Merge tag 'pull-nbd-2025-05-29' of https://repo.or.cz/qemu/ericb into staging

NBD patches for 2025-05-29

- Nir Soffer: Allow for larger Unix socket buffers in NBD
- Eric Blake: clean up mirror-sparse iotest issues

# -----BEGIN PGP SIGNATURE-----
#
# iQEzBAABCAAdFiEEccLMIrHEYCkn0vOqp6FrSiUnQ2oFAmg42T0ACgkQp6FrSiUn
# Q2r5nwgAg4ftfPBnynqL54dQ6rPKPOwW3n4Ei26EsC86OcFIGEGuCK6UGBH4bH6d
# BgyjNWY/6/t90vnXcBGVFmxrugHGh3TwOpAY08TqW0LGmpJiwX5wZTk3cVbcwXat
# ME8oYeOQwLwqboFthlgnXsUuQrKtXrkY27154ztH354x4bi5AmHi//Or4+EdFf8L
# /cCmS7uHPiHV9l1+U1hV4i1UQ+3rWHIOcfn/sKeEwPfrlyEW+2fxWUjl7qyf/Mqz
# EwCtkjz4WsFTxYyQPN6r3NyoEIZDRK27srubVhat6Fk9gOnR5Rh2MCntyxUpXmo5
# 4xD3QkVbXVRhXv6n6rjmA/Q3bvZ1oQ==
# =yjPj
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 29 May 2025 18:01:33 EDT
# gpg:                using RSA key 71C2CC22B1C4602927D2F3AAA7A16B4A2527436A
# gpg: Good signature from "Eric Blake <eblake@redhat.com>" [full]
# gpg:                 aka "Eric Blake (Free Software Programmer) <ebb9@byu.net>" [full]
# gpg:                 aka "[jpeg image of size 6874]" [full]
# Primary key fingerprint: 71C2 CC22 B1C4 6029 27D2  F3AA A7A1 6B4A 2527 436A

* tag 'pull-nbd-2025-05-29' of https://repo.or.cz/qemu/ericb:
  iotests: Filter out ZFS in several tests
  iotests: Improve mirror-sparse on ext4 and xfs
  iotests: Use disk_usage in more places
  nbd: Set unix socket send buffer on Linux
  nbd: Set unix socket send buffer on macOS
  io: Add helper for setting socket send buffer size

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

15 files changed, 105 insertions, 6 deletions

diff --git a/include/io/channel-socket.h b/include/io/channel-socket.h
index ab15577..a88cf8b 100644
--- a/include/io/channel-socket.h
+++ b/include/io/channel-socket.h
@@ -261,5 +261,18 @@ QIOChannelSocket *
 qio_channel_socket_accept(QIOChannelSocket *ioc,
                           Error **errp);
 
+/**
+ * qio_channel_socket_set_send_buffer:
+ * @ioc: the socket channel object
+ * @size: buffer size
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Set the underlying socket send buffer size.
+ *
+ * Retruns: 0 on success, or -1 on error.
+ */
+int qio_channel_socket_set_send_buffer(QIOChannelSocket *ioc,
+                                       size_t size,
+                                       Error **errp);
 
 #endif /* QIO_CHANNEL_SOCKET_H */
diff --git a/io/channel-socket.c b/io/channel-socket.c
index 088b49f..3b7ca92 100644
--- a/io/channel-socket.c
+++ b/io/channel-socket.c
@@ -78,6 +78,17 @@ qio_channel_socket_new(void)
     return sioc;
 }
 
+int qio_channel_socket_set_send_buffer(QIOChannelSocket *ioc,
+                                       size_t size,
+                                       Error **errp)
+{
+    if (setsockopt(ioc->fd, SOL_SOCKET, SO_SNDBUF, &size, sizeof(size)) < 0) {
+        error_setg_errno(errp, errno, "Unable to set socket send buffer size");
+        return -1;
+    }
+
+    return 0;
+}
 
 static int
 qio_channel_socket_set_fd(QIOChannelSocket *sioc,
diff --git a/nbd/client-connection.c b/nbd/client-connection.c
index b11e266..79ea97e 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 589a748..2a133a6 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 +267,26 @@ 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.
+ * On Linux we need to increase net.core.wmem_max to make this effective.
+ */
+#if defined(__APPLE__) || defined(__linux__)
+#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 715d92d..6bafeef 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 2076fb2..d242be9 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);
 }
diff --git a/tests/qemu-iotests/106 b/tests/qemu-iotests/106
index ae0fc46..5554843 100755
--- a/tests/qemu-iotests/106
+++ b/tests/qemu-iotests/106
@@ -40,6 +40,7 @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 _supported_fmt raw
 _supported_proto file fuse
 _supported_os Linux
+_require_disk_usage
 
 # in kB
 CREATION_SIZE=128
diff --git a/tests/qemu-iotests/125 b/tests/qemu-iotests/125
index 46279d6..708e7c5 100755
--- a/tests/qemu-iotests/125
+++ b/tests/qemu-iotests/125
@@ -35,7 +35,7 @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 get_image_size_on_host()
 {
-    echo $(($(stat -c '%b * %B' "$TEST_IMG_FILE")))
+    disk_usage "$TEST_IMG_FILE"
 }
 
 # get standard environment and filters
diff --git a/tests/qemu-iotests/175 b/tests/qemu-iotests/175
index f74f053..bbbf550 100755
--- a/tests/qemu-iotests/175
+++ b/tests/qemu-iotests/175
@@ -77,6 +77,7 @@ _supported_os Linux
 
 _default_cache_mode none
 _supported_cache_modes none directsync
+_require_disk_usage
 
 size=$((1 * 1024 * 1024))
 
diff --git a/tests/qemu-iotests/221 b/tests/qemu-iotests/221
index c463fd4..eba00b8 100755
--- a/tests/qemu-iotests/221
+++ b/tests/qemu-iotests/221
@@ -41,6 +41,7 @@ _supported_os Linux
 
 _default_cache_mode writeback
 _supported_cache_modes writeback writethrough unsafe
+_require_disk_usage
 
 echo
 echo "=== Check mapping of unaligned raw image ==="
diff --git a/tests/qemu-iotests/253 b/tests/qemu-iotests/253
index 35039d2..6da85e6 100755
--- a/tests/qemu-iotests/253
+++ b/tests/qemu-iotests/253
@@ -41,6 +41,7 @@ _supported_os Linux
 
 _default_cache_mode none
 _supported_cache_modes none directsync
+_require_disk_usage
 
 echo
 echo "=== Check mapping of unaligned raw image ==="
diff --git a/tests/qemu-iotests/308 b/tests/qemu-iotests/308
index ea81dc4..6eced3a 100755
--- a/tests/qemu-iotests/308
+++ b/tests/qemu-iotests/308
@@ -51,6 +51,7 @@ _unsupported_fmt vpc
 
 _supported_proto file # We create the FUSE export manually
 _supported_os Linux # We need /dev/urandom
+_require_disk_usage
 
 # $1: Export ID
 # $2: Options (beyond the node-name and ID)
@@ -290,7 +291,7 @@ echo '--- Try growing non-growable export ---'
 
 # Get the current size so we can write beyond the EOF
 orig_len=$(get_proto_len "$EXT_MP" "$TEST_IMG")
-orig_disk_usage=$(stat -c '%b' "$TEST_IMG")
+orig_disk_usage=$(disk_usage "$TEST_IMG")
 
 # Should fail (exports are non-growable by default)
 # (Note that qemu-io can never write beyond the EOF, so we have to use
@@ -312,7 +313,7 @@ else
     echo 'OK: Post-truncate image size is as expected'
 fi
 
-new_disk_usage=$(stat -c '%b' "$TEST_IMG")
+new_disk_usage=$(disk_usage "$TEST_IMG")
 if [ "$new_disk_usage" -gt "$orig_disk_usage" ]; then
     echo 'OK: Disk usage grew with fallocate'
 else
diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc
index 237f746..e977cb4 100644
--- a/tests/qemu-iotests/common.rc
+++ b/tests/qemu-iotests/common.rc
@@ -996,6 +996,36 @@ _require_large_file()
     rm "$FILENAME"
 }
 
+# Check whether disk_usage can be reliably used.
+_require_disk_usage()
+{
+    local unusable=false
+    # ZFS triggers known failures on this front; it does not immediately
+    # allocate files, and then aggressively compresses writes even when full
+    # allocation was requested.
+    if [ -z "$TEST_IMG_FILE" ]; then
+        FILENAME="$TEST_IMG"
+    else
+        FILENAME="$TEST_IMG_FILE"
+    fi
+    if [ -e "FILENAME" ]; then
+        echo "unwilling to overwrite existing file"
+        exit 1
+    fi
+    $QEMU_IMG create -f raw "$FILENAME" 5M > /dev/null
+    if [ $(disk_usage "$FILENAME") -gt $((1024*1024)) ]; then
+        unusable=true
+    fi
+    $QEMU_IMG create -f raw -o preallocation=full "$FILENAME" 5M > /dev/null
+    if [ $(disk_usage "$FILENAME") -lt $((4*1024*1024)) ]; then
+        unusable=true
+    fi
+    rm -f "$FILENAME"
+    if $unusable; then
+        _notrun "file system on $TEST_DIR does not handle sparse files nicely"
+    fi
+}
+
 # Check that a set of devices is available in the QEMU binary
 #
 _require_devices()
diff --git a/tests/qemu-iotests/tests/mirror-sparse b/tests/qemu-iotests/tests/mirror-sparse
index 8c52a4e..cfcaa60 100755
--- a/tests/qemu-iotests/tests/mirror-sparse
+++ b/tests/qemu-iotests/tests/mirror-sparse
@@ -40,6 +40,7 @@ cd ..
 _supported_fmt qcow2 raw  # Format of the source. dst is always raw file
 _supported_proto file
 _supported_os Linux
+_require_disk_usage
 
 echo
 echo "=== Initial image setup ==="
@@ -96,13 +97,15 @@ _send_qemu_cmd $h1 '{"execute": "blockdev-del", "arguments":
                 {"node-name": "dst"}}' 'return' \
                   | _filter_block_job_offset | _filter_block_job_len
 $QEMU_IMG compare -U -f $IMGFMT -F raw $TEST_IMG.base $TEST_IMG
+# Some filesystems can fudge allocations for various reasons; rather
+# than expecting precise 2M and 20M images, it is better to allow for slop.
 result=$(disk_usage $TEST_IMG)
-if test $result -lt $((3*1024*1024)); then
+if test $result -lt $((4*1024*1024)); then
     actual=sparse
-elif test $result = $((20*1024*1024)); then
+elif test $result -gt $((19*1024*1024)); then
     actual=full
 else
-    actual=unknown
+    actual="unexpected size ($result)"
 fi
 echo "Destination is $actual; expected $expected"
 }
diff --git a/tests/qemu-iotests/tests/write-zeroes-unmap b/tests/qemu-iotests/tests/write-zeroes-unmap
index 7cfeeaf..f90fb8e 100755
--- a/tests/qemu-iotests/tests/write-zeroes-unmap
+++ b/tests/qemu-iotests/tests/write-zeroes-unmap
@@ -32,6 +32,7 @@ cd ..
 _supported_fmt raw
 _supported_proto file
 _supported_os Linux
+_require_disk_usage
 
 create_test_image() {
     _make_test_img -f $IMGFMT 1m