[PATCH] release/checks/integration: handle partial sends

[PATCH] release/checks/integration: handle partial sends

[Alyssa Ross]

Sometimes we see a test failure that looks like this:

	unexpected connection data: qemu-system-aarch64: terminating on signal 15 from pid 184 ()

I think this is because, now that the nc command in the networking
integration test has a timeout, it's possible for it to time out after
having opened the connection, but before having written all its input
to it.  Therefore, ignore connections that send a prefix of the
expected data (including nothing), and just wait for the next
connection rather than failing if that happens.

Closes: https://spectrum-os.org/lists/archives/spectrum-devel/875xbl33vw.fsf@alyssa.is/
Fixes: c61b297 ("release/checks/integration: add nc timeout")
Signed-off-by: Alyssa Ross <hi@alyssa.is>
---
Please test!  It's difficult to know if I've solved the problem for 
real, since it happens transiently.

 release/checks/integration/networking.c | 49 +++++++++++++++----------
 1 file changed, 30 insertions(+), 19 deletions(-)

diff --git a/release/checks/integration/networking.c b/release/checks/integration/networking.c
index 97d7895..a445af1 100644
--- a/release/checks/integration/networking.c
+++ b/release/checks/integration/networking.c
@@ -57,32 +57,43 @@ static int setup_server(void)
 
 static void expect_connection(int listener)
 {
-	int conn_fd;
-	FILE *conn;
+	int conn, r;
 	char msg[7];
 	size_t len;
 
-	fputs("waiting for server connection\n", stderr);
-	if ((conn_fd = accept(listener, nullptr, nullptr)) == -1) {
-		perror("accept");
-		exit(EXIT_FAILURE);
-	}
-	fputs("accepted connection!\n", stderr);
-	if (!(conn = fdopen(conn_fd, "r"))) {
-		perror("fdopen(server connection)");
-		exit(EXIT_FAILURE);
-	}
+	for (;;) {
+		len = 0;
 
-	len = fread(msg, 1, sizeof msg, conn);
-	if (len != 6 || memcmp("hello\n", msg, 6)) {
-		if (ferror(conn))
-			perror("fread(server connection)");
-		else
+		fputs("waiting for server connection\n", stderr);
+		if ((conn = accept(listener, nullptr, nullptr)) == -1) {
+			perror("accept");
+			exit(EXIT_FAILURE);
+		}
+		fputs("accepted connection!\n", stderr);
+
+		for (;;) {
+			r = read(conn, msg + len, sizeof msg - len);
+			if (r == -1) {
+				perror("read");
+				exit(EXIT_FAILURE);
+			}
+			if (r == 0)
+				break;
+			len += r;
+		}
+
+		if (memcmp("hello\n", msg, len) || len > 6) {
 			fprintf(stderr, "unexpected connection data: %.*s",
 			        (int)len, msg);
-		exit(EXIT_FAILURE);
+			exit(EXIT_FAILURE);
+		}
+
+		// If connection was disconnect partway through, try again.
+		if (len < 6)
+			continue;
+
+		return;
 	}
-	fclose(conn);
 }
 
 static void drain_connections(int listener)

base-commit: 067c6a5d50971242f9cb8ac0ac76e20d88a9b5c1
-- 
2.51.0

Re: [PATCH] release/checks/integration: handle partial sends

[Yureka]

Thanks for looking into this.

On 11/29/25 17:35, Alyssa Ross wrote:
> Sometimes we see a test failure that looks like this:
>
> unexpected connection data: qemu-system-aarch64: terminating on signal 
> 15 from pid 184 ()
>
> I think this is because, now that the nc command in the networking
> integration test has a timeout, it's possible for it to time out after
> having opened the connection, but before having written all its input
> to it. Therefore, ignore connections that send a prefix of the
> expected data (including nothing), and just wait for the next
> connection rather than failing if that happens.
>
> Closes: 
> https://spectrum-os.org/lists/archives/spectrum-devel/875xbl33vw.fsf@alyssa.is/
> Fixes: c61b297 ("release/checks/integration: add nc timeout")
> Signed-off-by: Alyssa Ross <hi@alyssa.is>
> ---
> Please test! It's difficult to know if I've solved the problem for
> real, since it happens transiently.
>
> release/checks/integration/networking.c | 49 +++++++++++++++----------
> 1 file changed, 30 insertions(+), 19 deletions(-)
>
> diff --git a/release/checks/integration/networking.c 
> b/release/checks/integration/networking.c
> index 97d7895..a445af1 100644
> --- a/release/checks/integration/networking.c
> +++ b/release/checks/integration/networking.c
> @@ -57,32 +57,43 @@ static int setup_server(void)
> static void expect_connection(int listener)
> {
> - int conn_fd;
> - FILE *conn;
> + int conn, r;
> char msg[7];
> size_t len;
> - fputs("waiting for server connection\n", stderr);
> - if ((conn_fd = accept(listener, nullptr, nullptr)) == -1) {
> - perror("accept");
> - exit(EXIT_FAILURE);
> - }
> - fputs("accepted connection!\n", stderr);
> - if (!(conn = fdopen(conn_fd, "r"))) {
> - perror("fdopen(server connection)");
> - exit(EXIT_FAILURE);
> - }
> + for (;;) {
> + len = 0;
> - len = fread(msg, 1, sizeof msg, conn);
> - if (len != 6 || memcmp("hello\n", msg, 6)) {
> - if (ferror(conn))
> - perror("fread(server connection)");
> - else
> + fputs("waiting for server connection\n", stderr);
> + if ((conn = accept(listener, nullptr, nullptr)) == -1) {
> + perror("accept");
> + exit(EXIT_FAILURE);
> + }
> + fputs("accepted connection!\n", stderr);
> +
> + for (;;) {
> + r = read(conn, msg + len, sizeof msg - len);
> + if (r == -1) {
> + perror("read");
> + exit(EXIT_FAILURE);
> + }
> + if (r == 0)
> + break;
> + len += r;
> + }
> +
> + if (memcmp("hello\n", msg, len) || len > 6) {
> fprintf(stderr, "unexpected connection data: %.*s",
> (int)len, msg);
> - exit(EXIT_FAILURE);
> + exit(EXIT_FAILURE);
> + }
> +
> + // If connection was disconnect partway through, try again.
> + if (len < 6)
> + continue;
> +
> + return;
> }
> - fclose(conn);

Is it intentional that the connection is never closed?

> }
> static void drain_connections(int listener)
>
> base-commit: 067c6a5d50971242f9cb8ac0ac76e20d88a9b5c1

Re: [PATCH] release/checks/integration: handle partial sends

[Alyssa Ross]

[-- Attachment #1: Type: text/plain, Size: 2998 bytes --]

Yureka <yuka@yuka.dev> writes:

> Thanks for looking into this.
>
> On 11/29/25 17:35, Alyssa Ross wrote:
>> Sometimes we see a test failure that looks like this:
>>
>> unexpected connection data: qemu-system-aarch64: terminating on signal 
>> 15 from pid 184 ()
>>
>> I think this is because, now that the nc command in the networking
>> integration test has a timeout, it's possible for it to time out after
>> having opened the connection, but before having written all its input
>> to it. Therefore, ignore connections that send a prefix of the
>> expected data (including nothing), and just wait for the next
>> connection rather than failing if that happens.
>>
>> Closes: 
>> https://spectrum-os.org/lists/archives/spectrum-devel/875xbl33vw.fsf@alyssa.is/
>> Fixes: c61b297 ("release/checks/integration: add nc timeout")
>> Signed-off-by: Alyssa Ross <hi@alyssa.is>
>> ---
>> Please test! It's difficult to know if I've solved the problem for
>> real, since it happens transiently.
>>
>> release/checks/integration/networking.c | 49 +++++++++++++++----------
>> 1 file changed, 30 insertions(+), 19 deletions(-)
>>
>> diff --git a/release/checks/integration/networking.c 
>> b/release/checks/integration/networking.c
>> index 97d7895..a445af1 100644
>> --- a/release/checks/integration/networking.c
>> +++ b/release/checks/integration/networking.c
>> @@ -57,32 +57,43 @@ static int setup_server(void)
>> static void expect_connection(int listener)
>> {
>> - int conn_fd;
>> - FILE *conn;
>> + int conn, r;
>> char msg[7];
>> size_t len;
>> - fputs("waiting for server connection\n", stderr);
>> - if ((conn_fd = accept(listener, nullptr, nullptr)) == -1) {
>> - perror("accept");
>> - exit(EXIT_FAILURE);
>> - }
>> - fputs("accepted connection!\n", stderr);
>> - if (!(conn = fdopen(conn_fd, "r"))) {
>> - perror("fdopen(server connection)");
>> - exit(EXIT_FAILURE);
>> - }
>> + for (;;) {
>> + len = 0;
>> - len = fread(msg, 1, sizeof msg, conn);
>> - if (len != 6 || memcmp("hello\n", msg, 6)) {
>> - if (ferror(conn))
>> - perror("fread(server connection)");
>> - else
>> + fputs("waiting for server connection\n", stderr);
>> + if ((conn = accept(listener, nullptr, nullptr)) == -1) {
>> + perror("accept");
>> + exit(EXIT_FAILURE);
>> + }
>> + fputs("accepted connection!\n", stderr);
>> +
>> + for (;;) {
>> + r = read(conn, msg + len, sizeof msg - len);
>> + if (r == -1) {
>> + perror("read");
>> + exit(EXIT_FAILURE);
>> + }
>> + if (r == 0)
>> + break;
>> + len += r;
>> + }
>> +
>> + if (memcmp("hello\n", msg, len) || len > 6) {
>> fprintf(stderr, "unexpected connection data: %.*s",
>> (int)len, msg);
>> - exit(EXIT_FAILURE);
>> + exit(EXIT_FAILURE);
>> + }
>> +
>> + // If connection was disconnect partway through, try again.
>> + if (len < 6)
>> + continue;
>> +
>> + return;
>> }
>> - fclose(conn);
>
> Is it intentional that the connection is never closed?

It is not, thanks!

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 227 bytes --]