static void primary_vm_do_failover(void)
{
MigrationState *s = migrate_get_current();
int old_state;
migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
/*
* Wake up COLO thread which may blocked in recv() or send(),
* The s->rp_state.from_dst_file and s->to_dst_file may use the
* same fd, but we still shutdown the fd for twice, it is harmless.
*/
if (s->to_dst_file) {
qemu_file_shutdown(s->to_dst_file);
}
if (s->rp_state.from_dst_file) {
qemu_file_shutdown(s->rp_state.from_dst_file);
}
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_COMPLETED);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Incorrect state (%s) while doing failover for Primary VM",
FailoverStatus_lookup[old_state]);
return;
}
/* Notify COLO thread that failover work is finished */
qemu_sem_post(&s->colo_exit_sem);
}
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->state != MIG_STATE_ACTIVE);
if (s->state != MIG_STATE_COMPLETED) {
qemu_savevm_state_cancel();
if (s->state == MIG_STATE_CANCELLING) {
migrate_set_state(s, MIG_STATE_CANCELLING, MIG_STATE_CANCELLED);
}
}
notifier_list_notify(&migration_state_notifiers, s);
}
static void migrate_fd_cancel(MigrationState *s)
{
int old_state ;
QEMUFile *f = migrate_get_current()->file;
trace_migrate_fd_cancel();
do {
old_state = s->state;
if (old_state != MIGRATION_STATUS_SETUP &&
old_state != MIGRATION_STATUS_ACTIVE) {
break;
}
migrate_set_state(s, old_state, MIGRATION_STATUS_CANCELLING);
} while (s->state != MIGRATION_STATUS_CANCELLING);
/*
* If we're unlucky the migration code might be stuck somewhere in a
* send/write while the network has failed and is waiting to timeout;
* if we've got shutdown(2) available then we can force it to quit.
* The outgoing qemu file gets closed in migrate_fd_cleanup that is
* called in a bh, so there is no race against this cancel.
*/
if (s->state == MIGRATION_STATUS_CANCELLING && f) {
qemu_file_shutdown(f);
}
}
static void secondary_vm_do_failover(void)
{
int old_state;
MigrationIncomingState *mis = migration_incoming_get_current();
/* Can not do failover during the process of VM's loading VMstate, Or
* it will break the secondary VM.
*/
if (vmstate_loading) {
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_RELAUNCH);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Unknown error while do failover for secondary VM,"
"old_state: %s", FailoverStatus_lookup[old_state]);
}
return;
}
migrate_set_state(&mis->state, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
if (!autostart) {
error_report("\"-S\" qemu option will be ignored in secondary side");
/* recover runstate to normal migration finish state */
autostart = true;
}
/*
* Make sure COLO incoming thread not block in recv or send,
* If mis->from_src_file and mis->to_src_file use the same fd,
* The second shutdown() will return -1, we ignore this value,
* It is harmless.
*/
if (mis->from_src_file) {
qemu_file_shutdown(mis->from_src_file);
}
if (mis->to_src_file) {
qemu_file_shutdown(mis->to_src_file);
}
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_COMPLETED);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Incorrect state (%s) while doing failover for "
"secondary VM", FailoverStatus_lookup[old_state]);
return;
}
/* Notify COLO incoming thread that failover work is finished */
qemu_sem_post(&mis->colo_incoming_sem);
/* For Secondary VM, jump to incoming co */
if (mis->migration_incoming_co) {
qemu_coroutine_enter(mis->migration_incoming_co);
}
}
void migrate_start_colo_process(MigrationState *s)
{
qemu_mutex_unlock_iothread();
qemu_sem_init(&s->colo_checkpoint_sem, 0);
s->colo_delay_timer = timer_new_ms(QEMU_CLOCK_HOST,
colo_checkpoint_notify, s);
qemu_sem_init(&s->colo_exit_sem, 0);
migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COLO);
colo_process_checkpoint(s);
qemu_mutex_lock_iothread();
}
static void migrate_fd_cancel(MigrationState *s)
{
int old_state ;
DPRINTF("cancelling migration\n");
do {
old_state = s->state;
if (old_state != MIG_STATE_SETUP && old_state != MIG_STATE_ACTIVE) {
break;
}
migrate_set_state(s, old_state, MIG_STATE_CANCELLING);
} while (s->state != MIG_STATE_CANCELLING);
}
static void primary_vm_do_failover(void)
{
#ifdef CONFIG_REPLICATION
MigrationState *s = migrate_get_current();
int old_state;
Error *local_err = NULL;
migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
/*
* kick COLO thread which might wait at
* qemu_sem_wait(&s->colo_checkpoint_sem).
*/
colo_checkpoint_notify(migrate_get_current());
/*
* Wake up COLO thread which may blocked in recv() or send(),
* The s->rp_state.from_dst_file and s->to_dst_file may use the
* same fd, but we still shutdown the fd for twice, it is harmless.
*/
if (s->to_dst_file) {
qemu_file_shutdown(s->to_dst_file);
}
if (s->rp_state.from_dst_file) {
qemu_file_shutdown(s->rp_state.from_dst_file);
}
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_COMPLETED);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Incorrect state (%s) while doing failover for Primary VM",
FailoverStatus_str(old_state));
return;
}
replication_stop_all(true, &local_err);
if (local_err) {
error_report_err(local_err);
local_err = NULL;
}
/* Notify COLO thread that failover work is finished */
qemu_sem_post(&s->colo_exit_sem);
#else
abort();
#endif
}
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;
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));
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;
}
/* 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;
}
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();
qemu_system_reset(VMRESET_SILENT);
vmstate_loading = true;
if (qemu_loadvm_state(fb) < 0) {
error_report("COLO: loadvm failed");
qemu_mutex_unlock_iothread();
goto out;
}
vmstate_loading = false;
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);
}
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_exit_colo();
return NULL;
}
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 void secondary_vm_do_failover(void)
{
/* COLO needs enable block-replication */
#ifdef CONFIG_REPLICATION
int old_state;
MigrationIncomingState *mis = migration_incoming_get_current();
Error *local_err = NULL;
/* Can not do failover during the process of VM's loading VMstate, Or
* it will break the secondary VM.
*/
if (vmstate_loading) {
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_RELAUNCH);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Unknown error while do failover for secondary VM,"
"old_state: %s", FailoverStatus_str(old_state));
}
return;
}
migrate_set_state(&mis->state, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
replication_stop_all(true, &local_err);
if (local_err) {
error_report_err(local_err);
}
/* Notify all filters of all NIC to do checkpoint */
colo_notify_filters_event(COLO_EVENT_FAILOVER, &local_err);
if (local_err) {
error_report_err(local_err);
}
if (!autostart) {
error_report("\"-S\" qemu option will be ignored in secondary side");
/* recover runstate to normal migration finish state */
autostart = true;
}
/*
* Make sure COLO incoming thread not block in recv or send,
* If mis->from_src_file and mis->to_src_file use the same fd,
* The second shutdown() will return -1, we ignore this value,
* It is harmless.
*/
if (mis->from_src_file) {
qemu_file_shutdown(mis->from_src_file);
}
if (mis->to_src_file) {
qemu_file_shutdown(mis->to_src_file);
}
old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
FAILOVER_STATUS_COMPLETED);
if (old_state != FAILOVER_STATUS_ACTIVE) {
error_report("Incorrect state (%s) while doing failover for "
"secondary VM", FailoverStatus_str(old_state));
return;
}
/* Notify COLO incoming thread that failover work is finished */
qemu_sem_post(&mis->colo_incoming_sem);
/* For Secondary VM, jump to incoming co */
if (mis->migration_incoming_co) {
qemu_coroutine_enter(mis->migration_incoming_co);
}
#else
abort();
#endif
}
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;
}
