perf bench mem: Allow chunking on a memory region

There can be a significant gap in memset/memcpy performance depending
on the size of the region being operated on.

With chunk-size=4kb:

  $ echo madvise > /sys/kernel/mm/transparent_hugepage/enabled

  $ perf bench mem memset -p 4kb -k 4kb -s 4gb -l 10 -f x86-64-stosq
  # Running 'mem/memset' benchmark:
  # function 'x86-64-stosq' (movsq-based memset() in arch/x86/lib/memset_64.S)
  # Copying 4gb bytes ...

      13.011655 GB/sec

With chunk-size=1gb:

  $ echo madvise > /sys/kernel/mm/transparent_hugepage/enabled

  $ perf bench mem memset -p 4kb -k 1gb -s 4gb -l 10 -f x86-64-stosq
  # Running 'mem/memset' benchmark:
  # function 'x86-64-stosq' (movsq-based memset() in arch/x86/lib/memset_64.S)
  # Copying 4gb bytes ...

      21.936355 GB/sec

So, allow the user to specify the chunk-size.

The default value is identical to the total size of the region, which
preserves current behaviour.

Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Raghavendra K T <raghavendra.kt@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 18 insertions, 2 deletions

diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 6aa1f02553ba..69968ba63d81 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -36,6 +36,7 @@
 static const char	*size_str	= "1MB";
 static const char	*function_str	= "all";
 static const char	*page_size_str	= "4KB";
+static const char	*chunk_size_str	= "0";
 static unsigned int	nr_loops	= 1;
 static bool		use_cycles;
 static int		cycles_fd;
@@ -49,6 +50,10 @@ static const struct option options[] = {
 		    "Specify page-size for mapping memory buffers. "
 		    "Available sizes: 4KB, 2MB, 1GB (case insensitive)"),
 
+	OPT_STRING('k', "chunk", &chunk_size_str, "0",
+		    "Specify the chunk-size for each invocation. "
+		    "Available units: B, KB, MB, GB and TB (case insensitive)"),
+
 	OPT_STRING('f', "function", &function_str, "all",
 		    "Specify the function to run, \"all\" runs all available functions, \"help\" lists them"),
 
@@ -69,6 +74,7 @@ union bench_clock {
 struct bench_params {
 	size_t		size;
 	size_t		size_total;
+	size_t		chunk_size;
 	unsigned int	nr_loops;
 	unsigned int	page_shift;
 };
@@ -243,6 +249,14 @@ static int bench_mem_common(int argc, const char **argv, struct bench_mem_info *
 	}
 	p.size_total = p.size * p.nr_loops;
 
+	p.chunk_size = (size_t)perf_atoll((char *)chunk_size_str);
+	if ((s64)p.chunk_size < 0 || (s64)p.chunk_size > (s64)p.size) {
+		fprintf(stderr, "Invalid chunk_size:%s\n", chunk_size_str);
+		return 1;
+	}
+	if (!p.chunk_size)
+		p.chunk_size = p.size;
+
 	page_size = (unsigned int)perf_atoll((char *)page_size_str);
 	if (page_size != (1 << PAGE_SHIFT_4KB) &&
 	    page_size != (1 << PAGE_SHIFT_2MB) &&
@@ -300,7 +314,8 @@ static int do_memcpy(const struct function *r, struct bench_params *p,
 
 	clock_get(&start);
 	for (unsigned int i = 0; i < p->nr_loops; ++i)
-		fn(dst, src, p->size);
+		for (size_t off = 0; off < p->size; off += p->chunk_size)
+			fn(dst + off, src + off, min(p->chunk_size, p->size - off));
 	clock_get(&end);
 
 	*rt = clock_diff(&start, &end);
@@ -402,7 +417,8 @@ static int do_memset(const struct function *r, struct bench_params *p,
 
 	clock_get(&start);
 	for (unsigned int i = 0; i < p->nr_loops; ++i)
-		fn(dst, i, p->size);
+		for (size_t off = 0; off < p->size; off += p->chunk_size)
+			fn(dst + off, i, min(p->chunk_size, p->size - off));
 	clock_get(&end);
 
 	*rt = clock_diff(&start, &end);