Beispiel #1
0
static void colo_process_checkpoint(MigrationState *s)
{
    QIOChannelBuffer *bioc;
    QEMUFile *fb = NULL;
    int64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
    Error *local_err = NULL;
    int ret;

    failover_init_state();

    s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file);
    if (!s->rp_state.from_dst_file) {
        error_report("Open QEMUFile from_dst_file failed");
        goto out;
    }

    /*
     * Wait for Secondary finish loading VM states and enter COLO
     * restore.
     */
    colo_receive_check_message(s->rp_state.from_dst_file,
                       COLO_MESSAGE_CHECKPOINT_READY, &local_err);
    if (local_err) {
        goto out;
    }
    bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
    fb = qemu_fopen_channel_output(QIO_CHANNEL(bioc));
    object_unref(OBJECT(bioc));

    qemu_mutex_lock_iothread();
    vm_start();
    qemu_mutex_unlock_iothread();
    trace_colo_vm_state_change("stop", "run");

    timer_mod(s->colo_delay_timer,
            current_time + s->parameters.x_checkpoint_delay);

    while (s->state == MIGRATION_STATUS_COLO) {
        if (failover_get_state() != FAILOVER_STATUS_NONE) {
            error_report("failover request");
            goto out;
        }

        qemu_sem_wait(&s->colo_checkpoint_sem);

        ret = colo_do_checkpoint_transaction(s, bioc, fb);
        if (ret < 0) {
            goto out;
        }
    }

out:
    /* Throw the unreported error message after exited from loop */
    if (local_err) {
        error_report_err(local_err);
    }

    if (fb) {
        qemu_fclose(fb);
    }

    timer_del(s->colo_delay_timer);

    /* Hope this not to be too long to wait here */
    qemu_sem_wait(&s->colo_exit_sem);
    qemu_sem_destroy(&s->colo_exit_sem);
    /*
     * Must be called after failover BH is completed,
     * Or the failover BH may shutdown the wrong fd that
     * re-used by other threads after we release here.
     */
    if (s->rp_state.from_dst_file) {
        qemu_fclose(s->rp_state.from_dst_file);
    }
}
Beispiel #2
0
static void colo_process_checkpoint(MigrationState *s)
{
    QIOChannelBuffer *bioc;
    QEMUFile *fb = NULL;
    int64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
    Error *local_err = NULL;
    int ret;

    failover_init_state();

    s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file);
    if (!s->rp_state.from_dst_file) {
        error_report("Open QEMUFile from_dst_file failed");
        goto out;
    }

    packets_compare_notifier.notify = colo_compare_notify_checkpoint;
    colo_compare_register_notifier(&packets_compare_notifier);

    /*
     * Wait for Secondary finish loading VM states and enter COLO
     * restore.
     */
    colo_receive_check_message(s->rp_state.from_dst_file,
                       COLO_MESSAGE_CHECKPOINT_READY, &local_err);
    if (local_err) {
        goto out;
    }
    bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
    fb = qemu_fopen_channel_output(QIO_CHANNEL(bioc));
    object_unref(OBJECT(bioc));

    qemu_mutex_lock_iothread();
#ifdef CONFIG_REPLICATION
    replication_start_all(REPLICATION_MODE_PRIMARY, &local_err);
    if (local_err) {
        qemu_mutex_unlock_iothread();
        goto out;
    }
#else
        abort();
#endif

    vm_start();
    qemu_mutex_unlock_iothread();
    trace_colo_vm_state_change("stop", "run");

    timer_mod(s->colo_delay_timer,
            current_time + s->parameters.x_checkpoint_delay);

    while (s->state == MIGRATION_STATUS_COLO) {
        if (failover_get_state() != FAILOVER_STATUS_NONE) {
            error_report("failover request");
            goto out;
        }

        qemu_sem_wait(&s->colo_checkpoint_sem);

        if (s->state != MIGRATION_STATUS_COLO) {
            goto out;
        }
        ret = colo_do_checkpoint_transaction(s, bioc, fb);
        if (ret < 0) {
            goto out;
        }
    }

out:
    /* Throw the unreported error message after exited from loop */
    if (local_err) {
        error_report_err(local_err);
    }

    if (fb) {
        qemu_fclose(fb);
    }

    /*
     * There are only two reasons we can get here, some error happened
     * or the user triggered failover.
     */
    switch (failover_get_state()) {
    case FAILOVER_STATUS_NONE:
        qapi_event_send_colo_exit(COLO_MODE_PRIMARY,
                                  COLO_EXIT_REASON_ERROR);
        break;
    case FAILOVER_STATUS_REQUIRE:
        qapi_event_send_colo_exit(COLO_MODE_PRIMARY,
                                  COLO_EXIT_REASON_REQUEST);
        break;
    default:
        abort();
    }

    /* Hope this not to be too long to wait here */
    qemu_sem_wait(&s->colo_exit_sem);
    qemu_sem_destroy(&s->colo_exit_sem);

    /*
     * 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
     * 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);

    /*
     * Must be called after failover BH is completed,
     * Or the failover BH may shutdown the wrong fd that
     * re-used by other threads after we release here.
     */
    if (s->rp_state.from_dst_file) {
        qemu_fclose(s->rp_state.from_dst_file);
    }
}