Add two mmap() workloads: one that eagerly populates a region and
another that demand faults it in.
The intent is to probe the memory subsytem performance incurred
by mmap().
$ perf bench mem map -s 4gb -p 4kb -l 10 -f populate
# Running 'mem/map' benchmark:
# function 'populate' (Eagerly populated map)
# Copying 4gb bytes ...
1.811691 GB/sec
$ perf bench mem map -s 4gb -p 2mb -l 10 -f populate
# Running 'mem/map' benchmark:
# function 'populate' (Eagerly populated map)
# Copying 4gb bytes ...
12.272017 GB/sec
$ perf bench mem map -s 4gb -p 1gb -l 10 -f populate
# Running 'mem/map' benchmark:
# function 'populate' (Eagerly populated map)
# Copying 4gb bytes ...
17.085927 GB/sec
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
---
tools/perf/bench/bench.h | 1 +
tools/perf/bench/mem-functions.c | 96 ++++++++++++++++++++++++++++++++
tools/perf/builtin-bench.c | 1 +
3 files changed, 98 insertions(+)
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 9f736423af53..46484bb0eefb 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -28,6 +28,7 @@ int bench_syscall_fork(int argc, const char **argv);
int bench_syscall_execve(int argc, const char **argv);
int bench_mem_memcpy(int argc, const char **argv);
int bench_mem_memset(int argc, const char **argv);
+int bench_mem_map(int argc, const char **argv);
int bench_mem_find_bit(int argc, const char **argv);
int bench_futex_hash(int argc, const char **argv);
int bench_futex_wake(int argc, const char **argv);
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 8a37da149327..ea62e3583a70 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -40,6 +40,7 @@ static const char *chunk_size_str = "0";
static unsigned int nr_loops = 1;
static bool use_cycles;
static int cycles_fd;
+static unsigned int seed;
static const struct option bench_common_options[] = {
OPT_STRING('s', "size", &size_str, "1MB",
@@ -81,6 +82,7 @@ struct bench_params {
size_t chunk_size;
unsigned int nr_loops;
unsigned int page_shift;
+ unsigned int seed;
};
struct bench_mem_info {
@@ -98,6 +100,7 @@ typedef void (*mem_fini_t)(struct bench_mem_info *, struct bench_params *,
void **, void **);
typedef void *(*memcpy_t)(void *, const void *, size_t);
typedef void *(*memset_t)(void *, int, size_t);
+typedef void (*map_op_t)(void *, size_t, unsigned int, bool);
struct function {
const char *name;
@@ -108,6 +111,7 @@ struct function {
union {
memcpy_t memcpy;
memset_t memset;
+ map_op_t map_op;
};
} fn;
};
@@ -160,6 +164,14 @@ static union bench_clock clock_diff(union bench_clock *s, union bench_clock *e)
return t;
}
+static void clock_accum(union bench_clock *a, union bench_clock *b)
+{
+ if (use_cycles)
+ a->cycles += b->cycles;
+ else
+ timeradd(&a->tv, &b->tv, &a->tv);
+}
+
static double timeval2double(struct timeval *ts)
{
return (double)ts->tv_sec + (double)ts->tv_usec / (double)USEC_PER_SEC;
@@ -270,6 +282,8 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
}
p.page_shift = ilog2(page_size);
+ p.seed = seed;
+
if (!strncmp(function_str, "all", 3)) {
for (i = 0; info->functions[i].name; i++)
__bench_mem_function(info, &p, i);
@@ -464,3 +478,85 @@ int bench_mem_memset(int argc, const char **argv)
return bench_mem_common(argc, argv, &info);
}
+
+static void map_page_touch(void *dst, size_t size, unsigned int page_shift, bool random)
+{
+ unsigned long npages = size / (1 << page_shift);
+ unsigned long offset = 0, r = 0;
+
+ for (unsigned long i = 0; i < npages; i++) {
+ if (random)
+ r = rand() % (1 << page_shift);
+
+ *((char *)dst + offset + r) = *(char *)(dst + offset + r) + i;
+ offset += 1 << page_shift;
+ }
+}
+
+static int do_map(const struct function *r, struct bench_params *p,
+ void *src __maybe_unused, void *dst __maybe_unused,
+ union bench_clock *accum)
+{
+ union bench_clock start, end, diff;
+ map_op_t fn = r->fn.map_op;
+ bool populate = strcmp(r->name, "populate") == 0;
+
+ if (p->seed)
+ srand(p->seed);
+
+ for (unsigned int i = 0; i < p->nr_loops; i++) {
+ clock_get(&start);
+ dst = bench_mmap(p->size, populate, p->page_shift);
+ if (!dst)
+ goto out;
+
+ fn(dst, p->size, p->page_shift, p->seed);
+ clock_get(&end);
+ diff = clock_diff(&start, &end);
+ clock_accum(accum, &diff);
+
+ bench_munmap(dst, p->size);
+ }
+
+ return 0;
+out:
+ printf("# Memory allocation failed - maybe size (%s) %s?\n", size_str,
+ p->page_shift != PAGE_SHIFT_4KB ? "has insufficient hugepages" : "is too large");
+ return -1;
+}
+
+static const char * const bench_mem_map_usage[] = {
+ "perf bench mem map <options>",
+ NULL
+};
+
+static const struct function map_functions[] = {
+ { .name = "populate",
+ .desc = "Eagerly populated map",
+ .fn.map_op = map_page_touch },
+
+ { .name = "demand",
+ .desc = "Demand loaded map",
+ .fn.map_op = map_page_touch },
+
+ { .name = NULL, }
+};
+
+int bench_mem_map(int argc, const char **argv)
+{
+ static const struct option bench_map_options[] = {
+ OPT_UINTEGER('r', "randomize", &seed,
+ "Seed to randomize page RW offset with."),
+ OPT_PARENT(bench_common_options),
+ OPT_END()
+ };
+
+ struct bench_mem_info info = {
+ .functions = map_functions,
+ .do_op = do_map,
+ .usage = bench_mem_map_usage,
+ .options = bench_map_options,
+ };
+
+ return bench_mem_common(argc, argv, &info);
+}
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 2c1a9f3d847a..a20bd9882f0a 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -65,6 +65,7 @@ static struct bench mem_benchmarks[] = {
{ "memcpy", "Benchmark for memcpy() functions", bench_mem_memcpy },
{ "memset", "Benchmark for memset() functions", bench_mem_memset },
{ "find_bit", "Benchmark for find_bit() functions", bench_mem_find_bit },
+ { "map", "Benchmark for mmap() mappings", bench_mem_map },
{ "all", "Run all memory access benchmarks", NULL },
{ NULL, NULL, NULL }
};
--
2.43.5On Wed, Jul 09, 2025 at 05:59:21PM -0700, Ankur Arora wrote:
> Add two mmap() workloads: one that eagerly populates a region and
> another that demand faults it in.
>
> The intent is to probe the memory subsytem performance incurred
> by mmap().
Maybe better to name 'mmap' as other tests named after the actual
function. Also please update the documentation.
Thanks,
Namhyung
>
> $ perf bench mem map -s 4gb -p 4kb -l 10 -f populate
> # Running 'mem/map' benchmark:
> # function 'populate' (Eagerly populated map)
> # Copying 4gb bytes ...
>
> 1.811691 GB/sec
>
> $ perf bench mem map -s 4gb -p 2mb -l 10 -f populate
> # Running 'mem/map' benchmark:
> # function 'populate' (Eagerly populated map)
> # Copying 4gb bytes ...
>
> 12.272017 GB/sec
>
> $ perf bench mem map -s 4gb -p 1gb -l 10 -f populate
> # Running 'mem/map' benchmark:
> # function 'populate' (Eagerly populated map)
> # Copying 4gb bytes ...
>
> 17.085927 GB/sec
>
> Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
> ---
> tools/perf/bench/bench.h | 1 +
> tools/perf/bench/mem-functions.c | 96 ++++++++++++++++++++++++++++++++
> tools/perf/builtin-bench.c | 1 +
> 3 files changed, 98 insertions(+)
>
> diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
> index 9f736423af53..46484bb0eefb 100644
> --- a/tools/perf/bench/bench.h
> +++ b/tools/perf/bench/bench.h
> @@ -28,6 +28,7 @@ int bench_syscall_fork(int argc, const char **argv);
> int bench_syscall_execve(int argc, const char **argv);
> int bench_mem_memcpy(int argc, const char **argv);
> int bench_mem_memset(int argc, const char **argv);
> +int bench_mem_map(int argc, const char **argv);
> int bench_mem_find_bit(int argc, const char **argv);
> int bench_futex_hash(int argc, const char **argv);
> int bench_futex_wake(int argc, const char **argv);
> diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
> index 8a37da149327..ea62e3583a70 100644
> --- a/tools/perf/bench/mem-functions.c
> +++ b/tools/perf/bench/mem-functions.c
> @@ -40,6 +40,7 @@ static const char *chunk_size_str = "0";
> static unsigned int nr_loops = 1;
> static bool use_cycles;
> static int cycles_fd;
> +static unsigned int seed;
>
> static const struct option bench_common_options[] = {
> OPT_STRING('s', "size", &size_str, "1MB",
> @@ -81,6 +82,7 @@ struct bench_params {
> size_t chunk_size;
> unsigned int nr_loops;
> unsigned int page_shift;
> + unsigned int seed;
> };
>
> struct bench_mem_info {
> @@ -98,6 +100,7 @@ typedef void (*mem_fini_t)(struct bench_mem_info *, struct bench_params *,
> void **, void **);
> typedef void *(*memcpy_t)(void *, const void *, size_t);
> typedef void *(*memset_t)(void *, int, size_t);
> +typedef void (*map_op_t)(void *, size_t, unsigned int, bool);
>
> struct function {
> const char *name;
> @@ -108,6 +111,7 @@ struct function {
> union {
> memcpy_t memcpy;
> memset_t memset;
> + map_op_t map_op;
> };
> } fn;
> };
> @@ -160,6 +164,14 @@ static union bench_clock clock_diff(union bench_clock *s, union bench_clock *e)
> return t;
> }
>
> +static void clock_accum(union bench_clock *a, union bench_clock *b)
> +{
> + if (use_cycles)
> + a->cycles += b->cycles;
> + else
> + timeradd(&a->tv, &b->tv, &a->tv);
> +}
> +
> static double timeval2double(struct timeval *ts)
> {
> return (double)ts->tv_sec + (double)ts->tv_usec / (double)USEC_PER_SEC;
> @@ -270,6 +282,8 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
> }
> p.page_shift = ilog2(page_size);
>
> + p.seed = seed;
> +
> if (!strncmp(function_str, "all", 3)) {
> for (i = 0; info->functions[i].name; i++)
> __bench_mem_function(info, &p, i);
> @@ -464,3 +478,85 @@ int bench_mem_memset(int argc, const char **argv)
>
> return bench_mem_common(argc, argv, &info);
> }
> +
> +static void map_page_touch(void *dst, size_t size, unsigned int page_shift, bool random)
> +{
> + unsigned long npages = size / (1 << page_shift);
> + unsigned long offset = 0, r = 0;
> +
> + for (unsigned long i = 0; i < npages; i++) {
> + if (random)
> + r = rand() % (1 << page_shift);
> +
> + *((char *)dst + offset + r) = *(char *)(dst + offset + r) + i;
> + offset += 1 << page_shift;
> + }
> +}
> +
> +static int do_map(const struct function *r, struct bench_params *p,
> + void *src __maybe_unused, void *dst __maybe_unused,
> + union bench_clock *accum)
> +{
> + union bench_clock start, end, diff;
> + map_op_t fn = r->fn.map_op;
> + bool populate = strcmp(r->name, "populate") == 0;
> +
> + if (p->seed)
> + srand(p->seed);
> +
> + for (unsigned int i = 0; i < p->nr_loops; i++) {
> + clock_get(&start);
> + dst = bench_mmap(p->size, populate, p->page_shift);
> + if (!dst)
> + goto out;
> +
> + fn(dst, p->size, p->page_shift, p->seed);
> + clock_get(&end);
> + diff = clock_diff(&start, &end);
> + clock_accum(accum, &diff);
> +
> + bench_munmap(dst, p->size);
> + }
> +
> + return 0;
> +out:
> + printf("# Memory allocation failed - maybe size (%s) %s?\n", size_str,
> + p->page_shift != PAGE_SHIFT_4KB ? "has insufficient hugepages" : "is too large");
> + return -1;
> +}
> +
> +static const char * const bench_mem_map_usage[] = {
> + "perf bench mem map <options>",
> + NULL
> +};
> +
> +static const struct function map_functions[] = {
> + { .name = "populate",
> + .desc = "Eagerly populated map",
> + .fn.map_op = map_page_touch },
> +
> + { .name = "demand",
> + .desc = "Demand loaded map",
> + .fn.map_op = map_page_touch },
> +
> + { .name = NULL, }
> +};
> +
> +int bench_mem_map(int argc, const char **argv)
> +{
> + static const struct option bench_map_options[] = {
> + OPT_UINTEGER('r', "randomize", &seed,
> + "Seed to randomize page RW offset with."),
> + OPT_PARENT(bench_common_options),
> + OPT_END()
> + };
> +
> + struct bench_mem_info info = {
> + .functions = map_functions,
> + .do_op = do_map,
> + .usage = bench_mem_map_usage,
> + .options = bench_map_options,
> + };
> +
> + return bench_mem_common(argc, argv, &info);
> +}
> diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
> index 2c1a9f3d847a..a20bd9882f0a 100644
> --- a/tools/perf/builtin-bench.c
> +++ b/tools/perf/builtin-bench.c
> @@ -65,6 +65,7 @@ static struct bench mem_benchmarks[] = {
> { "memcpy", "Benchmark for memcpy() functions", bench_mem_memcpy },
> { "memset", "Benchmark for memset() functions", bench_mem_memset },
> { "find_bit", "Benchmark for find_bit() functions", bench_mem_find_bit },
> + { "map", "Benchmark for mmap() mappings", bench_mem_map },
> { "all", "Run all memory access benchmarks", NULL },
> { NULL, NULL, NULL }
> };
> --
> 2.43.5
>
Namhyung Kim <namhyung@kernel.org> writes: > On Wed, Jul 09, 2025 at 05:59:21PM -0700, Ankur Arora wrote: >> Add two mmap() workloads: one that eagerly populates a region and >> another that demand faults it in. >> >> The intent is to probe the memory subsytem performance incurred >> by mmap(). > > Maybe better to name 'mmap' as other tests named after the actual > function. That's true. My reason for not doing it was that these tests were oriented towards testing the memory subsystem instead of the system call itself. But I guess "map" is not a good name either. Any suggestions? > Also please update the documentation. Will do. Thanks Ankur
© 2016 - 2025 Red Hat, Inc.