Using hard-coded constant timeout to wait for some expected
event is deemed to fail sooner or later, especially in slow
env.
Our CI has spotted another of such race:
# TEST: ipv6: cleanup of cached exceptions - nexthop objects [FAIL]
# can't delete veth device in a timely manner, PMTU dst likely leaked
Replace the crude sleep with a loop looking for the expected condition
at low interval for a much longer range.
Fixes: b3cc4f8a8a41 ("selftests: pmtu: add explicit tests for PMTU exceptions cleanup")
Signed-off-by: Paolo Abeni <pabeni@xxxxxxxxxx>
---
tools/testing/selftests/net/pmtu.sh | 18 +++++++++++++-----
1 file changed, 13 insertions(+), 5 deletions(-)
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index f0febc19baae..d65fdd407d73 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -1957,6 +1957,13 @@ check_command() {
return 0
}
+check_running() {
+ pid=${1}
+ cmd=${2}
+
+ [ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "{cmd}" ]
+}
+
test_cleanup_vxlanX_exception() {
outer="${1}"
encap="vxlan"
@@ -1987,11 +1994,12 @@ test_cleanup_vxlanX_exception() {
${ns_a} ip link del dev veth_A-R1 &
iplink_pid=$!
- sleep 1
- if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then
- err " can't delete veth device in a timely manner, PMTU dst likely leaked"
- return 1
- fi
+ for i in $(seq 1 20); do
+ check_running ${iplink_pid} "iplinkdeldevveth_A-R1" || return 0
+ sleep 0.1
+ done
+ err " can't delete veth device in a timely manner, PMTU dst likely leaked"
+ return 1
}
test_cleanup_ipv6_exception() {
--
2.43.0
