[LTP] [PATCH v2] pipe13: Scale child reap window with LTP_TIMEOUT_MUL

[Stephen Bertram via ltp <ltp@lists.linux.it>]

The post-close wait used a fixed 1000000 us cap on exponential backoff.
Scale that cap with tst_multiply_timeout() so debug
kernels and LTP_TIMEOUT_MUL apply, fixing failures under parallel
Kirk workers without changing default behavior on non-debug systems.

Before (only with case 100):

pipe13.c:50: TINFO: Creating 100 child processes
pipe13.c:81: TINFO: pid 435007 still sleeps
...
pipe13.c:81: TINFO: pid 435300 still sleeps
pipe13.c:89: TFAIL: Closed pipe didn't wake up everyone
The list varied but sometimes up to 20 would remained asleep.

Test is passing after using TST_RETRY_FN_EXP_BACKOFF() so timeout
scaling follows the standard LTP path (tst_multiply_timeout, debug
kconfig, LTP_TIMEOUT_MUL).

The failure before would happen, when using 4 paralell workers
on a debug kernel, about 1 to 2 times when iterated 5 times.
Tested on aarch64 debug+PREEMPT_RT: kirk -w 4 pipe13 -i 100, 400 runs,
0 fail.

Signed-off-by: Stephen Bertram <sbertram@redhat.com>
---
 testcases/kernel/syscalls/pipe/pipe13.c | 44 +++++++++++++++----------
 1 file changed, 27 insertions(+), 17 deletions(-)

diff --git a/testcases/kernel/syscalls/pipe/pipe13.c b/testcases/kernel/syscalls/pipe/pipe13.c
index 5d76e1f00..7f7685a2c 100644
--- a/testcases/kernel/syscalls/pipe/pipe13.c
+++ b/testcases/kernel/syscalls/pipe/pipe13.c
@@ -26,6 +26,28 @@ static unsigned int tcases[] = {
 };
 
 static int fds[2];
+static unsigned int reap_child_num;
+static unsigned int reap_count;
+static int *reap_pids;
+
+static int reap_children_once(void)
+{
+	unsigned int i;
+	int ret;
+
+	while ((ret = waitpid(-1, NULL, WNOHANG)) > 0) {
+		reap_count++;
+		for (i = 0; i < reap_child_num; i++) {
+			if (reap_pids[i] == ret)
+				reap_pids[i] = 0;
+		}
+	}
+	if (ret < 0 && errno != ECHILD)
+		tst_brk(TBROK | TERRNO, "waitpid()");
+	return reap_count;
+}
+
+#define ALL_CHILDREN_REAPED(cnt) ((unsigned int)(cnt) >= reap_child_num)
 
 static void do_child(unsigned int i)
 {
@@ -41,8 +63,7 @@ static void do_child(unsigned int i)
 
 static void verify_pipe(unsigned int n)
 {
-	int ret;
-	unsigned int i, cnt = 0, sleep_us = 1, fail = 0;
+	unsigned int i, fail = 0;
 	unsigned int child_num = tcases[n];
 	int pid[child_num];
 
@@ -60,21 +81,10 @@ static void verify_pipe(unsigned int n)
 	SAFE_CLOSE(fds[0]);
 	SAFE_CLOSE(fds[1]);
 
-	while (cnt < child_num && sleep_us < 1000000) {
-		ret = waitpid(-1, NULL, WNOHANG);
-		if (ret < 0)
-			tst_brk(TBROK | TERRNO, "waitpid()");
-		if (ret > 0) {
-			cnt++;
-			for (i = 0; i < child_num; i++) {
-				if (pid[i] == ret)
-					pid[i] = 0;
-			}
-			continue;
-		}
-		usleep(sleep_us);
-		sleep_us *= 2;
-	}
+	reap_child_num = child_num;
+	reap_count = 0;
+	reap_pids = pid;
+	TST_RETRY_FN_EXP_BACKOFF(reap_children_once(), ALL_CHILDREN_REAPED, 1);
 
 	for (i = 0; i < child_num; i++) {
 		if (pid[i]) {
-- 
2.54.0


-- 
Mailing list info: https://lists.linux.it/listinfo/ltp