#include "migration/failover.h"
#include "migration/ram.h"
#ifdef CONFIG_REPLICATION
-#include "replication.h"
+#include "block/replication.h"
#endif
#include "net/colo-compare.h"
#include "net/colo.h"
* kick COLO thread which might wait at
* qemu_sem_wait(&s->colo_checkpoint_sem).
*/
- colo_checkpoint_notify(migrate_get_current());
+ colo_checkpoint_notify(s);
/*
* Wake up COLO thread which may blocked in recv() or send(),
vm_stop_force_state(RUN_STATE_COLO);
}
- switch (get_colo_mode()) {
+ switch (last_colo_mode = get_colo_mode()) {
case COLO_MODE_PRIMARY:
primary_vm_do_failover();
break;
void qmp_xen_colo_do_checkpoint(Error **errp)
{
- replication_do_checkpoint_all(errp);
+ Error *err = NULL;
+
+ replication_do_checkpoint_all(&err);
+ if (err) {
+ error_propagate(errp, err);
+ return;
+ }
/* Notify all filters of all NIC to do checkpoint */
colo_notify_filters_event(COLO_EVENT_CHECKPOINT, errp);
}
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
if (ret < 0) {
goto out;
}
+
+ if (migrate_auto_converge()) {
+ mig_throttle_counter_reset();
+ }
/*
* Only save VM's live state, which not including device state.
* TODO: We may need a timeout mechanism to prevent COLO process
goto out;
}
+ qemu_event_reset(&s->colo_checkpoint_event);
+ colo_notify_compares_event(NULL, COLO_EVENT_CHECKPOINT, &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) {
{
QIOChannelBuffer *bioc;
QEMUFile *fb = NULL;
- int64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
Error *local_err = NULL;
int ret;
- last_colo_mode = get_colo_mode();
- if (last_colo_mode != COLO_MODE_PRIMARY) {
+ if (get_colo_mode() != COLO_MODE_PRIMARY) {
error_report("COLO mode must be COLO_MODE_PRIMARY");
return;
}
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
- timer_mod(s->colo_delay_timer,
- current_time + s->parameters.x_checkpoint_delay);
+ timer_mod(s->colo_delay_timer, qemu_clock_get_ms(QEMU_CLOCK_HOST) +
+ s->parameters.x_checkpoint_delay);
while (s->state == MIGRATION_STATUS_COLO) {
if (failover_get_state() != FAILOVER_STATUS_NONE) {
goto out;
}
- qemu_sem_wait(&s->colo_checkpoint_sem);
+ qemu_event_wait(&s->colo_checkpoint_event);
if (s->state != MIGRATION_STATUS_COLO) {
goto out;
/*
* It is safe to unregister notifier after failover finished.
* Besides, colo_delay_timer and colo_checkpoint_sem can't be
- * released befor unregister notifier, or there will be use-after-free
+ * released before unregister notifier, or there will be use-after-free
* error.
*/
colo_compare_unregister_notifier(&packets_compare_notifier);
- timer_del(s->colo_delay_timer);
timer_free(s->colo_delay_timer);
- qemu_sem_destroy(&s->colo_checkpoint_sem);
+ qemu_event_destroy(&s->colo_checkpoint_event);
/*
* Must be called after failover BH is completed,
*/
if (s->rp_state.from_dst_file) {
qemu_fclose(s->rp_state.from_dst_file);
+ s->rp_state.from_dst_file = NULL;
}
}
MigrationState *s = opaque;
int64_t next_notify_time;
- qemu_sem_post(&s->colo_checkpoint_sem);
+ qemu_event_set(&s->colo_checkpoint_event);
s->colo_checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
next_notify_time = s->colo_checkpoint_time +
s->parameters.x_checkpoint_delay;
void migrate_start_colo_process(MigrationState *s)
{
qemu_mutex_unlock_iothread();
- qemu_sem_init(&s->colo_checkpoint_sem, 0);
+ qemu_event_init(&s->colo_checkpoint_event, false);
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();
}
qemu_mutex_lock_iothread();
vm_stop_force_state(RUN_STATE_COLO);
- trace_colo_vm_state_change("run", "stop");
qemu_mutex_unlock_iothread();
+ trace_colo_vm_state_change("run", "stop");
/* FIXME: This is unnecessary for periodic checkpoint mode */
colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY,
}
qemu_mutex_lock_iothread();
- cpu_synchronize_all_pre_loadvm();
+ cpu_synchronize_all_states();
ret = qemu_loadvm_state_main(mis->from_src_file, mis);
qemu_mutex_unlock_iothread();
qemu_mutex_lock_iothread();
vmstate_loading = true;
+ colo_flush_ram_cache();
ret = qemu_load_device_state(fb);
if (ret < 0) {
error_setg(errp, "COLO: load device state failed");
+ vmstate_loading = false;
qemu_mutex_unlock_iothread();
return;
}
replication_get_error_all(&local_err);
if (local_err) {
error_propagate(errp, local_err);
+ vmstate_loading = false;
qemu_mutex_unlock_iothread();
return;
}
replication_do_checkpoint_all(&local_err);
if (local_err) {
error_propagate(errp, local_err);
+ vmstate_loading = false;
qemu_mutex_unlock_iothread();
return;
}
if (local_err) {
error_propagate(errp, local_err);
+ vmstate_loading = false;
qemu_mutex_unlock_iothread();
return;
}
vmstate_loading = false;
vm_start();
- trace_colo_vm_state_change("stop", "run");
qemu_mutex_unlock_iothread();
+ trace_colo_vm_state_change("stop", "run");
if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
- failover_set_state(FAILOVER_STATUS_RELAUNCH,
- FAILOVER_STATUS_NONE);
- failover_request_active(NULL);
return;
}
colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED,
&local_err);
- if (local_err) {
- error_propagate(errp, local_err);
- }
+ error_propagate(errp, local_err);
}
static void colo_wait_handle_message(MigrationIncomingState *mis,
}
}
+void colo_shutdown(void)
+{
+ MigrationIncomingState *mis = NULL;
+ MigrationState *s = NULL;
+
+ switch (get_colo_mode()) {
+ case COLO_MODE_PRIMARY:
+ s = migrate_get_current();
+ qemu_event_set(&s->colo_checkpoint_event);
+ qemu_sem_post(&s->colo_exit_sem);
+ break;
+ case COLO_MODE_SECONDARY:
+ mis = migration_incoming_get_current();
+ qemu_sem_post(&mis->colo_incoming_sem);
+ break;
+ default:
+ break;
+ }
+}
+
void *colo_process_incoming_thread(void *opaque)
{
MigrationIncomingState *mis = opaque;
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COLO);
- last_colo_mode = get_colo_mode();
- if (last_colo_mode != COLO_MODE_SECONDARY) {
+ if (get_colo_mode() != COLO_MODE_SECONDARY) {
error_report("COLO mode must be COLO_MODE_SECONDARY");
return NULL;
}
abort();
#endif
vm_start();
- trace_colo_vm_state_change("stop", "run");
qemu_mutex_unlock_iothread();
+ trace_colo_vm_state_change("stop", "run");
colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY,
&local_err);
error_report_err(local_err);
break;
}
+
+ if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
+ failover_set_state(FAILOVER_STATUS_RELAUNCH,
+ FAILOVER_STATUS_NONE);
+ failover_request_active(NULL);
+ break;
+ }
+
if (failover_get_state() != FAILOVER_STATUS_NONE) {
error_report("failover request");
break;
}
out:
- vmstate_loading = false;
-
/*
* There are only two reasons we can get here, some error happened
* or the user triggered failover.
/* 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);
- mis->to_src_file = NULL;
- }
rcu_unregister_thread();
return NULL;
projects / mirror_qemu.git / blobdiff