS_STRESS:$(srcroot)%.c=$(objroot)%)
+	$(SHELL) $(objroot)test/test.sh $(TESTS_STRESS_CPP:$(srcroot)%.cpp=$(objroot)%)
 check: check_unit check_integration check_integration_decay check_integration_prof
 
 clean:

test/include/test/bench.h

@@ -23,7 +23,7 @@ fmt_nsecs(uint64_t usec, uint64_t iters, char *buf) {
 	uint64_t nsecs_per_iter1000 = nsec1000 / iters;
 	uint64_t intpart = nsecs_per_iter1000 / 1000;
 	uint64_t fracpart = nsecs_per_iter1000 % 1000;
-	malloc_snprintf(buf, FMT_NSECS_BUF_SIZE, "%"FMTu64".%03"FMTu64, intpart,
+	malloc_snprintf(buf, FMT_NSECS_BUF_SIZE, "%" FMTu64 ".%03" FMTu64, intpart,
 	    fracpart);
 }
 
@@ -40,8 +40,8 @@ compare_funcs(uint64_t nwarmup, uint64_t niter, const char *name_a,
 		return;
 	}
 
-	time_func(&timer_a, nwarmup, niter, func_a);
+	time_func(&timer_a, nwarmup, niter, (void (*)())func_a);
-	time_func(&timer_b, nwarmup, niter, func_b);
+	time_func(&timer_b, nwarmup, niter, (void (*)())func_b);
 
 	uint64_t usec_a = timer_usec(&timer_a);
 	char buf_a[FMT_NSECS_BUF_SIZE];
@@ -52,8 +52,8 @@ compare_funcs(uint64_t nwarmup, uint64_t niter, const char *name_a,
 	fmt_nsecs(usec_b, niter, buf_b);
 
 	timer_ratio(&timer_a, &timer_b, ratio_buf, sizeof(ratio_buf));
-	malloc_printf("%"FMTu64" iterations, %s=%"FMTu64"us (%s ns/iter), "
+	malloc_printf("%" FMTu64 " iterations, %s=%" FMTu64 "us (%s ns/iter), "
-	    "%s=%"FMTu64"us (%s ns/iter), time consumption ratio=%s:1\n",
+	    "%s=%" FMTu64 "us (%s ns/iter), time consumption ratio=%s:1\n",
 	    niter, name_a, usec_a, buf_a, name_b, usec_b, buf_b, ratio_buf);
 
 	dallocx(p, 0);

test/include/test/jemalloc_test.h.in

@@ -88,7 +88,8 @@ static const bool config_debug =
  * public jemalloc interfaces with jet_ prefixes, so that stress tests can use
  * a separate allocator for their internal data structures.
  */
-#elif defined(JEMALLOC_STRESS_TEST)
+#elif defined(JEMALLOC_STRESS_TEST) || \
+    defined(JEMALLOC_STRESS_CPP_TEST)
 #  include "jemalloc/jemalloc@install_suffix@.h"
 
 #  include "jemalloc/jemalloc_protos_jet.h"

test/stress/cpp/microbench.cpp

@@ -0,0 +1,83 @@
+#include "test/jemalloc_test.h"
+#include "test/bench.h"
+
+static void
+malloc_free(void) {
+	void *p = malloc(1);
+	expect_ptr_not_null(p, "Unexpected new failure");
+	free(p);
+}
+
+static void
+new_delete(void) {
+	auto p = ::operator new(1);
+	expect_ptr_not_null(p, "Unexpected new failure");
+	::operator delete(p);
+}
+
+static void
+malloc_free_array(void) {
+	void *p = malloc(sizeof(int)*8);
+	expect_ptr_not_null(p, "Unexpected new[] failure");
+	free(p);
+}
+
+static void
+new_delete_array(void) {
+	auto p = new int[8];
+	expect_ptr_not_null(p, "Unexpected new[] failure");
+	delete[] p;
+}
+
+#if __cpp_sized_deallocation >= 201309
+static void
+new_sized_delete(void) {
+	auto p = ::operator new(1);
+	expect_ptr_not_null(p, "Unexpected new failure");
+	::operator delete(p, 1);
+}
+
+static void
+malloc_sdallocx(void) {
+	void *p = malloc(1);
+	expect_ptr_not_null(p, "Unexpected new failure");
+        sdallocx(p, 1, 0);
+}
+#endif
+
+TEST_BEGIN(test_free_vs_delete) {
+	compare_funcs(10*1000*1000, 100*1000*1000, 
+	    "malloc_free", (void *)malloc_free, 
+	    "new_delete", (void *)new_delete);
+}
+TEST_END
+
+TEST_BEGIN(test_free_array_vs_delete_array) {
+	compare_funcs(10*1000*1000, 100*1000*1000, 
+	    "malloc_free_array", (void *)malloc_free_array, 
+	    "delete_array", (void *)new_delete_array);
+}
+TEST_END
+
+
+TEST_BEGIN(test_sized_delete_vs_sdallocx) {
+#if __cpp_sized_deallocation >= 201309
+	compare_funcs(10*1000*1000, 100*1000*1000, 
+	    "new_size_delete", (void *)new_sized_delete, 
+	    "malloc_sdallocx", (void *)malloc_sdallocx);
+#else
+	malloc_printf("Skipping test_sized_delete_vs_sdallocx since \
+	    sized deallocation is not enabled.\n");
+#endif
+}
+TEST_END
+
+
+int
+main() {
+	return test_no_reentrancy(
+	    test_free_vs_delete,
+	    test_free_array_vs_delete_array,
+	    test_sized_delete_vs_sdallocx);
+	    
+}