On macOS we need to increase unix 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.

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': 255}}"

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>
---
 nbd/client-connection.c |  3 +++
 nbd/common.c            | 25 +++++++++++++++++++++++++
 nbd/nbd-internal.h      |  5 +++++
 nbd/server.c            |  2 ++
 4 files changed, 35 insertions(+)

diff --git a/nbd/client-connection.c b/nbd/client-connection.c
index b11e266807..79ea97e4cc 100644
--- a/nbd/client-connection.c
+++ b/nbd/client-connection.c
@@ -31,6 +31,8 @@
 #include "qapi/clone-visitor.h"
 #include "qemu/coroutine.h"
 
+#include "nbd/nbd-internal.h"
+
 struct NBDClientConnection {
     /* Initialization constants, never change */
     SocketAddress *saddr; /* address to connect to */
@@ -140,6 +142,7 @@ static int nbd_connect(QIOChannelSocket *sioc, SocketAddress *addr,
         return ret;
     }
 
+    nbd_set_socket_send_buffer(sioc);
     qio_channel_set_delay(QIO_CHANNEL(sioc), false);
 
     if (!info) {
diff --git a/nbd/common.c b/nbd/common.c
index 589a748cfe..9436e9d1d1 100644
--- a/nbd/common.c
+++ b/nbd/common.c
@@ -18,6 +18,9 @@
 
 #include "qemu/osdep.h"
 #include "trace.h"
+#include "io/channel-socket.h"
+#include "qapi/error.h"
+#include "qemu/units.h"
 #include "nbd-internal.h"
 
 /* Discard length bytes from channel.  Return -errno on failure and 0 on
@@ -264,3 +267,25 @@ const char *nbd_mode_lookup(NBDMode mode)
         return "<unknown>";
     }
 }
+
+/*
+ * Testing shows that 2m send buffer is optimal. Changing the receive buffer
+ * size has no effect on performance.
+ */
+#if defined(__APPLE__)
+#define UNIX_STREAM_SOCKET_SEND_BUFFER_SIZE (2 * MiB)
+#endif
+
+void nbd_set_socket_send_buffer(QIOChannelSocket *sioc)
+{
+#ifdef UNIX_STREAM_SOCKET_SEND_BUFFER_SIZE
+    if (sioc->localAddr.ss_family == AF_UNIX) {
+        size_t size = UNIX_STREAM_SOCKET_SEND_BUFFER_SIZE;
+        Error *errp = NULL;
+
+        if (qio_channel_socket_set_send_buffer(sioc, size, &errp) < 0) {
+            warn_report_err(errp);
+        }
+    }
+#endif /* UNIX_STREAM_SOCKET_SEND_BUFFER_SIZE */
+}
diff --git a/nbd/nbd-internal.h b/nbd/nbd-internal.h
index 715d92d6ef..6bafeef5dd 100644
--- a/nbd/nbd-internal.h
+++ b/nbd/nbd-internal.h
@@ -74,4 +74,9 @@ static inline int nbd_write(QIOChannel *ioc, const void *buffer, size_t size,
 
 int nbd_drop(QIOChannel *ioc, size_t size, Error **errp);
 
+/* nbd_set_socket_send_buffer
+ * Set the socket send buffer size for optimal performance.
+ */
+void nbd_set_socket_send_buffer(QIOChannelSocket *sioc);
+
 #endif
diff --git a/nbd/server.c b/nbd/server.c
index 2076fb2666..d242be9811 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -3291,6 +3291,8 @@ void nbd_client_new(QIOChannelSocket *sioc,
     client->close_fn = close_fn;
     client->owner = owner;
 
+    nbd_set_socket_send_buffer(sioc);
+
     co = qemu_coroutine_create(nbd_co_client_start, client);
     qemu_coroutine_enter(co);
 }
-- 
2.39.5 (Apple Git-154)

On Sat, May 17, 2025 at 11:11:53PM +0300, Nir Soffer wrote:
> On macOS we need to increase unix 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.
> 
> 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': 255}}"
> 
> 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>
> ---
>  nbd/client-connection.c |  3 +++
>  nbd/common.c            | 25 +++++++++++++++++++++++++
>  nbd/nbd-internal.h      |  5 +++++
>  nbd/server.c            |  2 ++
>  4 files changed, 35 insertions(+)

Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>


With regards,
Daniel
-- 
|: https://berrange.com      -o-    https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org         -o-            https://fstop138.berrange.com :|
|: https://entangle-photo.org    -o-    https://www.instagram.com/dberrange :|