[PATCH net-next] selftests: drv-net: cope with slow env in so_txtime.py test

[PATCH net-next] selftests: drv-net: cope with slow env in so_txtime.py test

[Willem de Bruijn]

From: Willem de Bruijn <willemb@google.com>

This test was converted from shell script to drv-net test.

The new version is flaky in dbg builds on the netdev.bots dashboard.
The previous shell script had more protections to avoid these. Added
in commit a7ee79b9c455 ("selftests: net: cope with slow env in
so_txtime.sh test").

Add the same overall protection:

- Suppress so_txtime process failure if KSFT_MACHINE_SLOW

Also relax two timeouts to reduce the number of process failures
themselves

- Increase SO_RCVTIMEO to 2 seconds
- Increase process start-up stabilization to 2 seconds

Delays were experimentally arrived at while running with vng
built with kernel/configs/debug.config

Fixes: 5c6baef3885c ("selftests: drv-net: convert so_txtime to drv-net")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/netdev/20260510174219.74aeee6d@kernel.org/
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
 tools/testing/selftests/drivers/net/so_txtime.c  | 10 ++++++++--
 tools/testing/selftests/drivers/net/so_txtime.py | 11 +++++++++--
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/so_txtime.c b/tools/testing/selftests/drivers/net/so_txtime.c
index b6930883569b..75f3beef13d9 100644
--- a/tools/testing/selftests/drivers/net/so_txtime.c
+++ b/tools/testing/selftests/drivers/net/so_txtime.c
@@ -38,6 +38,7 @@
 static int	cfg_clockid	= CLOCK_TAI;
 static uint16_t	cfg_port	= 8000;
 static int	cfg_variance_us	= 4000;
+static bool	cfg_machine_slow;
 static uint64_t	cfg_start_time_ns;
 static int	cfg_mark;
 static bool	cfg_rx;
@@ -142,7 +143,7 @@ static void do_recv_one(int fdr, struct timed_send *ts)
 
 	if (llabs(tstop - texpect) > cfg_variance_us) {
 		fprintf(stderr, "exceeds variance (%d us)\n", cfg_variance_us);
-		if (!getenv("KSFT_MACHINE_SLOW"))
+		if (!cfg_machine_slow)
 			errors++;
 	}
 }
@@ -263,7 +264,7 @@ static void start_time_wait(void)
 	now = gettime_ns(CLOCK_REALTIME);
 	if (cfg_start_time_ns < now) {
 		fprintf(stderr, "FAIL: start time already passed\n");
-		if (!getenv("KSFT_MACHINE_SLOW"))
+		if (!cfg_machine_slow)
 			errors++;
 		return;
 	}
@@ -326,6 +327,9 @@ static int setup_rx(struct sockaddr *addr, socklen_t alen)
 	if (bind(fd, addr, alen))
 		error(1, errno, "bind");
 
+	if (cfg_machine_slow)
+		tv.tv_sec = 2;
+
 	if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
 		error(1, errno, "setsockopt rcv timeout");
 
@@ -512,6 +516,8 @@ static void parse_opts(int argc, char **argv)
 	setup_sockaddr(domain, saddr, &cfg_src_addr);
 
 	cfg_num_pkt = parse_io(argv[optind], cfg_buf);
+
+	cfg_machine_slow = getenv("KSFT_MACHINE_SLOW");
 }
 
 int main(int argc, char **argv)
diff --git a/tools/testing/selftests/drivers/net/so_txtime.py b/tools/testing/selftests/drivers/net/so_txtime.py
index 5b54ce76dff4..e7de8fe22c1e 100755
--- a/tools/testing/selftests/drivers/net/so_txtime.py
+++ b/tools/testing/selftests/drivers/net/so_txtime.py
@@ -6,6 +6,7 @@
 Test delivery time in FQ and ETF qdiscs.
 """
 
+import os
 import time
 
 from lib.py import ksft_exit, ksft_run, ksft_variants
@@ -15,17 +16,23 @@ from lib.py import NetDrvEpEnv, bkg, cmd, defer, tc
 
 def test_so_txtime(cfg, clockid, ipver, args_tx, args_rx, expect_success):
     """Main function. Run so_txtime as sender and receiver."""
+    slow_machine = os.environ.get('KSFT_MACHINE_SLOW')
+
     bin_path = cfg.test_dir / "so_txtime"
 
-    tstart = time.time_ns() + 200_000_000
+    tstart = time.time_ns() + (2000_000_000 if slow_machine else 200_000_000)
 
     cmd_addr = f"-S {cfg.addr_v[ipver]} -D {cfg.remote_addr_v[ipver]}"
     cmd_base = f"{bin_path} -{ipver} -c {clockid} -t {tstart} {cmd_addr}"
     cmd_rx = f"{cmd_base} {args_rx} -r"
     cmd_tx = f"{cmd_base} {args_tx}"
 
+    expect_fail = not expect_success
+    if slow_machine:
+        expect_success = False
+
     with bkg(cmd_rx, host=cfg.remote, fail=expect_success,
-             expect_fail=(not expect_success), exit_wait=True):
+             expect_fail=expect_fail, exit_wait=True):
         cmd(cmd_tx)
 
 
-- 
2.54.0.563.g4f69b47b94-goog