@@ -49,6 +49,11 @@ struct QIOChannelSocket {
socklen_t remoteAddrLen;
ssize_t zero_copy_queued;
ssize_t zero_copy_sent;
+ /**
+ * This flag indicates whether any new data was successfully sent with
+ * zerocopy since the last qio_channel_socket_flush() call.
+ */
+ bool new_zero_copy_sent_success;
};
@@ -37,6 +37,12 @@
#define SOCKET_MAX_FDS 16
+#ifdef QEMU_MSG_ZEROCOPY
+static int qio_channel_socket_flush_internal(QIOChannel *ioc,
+ bool block,
+ Error **errp);
+#endif
+
SocketAddress *
qio_channel_socket_get_local_address(QIOChannelSocket *ioc,
Error **errp)
@@ -65,6 +71,7 @@ qio_channel_socket_new(void)
sioc->fd = -1;
sioc->zero_copy_queued = 0;
sioc->zero_copy_sent = 0;
+ sioc->new_zero_copy_sent_success = FALSE;
ioc = QIO_CHANNEL(sioc);
qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN);
@@ -566,6 +573,7 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
size_t fdsize = sizeof(int) * nfds;
struct cmsghdr *cmsg;
int sflags = 0;
+ bool zero_copy_flush_pending = TRUE;
memset(control, 0, CMSG_SPACE(sizeof(int) * SOCKET_MAX_FDS));
@@ -612,9 +620,25 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
goto retry;
case ENOBUFS:
if (flags & QIO_CHANNEL_WRITE_FLAG_ZERO_COPY) {
- error_setg_errno(errp, errno,
- "Process can't lock enough memory for using MSG_ZEROCOPY");
- return -1;
+ /**
+ * Socket error queueing may exhaust the OPTMEM limit. Try
+ * flushing the error queue once.
+ */
+ if (zero_copy_flush_pending) {
+ ret = qio_channel_socket_flush_internal(ioc, false, errp);
+ if (ret < 0) {
+ error_setg_errno(errp, errno,
+ "Zerocopy flush failed");
+ return -1;
+ }
+ zero_copy_flush_pending = FALSE;
+ goto retry;
+ } else {
+ error_setg_errno(errp, errno,
+ "Process can't lock enough memory for "
+ "using MSG_ZEROCOPY");
+ return -1;
+ }
}
break;
}
@@ -725,8 +749,9 @@ static ssize_t qio_channel_socket_writev(QIOChannel *ioc,
#ifdef QEMU_MSG_ZEROCOPY
-static int qio_channel_socket_flush(QIOChannel *ioc,
- Error **errp)
+static int qio_channel_socket_flush_internal(QIOChannel *ioc,
+ bool block,
+ Error **errp)
{
QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
struct msghdr msg = {};
@@ -734,7 +759,6 @@ static int qio_channel_socket_flush(QIOChannel *ioc,
struct cmsghdr *cm;
char control[CMSG_SPACE(sizeof(*serr))];
int received;
- int ret;
if (sioc->zero_copy_queued == sioc->zero_copy_sent) {
return 0;
@@ -744,16 +768,19 @@ static int qio_channel_socket_flush(QIOChannel *ioc,
msg.msg_controllen = sizeof(control);
memset(control, 0, sizeof(control));
- ret = 1;
-
while (sioc->zero_copy_sent < sioc->zero_copy_queued) {
received = recvmsg(sioc->fd, &msg, MSG_ERRQUEUE);
if (received < 0) {
switch (errno) {
case EAGAIN:
- /* Nothing on errqueue, wait until something is available */
- qio_channel_wait(ioc, G_IO_ERR);
- continue;
+ if (block) {
+ /* Nothing on errqueue, wait until something is
+ * available.
+ */
+ qio_channel_wait(ioc, G_IO_ERR);
+ continue;
+ }
+ return 0;
case EINTR:
continue;
default:
@@ -791,13 +818,32 @@ static int qio_channel_socket_flush(QIOChannel *ioc,
/* No errors, count successfully finished sendmsg()*/
sioc->zero_copy_sent += serr->ee_data - serr->ee_info + 1;
- /* If any sendmsg() succeeded using zero copy, return 0 at the end */
+ /* If any sendmsg() succeeded using zero copy, mark zerocopy success */
if (serr->ee_code != SO_EE_CODE_ZEROCOPY_COPIED) {
- ret = 0;
+ sioc->new_zero_copy_sent_success = TRUE;
}
}
- return ret;
+ return 0;
+}
+
+static int qio_channel_socket_flush(QIOChannel *ioc,
+ Error **errp)
+{
+ QIOChannelSocket *sioc = QIO_CHANNEL_SOCKET(ioc);
+ int ret;
+
+ ret = qio_channel_socket_flush_internal(ioc, true, errp);
+ if (ret < 0) {
+ return ret;
+ }
+
+ if (sioc->new_zero_copy_sent_success) {
+ sioc->new_zero_copy_sent_success = FALSE;
+ return 0;
+ }
+
+ return 1;
}
#endif /* QEMU_MSG_ZEROCOPY */
We allocate extra metadata SKBs in case of a zerocopy send. This metadata memory is accounted for in the OPTMEM limit. If there is any error while sending zerocopy packets or if zerocopy is skipped, these metadata SKBs are queued in the socket error queue. This error queue is freed when userspace reads it. Usually, if there are continuous failures, we merge the metadata into a single SKB and free another one. As a result, it never exceeds the OPTMEM limit. However, if there is any out-of-order processing or intermittent zerocopy failures, this error chain can grow significantly, exhausting the OPTMEM limit. As a result, all new sendmsg requests fail to allocate any new SKB, leading to an ENOBUF error. Depending on the amount of data queued before the flush (i.e., large live migration iterations), even large OPTMEM limits are prone to failure. To work around this, if we encounter an ENOBUF error with a zerocopy sendmsg, we flush the error queue and retry once more. V2: 1. Removed the dirty_sync_missed_zero_copy migration stat. 2. Made the call to qio_channel_socket_flush_internal() from qio_channel_socket_writev() non-blocking. V3: 1. Add the dirty_sync_missed_zero_copy migration stat again. Signed-off-by: Manish Mishra <manish.mishra@nutanix.com> --- include/io/channel-socket.h | 5 +++ io/channel-socket.c | 74 ++++++++++++++++++++++++++++++------- 2 files changed, 65 insertions(+), 14 deletions(-)