aboutsummaryrefslogtreecommitdiff
path: root/migration
diff options
context:
space:
mode:
Diffstat (limited to 'migration')
-rw-r--r--migration/channel.c3
-rw-r--r--migration/migration.c52
-rw-r--r--migration/migration.h6
-rw-r--r--migration/multifd.c74
-rw-r--r--migration/multifd.h4
-rw-r--r--migration/ram.c29
-rw-r--r--migration/rdma.c1
-rw-r--r--migration/socket.c12
8 files changed, 155 insertions, 26 deletions
diff --git a/migration/channel.c b/migration/channel.c
index c6a8dcf1d7..a162d00fea 100644
--- a/migration/channel.c
+++ b/migration/channel.c
@@ -38,8 +38,7 @@ void migration_channel_process_incoming(QIOChannel *ioc)
trace_migration_set_incoming_channel(
ioc, object_get_typename(OBJECT(ioc)));
- if (s->parameters.tls_creds &&
- *s->parameters.tls_creds &&
+ if (migrate_use_tls() &&
!object_dynamic_cast(OBJECT(ioc),
TYPE_QIO_CHANNEL_TLS)) {
migration_tls_channel_process_incoming(s, ioc, &local_err);
diff --git a/migration/migration.c b/migration/migration.c
index 5a31b23bd6..31739b2af9 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -910,6 +910,10 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp)
params->multifd_zlib_level = s->parameters.multifd_zlib_level;
params->has_multifd_zstd_level = true;
params->multifd_zstd_level = s->parameters.multifd_zstd_level;
+#ifdef CONFIG_LINUX
+ params->has_zero_copy_send = true;
+ params->zero_copy_send = s->parameters.zero_copy_send;
+#endif
params->has_xbzrle_cache_size = true;
params->xbzrle_cache_size = s->parameters.xbzrle_cache_size;
params->has_max_postcopy_bandwidth = true;
@@ -1493,7 +1497,16 @@ static bool migrate_params_check(MigrationParameters *params, Error **errp)
error_prepend(errp, "Invalid mapping given for block-bitmap-mapping: ");
return false;
}
-
+#ifdef CONFIG_LINUX
+ if (params->zero_copy_send &&
+ (!migrate_use_multifd() ||
+ params->multifd_compression != MULTIFD_COMPRESSION_NONE ||
+ (params->tls_creds && *params->tls_creds))) {
+ error_setg(errp,
+ "Zero copy only available for non-compressed non-TLS multifd migration");
+ return false;
+ }
+#endif
return true;
}
@@ -1567,6 +1580,11 @@ static void migrate_params_test_apply(MigrateSetParameters *params,
if (params->has_multifd_compression) {
dest->multifd_compression = params->multifd_compression;
}
+#ifdef CONFIG_LINUX
+ if (params->has_zero_copy_send) {
+ dest->zero_copy_send = params->zero_copy_send;
+ }
+#endif
if (params->has_xbzrle_cache_size) {
dest->xbzrle_cache_size = params->xbzrle_cache_size;
}
@@ -1679,6 +1697,11 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp)
if (params->has_multifd_compression) {
s->parameters.multifd_compression = params->multifd_compression;
}
+#ifdef CONFIG_LINUX
+ if (params->has_zero_copy_send) {
+ s->parameters.zero_copy_send = params->zero_copy_send;
+ }
+#endif
if (params->has_xbzrle_cache_size) {
s->parameters.xbzrle_cache_size = params->xbzrle_cache_size;
xbzrle_cache_resize(params->xbzrle_cache_size, errp);
@@ -2563,6 +2586,26 @@ int migrate_multifd_zstd_level(void)
return s->parameters.multifd_zstd_level;
}
+#ifdef CONFIG_LINUX
+bool migrate_use_zero_copy_send(void)
+{
+ MigrationState *s;
+
+ s = migrate_get_current();
+
+ return s->parameters.zero_copy_send;
+}
+#endif
+
+int migrate_use_tls(void)
+{
+ MigrationState *s;
+
+ s = migrate_get_current();
+
+ return s->parameters.tls_creds && *s->parameters.tls_creds;
+}
+
int migrate_use_xbzrle(void)
{
MigrationState *s;
@@ -4206,6 +4249,10 @@ static Property migration_properties[] = {
DEFINE_PROP_UINT8("multifd-zstd-level", MigrationState,
parameters.multifd_zstd_level,
DEFAULT_MIGRATE_MULTIFD_ZSTD_LEVEL),
+#ifdef CONFIG_LINUX
+ DEFINE_PROP_BOOL("zero_copy_send", MigrationState,
+ parameters.zero_copy_send, false),
+#endif
DEFINE_PROP_SIZE("xbzrle-cache-size", MigrationState,
parameters.xbzrle_cache_size,
DEFAULT_MIGRATE_XBZRLE_CACHE_SIZE),
@@ -4303,6 +4350,9 @@ static void migration_instance_init(Object *obj)
params->has_multifd_compression = true;
params->has_multifd_zlib_level = true;
params->has_multifd_zstd_level = true;
+#ifdef CONFIG_LINUX
+ params->has_zero_copy_send = true;
+#endif
params->has_xbzrle_cache_size = true;
params->has_max_postcopy_bandwidth = true;
params->has_max_cpu_throttle = true;
diff --git a/migration/migration.h b/migration/migration.h
index a863032b71..485d58b95f 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -375,6 +375,12 @@ MultiFDCompression migrate_multifd_compression(void);
int migrate_multifd_zlib_level(void);
int migrate_multifd_zstd_level(void);
+#ifdef CONFIG_LINUX
+bool migrate_use_zero_copy_send(void);
+#else
+#define migrate_use_zero_copy_send() (false)
+#endif
+int migrate_use_tls(void);
int migrate_use_xbzrle(void);
uint64_t migrate_xbzrle_cache_size(void);
bool migrate_colo_enabled(void);
diff --git a/migration/multifd.c b/migration/multifd.c
index 9ea4f581e2..9282ab6aa4 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -566,19 +566,34 @@ void multifd_save_cleanup(void)
multifd_send_state = NULL;
}
-void multifd_send_sync_main(QEMUFile *f)
+int multifd_send_sync_main(QEMUFile *f)
{
int i;
+ bool flush_zero_copy;
if (!migrate_use_multifd()) {
- return;
+ return 0;
}
if (multifd_send_state->pages->num) {
if (multifd_send_pages(f) < 0) {
error_report("%s: multifd_send_pages fail", __func__);
- return;
+ return -1;
}
}
+
+ /*
+ * When using zero-copy, it's necessary to flush the pages before any of
+ * the pages can be sent again, so we'll make sure the new version of the
+ * pages will always arrive _later_ than the old pages.
+ *
+ * Currently we achieve this by flushing the zero-page requested writes
+ * per ram iteration, but in the future we could potentially optimize it
+ * to be less frequent, e.g. only after we finished one whole scanning of
+ * all the dirty bitmaps.
+ */
+
+ flush_zero_copy = migrate_use_zero_copy_send();
+
for (i = 0; i < migrate_multifd_channels(); i++) {
MultiFDSendParams *p = &multifd_send_state->params[i];
@@ -589,7 +604,7 @@ void multifd_send_sync_main(QEMUFile *f)
if (p->quit) {
error_report("%s: channel %d has already quit", __func__, i);
qemu_mutex_unlock(&p->mutex);
- return;
+ return -1;
}
p->packet_num = multifd_send_state->packet_num++;
@@ -600,6 +615,17 @@ void multifd_send_sync_main(QEMUFile *f)
ram_counters.transferred += p->packet_len;
qemu_mutex_unlock(&p->mutex);
qemu_sem_post(&p->sem);
+
+ if (flush_zero_copy && p->c) {
+ int ret;
+ Error *err = NULL;
+
+ ret = qio_channel_flush(p->c, &err);
+ if (ret < 0) {
+ error_report_err(err);
+ return -1;
+ }
+ }
}
for (i = 0; i < migrate_multifd_channels(); i++) {
MultiFDSendParams *p = &multifd_send_state->params[i];
@@ -608,6 +634,8 @@ void multifd_send_sync_main(QEMUFile *f)
qemu_sem_wait(&p->sem_sync);
}
trace_multifd_send_sync_main(multifd_send_state->packet_num);
+
+ return 0;
}
static void *multifd_send_thread(void *opaque)
@@ -615,6 +643,7 @@ static void *multifd_send_thread(void *opaque)
MultiFDSendParams *p = opaque;
Error *local_err = NULL;
int ret = 0;
+ bool use_zero_copy_send = migrate_use_zero_copy_send();
trace_multifd_send_thread_start(p->id);
rcu_register_thread();
@@ -637,9 +666,14 @@ static void *multifd_send_thread(void *opaque)
if (p->pending_job) {
uint64_t packet_num = p->packet_num;
uint32_t flags = p->flags;
- p->iovs_num = 1;
p->normal_num = 0;
+ if (use_zero_copy_send) {
+ p->iovs_num = 0;
+ } else {
+ p->iovs_num = 1;
+ }
+
for (int i = 0; i < p->pages->num; i++) {
p->normal[p->normal_num] = p->pages->offset[i];
p->normal_num++;
@@ -663,11 +697,21 @@ static void *multifd_send_thread(void *opaque)
trace_multifd_send(p->id, packet_num, p->normal_num, flags,
p->next_packet_size);
- p->iov[0].iov_len = p->packet_len;
- p->iov[0].iov_base = p->packet;
+ if (use_zero_copy_send) {
+ /* Send header first, without zerocopy */
+ ret = qio_channel_write_all(p->c, (void *)p->packet,
+ p->packet_len, &local_err);
+ if (ret != 0) {
+ break;
+ }
+ } else {
+ /* Send header using the same writev call */
+ p->iov[0].iov_len = p->packet_len;
+ p->iov[0].iov_base = p->packet;
+ }
- ret = qio_channel_writev_all(p->c, p->iov, p->iovs_num,
- &local_err);
+ ret = qio_channel_writev_full_all(p->c, p->iov, p->iovs_num, NULL,
+ 0, p->write_flags, &local_err);
if (ret != 0) {
break;
}
@@ -782,15 +826,12 @@ static bool multifd_channel_connect(MultiFDSendParams *p,
QIOChannel *ioc,
Error *error)
{
- MigrationState *s = migrate_get_current();
-
trace_multifd_set_outgoing_channel(
ioc, object_get_typename(OBJECT(ioc)),
migrate_get_current()->hostname, error);
if (!error) {
- if (s->parameters.tls_creds &&
- *s->parameters.tls_creds &&
+ if (migrate_use_tls() &&
!object_dynamic_cast(OBJECT(ioc),
TYPE_QIO_CHANNEL_TLS)) {
multifd_tls_channel_connect(p, ioc, &error);
@@ -898,6 +939,13 @@ int multifd_save_setup(Error **errp)
/* We need one extra place for the packet header */
p->iov = g_new0(struct iovec, page_count + 1);
p->normal = g_new0(ram_addr_t, page_count);
+
+ if (migrate_use_zero_copy_send()) {
+ p->write_flags = QIO_CHANNEL_WRITE_FLAG_ZERO_COPY;
+ } else {
+ p->write_flags = 0;
+ }
+
socket_send_channel_create(multifd_new_send_channel_async, p);
}
diff --git a/migration/multifd.h b/migration/multifd.h
index 7d0effcb03..4d8d89e5e5 100644
--- a/migration/multifd.h
+++ b/migration/multifd.h
@@ -20,7 +20,7 @@ int multifd_load_cleanup(Error **errp);
bool multifd_recv_all_channels_created(void);
bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp);
void multifd_recv_sync_main(void);
-void multifd_send_sync_main(QEMUFile *f);
+int multifd_send_sync_main(QEMUFile *f);
int multifd_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset);
/* Multifd Compression flags */
@@ -92,6 +92,8 @@ typedef struct {
uint32_t packet_len;
/* pointer to the packet */
MultiFDPacket_t *packet;
+ /* multifd flags for sending ram */
+ int write_flags;
/* multifd flags for each packet */
uint32_t flags;
/* size of the next packet that contains pages */
diff --git a/migration/ram.c b/migration/ram.c
index a2489a2699..5f5e37f64d 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -2909,6 +2909,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
{
RAMState **rsp = opaque;
RAMBlock *block;
+ int ret;
if (compress_threads_save_setup()) {
return -1;
@@ -2943,7 +2944,11 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
ram_control_before_iterate(f, RAM_CONTROL_SETUP);
ram_control_after_iterate(f, RAM_CONTROL_SETUP);
- multifd_send_sync_main(f);
+ ret = multifd_send_sync_main(f);
+ if (ret < 0) {
+ return ret;
+ }
+
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
qemu_fflush(f);
@@ -3052,7 +3057,11 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
out:
if (ret >= 0
&& migration_is_setup_or_active(migrate_get_current()->state)) {
- multifd_send_sync_main(rs->f);
+ ret = multifd_send_sync_main(rs->f);
+ if (ret < 0) {
+ return ret;
+ }
+
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
qemu_fflush(f);
ram_transferred_add(8);
@@ -3112,13 +3121,19 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
ram_control_after_iterate(f, RAM_CONTROL_FINISH);
}
- if (ret >= 0) {
- multifd_send_sync_main(rs->f);
- qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
- qemu_fflush(f);
+ if (ret < 0) {
+ return ret;
}
- return ret;
+ ret = multifd_send_sync_main(rs->f);
+ if (ret < 0) {
+ return ret;
+ }
+
+ qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
+ qemu_fflush(f);
+
+ return 0;
}
static void ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size,
diff --git a/migration/rdma.c b/migration/rdma.c
index ef1e65ec36..672d1958a9 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -2840,6 +2840,7 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc,
size_t niov,
int *fds,
size_t nfds,
+ int flags,
Error **errp)
{
QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc);
diff --git a/migration/socket.c b/migration/socket.c
index 05705a32d8..4fd5e85f50 100644
--- a/migration/socket.c
+++ b/migration/socket.c
@@ -74,9 +74,17 @@ static void socket_outgoing_migration(QIOTask *task,
if (qio_task_propagate_error(task, &err)) {
trace_migration_socket_outgoing_error(error_get_pretty(err));
- } else {
- trace_migration_socket_outgoing_connected(data->hostname);
+ goto out;
}
+
+ trace_migration_socket_outgoing_connected(data->hostname);
+
+ if (migrate_use_zero_copy_send() &&
+ !qio_channel_has_feature(sioc, QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY)) {
+ error_setg(&err, "Zero copy send feature not detected in host kernel");
+ }
+
+out:
migration_channel_connect(data->s, sioc, data->hostname, err);
object_unref(OBJECT(sioc));
}
generated by cgit v1.2.3 (git 2.26.2) at 2024-12-02 06:10:30 +0000