From: Namhyung Kim <namhyung@kernel.org>
To: Ankur Arora <ankur.a.arora@oracle.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, x86@kernel.org,
akpm@linux-foundation.org, david@redhat.com, bp@alien8.de,
dave.hansen@linux.intel.com, hpa@zytor.com, mingo@redhat.com,
mjguzik@gmail.com, luto@kernel.org, peterz@infradead.org,
acme@kernel.org, tglx@linutronix.de, willy@infradead.org,
raghavendra.kt@amd.com, boris.ostrovsky@oracle.com,
konrad.wilk@oracle.com
Subject: Re: [PATCH v5 01/14] perf bench mem: Remove repetition around time measurement
Date: Tue, 15 Jul 2025 13:04:16 -0700 [thread overview]
Message-ID: <aHa0QLtTCe1BmkMd@google.com> (raw)
In-Reply-To: <20250710005926.1159009-2-ankur.a.arora@oracle.com>
Hello,
On Wed, Jul 09, 2025 at 05:59:13PM -0700, Ankur Arora wrote:
> We have two copies of each mem benchmark: one using cycles to
> measure time, the second for gettimeofday().
>
> Unify.
>
> Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Thanks,
Namhyung
> ---
> tools/perf/bench/mem-functions.c | 110 +++++++++++++------------------
> 1 file changed, 46 insertions(+), 64 deletions(-)
>
> diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
> index 19d45c377ac1..8599ed96ee1f 100644
> --- a/tools/perf/bench/mem-functions.c
> +++ b/tools/perf/bench/mem-functions.c
> @@ -51,6 +51,11 @@ static const struct option options[] = {
> OPT_END()
> };
>
> +union bench_clock {
> + u64 cycles;
> + struct timeval tv;
> +};
> +
> typedef void *(*memcpy_t)(void *, const void *, size_t);
> typedef void *(*memset_t)(void *, int, size_t);
>
> @@ -91,6 +96,26 @@ static u64 get_cycles(void)
> return clk;
> }
>
> +static void clock_get(union bench_clock *t)
> +{
> + if (use_cycles)
> + t->cycles = get_cycles();
> + else
> + BUG_ON(gettimeofday(&t->tv, NULL));
> +}
> +
> +static union bench_clock clock_diff(union bench_clock *s, union bench_clock *e)
> +{
> + union bench_clock t;
> +
> + if (use_cycles)
> + t.cycles = e->cycles - s->cycles;
> + else
> + timersub(&e->tv, &s->tv, &t.tv);
> +
> + return t;
> +}
> +
> static double timeval2double(struct timeval *ts)
> {
> return (double)ts->tv_sec + (double)ts->tv_usec / (double)USEC_PER_SEC;
> @@ -109,8 +134,7 @@ static double timeval2double(struct timeval *ts)
>
> struct bench_mem_info {
> const struct function *functions;
> - u64 (*do_cycles)(const struct function *r, size_t size, void *src, void *dst);
> - double (*do_gettimeofday)(const struct function *r, size_t size, void *src, void *dst);
> + union bench_clock (*do_op)(const struct function *r, size_t size, void *src, void *dst);
> const char *const *usage;
> bool alloc_src;
> };
> @@ -119,7 +143,7 @@ static void __bench_mem_function(struct bench_mem_info *info, int r_idx, size_t
> {
> const struct function *r = &info->functions[r_idx];
> double result_bps = 0.0;
> - u64 result_cycles = 0;
> + union bench_clock rt = { 0 };
> void *src = NULL, *dst = zalloc(size);
>
> printf("# function '%s' (%s)\n", r->name, r->desc);
> @@ -136,25 +160,23 @@ static void __bench_mem_function(struct bench_mem_info *info, int r_idx, size_t
> if (bench_format == BENCH_FORMAT_DEFAULT)
> printf("# Copying %s bytes ...\n\n", size_str);
>
> - if (use_cycles) {
> - result_cycles = info->do_cycles(r, size, src, dst);
> - } else {
> - result_bps = info->do_gettimeofday(r, size, src, dst);
> - }
> + rt = info->do_op(r, size, src, dst);
>
> switch (bench_format) {
> case BENCH_FORMAT_DEFAULT:
> if (use_cycles) {
> - printf(" %14lf cycles/byte\n", (double)result_cycles/size_total);
> + printf(" %14lf cycles/byte\n", (double)rt.cycles/size_total);
> } else {
> + result_bps = size_total/timeval2double(&rt.tv);
> print_bps(result_bps);
> }
> break;
>
> case BENCH_FORMAT_SIMPLE:
> if (use_cycles) {
> - printf("%lf\n", (double)result_cycles/size_total);
> + printf("%lf\n", (double)rt.cycles/size_total);
> } else {
> + result_bps = size_total/timeval2double(&rt.tv);
> printf("%lf\n", result_bps);
> }
> break;
> @@ -235,38 +257,21 @@ static void memcpy_prefault(memcpy_t fn, size_t size, void *src, void *dst)
> fn(dst, src, size);
> }
>
> -static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst)
> +static union bench_clock do_memcpy(const struct function *r, size_t size,
> + void *src, void *dst)
> {
> - u64 cycle_start = 0ULL, cycle_end = 0ULL;
> + union bench_clock start, end;
> memcpy_t fn = r->fn.memcpy;
> int i;
>
> memcpy_prefault(fn, size, src, dst);
>
> - cycle_start = get_cycles();
> + clock_get(&start);
> for (i = 0; i < nr_loops; ++i)
> fn(dst, src, size);
> - cycle_end = get_cycles();
> + clock_get(&end);
>
> - return cycle_end - cycle_start;
> -}
> -
> -static double do_memcpy_gettimeofday(const struct function *r, size_t size, void *src, void *dst)
> -{
> - struct timeval tv_start, tv_end, tv_diff;
> - memcpy_t fn = r->fn.memcpy;
> - int i;
> -
> - memcpy_prefault(fn, size, src, dst);
> -
> - BUG_ON(gettimeofday(&tv_start, NULL));
> - for (i = 0; i < nr_loops; ++i)
> - fn(dst, src, size);
> - BUG_ON(gettimeofday(&tv_end, NULL));
> -
> - timersub(&tv_end, &tv_start, &tv_diff);
> -
> - return (double)(((double)size * nr_loops) / timeval2double(&tv_diff));
> + return clock_diff(&start, &end);
> }
>
> struct function memcpy_functions[] = {
> @@ -292,8 +297,7 @@ int bench_mem_memcpy(int argc, const char **argv)
> {
> struct bench_mem_info info = {
> .functions = memcpy_functions,
> - .do_cycles = do_memcpy_cycles,
> - .do_gettimeofday = do_memcpy_gettimeofday,
> + .do_op = do_memcpy,
> .usage = bench_mem_memcpy_usage,
> .alloc_src = true,
> };
> @@ -301,9 +305,10 @@ int bench_mem_memcpy(int argc, const char **argv)
> return bench_mem_common(argc, argv, &info);
> }
>
> -static u64 do_memset_cycles(const struct function *r, size_t size, void *src __maybe_unused, void *dst)
> +static union bench_clock do_memset(const struct function *r, size_t size,
> + void *src __maybe_unused, void *dst)
> {
> - u64 cycle_start = 0ULL, cycle_end = 0ULL;
> + union bench_clock start, end;
> memset_t fn = r->fn.memset;
> int i;
>
> @@ -313,34 +318,12 @@ static u64 do_memset_cycles(const struct function *r, size_t size, void *src __m
> */
> fn(dst, -1, size);
>
> - cycle_start = get_cycles();
> + clock_get(&start);
> for (i = 0; i < nr_loops; ++i)
> fn(dst, i, size);
> - cycle_end = get_cycles();
> + clock_get(&end);
>
> - return cycle_end - cycle_start;
> -}
> -
> -static double do_memset_gettimeofday(const struct function *r, size_t size, void *src __maybe_unused, void *dst)
> -{
> - struct timeval tv_start, tv_end, tv_diff;
> - memset_t fn = r->fn.memset;
> - int i;
> -
> - /*
> - * We prefault the freshly allocated memory range here,
> - * to not measure page fault overhead:
> - */
> - fn(dst, -1, size);
> -
> - BUG_ON(gettimeofday(&tv_start, NULL));
> - for (i = 0; i < nr_loops; ++i)
> - fn(dst, i, size);
> - BUG_ON(gettimeofday(&tv_end, NULL));
> -
> - timersub(&tv_end, &tv_start, &tv_diff);
> -
> - return (double)(((double)size * nr_loops) / timeval2double(&tv_diff));
> + return clock_diff(&start, &end);
> }
>
> static const char * const bench_mem_memset_usage[] = {
> @@ -366,8 +349,7 @@ int bench_mem_memset(int argc, const char **argv)
> {
> struct bench_mem_info info = {
> .functions = memset_functions,
> - .do_cycles = do_memset_cycles,
> - .do_gettimeofday = do_memset_gettimeofday,
> + .do_op = do_memset,
> .usage = bench_mem_memset_usage,
> };
>
> --
> 2.43.5
>
next prev parent reply other threads:[~2025-07-15 20:04 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-10 0:59 [PATCH v5 00/14] mm: folio_zero_user: clearing of page-extents Ankur Arora
2025-07-10 0:59 ` [PATCH v5 01/14] perf bench mem: Remove repetition around time measurement Ankur Arora
2025-07-15 20:04 ` Namhyung Kim [this message]
2025-07-10 0:59 ` [PATCH v5 02/14] perf bench mem: Defer type munging of size to float Ankur Arora
2025-07-15 20:05 ` Namhyung Kim
2025-07-16 2:17 ` Ankur Arora
2025-07-10 0:59 ` [PATCH v5 03/14] perf bench mem: Move mem op parameters into a structure Ankur Arora
2025-07-15 20:06 ` Namhyung Kim
2025-07-10 0:59 ` [PATCH v5 04/14] perf bench mem: Pull out init/fini logic Ankur Arora
2025-07-15 20:09 ` Namhyung Kim
2025-07-10 0:59 ` [PATCH v5 05/14] perf bench mem: Switch from zalloc() to mmap() Ankur Arora
2025-07-15 20:09 ` Namhyung Kim
2025-07-10 0:59 ` [PATCH v5 06/14] perf bench mem: Allow mapping of hugepages Ankur Arora
2025-07-15 20:12 ` Namhyung Kim
2025-07-16 2:32 ` Ankur Arora
2025-07-10 0:59 ` [PATCH v5 07/14] perf bench mem: Allow chunking on a memory region Ankur Arora
2025-07-15 20:17 ` Namhyung Kim
2025-07-16 2:34 ` Ankur Arora
2025-07-10 0:59 ` [PATCH v5 08/14] perf bench mem: Refactor mem_options Ankur Arora
2025-07-15 20:18 ` Namhyung Kim
2025-07-10 0:59 ` [PATCH v5 09/14] perf bench mem: Add mmap() workloads Ankur Arora
2025-07-15 20:20 ` Namhyung Kim
2025-07-16 2:40 ` Ankur Arora
2025-07-10 0:59 ` [PATCH v5 10/14] x86/mm: Simplify clear_page_* Ankur Arora
2025-07-11 11:47 ` David Hildenbrand
2025-07-11 17:26 ` Ankur Arora
2025-07-11 19:03 ` David Hildenbrand
2025-07-11 19:24 ` Ankur Arora
2025-07-11 19:27 ` David Hildenbrand
2025-07-10 0:59 ` [PATCH v5 11/14] x86/clear_page: Introduce clear_pages() Ankur Arora
2025-07-10 0:59 ` [PATCH v5 12/14] mm: add config option for clearing page-extents Ankur Arora
2025-07-10 7:58 ` Andrew Morton
2025-07-10 16:31 ` Ankur Arora
2025-07-11 11:39 ` David Hildenbrand
2025-07-11 17:25 ` Ankur Arora
2025-07-11 19:14 ` David Hildenbrand
2025-07-11 19:35 ` Ankur Arora
2025-07-11 11:40 ` David Hildenbrand
2025-07-11 17:32 ` Ankur Arora
2025-07-11 19:26 ` David Hildenbrand
2025-07-11 19:42 ` Ankur Arora
2025-07-14 20:35 ` Ankur Arora
2025-07-15 20:59 ` David Hildenbrand
2025-07-10 0:59 ` [PATCH v5 13/14] mm: memory: support " Ankur Arora
2025-07-11 11:44 ` David Hildenbrand
2025-07-11 13:27 ` Raghavendra K T
2025-07-11 17:39 ` Ankur Arora
2025-07-15 22:08 ` David Hildenbrand
2025-07-16 3:19 ` Ankur Arora
2025-07-16 8:03 ` David Hildenbrand
2025-07-16 17:54 ` Ankur Arora
2025-07-10 0:59 ` [PATCH v5 14/14] x86/clear_pages: Support clearing of page-extents Ankur Arora
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=aHa0QLtTCe1BmkMd@google.com \
--to=namhyung@kernel.org \
--cc=acme@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=ankur.a.arora@oracle.com \
--cc=boris.ostrovsky@oracle.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=david@redhat.com \
--cc=hpa@zytor.com \
--cc=konrad.wilk@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=mjguzik@gmail.com \
--cc=peterz@infradead.org \
--cc=raghavendra.kt@amd.com \
--cc=tglx@linutronix.de \
--cc=willy@infradead.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.