static void migrate_fd_put_ready(void *opaque)
{
MigrationState *s = opaque;
int ret;
if (s->state != MIG_STATE_ACTIVE) {
DPRINTF("put_ready returning because of non-active state\n");
return;
}
DPRINTF("iterate\n");
ret = qemu_savevm_state_iterate(s->mon, s->file);
if (ret < 0) {
migrate_fd_error(s);
} else if (ret == 1) {
int old_vm_running = runstate_is_running();
DPRINTF("done iterating\n");
vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
if (qemu_savevm_state_complete(s->mon, s->file) < 0) {
migrate_fd_error(s);
} else {
migrate_fd_completed(s);
}
if (s->state != MIG_STATE_COMPLETED) {
if (old_vm_running) {
vm_start();
}
}
}
}
void colo_do_failover(MigrationState *s)
{
/* Make sure VM stopped while failover happened. */
if (!colo_runstate_is_stopped()) {
vm_stop_force_state(RUN_STATE_COLO);
}
if (get_colo_mode() == COLO_MODE_PRIMARY) {
primary_vm_do_failover();
} else {
secondary_vm_do_failover();
}
}
void migrate_fd_put_ready(MigrationState *s)
{
int ret;
if (s->state != MIG_STATE_ACTIVE) {
DPRINTF("put_ready returning because of non-active state\n");
return;
}
DPRINTF("iterate\n");
ret = qemu_savevm_state_iterate(s->file);
if (ret < 0) {
migrate_fd_error(s);
} else if (ret == 1) {
int old_vm_running = runstate_is_running();
int64_t start_time, end_time;
DPRINTF("done iterating\n");
start_time = qemu_get_clock_ms(rt_clock);
qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER);
vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
if (qemu_savevm_state_complete(s->file) < 0) {
migrate_fd_error(s);
} else {
migrate_fd_completed(s);
}
end_time = qemu_get_clock_ms(rt_clock);
s->total_time = end_time - s->total_time;
s->downtime = end_time - start_time;
if (s->state != MIG_STATE_COMPLETED) {
if (old_vm_running) {
vm_start();
}
}
}
}
static int colo_do_checkpoint_transaction(MigrationState *s,
QIOChannelBuffer *bioc,
QEMUFile *fb)
{
Error *local_err = NULL;
int ret = -1;
colo_send_message(s->to_dst_file, COLO_MESSAGE_CHECKPOINT_REQUEST,
&local_err);
if (local_err) {
goto out;
}
colo_receive_check_message(s->rp_state.from_dst_file,
COLO_MESSAGE_CHECKPOINT_REPLY, &local_err);
if (local_err) {
goto out;
}
/* Reset channel-buffer directly */
qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL);
bioc->usage = 0;
qemu_mutex_lock_iothread();
if (failover_get_state() != FAILOVER_STATUS_NONE) {
qemu_mutex_unlock_iothread();
goto out;
}
vm_stop_force_state(RUN_STATE_COLO);
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("run", "stop");
/*
* Failover request bh could be called after vm_stop_force_state(),
* So we need check failover_request_is_active() again.
*/
if (failover_get_state() != FAILOVER_STATUS_NONE) {
goto out;
}
/* Disable block migration */
s->params.blk = 0;
s->params.shared = 0;
qemu_savevm_state_header(fb);
qemu_savevm_state_begin(fb, &s->params);
qemu_mutex_lock_iothread();
qemu_savevm_state_complete_precopy(fb, false);
qemu_mutex_unlock_iothread();
qemu_fflush(fb);
colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
if (local_err) {
goto out;
}
/*
* We need the size of the VMstate data in Secondary side,
* With which we can decide how much data should be read.
*/
colo_send_message_value(s->to_dst_file, COLO_MESSAGE_VMSTATE_SIZE,
bioc->usage, &local_err);
if (local_err) {
goto out;
}
qemu_put_buffer(s->to_dst_file, bioc->data, bioc->usage);
qemu_fflush(s->to_dst_file);
ret = qemu_file_get_error(s->to_dst_file);
if (ret < 0) {
goto out;
}
colo_receive_check_message(s->rp_state.from_dst_file,
COLO_MESSAGE_VMSTATE_RECEIVED, &local_err);
if (local_err) {
goto out;
}
colo_receive_check_message(s->rp_state.from_dst_file,
COLO_MESSAGE_VMSTATE_LOADED, &local_err);
if (local_err) {
goto out;
}
ret = 0;
qemu_mutex_lock_iothread();
vm_start();
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
out:
if (local_err) {
error_report_err(local_err);
}
return ret;
}
void *colo_process_incoming_thread(void *opaque)
{
MigrationIncomingState *mis = opaque;
QEMUFile *fb = NULL;
QIOChannelBuffer *bioc = NULL; /* Cache incoming device state */
uint64_t total_size;
uint64_t value;
Error *local_err = NULL;
int ret;
rcu_register_thread();
qemu_sem_init(&mis->colo_incoming_sem, 0);
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COLO);
failover_init_state();
mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
if (!mis->to_src_file) {
error_report("COLO incoming thread: Open QEMUFile to_src_file failed");
goto out;
}
/*
* Note: the communication between Primary side and Secondary side
* should be sequential, we set the fd to unblocked in migration incoming
* coroutine, and here we are in the COLO incoming thread, so it is ok to
* set the fd back to blocked.
*/
qemu_file_set_blocking(mis->from_src_file, true);
bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
fb = qemu_fopen_channel_input(QIO_CHANNEL(bioc));
object_unref(OBJECT(bioc));
qemu_mutex_lock_iothread();
#ifdef CONFIG_REPLICATION
replication_start_all(REPLICATION_MODE_SECONDARY, &local_err);
if (local_err) {
qemu_mutex_unlock_iothread();
goto out;
}
#else
abort();
#endif
vm_start();
trace_colo_vm_state_change("stop", "run");
qemu_mutex_unlock_iothread();
colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY,
&local_err);
if (local_err) {
goto out;
}
while (mis->state == MIGRATION_STATUS_COLO) {
int request = 0;
colo_wait_handle_message(mis->from_src_file, &request, &local_err);
if (local_err) {
goto out;
}
assert(request);
if (failover_get_state() != FAILOVER_STATUS_NONE) {
error_report("failover request");
goto out;
}
qemu_mutex_lock_iothread();
vm_stop_force_state(RUN_STATE_COLO);
trace_colo_vm_state_change("run", "stop");
qemu_mutex_unlock_iothread();
/* FIXME: This is unnecessary for periodic checkpoint mode */
colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY,
&local_err);
if (local_err) {
goto out;
}
colo_receive_check_message(mis->from_src_file,
COLO_MESSAGE_VMSTATE_SEND, &local_err);
if (local_err) {
goto out;
}
qemu_mutex_lock_iothread();
cpu_synchronize_all_pre_loadvm();
ret = qemu_loadvm_state_main(mis->from_src_file, mis);
qemu_mutex_unlock_iothread();
if (ret < 0) {
error_report("Load VM's live state (ram) error");
goto out;
}
value = colo_receive_message_value(mis->from_src_file,
COLO_MESSAGE_VMSTATE_SIZE, &local_err);
if (local_err) {
goto out;
}
/*
* Read VM device state data into channel buffer,
* It's better to re-use the memory allocated.
* Here we need to handle the channel buffer directly.
*/
if (value > bioc->capacity) {
bioc->capacity = value;
bioc->data = g_realloc(bioc->data, bioc->capacity);
}
total_size = qemu_get_buffer(mis->from_src_file, bioc->data, value);
if (total_size != value) {
error_report("Got %" PRIu64 " VMState data, less than expected"
" %" PRIu64, total_size, value);
goto out;
}
bioc->usage = total_size;
qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL);
colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED,
&local_err);
if (local_err) {
goto out;
}
qemu_mutex_lock_iothread();
vmstate_loading = true;
ret = qemu_load_device_state(fb);
if (ret < 0) {
error_report("COLO: load device state failed");
qemu_mutex_unlock_iothread();
goto out;
}
#ifdef CONFIG_REPLICATION
replication_get_error_all(&local_err);
if (local_err) {
qemu_mutex_unlock_iothread();
goto out;
}
/* discard colo disk buffer */
replication_do_checkpoint_all(&local_err);
if (local_err) {
qemu_mutex_unlock_iothread();
goto out;
}
#else
abort();
#endif
/* Notify all filters of all NIC to do checkpoint */
colo_notify_filters_event(COLO_EVENT_CHECKPOINT, &local_err);
if (local_err) {
qemu_mutex_unlock_iothread();
goto out;
}
vmstate_loading = false;
vm_start();
trace_colo_vm_state_change("stop", "run");
qemu_mutex_unlock_iothread();
if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
failover_set_state(FAILOVER_STATUS_RELAUNCH,
FAILOVER_STATUS_NONE);
failover_request_active(NULL);
goto out;
}
colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED,
&local_err);
if (local_err) {
goto out;
}
}
out:
vmstate_loading = false;
/* Throw the unreported error message after exited from loop */
if (local_err) {
error_report_err(local_err);
}
switch (failover_get_state()) {
case FAILOVER_STATUS_NONE:
qapi_event_send_colo_exit(COLO_MODE_SECONDARY,
COLO_EXIT_REASON_ERROR);
break;
case FAILOVER_STATUS_REQUIRE:
qapi_event_send_colo_exit(COLO_MODE_SECONDARY,
COLO_EXIT_REASON_REQUEST);
break;
default:
abort();
}
if (fb) {
qemu_fclose(fb);
}
/* Hope this not to be too long to loop here */
qemu_sem_wait(&mis->colo_incoming_sem);
qemu_sem_destroy(&mis->colo_incoming_sem);
/* Must be called after failover BH is completed */
if (mis->to_src_file) {
qemu_fclose(mis->to_src_file);
}
migration_incoming_disable_colo();
rcu_unregister_thread();
return NULL;
}
static int colo_do_checkpoint_transaction(MigrationState *s,
QIOChannelBuffer *bioc,
QEMUFile *fb)
{
Error *local_err = NULL;
int ret = -1;
colo_send_message(s->to_dst_file, COLO_MESSAGE_CHECKPOINT_REQUEST,
&local_err);
if (local_err) {
goto out;
}
colo_receive_check_message(s->rp_state.from_dst_file,
COLO_MESSAGE_CHECKPOINT_REPLY, &local_err);
if (local_err) {
goto out;
}
/* Reset channel-buffer directly */
qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL);
bioc->usage = 0;
qemu_mutex_lock_iothread();
if (failover_get_state() != FAILOVER_STATUS_NONE) {
qemu_mutex_unlock_iothread();
goto out;
}
vm_stop_force_state(RUN_STATE_COLO);
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("run", "stop");
/*
* Failover request bh could be called after vm_stop_force_state(),
* So we need check failover_request_is_active() again.
*/
if (failover_get_state() != FAILOVER_STATUS_NONE) {
goto out;
}
colo_notify_compares_event(NULL, COLO_EVENT_CHECKPOINT, &local_err);
if (local_err) {
goto out;
}
/* Disable block migration */
migrate_set_block_enabled(false, &local_err);
qemu_mutex_lock_iothread();
#ifdef CONFIG_REPLICATION
replication_do_checkpoint_all(&local_err);
if (local_err) {
qemu_mutex_unlock_iothread();
goto out;
}
#else
abort();
#endif
colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
if (local_err) {
qemu_mutex_unlock_iothread();
goto out;
}
/* Note: device state is saved into buffer */
ret = qemu_save_device_state(fb);
qemu_mutex_unlock_iothread();
if (ret < 0) {
goto out;
}
/*
* Only save VM's live state, which not including device state.
* TODO: We may need a timeout mechanism to prevent COLO process
* to be blocked here.
*/
qemu_savevm_live_state(s->to_dst_file);
qemu_fflush(fb);
/*
* We need the size of the VMstate data in Secondary side,
* With which we can decide how much data should be read.
*/
colo_send_message_value(s->to_dst_file, COLO_MESSAGE_VMSTATE_SIZE,
bioc->usage, &local_err);
if (local_err) {
goto out;
}
qemu_put_buffer(s->to_dst_file, bioc->data, bioc->usage);
qemu_fflush(s->to_dst_file);
ret = qemu_file_get_error(s->to_dst_file);
if (ret < 0) {
goto out;
}
colo_receive_check_message(s->rp_state.from_dst_file,
COLO_MESSAGE_VMSTATE_RECEIVED, &local_err);
if (local_err) {
goto out;
}
colo_receive_check_message(s->rp_state.from_dst_file,
COLO_MESSAGE_VMSTATE_LOADED, &local_err);
if (local_err) {
goto out;
}
ret = 0;
qemu_mutex_lock_iothread();
vm_start();
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
out:
if (local_err) {
error_report_err(local_err);
}
return ret;
}
static void *buffered_file_thread(void *opaque)
{
MigrationState *s = opaque;
int64_t initial_time = qemu_get_clock_ms(rt_clock);
int64_t max_size = 0;
bool last_round = false;
int ret;
qemu_mutex_lock_iothread();
DPRINTF("beginning savevm\n");
ret = qemu_savevm_state_begin(s->file, &s->params);
if (ret < 0) {
DPRINTF("failed, %d\n", ret);
qemu_mutex_unlock_iothread();
goto out;
}
qemu_mutex_unlock_iothread();
while (true) {
int64_t current_time = qemu_get_clock_ms(rt_clock);
uint64_t pending_size;
qemu_mutex_lock_iothread();
if (s->state != MIG_STATE_ACTIVE) {
DPRINTF("put_ready returning because of non-active state\n");
qemu_mutex_unlock_iothread();
break;
}
if (s->complete) {
qemu_mutex_unlock_iothread();
break;
}
if (s->bytes_xfer < s->xfer_limit) {
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) {
ret = qemu_savevm_state_iterate(s->file);
if (ret < 0) {
qemu_mutex_unlock_iothread();
break;
}
} else {
int old_vm_running = runstate_is_running();
int64_t start_time, end_time;
DPRINTF("done iterating\n");
start_time = qemu_get_clock_ms(rt_clock);
qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER);
if (old_vm_running) {
vm_stop(RUN_STATE_FINISH_MIGRATE);
} else {
vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
}
ret = qemu_savevm_state_complete(s->file);
if (ret < 0) {
qemu_mutex_unlock_iothread();
break;
} else {
migrate_fd_completed(s);
}
end_time = qemu_get_clock_ms(rt_clock);
s->total_time = end_time - s->total_time;
s->downtime = end_time - start_time;
if (s->state != MIG_STATE_COMPLETED) {
if (old_vm_running) {
vm_start();
}
}
last_round = true;
}
}
qemu_mutex_unlock_iothread();
if (current_time >= initial_time + BUFFER_DELAY) {
uint64_t transferred_bytes = s->bytes_xfer;
uint64_t time_spent = current_time - initial_time;
double bandwidth = transferred_bytes / time_spent;
max_size = bandwidth * migrate_max_downtime() / 1000000;
DPRINTF("transferred %" PRIu64 " time_spent %" PRIu64
" bandwidth %g max_size %" PRId64 "\n",
transferred_bytes, time_spent, bandwidth, max_size);
s->bytes_xfer = 0;
initial_time = current_time;
}
if (!last_round && (s->bytes_xfer >= s->xfer_limit)) {
/* usleep expects microseconds */
g_usleep((initial_time + BUFFER_DELAY - current_time)*1000);
}
ret = buffered_flush(s);
if (ret < 0) {
break;
}
}
out:
if (ret < 0) {
migrate_fd_error(s);
}
g_free(s->buffer);
return NULL;
}
static void *migration_thread(void *opaque)
{
MigrationState *s = opaque;
int64_t initial_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
int64_t setup_start = qemu_clock_get_ms(QEMU_CLOCK_HOST);
int64_t initial_bytes = 0;
int64_t max_size = 0;
int64_t start_time = initial_time;
bool old_vm_running = false;
DPRINTF("beginning savevm\n");
qemu_savevm_state_begin(s->file, &s->params);
s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - 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 (!qemu_file_rate_limit(s->file)) {
DPRINTF("iterate\n");
pending_size = qemu_savevm_state_pending(s->file, max_size);
DPRINTF("pending size %" PRIu64 " max %" PRIu64 "\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_clock_get_ms(QEMU_CLOCK_REALTIME);
qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER);
old_vm_running = runstate_is_running();
ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
if (ret >= 0) {
qemu_file_set_rate_limit(s->file, INT64_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;
}
}
}
if (qemu_file_get_error(s->file)) {
migrate_set_state(s, MIG_STATE_ACTIVE, MIG_STATE_ERROR);
break;
}
current_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
if (current_time >= initial_time + BUFFER_DELAY) {
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);
/* if we haven't sent anything, we don't want to recalculate
10000 is a small enough number for our purposes */
if (s->dirty_bytes_rate && transferred_bytes > 10000) {
s->expected_downtime = s->dirty_bytes_rate / bandwidth;
}
qemu_file_reset_rate_limit(s->file);
initial_time = current_time;
initial_bytes = qemu_ftell(s->file);
}
if (qemu_file_rate_limit(s->file)) {
/* usleep expects microseconds */
g_usleep((initial_time + BUFFER_DELAY - current_time)*1000);
}
}
qemu_mutex_lock_iothread();
if (s->state == MIG_STATE_COMPLETED) {
int64_t end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
s->total_time = end_time - s->total_time;
s->downtime = end_time - start_time;
runstate_set(RUN_STATE_POSTMIGRATE);
} else {
if (old_vm_running) {
vm_start();
}
}
qemu_bh_schedule(s->cleanup_bh);
qemu_mutex_unlock_iothread();
return NULL;
}