@@ -357,11 +357,20 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
goto out;
}
+ colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
+ if (local_err) {
+ 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_savevm_state_begin(s->to_dst_file, &s->params);
+ ret = qemu_file_get_error(s->to_dst_file);
+ if (ret < 0) {
+ error_report("Save VM state begin error");
+ goto out;
+ }
/* We call this API although this may do nothing on primary side. */
qemu_mutex_lock_iothread();
@@ -372,15 +381,21 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
}
qemu_mutex_lock_iothread();
- qemu_savevm_state_complete_precopy(fb, false);
+ /*
+ * 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);
+ /* Note: device state is saved into buffer */
+ ret = qemu_save_device_state(fb);
qemu_mutex_unlock_iothread();
-
- qemu_fflush(fb);
-
- colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
- if (local_err) {
+ if (ret < 0) {
+ error_report("Save device state error");
goto out;
}
+ 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.
@@ -621,6 +636,7 @@ void *colo_process_incoming_thread(void *opaque)
uint64_t total_size;
uint64_t value;
Error *local_err = NULL;
+ int ret;
qemu_sem_init(&mis->colo_incoming_sem, 0);
@@ -693,6 +709,17 @@ void *colo_process_incoming_thread(void *opaque)
goto out;
}
+ ret = qemu_loadvm_state_begin(mis->from_src_file);
+ if (ret < 0) {
+ error_report("Load vm state begin error, ret=%d", ret);
+ goto out;
+ }
+ ret = qemu_loadvm_state_main(mis->from_src_file, mis);
+ 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) {
@@ -726,8 +753,10 @@ void *colo_process_incoming_thread(void *opaque)
qemu_mutex_lock_iothread();
qemu_system_reset(VMRESET_SILENT);
vmstate_loading = true;
- if (qemu_loadvm_state(fb) < 0) {
- error_report("COLO: loadvm failed");
+ colo_flush_ram_cache();
+ ret = qemu_load_device_state(fb);
+ if (ret < 0) {
+ error_report("COLO: load device state failed");
qemu_mutex_unlock_iothread();
goto out;
}
@@ -2602,7 +2602,6 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
bool postcopy_running = postcopy_state_get() >= POSTCOPY_INCOMING_LISTENING;
/* ADVISE is earlier, it shows the source has the postcopy capability on */
bool postcopy_advised = postcopy_state_get() >= POSTCOPY_INCOMING_ADVISE;
- bool need_flush = false;
seq_iter++;
@@ -2637,7 +2636,6 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
/* After going into COLO, we should load the Page into colo_cache */
if (migration_incoming_in_colo_state()) {
host = colo_cache_from_block_offset(block, addr);
- need_flush = true;
} else {
host = host_from_ram_block_offset(block, addr);
}
@@ -2745,9 +2743,6 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
rcu_read_unlock();
trace_ram_load_complete(ret, seq_iter);
- if (!ret && ram_cache_enable && need_flush) {
- colo_flush_ram_cache();
- }
return ret;
}
@@ -1003,6 +1003,10 @@ void qemu_savevm_state_begin(QEMUFile *f,
break;
}
}
+ if (migration_in_colo_state()) {
+ qemu_put_byte(f, QEMU_VM_EOF);
+ qemu_fflush(f);
+ }
}
/*