selftests/bpf: make tcp_rtt test more robust to failures
Subsystems (5)
PATCH v2 1/1 selftests/bpf: make tcp_rtt test more robust to failures
Switch to non-blocking accept and wait for server thread to exit before proceeding. I noticed that sometimes tcp_rtt server thread failure would "spill over" into other tests (that would run after tcp_rtt), probably just because server thread exits much later and tcp_rtt doesn't wait for it.
v1->v2:
- add usleep() while waiting on initial non-blocking accept() (Stanislav);
--- .../selftests/bpf/prog_tests/tcp_rtt.c | 32 ++++++++++++------- 1 file changed, 20 insertions(+), 12 deletions(-)
tools/testing/selftests/bpf/prog_tests/tcp_rtt.c +20 -12
@@ -188,7 +188,7 @@ static int start_server(void) };int fd; - fd =socket (AF_INET ,SOCK_STREAM ,0 ); + fd =socket (AF_INET ,SOCK_STREAM |SOCK_NONBLOCK ,0 );if (fd <0 ) {log_err ("Failed to create server socket" );return -1 ;
@@ -205,6 +205,7 @@ static int start_server(void)static pthread_mutex_t server_started_mtx =PTHREAD_MUTEX_INITIALIZER ;static pthread_cond_t server_started =PTHREAD_COND_INITIALIZER ; +static volatile bool server_done = false;static void *server_thread (void *arg) {
@@ -222,23 +223,24 @@ static void *server_thread(void *arg)if (CHECK_FAIL (err <0 )) {perror ("Failed to listed on socket" ); -return NULL ; +return ERR_PTR (err); } - client_fd =accept (fd, (struct sockaddr *)&addr, &len); +while (!server_done) { + client_fd =accept (fd, (struct sockaddr *)&addr, &len); +if (client_fd ==-1 && errno ==EAGAIN ) { +usleep (50 ); +continue ; + } +break ; + }if (CHECK_FAIL (client_fd <0 )) {perror ("Failed to accept client" ); -return NULL ; +return ERR_PTR (err); } -/* Wait for the next connection (that never arrives) -* to keep this thread alive to prevent calling -* close() on client_fd. -*/ -if (CHECK_FAIL (accept (fd, (struct sockaddr *)&addr, &len) >=0 )) { -perror ("Unexpected success in second accept" ); -return NULL ; - } +while (!server_done) +usleep (50 );close (client_fd);
@@ -249,6 +251,7 @@ void test_tcp_rtt(void) {int server_fd, cgroup_fd;pthread_t tid; +void *server_res; cgroup_fd =test__join_cgroup ("/tcp_rtt" );if (CHECK_FAIL (cgroup_fd <0 ))
@@ -267,6 +270,11 @@ void test_tcp_rtt(void)pthread_mutex_unlock (&server_started_mtx);CHECK_FAIL (run_test (cgroup_fd, server_fd)); + + server_done = true; +pthread_join (tid, &server_res); +CHECK_FAIL (IS_ERR (server_res)); + close_server_fd:close (server_fd); close_cgroup_fd:
Signature · 1 line
2.17.1
Alexei Starovoitov
AppliedQuoted 6 lines · Andrii Nakryiko
Switch to non-blocking accept and wait for server thread to exit before proceeding. I noticed that sometimes
tcp_rttserver thread failure would "spill over" into other tests (that would run aftertcp_rtt), probably just because server thread exits much later andtcp_rttdoesn't wait for it.
Quoted 6 lines
v1->v2:
- addusleep()while waiting on initial non-blockingaccept()(Stanislav);Fixes 8a03222f508b ("selftests/bpf: test_progs: fix client/server race in tcp_rtt")Reviewed-by Stanislav Fomichev <[email protected]>Signed-off-by Andrii Nakryiko <[email protected]>
Applied. Thanks