perftest: fix premature exit when select() is interrupted by SIGALRM

The perftest framework makes extensive use of alarm() to control test
duration (--duration) and to schedule periodic tasks.

Functions such as `run_iter_bw()`, `run_iter_lat_send()`, and
`run_iter_bi()` install a handler via `signal(SIGALRM, catch_alarm)`
when the -D option is used, and then set an alarm.

In `run_iter_bw_server()` and `run_iter_bi()`, a watchdog is also
installed in iterations mode via `signal(SIGALRM, check_alive)`
followed by `alarm(60)` to detect stalled tests.

In the problematic case, `run_iter_bi()` with the -e option invokes
`ctx_notify_send_recv_events()`, which performs a `select()` on two file
descriptors:

`ctx->recv_channel->fd` — CQ receive completion channel

`ctx->send_channel->fd` — CQ send completion channel

When a completion event is generated, the kernel marks the corresponding
file descriptor readable and `select()` returns.

However, due to low processing speed on the some NICs, no completion
event is generated within 60 seconds(test case is not finished under
high pressure test). The watchdog `alarm()` fires, delivering SIGALRM,
which interrupts the blocking `select()` call. The function then exits
with an error instead of retrying.

This behavior exposes a robustness issue in perftest: SIGALRM in this
context is meant only as a check-alive signal, not as a fatal condition.
A `select()` call interrupted by SIGALRM should be restarted rather than
causing an unexpected termination.

This patch updates perftest to properly handle EINTR by retrying
`select()` when it is interrupted by SIGALRM, ensuring correct behavior
even under slow device processing conditions.

Signed-off-by: Ruizhe Zhou <zhouruizhe@resnics.com>

Author: SherrinZhou

src/perftest_communication.c

@@ -1294,9 +1294,10 @@ int rdma_client_connect(struct pingpong_context *ctx,struct perftest_parameters
 	}
 
 	if (event->event != RDMA_CM_EVENT_ESTABLISHED) {
-		fprintf(stderr, "Unexpected CM event bl blka %d\n", event->event);
+		fprintf(stderr, "Unexpected CM event bl blka %s; error: %d.\n",
+		rdma_event_str(event->event), event->status);
 		rdma_ack_cm_event(event);
-                return FAILURE;
+		return FAILURE;
 	}
 
 	if (user_param->connection_type == UD) {

src/perftest_resources.c

@@ -110,6 +110,7 @@ static __always_inline int poll_completions(
 struct perftest_parameters* duration_param;
 struct check_alive_data check_alive_data;
 
+volatile sig_atomic_t g_sigalarm_fired = 0;
 
 /******************************************************************************
  * Beginning
@@ -6621,6 +6622,7 @@ uint16_t ctx_get_local_lid(struct ibv_context *context,int port)
  ******************************************************************************/
 void catch_alarm(int sig)
 {
+	g_sigalarm_fired = 1;
 	switch (duration_param->state) {
 		case START_STATE:
 			duration_param->state = SAMPLE_STATE;
@@ -6648,6 +6650,7 @@ void catch_alarm(int sig)
 
 void check_alive(int sig)
 {
+	g_sigalarm_fired = 1;
 	if (check_alive_data.current_totrcnt > check_alive_data.last_totrcnt) {
 		check_alive_data.last_totrcnt = check_alive_data.current_totrcnt;
 		alarm(60);

src/perftest_resources.h

@@ -72,6 +72,9 @@
 #include <sys/socket.h>
 #include <netdb.h>
 #include <fcntl.h>
+#include <string.h>
+#include <errno.h>
+#include <signal.h>
 #include "perftest_parameters.h"
 
 #ifdef HAVE_CUDA
@@ -201,6 +204,7 @@ static inline uint64_t build_wr_id(uint32_t wr_index, uint16_t qp_index)
 	return ((uint64_t)wr_index) | ((uint64_t)qp_index << WR_ID_QP_INDEX_OFFSET);
 }
 
+extern volatile sig_atomic_t g_sigalarm_fired;
 /******************************************************************************
  * Perftest resources Structures and data types.
  ******************************************************************************/
@@ -942,15 +946,31 @@ static __inline void increase_rem_addr(struct ibv_send_wr *wr,int size,uint64_t
 static __inline int ctx_notify_send_recv_events(struct pingpong_context *ctx)
 {
 	fd_set rfds;
+	int ret;
 
-	FD_ZERO(&rfds);
-	FD_SET(ctx->recv_channel->fd, &rfds);
-	FD_SET(ctx->send_channel->fd, &rfds);
+	do {
+		FD_ZERO(&rfds);
+		FD_SET(ctx->recv_channel->fd, &rfds);
+		FD_SET(ctx->send_channel->fd, &rfds);
 
-	if (select(MAX(ctx->recv_channel->fd,
-		       ctx->send_channel->fd) + 1,
-		   &rfds, NULL, NULL, NULL) == -1) {
-		fprintf(stderr, "Failed to get completion events\n");
+		g_sigalarm_fired = 0;
+
+		ret = select(MAX(ctx->recv_channel->fd,
+			ctx->send_channel->fd) + 1,
+			&rfds, NULL, NULL, NULL);
+
+		if (ret == -1 && errno == EINTR) {
+			if (g_sigalarm_fired) {
+				fprintf(stderr, "Confirmed: select() was interrupted by SIGALARM. Retrying...\n");
+			} else {
+				fprintf(stderr, "Warning: select() interrupted by another signal. Retrying...\n");
+			}
+		}
+
+	} while (ret == -1 && errno == EINTR);
+
+	if (ret == -1) {
+		fprintf(stderr, "Failed to get completion events: %s\n", strerror(errno));
 		return FAILURE;
 	}