#endif
enum {
- MIG_STATE_ERROR,
+ MIG_STATE_ERROR = -1,
+ MIG_STATE_NONE,
MIG_STATE_SETUP,
MIG_STATE_CANCELLED,
MIG_STATE_ACTIVE,
MigrationState *migrate_get_current(void)
{
static MigrationState current_migration = {
- .state = MIG_STATE_SETUP,
+ .state = MIG_STATE_NONE,
.bandwidth_limit = MAX_THROTTLE,
.xbzrle_cache_size = DEFAULT_MIGRATE_CACHE_SIZE,
+ .mbps = -1,
};
return ¤t_migration;
if (strstart(uri, "tcp:", &p))
tcp_start_incoming_migration(p, errp);
+#ifdef CONFIG_RDMA
+ else if (strstart(uri, "x-rdma:", &p))
+ rdma_start_incoming_migration(p, errp);
+#endif
#if !defined(WIN32)
else if (strstart(uri, "exec:", &p))
exec_start_incoming_migration(p, errp);
qemu_fclose(f);
if (ret < 0) {
fprintf(stderr, "load of migration failed\n");
- exit(0);
+ exit(EXIT_FAILURE);
}
qemu_announce_self();
DPRINTF("successfully loaded vm state\n");
int fd = qemu_get_fd(f);
assert(fd != -1);
- socket_set_nonblock(fd);
+ qemu_set_nonblock(fd);
qemu_coroutine_enter(co, f);
}
MigrationState *s = migrate_get_current();
switch (s->state) {
- case MIG_STATE_SETUP:
+ case MIG_STATE_NONE:
/* no migration has happened ever */
break;
+ case MIG_STATE_SETUP:
+ info->has_status = true;
+ info->status = g_strdup("setup");
+ info->has_total_time = false;
+ break;
case MIG_STATE_ACTIVE:
info->has_status = true;
info->status = g_strdup("active");
- s->total_time;
info->has_expected_downtime = true;
info->expected_downtime = s->expected_downtime;
+ info->has_setup_time = true;
+ info->setup_time = s->setup_time;
info->has_ram = true;
info->ram = g_malloc0(sizeof(*info->ram));
info->ram->remaining = ram_bytes_remaining();
info->ram->total = ram_bytes_total();
info->ram->duplicate = dup_mig_pages_transferred();
+ info->ram->skipped = skipped_mig_pages_transferred();
info->ram->normal = norm_mig_pages_transferred();
info->ram->normal_bytes = norm_mig_bytes_transferred();
info->ram->dirty_pages_rate = s->dirty_pages_rate;
-
+ info->ram->mbps = s->mbps;
if (blk_mig_active()) {
info->has_disk = true;
info->total_time = s->total_time;
info->has_downtime = true;
info->downtime = s->downtime;
+ info->has_setup_time = true;
+ info->setup_time = s->setup_time;
info->has_ram = true;
info->ram = g_malloc0(sizeof(*info->ram));
info->ram->remaining = 0;
info->ram->total = ram_bytes_total();
info->ram->duplicate = dup_mig_pages_transferred();
+ info->ram->skipped = skipped_mig_pages_transferred();
info->ram->normal = norm_mig_pages_transferred();
info->ram->normal_bytes = norm_mig_bytes_transferred();
+ info->ram->mbps = s->mbps;
break;
case MIG_STATE_ERROR:
info->has_status = true;
MigrationState *s = migrate_get_current();
MigrationCapabilityStatusList *cap;
- if (s->state == MIG_STATE_ACTIVE) {
+ if (s->state == MIG_STATE_ACTIVE || s->state == MIG_STATE_SETUP) {
error_set(errp, QERR_MIGRATION_ACTIVE);
return;
}
/* shared migration helpers */
-static void migrate_fd_cleanup(MigrationState *s)
+static void migrate_fd_cleanup(void *opaque)
{
+ MigrationState *s = opaque;
+
+ qemu_bh_delete(s->cleanup_bh);
+ s->cleanup_bh = NULL;
+
if (s->file) {
DPRINTF("closing file\n");
+ qemu_mutex_unlock_iothread();
+ qemu_thread_join(&s->thread);
+ qemu_mutex_lock_iothread();
+
qemu_fclose(s->file);
s->file = NULL;
}
- assert(s->fd == -1);
assert(s->state != MIG_STATE_ACTIVE);
if (s->state != MIG_STATE_COMPLETED) {
notifier_list_notify(&migration_state_notifiers, s);
}
+static void migrate_set_state(MigrationState *s, int old_state, int new_state)
+{
+ if (atomic_cmpxchg(&s->state, old_state, new_state) == new_state) {
+ trace_migrate_set_state(new_state);
+ }
+}
+
void migrate_fd_error(MigrationState *s)
{
DPRINTF("setting error state\n");
+ assert(s->file == NULL);
s->state = MIG_STATE_ERROR;
trace_migrate_set_state(MIG_STATE_ERROR);
- migrate_fd_cleanup(s);
-}
-
-static void migrate_fd_completed(MigrationState *s)
-{
- DPRINTF("setting completed state\n");
- s->state = MIG_STATE_COMPLETED;
- trace_migrate_set_state(MIG_STATE_COMPLETED);
- migrate_fd_cleanup(s);
-}
-
-static ssize_t migrate_fd_put_buffer(MigrationState *s, const void *data,
- size_t size)
-{
- ssize_t ret;
-
- if (s->state != MIG_STATE_ACTIVE) {
- return -EIO;
- }
-
- do {
- ret = s->write(s, data, size);
- } while (ret == -1 && ((s->get_error(s)) == EINTR));
-
- if (ret == -1)
- ret = -(s->get_error(s));
-
- return ret;
+ notifier_list_notify(&migration_state_notifiers, s);
}
static void migrate_fd_cancel(MigrationState *s)
{
- if (s->state != MIG_STATE_ACTIVE)
- return;
-
DPRINTF("cancelling migration\n");
- s->state = MIG_STATE_CANCELLED;
- trace_migrate_set_state(MIG_STATE_CANCELLED);
- migrate_fd_cleanup(s);
-}
-
-int migrate_fd_close(MigrationState *s)
-{
- int rc = 0;
- if (s->fd != -1) {
- rc = s->close(s);
- s->fd = -1;
- }
- return rc;
+ migrate_set_state(s, s->state, MIG_STATE_CANCELLED);
}
void add_migration_state_change_notifier(Notifier *notify)
sizeof(enabled_capabilities));
memset(s, 0, sizeof(*s));
- s->bandwidth_limit = bandwidth_limit;
s->params = *params;
memcpy(s->enabled_capabilities, enabled_capabilities,
sizeof(enabled_capabilities));
params.blk = blk;
params.shared = inc;
- if (s->state == MIG_STATE_ACTIVE) {
+ if (s->state == MIG_STATE_ACTIVE || s->state == MIG_STATE_SETUP) {
error_set(errp, QERR_MIGRATION_ACTIVE);
return;
}
if (strstart(uri, "tcp:", &p)) {
tcp_start_outgoing_migration(s, p, &local_err);
+#ifdef CONFIG_RDMA
+ } else if (strstart(uri, "x-rdma:", &p)) {
+ rdma_start_outgoing_migration(s, p, &local_err);
+#endif
#if !defined(WIN32)
} else if (strstart(uri, "exec:", &p)) {
exec_start_outgoing_migration(s, p, &local_err);
if (value < 0) {
value = 0;
}
+ if (value > SIZE_MAX) {
+ value = SIZE_MAX;
+ }
s = migrate_get_current();
s->bandwidth_limit = value;
- qemu_file_set_rate_limit(s->file, s->bandwidth_limit);
+ if (s->file) {
+ qemu_file_set_rate_limit(s->file, s->bandwidth_limit / XFER_LIMIT_RATIO);
+ }
}
void qmp_migrate_set_downtime(double value, Error **errp)
max_downtime = (uint64_t)value;
}
-int migrate_use_xbzrle(void)
+bool migrate_rdma_pin_all(void)
{
MigrationState *s;
s = migrate_get_current();
- return s->enabled_capabilities[MIGRATION_CAPABILITY_XBZRLE];
+ return s->enabled_capabilities[MIGRATION_CAPABILITY_X_RDMA_PIN_ALL];
}
-int64_t migrate_xbzrle_cache_size(void)
+bool migrate_auto_converge(void)
{
MigrationState *s;
s = migrate_get_current();
- return s->xbzrle_cache_size;
-}
-
-/* migration thread support */
-
-
-static void buffered_flush(MigrationState *s)
-{
- size_t offset = 0;
- ssize_t ret = 0;
-
- DPRINTF("flushing %zu byte(s) of data\n", s->buffer_size);
-
- if (qemu_file_get_error(s->file)) {
- s->buffer_size = 0;
- return;
- }
- qemu_fflush(s->file);
-
- while (s->bytes_xfer < s->xfer_limit && offset < s->buffer_size) {
- size_t to_send = MIN(s->buffer_size - offset, s->xfer_limit - s->bytes_xfer);
- ret = migrate_fd_put_buffer(s, s->buffer + offset, to_send);
- if (ret <= 0) {
- DPRINTF("error flushing data, %zd\n", ret);
- break;
- } else {
- DPRINTF("flushed %zd byte(s)\n", ret);
- offset += ret;
- s->bytes_xfer += ret;
- }
- }
-
- DPRINTF("flushed %zu of %zu byte(s)\n", offset, s->buffer_size);
- memmove(s->buffer, s->buffer + offset, s->buffer_size - offset);
- s->buffer_size -= offset;
-
- if (ret < 0) {
- qemu_file_set_error(s->file, ret);
- }
-}
-
-static int buffered_put_buffer(void *opaque, const uint8_t *buf,
- int64_t pos, int size)
-{
- MigrationState *s = opaque;
- ssize_t error;
-
- DPRINTF("putting %d bytes at %" PRId64 "\n", size, pos);
-
- error = qemu_file_get_error(s->file);
- if (error) {
- DPRINTF("flush when error, bailing: %s\n", strerror(-error));
- return error;
- }
-
- if (size <= 0) {
- return size;
- }
-
- if (size > (s->buffer_capacity - s->buffer_size)) {
- DPRINTF("increasing buffer capacity from %zu by %zu\n",
- s->buffer_capacity, size + 1024);
-
- s->buffer_capacity += size + 1024;
-
- s->buffer = g_realloc(s->buffer, s->buffer_capacity);
- }
-
- memcpy(s->buffer + s->buffer_size, buf, size);
- s->buffer_size += size;
-
- return size;
+ return s->enabled_capabilities[MIGRATION_CAPABILITY_AUTO_CONVERGE];
}
-static int buffered_close(void *opaque)
+bool migrate_zero_blocks(void)
{
- MigrationState *s = opaque;
-
- DPRINTF("closing\n");
-
- return migrate_fd_close(s);
-}
+ MigrationState *s;
-static int buffered_get_fd(void *opaque)
-{
- MigrationState *s = opaque;
+ s = migrate_get_current();
- return s->fd;
+ return s->enabled_capabilities[MIGRATION_CAPABILITY_ZERO_BLOCKS];
}
-/*
- * The meaning of the return values is:
- * 0: We can continue sending
- * 1: Time to stop
- * negative: There has been an error
- */
-static int buffered_rate_limit(void *opaque)
+int migrate_use_xbzrle(void)
{
- MigrationState *s = opaque;
- int ret;
-
- ret = qemu_file_get_error(s->file);
- if (ret) {
- return ret;
- }
+ MigrationState *s;
- if (s->bytes_xfer >= s->xfer_limit) {
- return 1;
- }
+ s = migrate_get_current();
- return 0;
+ return s->enabled_capabilities[MIGRATION_CAPABILITY_XBZRLE];
}
-static int64_t buffered_set_rate_limit(void *opaque, int64_t new_rate)
+int64_t migrate_xbzrle_cache_size(void)
{
- MigrationState *s = opaque;
- if (qemu_file_get_error(s->file)) {
- goto out;
- }
- if (new_rate > SIZE_MAX) {
- new_rate = SIZE_MAX;
- }
+ MigrationState *s;
- s->xfer_limit = new_rate / XFER_LIMIT_RATIO;
+ s = migrate_get_current();
-out:
- return s->xfer_limit;
+ return s->xbzrle_cache_size;
}
-static int64_t buffered_get_rate_limit(void *opaque)
-{
- MigrationState *s = opaque;
-
- return s->xfer_limit;
-}
+/* migration thread support */
-static void *buffered_file_thread(void *opaque)
+static void *migration_thread(void *opaque)
{
MigrationState *s = opaque;
int64_t initial_time = qemu_get_clock_ms(rt_clock);
- int64_t sleep_time = 0;
+ int64_t setup_start = qemu_get_clock_ms(host_clock);
+ int64_t initial_bytes = 0;
int64_t max_size = 0;
int64_t start_time = initial_time;
bool old_vm_running = false;
- bool last_round = false;
- qemu_mutex_lock_iothread();
DPRINTF("beginning savevm\n");
qemu_savevm_state_begin(s->file, &s->params);
+ s->setup_time = qemu_get_clock_ms(host_clock) - setup_start;
+ migrate_set_state(s, MIG_STATE_SETUP, MIG_STATE_ACTIVE);
+
+ DPRINTF("setup complete\n");
+
while (s->state == MIG_STATE_ACTIVE) {
int64_t current_time;
uint64_t pending_size;
- if (s->bytes_xfer < s->xfer_limit) {
+ if (!qemu_file_rate_limit(s->file)) {
DPRINTF("iterate\n");
pending_size = qemu_savevm_state_pending(s->file, max_size);
DPRINTF("pending size %lu max %lu\n", pending_size, max_size);
if (pending_size && pending_size >= max_size) {
qemu_savevm_state_iterate(s->file);
} else {
+ int ret;
+
DPRINTF("done iterating\n");
+ qemu_mutex_lock_iothread();
start_time = qemu_get_clock_ms(rt_clock);
qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER);
old_vm_running = runstate_is_running();
- vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
- s->xfer_limit = INT_MAX;
- qemu_savevm_state_complete(s->file);
- last_round = true;
+
+ ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
+ if (ret >= 0) {
+ qemu_file_set_rate_limit(s->file, INT_MAX);
+ qemu_savevm_state_complete(s->file);
+ }
+ qemu_mutex_unlock_iothread();
+
+ if (ret < 0) {
+ migrate_set_state(s, MIG_STATE_ACTIVE, MIG_STATE_ERROR);
+ break;
+ }
+
+ if (!qemu_file_get_error(s->file)) {
+ migrate_set_state(s, MIG_STATE_ACTIVE, MIG_STATE_COMPLETED);
+ break;
+ }
}
}
- qemu_mutex_unlock_iothread();
+
+ if (qemu_file_get_error(s->file)) {
+ migrate_set_state(s, MIG_STATE_ACTIVE, MIG_STATE_ERROR);
+ break;
+ }
current_time = qemu_get_clock_ms(rt_clock);
if (current_time >= initial_time + BUFFER_DELAY) {
- uint64_t transferred_bytes = s->bytes_xfer;
- uint64_t time_spent = current_time - initial_time - sleep_time;
+ uint64_t transferred_bytes = qemu_ftell(s->file) - initial_bytes;
+ uint64_t time_spent = current_time - initial_time;
double bandwidth = transferred_bytes / time_spent;
max_size = bandwidth * migrate_max_downtime() / 1000000;
+ s->mbps = time_spent ? (((double) transferred_bytes * 8.0) /
+ ((double) time_spent / 1000.0)) / 1000.0 / 1000.0 : -1;
+
DPRINTF("transferred %" PRIu64 " time_spent %" PRIu64
" bandwidth %g max_size %" PRId64 "\n",
transferred_bytes, time_spent, bandwidth, max_size);
s->expected_downtime = s->dirty_bytes_rate / bandwidth;
}
- s->bytes_xfer = 0;
- sleep_time = 0;
+ qemu_file_reset_rate_limit(s->file);
initial_time = current_time;
+ initial_bytes = qemu_ftell(s->file);
}
- if (!last_round && (s->bytes_xfer >= s->xfer_limit)) {
+ if (qemu_file_rate_limit(s->file)) {
/* usleep expects microseconds */
g_usleep((initial_time + BUFFER_DELAY - current_time)*1000);
- sleep_time += qemu_get_clock_ms(rt_clock) - current_time;
- }
- buffered_flush(s);
- qemu_mutex_lock_iothread();
- if (qemu_file_get_error(s->file)) {
- migrate_fd_error(s);
- } else if (last_round && s->buffer_size == 0) {
- migrate_fd_completed(s);
}
}
+ qemu_mutex_lock_iothread();
if (s->state == MIG_STATE_COMPLETED) {
int64_t end_time = qemu_get_clock_ms(rt_clock);
s->total_time = end_time - s->total_time;
runstate_set(RUN_STATE_POSTMIGRATE);
} else {
if (old_vm_running) {
- assert(last_round);
vm_start();
}
}
-
+ qemu_bh_schedule(s->cleanup_bh);
qemu_mutex_unlock_iothread();
- g_free(s->buffer);
+
return NULL;
}
-static const QEMUFileOps buffered_file_ops = {
- .get_fd = buffered_get_fd,
- .put_buffer = buffered_put_buffer,
- .close = buffered_close,
- .rate_limit = buffered_rate_limit,
- .get_rate_limit = buffered_get_rate_limit,
- .set_rate_limit = buffered_set_rate_limit,
-};
-
void migrate_fd_connect(MigrationState *s)
{
- s->state = MIG_STATE_ACTIVE;
- trace_migrate_set_state(MIG_STATE_ACTIVE);
+ s->state = MIG_STATE_SETUP;
+ trace_migrate_set_state(MIG_STATE_SETUP);
- s->bytes_xfer = 0;
- s->buffer = NULL;
- s->buffer_size = 0;
- s->buffer_capacity = 0;
/* This is a best 1st approximation. ns to ms */
s->expected_downtime = max_downtime/1000000;
+ s->cleanup_bh = qemu_bh_new(migrate_fd_cleanup, s);
- s->xfer_limit = s->bandwidth_limit / XFER_LIMIT_RATIO;
-
- s->file = qemu_fopen_ops(s, &buffered_file_ops);
+ qemu_file_set_rate_limit(s->file,
+ s->bandwidth_limit / XFER_LIMIT_RATIO);
- qemu_thread_create(&s->thread, buffered_file_thread, s,
- QEMU_THREAD_DETACHED);
+ qemu_thread_create(&s->thread, migration_thread, s,
+ QEMU_THREAD_JOINABLE);
notifier_list_notify(&migration_state_notifiers, s);
}
projects / qemu.git / blobdiff