On macOS we need to increase unix stream socket buffers size on the
client and server to get good performance. We set socket buffers on
macOS after connecting or accepting a client connection.  For unix
datagram socket we need different configuration that can be done later.

Testing shows that setting socket receive buffer size (SO_RCVBUF) has no
effect on performance, so we set only the send buffer size (SO_SNDBUF).
It seems to work like Linux but not documented.

Testing shows that optimal buffer size is 512k to 4 MiB, depending on
the test case. The difference is very small, so I chose 2 MiB.

I tested reading from qemu-nbd and writing to qemu-nbd with qemu-img and
computing a blkhash with nbdcopy and blksum.

To focus on NBD communication and get less noisy results, I tested
reading and writing to null-co driver. I added a read-pattern option to
the null-co driver to return data full of 0xff:

    NULL="json:{'driver': 'raw', 'file': {'driver': 'null-co', 'size': '10g', 'read-pattern': -1}}"

For testing buffer size I added an environment variable for setting the
socket buffer size.

Read from qemu-nbd via qemu-img convert. In this test buffer size of 2m
is optimal (12.6 times faster).

    qemu-nbd -r -t -e 0 -f raw -k /tmp/nbd.sock "$NULL" &
    qemu-img convert -f raw -O raw -W -n "nbd+unix:///?socket=/tmp/nbd.sock" "$NULL"

| buffer size | time    | user    | system  |
|-------------|---------|---------|---------|
|     default |  13.361 |   2.653 |   5.702 |
|       65536 |   2.283 |   0.204 |   1.318 |
|      131072 |   1.673 |   0.062 |   1.008 |
|      262144 |   1.592 |   0.053 |   0.952 |
|      524288 |   1.496 |   0.049 |   0.887 |
|     1048576 |   1.234 |   0.047 |   0.738 |
|     2097152 |   1.060 |   0.080 |   0.602 |
|     4194304 |   1.061 |   0.076 |   0.604 |

Write to qemu-nbd with qemu-img convert. In this test buffer size of 2m
is optimal (9.2 times faster).

    qemu-nbd -t -e 0 -f raw -k /tmp/nbd.sock "$NULL" &
    qemu-img convert -f raw -O raw -W -n "$NULL" "nbd+unix:///?socket=/tmp/nbd.sock"

| buffer size | time    | user    | system  |
|-------------|---------|---------|---------|
|     default |   8.063 |   2.522 |   4.184 |
|       65536 |   1.472 |   0.430 |   0.867 |
|      131072 |   1.071 |   0.297 |   0.654 |
|      262144 |   1.012 |   0.239 |   0.587 |
|      524288 |   0.970 |   0.201 |   0.514 |
|     1048576 |   0.895 |   0.184 |   0.454 |
|     2097152 |   0.877 |   0.174 |   0.440 |
|     4194304 |   0.944 |   0.231 |   0.535 |

Compute a blkhash with nbdcopy, using 4 NBD connections and 256k request
size. In this test buffer size of 4m is optimal (5.1 times faster).

    qemu-nbd -r -t -e 0 -f raw -k /tmp/nbd.sock "$NULL" &
    nbdcopy --blkhash "nbd+unix:///?socket=/tmp/nbd.sock" null:

| buffer size | time    | user    | system  |
|-------------|---------|---------|---------|
|     default |   8.624 |   5.727 |   6.507 |
|       65536 |   2.563 |   4.760 |   2.498 |
|      131072 |   1.903 |   4.559 |   2.093 |
|      262144 |   1.759 |   4.513 |   1.935 |
|      524288 |   1.729 |   4.489 |   1.924 |
|     1048576 |   1.696 |   4.479 |   1.884 |
|     2097152 |   1.710 |   4.480 |   1.763 |
|     4194304 |   1.687 |   4.479 |   1.712 |

Compute a blkhash with blksum, using 1 NBD connection and 256k read
size. In this test buffer size of 512k is optimal (10.3 times faster).

    qemu-nbd -r -t -e 0 -f raw -k /tmp/nbd.sock "$NULL" &
    blksum "nbd+unix:///?socket=/tmp/nbd.sock"

| buffer size | time    | user    | system  |
|-------------|---------|---------|---------|
|     default |  13.085 |   5.664 |   6.461 |
|       65536 |   3.299 |   5.106 |   2.515 |
|      131072 |   2.396 |   4.989 |   2.069 |
|      262144 |   1.607 |   4.724 |   1.555 |
|      524288 |   1.271 |   4.528 |   1.224 |
|     1048576 |   1.294 |   4.565 |   1.333 |
|     2097152 |   1.299 |   4.569 |   1.344 |
|     4194304 |   1.291 |   4.559 |   1.327 |

Signed-off-by: Nir Soffer <nirsof@gmail.com>
---
 io/channel-socket.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/io/channel-socket.c b/io/channel-socket.c
index 608bcf066e..06901ab694 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -21,6 +21,7 @@
 #include "qapi/error.h"
 #include "qapi/qapi-visit-sockets.h"
 #include "qemu/module.h"
+#include "qemu/units.h"
 #include "io/channel-socket.h"
 #include "io/channel-util.h"
 #include "io/channel-watch.h"
@@ -37,6 +38,33 @@
 
 #define SOCKET_MAX_FDS 16
 
+/*
+ * Testing shows that 2m send buffer gives best throuput and lowest cpu usage.
+ * Changing the receive buffer size has no effect on performance.
+ */
+#ifdef __APPLE__
+#define UNIX_STREAM_SOCKET_SEND_BUFFER_SIZE (2 * MiB)
+#endif /* __APPLE__ */
+
+static void qio_channel_socket_set_buffers(QIOChannelSocket *ioc)
+{
+    if (ioc->localAddr.ss_family == AF_UNIX) {
+        int type;
+        socklen_t type_len = sizeof(type);
+
+        if (getsockopt(ioc->fd, SOL_SOCKET, SO_TYPE, &type, &type_len) == -1) {
+            return;
+        }
+
+#ifdef UNIX_STREAM_SOCKET_SEND_BUFFER_SIZE
+        if (type == SOCK_STREAM) {
+            const int value = UNIX_STREAM_SOCKET_SEND_BUFFER_SIZE;
+            setsockopt(ioc->fd, SOL_SOCKET, SO_SNDBUF, &value, sizeof(value));
+        }
+#endif /* UNIX_STREAM_SOCKET_SEND_BUFFER_SIZE */
+    }
+}
+
 SocketAddress *
 qio_channel_socket_get_local_address(QIOChannelSocket *ioc,
                                      Error **errp)
@@ -174,6 +202,8 @@ int qio_channel_socket_connect_sync(QIOChannelSocket *ioc,
     }
 #endif
 
+    qio_channel_socket_set_buffers(ioc);
+
     qio_channel_set_feature(QIO_CHANNEL(ioc),
                             QIO_CHANNEL_FEATURE_READ_MSG_PEEK);
 
@@ -410,6 +440,8 @@ qio_channel_socket_accept(QIOChannelSocket *ioc,
     }
 #endif /* WIN32 */
 
+    qio_channel_socket_set_buffers(cioc);
+
     qio_channel_set_feature(QIO_CHANNEL(cioc),
                             QIO_CHANNEL_FEATURE_READ_MSG_PEEK);
 
-- 
2.39.5 (Apple Git-154)