Some tests, like tc_tunnel or tc_edt, sporadically fail in CI with the
following logs:
(network_helpers.c:309: errno: Operation now in progress) \
Failed to connect to server
send_and_test_data:FAIL:connect to server unexpected error: -115
This is due to SO_RCVTIMEO and SO_SNDTIMEO being set on the client
socket (see settimeo() in client_socket()), allowing connect() to return
an error and to set errno to EINPROGRESS instead of blocking until
connection result is known. Increasing the timeout value for those tests
is likely not a good solution (and it has already been done by commit
2790db208b44 ("selftests/bpf: Improve tc_tunnel test reliability")):
they involve subtests that expect the connection to fail, and so
increasing the timeout value would increase overall test execution
duration again (not only the connection, but any socket operation).
Another solution, as documented in man 2 connect, is to poll the socket
for POLLOUT once connect has returned EINPROGRESS, and to get the actual
connection result through getsockopt: this allows to keep the overall
timeout values low for the general traffic, while letting a chance to
the connection to succeed even if CI runners are loaded.
When connect() returns EINPROGRESS, poll the socket for POLLOUT and
check the connection result via getsockopt(SO_ERROR).
Fixes: 99126abec5e5 ("bpf: selftests: A few improvements to network_helpers.c")
Signed-off-by: Alexis Lothoré (eBPF Foundation) <[email protected]>
---
I manage to reproduce the issue locally by running `./test_progs -a
tc_tunnel` in a qemu machine, while making all my CPUs busy with
stress-ng on host side; the issue happens pretty quickly. I have not
been able to reproduce the issue anymore with this fix.
---
tools/testing/selftests/bpf/network_helpers.c | 43 +++++++++++++++++++++++----
1 file changed, 38 insertions(+), 5 deletions(-)
diff --git a/tools/testing/selftests/bpf/network_helpers.c
b/tools/testing/selftests/bpf/network_helpers.c
index db935a9d9fc1..43c9e215c3f1 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -14,6 +14,7 @@
#include <sys/types.h>
#include <sys/un.h>
#include <sys/eventfd.h>
+#include <sys/poll.h>
#include <linux/err.h>
#include <linux/in.h>
@@ -40,6 +41,8 @@
#define IPPROTO_MPTCP 262
#endif
+#define CONNECTION_IN_PROGRESS_TIMEOUT_MS 3000
+
#define clean_errno() (errno == 0 ? "None" : strerror(errno))
#define log_err(MSG, ...) ({ \
int __save = errno; \
@@ -294,7 +297,8 @@ int client_socket(int family, int type,
int connect_to_addr(int type, const struct sockaddr_storage *addr, socklen_t
addrlen,
const struct network_helper_opts *opts)
{
- int fd;
+ socklen_t errlen;
+ int fd, err;
if (!opts)
opts = &default_opts;
@@ -305,13 +309,42 @@ int connect_to_addr(int type, const struct
sockaddr_storage *addr, socklen_t add
return -1;
}
- if (connect(fd, (const struct sockaddr *)addr, addrlen)) {
- log_err("Failed to connect to server");
- save_errno_close(fd);
- return -1;
+ err = connect(fd, (const struct sockaddr *)addr, addrlen);
+ if (err && errno == EINPROGRESS) {
+ struct pollfd pfd = { .fd = fd, .events = POLLOUT };
+
+ err = 0;
+ err = poll(&pfd, 1, CONNECTION_IN_PROGRESS_TIMEOUT_MS);
+
+ if (err <= 0) {
+ if (err == 0) {
+ log_err("Connection timeout");
+ errno = ETIMEDOUT;
+ } else {
+ log_err("Failed to poll connection status");
+ }
+ goto close;
+ }
+
+ errlen = sizeof(err);
+ if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &err, &errlen) < 0) {
+ log_err("Failed to getsockopt");
+ goto close;
+ }
+
+ if (err) {
+ log_err("Failed to connect to server");
+ errno = err;
+ goto close;
+ }
+ } else if (err) {
+ goto close;
}
return fd;
+close:
+ save_errno_close(fd);
+ return -1;
}
int connect_to_addr_str(int family, int type, const char *addr_str, __u16 port,
---
base-commit: 3d40a7b2210fcab4b147c006a5291d9eb4f6241f
change-id: 20260710-tc_tunnel_flaky-27e9a191bd03
Best regards,
--
Alexis Lothoré (eBPF Foundation) <[email protected]>
