int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
{
ram_addr_t addr;
uint64_t bytes_transferred_last;
double bwidth = 0;
uint64_t expected_time = 0;
if (stage < 0) {
cpu_physical_memory_set_dirty_tracking(0);
return 0;
}
if (cpu_physical_sync_dirty_bitmap(0, TARGET_PHYS_ADDR_MAX) != 0) {
qemu_file_set_error(f);
return 0;
}
if (stage == 1) {
bytes_transferred = 0;
/* Make sure all dirty bits are set */
for (addr = 0; addr < last_ram_offset; addr += TARGET_PAGE_SIZE) {
if (!cpu_physical_memory_get_dirty(addr, MIGRATION_DIRTY_FLAG)) {
cpu_physical_memory_set_dirty(addr);
}
}
/* Enable dirty memory tracking */
cpu_physical_memory_set_dirty_tracking(1);
qemu_put_be64(f, last_ram_offset | RAM_SAVE_FLAG_MEM_SIZE);
}
bytes_transferred_last = bytes_transferred;
bwidth = qemu_get_clock_ns(rt_clock);
while (!qemu_file_rate_limit(f)) {
int ret;
ret = ram_save_block(f);
bytes_transferred += ret * TARGET_PAGE_SIZE;
if (ret == 0) { /* no more blocks */
break;
}
}
bwidth = qemu_get_clock_ns(rt_clock) - bwidth;
bwidth = (bytes_transferred - bytes_transferred_last) / bwidth;
/* if we haven't transferred anything this round, force expected_time to a
* a very high value, but without crashing */
if (bwidth == 0) {
bwidth = 0.000001;
}
/* try transferring iterative blocks of memory */
if (stage == 3) {
/* flush all remaining blocks regardless of rate limiting */
while (ram_save_block(f) != 0) {
bytes_transferred += TARGET_PAGE_SIZE;
}
cpu_physical_memory_set_dirty_tracking(0);
}
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
expected_time = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
return (stage == 2) && (expected_time <= migrate_max_downtime());
}
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;
}
