Re: [bpf-next PATCH v2 3/7] bpf: sockmap sample, use fork() for send and recv

On 01/11/2018 01:08 PM, Martin KaFai Lau wrote:

On Wed, Jan 10, 2018 at 10:39:37AM -0800, John Fastabend wrote:

quoted

Currently for SENDMSG tests first send completes then recv runs. This
does not work well for large data sizes and/or many iterations. So
fork the recv and send handler so that we run both send and recv. In
the future we can add a parameter to do more than a single fork of
tx/rx.

With this we can get many GBps of data which helps exercise the
sockmap code.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
---

[...]

quoted

 static int sendmsg_test(int iov_count, int iov_buf, int cnt, int verbose)
 {
+	int txpid, rxpid, err = 0;
 	struct msg_stats s = {0};
-	int err;
-
-	err = msg_loop(c1, iov_count, iov_buf, cnt, &s, true);
-	if (err) {
-		fprintf(stderr,
-			"msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n",
-			iov_count, iov_buf, cnt, err);
-		return err;
+	int status;
+
+	errno = 0;
+
+	rxpid = fork();
+	if (rxpid == 0) {
+		err = msg_loop(p2, iov_count, iov_buf, cnt, &s, false);
+		if (err)
+			fprintf(stderr,
+				"msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
+				iov_count, iov_buf, cnt, err);
+		fprintf(stdout, "rx_sendmsg: TX_bytes %zu RX_bytes %zu\n",
+			s.bytes_sent, s.bytes_recvd);
+		shutdown(p2, SHUT_RDWR);
+		shutdown(p1, SHUT_RDWR);
+		exit(1);
+	} else if (rxpid == -1) {
+		perror("msg_loop_rx: ");
+		err = errno;

Bail out here instead of continuing the tx side?

Sure makes sense. No point in running the TX side here I guess.