[PATCH] perf bench: add --write-size option to sched pipe

[Breno Leitao <leitao@debian.org>]

The default ping-pong uses sizeof(int) (4 bytes) per iteration, which
exercises only the pipe-buffer merge path and keeps allocation entirely
out of the picture. That makes the bench a useful scheduler / context-
switch latency probe but unable to surface anything from the pipe
page-allocation hot path.

Add a -s/--write-size option that sets the bytes written and read per
ping-pong iteration. The buffer is allocated for each side via
struct thread_data and replaces the on-stack int previously used. The
default remains sizeof(int) so existing invocations are unchanged.

With --write-size set above PAGE_SIZE the bench drives anon_pipe_write()
through alloc_page() (or the bulk pre-alloc, if the relevant patch is
applied), which is what we want when measuring pipe locking and page
allocation work.

The bench is a ping-pong: both sides call write() before read(), so a
single write_size payload must fit entirely in the pipe buffer or both
sides deadlock waiting for the other to drain. Resize the pipe via
F_SETPIPE_SZ to match write_size (skipped at the sizeof(int) default),
and error out cleanly when the request exceeds
/proc/sys/fs/pipe-max-size.

Signed-off-by: Breno Leitao <leitao@debian.org>
---
This patch has been valuable for testing and verifying the pipe
enhancements currently under discussion at
https://lore.kernel.org/all/20260515-fix_pipe-v1-0-b14c840c7555@debian.org/
---
 tools/perf/bench/sched-pipe.c | 36 ++++++++++++++++++++++++++++++------
 1 file changed, 30 insertions(+), 6 deletions(-)

diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 70139036d68f0..77a7e35d7d809 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -39,6 +39,7 @@ struct thread_data {
 	int			epoll_fd;
 	bool			cgroup_failed;
 	pthread_t		pthread;
+	char			*buf;
 };
 
 #define LOOPS_DEFAULT 1000000
@@ -48,6 +49,7 @@ static	int			loops = LOOPS_DEFAULT;
 static bool			threaded;
 
 static bool			nonblocking;
+static unsigned int		write_size = sizeof(int);
 static char			*cgrp_names[2];
 static struct cgroup		*cgrps[2];
 
@@ -88,6 +90,9 @@ static const struct option options[] = {
 	OPT_BOOLEAN('n', "nonblocking",	&nonblocking,	"Use non-blocking operations"),
 	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
 	OPT_BOOLEAN('T', "threaded",	&threaded,	"Specify threads/process based task setup"),
+	OPT_UINTEGER('s', "write-size", &write_size,
+		     "Bytes per ping-pong write (default 4-bytes). Use larger "
+		     "values to exercise the pipe page-allocation path."),
 	OPT_CALLBACK('G', "cgroups", NULL, "SEND,RECV",
 		     "Put sender and receivers in given cgroups",
 		     parse_two_cgroups),
@@ -172,14 +177,14 @@ static void exit_cgroup(int nr)
 
 static inline int read_pipe(struct thread_data *td)
 {
-	int ret, m;
+	int ret;
 retry:
 	if (nonblocking) {
 		ret = epoll_wait(td->epoll_fd, &td->epoll_ev, 1, -1);
 		if (ret < 0)
 			return ret;
 	}
-	ret = read(td->pipe_read, &m, sizeof(int));
+	ret = read(td->pipe_read, td->buf, write_size);
 	if (nonblocking && ret < 0 && errno == EWOULDBLOCK)
 		goto retry;
 	return ret;
@@ -188,7 +193,7 @@ static inline int read_pipe(struct thread_data *td)
 static void *worker_thread(void *__tdata)
 {
 	struct thread_data *td = __tdata;
-	int i, ret, m = 0;
+	int i, ret;
 
 	ret = enter_cgroup(td->nr);
 	if (ret < 0) {
@@ -204,10 +209,10 @@ static void *worker_thread(void *__tdata)
 	}
 
 	for (i = 0; i < loops; i++) {
-		ret = write(td->pipe_write, &m, sizeof(int));
-		BUG_ON(ret != sizeof(int));
+		ret = write(td->pipe_write, td->buf, write_size);
+		BUG_ON(ret != (int)write_size);
 		ret = read_pipe(td);
-		BUG_ON(ret != sizeof(int));
+		BUG_ON(ret != (int)write_size);
 	}
 
 	return NULL;
@@ -239,6 +244,22 @@ int bench_sched_pipe(int argc, const char **argv)
 	BUG_ON(pipe2(pipe_1, flags));
 	BUG_ON(pipe2(pipe_2, flags));
 
+	/*
+	 * On custom write_size, set the pipe size to acommodate write_size
+	 */
+	if (write_size > sizeof(int) &&
+	    (fcntl(pipe_1[1], F_SETPIPE_SZ, write_size) < (int)write_size ||
+	     fcntl(pipe_2[1], F_SETPIPE_SZ, write_size) < (int)write_size)) {
+		fprintf(stderr, "--write-size %u exceeds /proc/sys/fs/pipe-max-size\n",
+			write_size);
+		return -1;
+	}
+
+	for (t = 0; t < nr_threads; t++) {
+		threads[t].buf = calloc(1, write_size);
+		BUG_ON(!threads[t].buf);
+	}
+
 	gettimeofday(&start, NULL);
 
 	for (t = 0; t < nr_threads; t++) {
@@ -287,6 +308,9 @@ int bench_sched_pipe(int argc, const char **argv)
 	gettimeofday(&stop, NULL);
 	timersub(&stop, &start, &diff);
 
+	for (t = 0; t < nr_threads; t++)
+		free(threads[t].buf);
+
 	exit_cgroup(0);
 	exit_cgroup(1);
 

---
base-commit: e98d21c170b01ddef366f023bbfcf6b31509fa83
change-id: 20260515-perf_bench_pipe-bae2ec777c4b

Best regards,
--  
Breno Leitao <leitao@debian.org>