* GNU GPL, version 2 or (at your option) any later version.
*/
+#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "sysemu/sysemu.h"
#include "block/block.h"
#include "qapi/qmp/qerror.h"
+#include "qapi/util.h"
#include "qemu/sockets.h"
#include "qemu/rcu.h"
#include "migration/block.h"
+#include "migration/postcopy-ram.h"
#include "qemu/thread.h"
#include "qmp-commands.h"
#include "trace.h"
-#include "qapi/util.h"
#include "qapi-event.h"
#include "qom/cpu.h"
+#include "exec/memory.h"
+#include "exec/address-spaces.h"
#define MAX_THROTTLE (32 << 20) /* Migration transfer speed throttling */
/* For outgoing */
MigrationState *migrate_get_current(void)
{
+ static bool once;
static MigrationState current_migration = {
.state = MIGRATION_STATUS_NONE,
.bandwidth_limit = MAX_THROTTLE,
DEFAULT_MIGRATE_X_CPU_THROTTLE_INCREMENT,
};
+ if (!once) {
+ qemu_mutex_init(¤t_migration.src_page_req_mutex);
+ once = true;
+ }
return ¤t_migration;
}
{
mis_current = g_new0(MigrationIncomingState, 1);
mis_current->from_src_file = f;
+ mis_current->state = MIGRATION_STATUS_NONE;
QLIST_INIT(&mis_current->loadvm_handlers);
qemu_mutex_init(&mis_current->rp_mutex);
qemu_event_init(&mis_current->main_thread_load_event, false);
s->received = true;
trace_migrate_global_state_post_load(runstate);
- r = qapi_enum_parse(RunState_lookup, runstate, RUN_STATE_MAX,
+ r = qapi_enum_parse(RunState_lookup, runstate, RUN_STATE__MAX,
-1, &local_err);
if (r == -1) {
deferred_incoming = true;
}
+/* Request a range of pages from the source VM at the given
+ * start address.
+ * rbname: Name of the RAMBlock to request the page in, if NULL it's the same
+ * as the last request (a name must have been given previously)
+ * Start: Address offset within the RB
+ * Len: Length in bytes required - must be a multiple of pagesize
+ */
+void migrate_send_rp_req_pages(MigrationIncomingState *mis, const char *rbname,
+ ram_addr_t start, size_t len)
+{
+ uint8_t bufc[12 + 1 + 255]; /* start (8), len (4), rbname upto 256 */
+ size_t msglen = 12; /* start + len */
+
+ *(uint64_t *)bufc = cpu_to_be64((uint64_t)start);
+ *(uint32_t *)(bufc + 8) = cpu_to_be32((uint32_t)len);
+
+ if (rbname) {
+ int rbname_len = strlen(rbname);
+ assert(rbname_len < 256);
+
+ bufc[msglen++] = rbname_len;
+ memcpy(bufc + msglen, rbname, rbname_len);
+ msglen += rbname_len;
+ migrate_send_rp_message(mis, MIG_RP_MSG_REQ_PAGES_ID, msglen, bufc);
+ } else {
+ migrate_send_rp_message(mis, MIG_RP_MSG_REQ_PAGES, msglen, bufc);
+ }
+}
+
void qemu_start_incoming_migration(const char *uri, Error **errp)
{
const char *p;
{
QEMUFile *f = opaque;
Error *local_err = NULL;
+ MigrationIncomingState *mis;
+ PostcopyState ps;
int ret;
- migration_incoming_state_new(f);
+ mis = migration_incoming_state_new(f);
postcopy_state_set(POSTCOPY_INCOMING_NONE);
- migrate_generate_event(MIGRATION_STATUS_ACTIVE);
+ migrate_set_state(&mis->state, MIGRATION_STATUS_NONE,
+ MIGRATION_STATUS_ACTIVE);
ret = qemu_loadvm_state(f);
+ ps = postcopy_state_get();
+ trace_process_incoming_migration_co_end(ret, ps);
+ if (ps != POSTCOPY_INCOMING_NONE) {
+ if (ps == POSTCOPY_INCOMING_ADVISE) {
+ /*
+ * Where a migration had postcopy enabled (and thus went to advise)
+ * but managed to complete within the precopy period, we can use
+ * the normal exit.
+ */
+ postcopy_ram_incoming_cleanup(mis);
+ } else if (ret >= 0) {
+ /*
+ * Postcopy was started, cleanup should happen at the end of the
+ * postcopy thread.
+ */
+ trace_process_incoming_migration_co_postcopy_end_main();
+ return;
+ }
+ /* Else if something went wrong then just fall out of the normal exit */
+ }
+
qemu_fclose(f);
free_xbzrle_decoded_buf();
- migration_incoming_state_destroy();
if (ret < 0) {
- migrate_generate_event(MIGRATION_STATUS_FAILED);
+ migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
+ MIGRATION_STATUS_FAILED);
error_report("load of migration failed: %s", strerror(-ret));
migrate_decompress_threads_join();
exit(EXIT_FAILURE);
/* Make sure all file formats flush their mutable metadata */
bdrv_invalidate_cache_all(&local_err);
if (local_err) {
- migrate_generate_event(MIGRATION_STATUS_FAILED);
+ migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
+ MIGRATION_STATUS_FAILED);
error_report_err(local_err);
migrate_decompress_threads_join();
exit(EXIT_FAILURE);
* observer sees this event they might start to prod at the VM assuming
* it's ready to use.
*/
- migrate_generate_event(MIGRATION_STATUS_COMPLETED);
+ migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
+ MIGRATION_STATUS_COMPLETED);
+ migration_incoming_state_destroy();
}
void process_incoming_migration(QEMUFile *f)
int i;
caps = NULL; /* silence compiler warning */
- for (i = 0; i < MIGRATION_CAPABILITY_MAX; i++) {
+ for (i = 0; i < MIGRATION_CAPABILITY__MAX; i++) {
if (head == NULL) {
head = g_malloc0(sizeof(*caps));
caps = head;
{
switch (state) {
case MIGRATION_STATUS_ACTIVE:
+ case MIGRATION_STATUS_POSTCOPY_ACTIVE:
case MIGRATION_STATUS_SETUP:
return true;
info->x_cpu_throttle_percentage = cpu_throttle_get_percentage();
}
+ get_xbzrle_cache_stats(info);
+ break;
+ case MIGRATION_STATUS_POSTCOPY_ACTIVE:
+ /* Mostly the same as active; TODO add some postcopy stats */
+ info->has_status = true;
+ info->has_total_time = true;
+ info->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME)
+ - s->total_time;
+ info->has_expected_downtime = true;
+ info->expected_downtime = s->expected_downtime;
+ info->has_setup_time = true;
+ info->setup_time = s->setup_time;
+
+ info->has_ram = true;
+ info->ram = g_malloc0(sizeof(*info->ram));
+ info->ram->transferred = ram_bytes_transferred();
+ info->ram->remaining = ram_bytes_remaining();
+ info->ram->total = ram_bytes_total();
+ info->ram->duplicate = dup_mig_pages_transferred();
+ info->ram->skipped = skipped_mig_pages_transferred();
+ info->ram->normal = norm_mig_pages_transferred();
+ info->ram->normal_bytes = norm_mig_bytes_transferred();
+ info->ram->dirty_pages_rate = s->dirty_pages_rate;
+ info->ram->mbps = s->mbps;
+
+ if (blk_mig_active()) {
+ info->has_disk = true;
+ info->disk = g_malloc0(sizeof(*info->disk));
+ info->disk->transferred = blk_mig_bytes_transferred();
+ info->disk->remaining = blk_mig_bytes_remaining();
+ info->disk->total = blk_mig_bytes_total();
+ }
+
get_xbzrle_cache_stats(info);
break;
case MIGRATION_STATUS_COMPLETED:
MigrationState *s = migrate_get_current();
if (!migrate_postcopy_ram()) {
- error_setg(errp, "Enable postcopy with migration_set_capability before"
+ error_setg(errp, "Enable postcopy with migrate_set_capability before"
" the start of migration");
return;
}
/* shared migration helpers */
-static void migrate_set_state(MigrationState *s, int old_state, int new_state)
+void migrate_set_state(int *state, int old_state, int new_state)
{
- if (atomic_cmpxchg(&s->state, old_state, new_state) == old_state) {
+ if (atomic_cmpxchg(state, old_state, new_state) == old_state) {
trace_migrate_set_state(new_state);
migrate_generate_event(new_state);
}
qemu_bh_delete(s->cleanup_bh);
s->cleanup_bh = NULL;
- if (s->file) {
+ flush_page_queue(s);
+
+ if (s->to_dst_file) {
trace_migrate_fd_cleanup();
qemu_mutex_unlock_iothread();
- qemu_thread_join(&s->thread);
+ if (s->migration_thread_running) {
+ qemu_thread_join(&s->thread);
+ s->migration_thread_running = false;
+ }
qemu_mutex_lock_iothread();
migrate_compress_threads_join();
- qemu_fclose(s->file);
- s->file = NULL;
+ qemu_fclose(s->to_dst_file);
+ s->to_dst_file = NULL;
}
- assert(s->state != MIGRATION_STATUS_ACTIVE);
+ assert((s->state != MIGRATION_STATUS_ACTIVE) &&
+ (s->state != MIGRATION_STATUS_POSTCOPY_ACTIVE));
if (s->state == MIGRATION_STATUS_CANCELLING) {
- migrate_set_state(s, MIGRATION_STATUS_CANCELLING,
+ migrate_set_state(&s->state, MIGRATION_STATUS_CANCELLING,
MIGRATION_STATUS_CANCELLED);
}
void migrate_fd_error(MigrationState *s)
{
trace_migrate_fd_error();
- assert(s->file == NULL);
- migrate_set_state(s, MIGRATION_STATUS_SETUP, MIGRATION_STATUS_FAILED);
+ assert(s->to_dst_file == NULL);
+ migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
+ MIGRATION_STATUS_FAILED);
notifier_list_notify(&migration_state_notifiers, s);
}
static void migrate_fd_cancel(MigrationState *s)
{
int old_state ;
- QEMUFile *f = migrate_get_current()->file;
+ QEMUFile *f = migrate_get_current()->to_dst_file;
trace_migrate_fd_cancel();
if (s->rp_state.from_dst_file) {
if (!migration_is_setup_or_active(old_state)) {
break;
}
- migrate_set_state(s, old_state, MIGRATION_STATUS_CANCELLING);
+ migrate_set_state(&s->state, old_state, MIGRATION_STATUS_CANCELLING);
} while (s->state != MIGRATION_STATUS_CANCELLING);
/*
s->state == MIGRATION_STATUS_FAILED);
}
+bool migration_in_postcopy(MigrationState *s)
+{
+ return (s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE);
+}
+
MigrationState *migrate_init(const MigrationParams *params)
{
MigrationState *s = migrate_get_current();
- int64_t bandwidth_limit = s->bandwidth_limit;
- bool enabled_capabilities[MIGRATION_CAPABILITY_MAX];
- int64_t xbzrle_cache_size = s->xbzrle_cache_size;
- int compress_level = s->parameters[MIGRATION_PARAMETER_COMPRESS_LEVEL];
- int compress_thread_count =
- s->parameters[MIGRATION_PARAMETER_COMPRESS_THREADS];
- int decompress_thread_count =
- s->parameters[MIGRATION_PARAMETER_DECOMPRESS_THREADS];
- int x_cpu_throttle_initial =
- s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL];
- int x_cpu_throttle_increment =
- s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT];
-
- memcpy(enabled_capabilities, s->enabled_capabilities,
- sizeof(enabled_capabilities));
- memset(s, 0, sizeof(*s));
+ /*
+ * Reinitialise all migration state, except
+ * parameters/capabilities that the user set, and
+ * locks.
+ */
+ s->bytes_xfer = 0;
+ s->xfer_limit = 0;
+ s->cleanup_bh = 0;
+ s->to_dst_file = NULL;
+ s->state = MIGRATION_STATUS_NONE;
s->params = *params;
- memcpy(s->enabled_capabilities, enabled_capabilities,
- sizeof(enabled_capabilities));
- s->xbzrle_cache_size = xbzrle_cache_size;
-
- s->parameters[MIGRATION_PARAMETER_COMPRESS_LEVEL] = compress_level;
- s->parameters[MIGRATION_PARAMETER_COMPRESS_THREADS] =
- compress_thread_count;
- s->parameters[MIGRATION_PARAMETER_DECOMPRESS_THREADS] =
- decompress_thread_count;
- s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL] =
- x_cpu_throttle_initial;
- s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT] =
- x_cpu_throttle_increment;
- s->bandwidth_limit = bandwidth_limit;
- migrate_set_state(s, MIGRATION_STATUS_NONE, MIGRATION_STATUS_SETUP);
+ s->rp_state.from_dst_file = NULL;
+ s->rp_state.error = false;
+ s->mbps = 0.0;
+ s->downtime = 0;
+ s->expected_downtime = 0;
+ s->dirty_pages_rate = 0;
+ s->dirty_bytes_rate = 0;
+ s->setup_time = 0;
+ s->dirty_sync_count = 0;
+ s->start_postcopy = false;
+ s->migration_thread_running = false;
+ s->last_req_rb = NULL;
+
+ migrate_set_state(&s->state, MIGRATION_STATUS_NONE, MIGRATION_STATUS_SETUP);
+
+ QSIMPLEQ_INIT(&s->src_page_requests);
s->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
return s;
return;
}
- /* We are starting a new migration, so we want to start in a clean
- state. This change is only needed if previous migration
- failed/was cancelled. We don't use migrate_set_state() because
- we are setting the initial state, not changing it. */
- s->state = MIGRATION_STATUS_NONE;
-
s = migrate_init(¶ms);
if (strstart(uri, "tcp:", &p)) {
} else {
error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "uri",
"a valid migration protocol");
- migrate_set_state(s, MIGRATION_STATUS_SETUP, MIGRATION_STATUS_FAILED);
+ migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
+ MIGRATION_STATUS_FAILED);
return;
}
s = migrate_get_current();
s->bandwidth_limit = value;
- if (s->file) {
- qemu_file_set_rate_limit(s->file, s->bandwidth_limit / XFER_LIMIT_RATIO);
+ if (s->to_dst_file) {
+ qemu_file_set_rate_limit(s->to_dst_file,
+ s->bandwidth_limit / XFER_LIMIT_RATIO);
}
}
[MIG_RP_MSG_INVALID] = { .len = -1, .name = "INVALID" },
[MIG_RP_MSG_SHUT] = { .len = 4, .name = "SHUT" },
[MIG_RP_MSG_PONG] = { .len = 4, .name = "PONG" },
+ [MIG_RP_MSG_REQ_PAGES] = { .len = 12, .name = "REQ_PAGES" },
+ [MIG_RP_MSG_REQ_PAGES_ID] = { .len = -1, .name = "REQ_PAGES_ID" },
[MIG_RP_MSG_MAX] = { .len = -1, .name = "MAX" },
};
+/*
+ * Process a request for pages received on the return path,
+ * We're allowed to send more than requested (e.g. to round to our page size)
+ * and we don't need to send pages that have already been sent.
+ */
+static void migrate_handle_rp_req_pages(MigrationState *ms, const char* rbname,
+ ram_addr_t start, size_t len)
+{
+ long our_host_ps = getpagesize();
+
+ trace_migrate_handle_rp_req_pages(rbname, start, len);
+
+ /*
+ * Since we currently insist on matching page sizes, just sanity check
+ * we're being asked for whole host pages.
+ */
+ if (start & (our_host_ps-1) ||
+ (len & (our_host_ps-1))) {
+ error_report("%s: Misaligned page request, start: " RAM_ADDR_FMT
+ " len: %zd", __func__, start, len);
+ mark_source_rp_bad(ms);
+ return;
+ }
+
+ if (ram_save_queue_pages(ms, rbname, start, len)) {
+ mark_source_rp_bad(ms);
+ }
+}
+
/*
* Handles messages sent on the return path towards the source VM
*
const int max_len = 512;
uint8_t buf[max_len];
uint32_t tmp32, sibling_error;
+ ram_addr_t start = 0; /* =0 to silence warning */
+ size_t len = 0, expected_len;
int res;
trace_source_return_path_thread_entry();
trace_source_return_path_thread_pong(tmp32);
break;
+ case MIG_RP_MSG_REQ_PAGES:
+ start = be64_to_cpup((uint64_t *)buf);
+ len = be32_to_cpup((uint32_t *)(buf + 8));
+ migrate_handle_rp_req_pages(ms, NULL, start, len);
+ break;
+
+ case MIG_RP_MSG_REQ_PAGES_ID:
+ expected_len = 12 + 1; /* header + termination */
+
+ if (header_len >= expected_len) {
+ start = be64_to_cpup((uint64_t *)buf);
+ len = be32_to_cpup((uint32_t *)(buf + 8));
+ /* Now we expect an idstr */
+ tmp32 = buf[12]; /* Length of the following idstr */
+ buf[13 + tmp32] = '\0';
+ expected_len += tmp32;
+ }
+ if (header_len != expected_len) {
+ error_report("RP: Req_Page_id with length %d expecting %zd",
+ header_len, expected_len);
+ mark_source_rp_bad(ms);
+ goto out;
+ }
+ migrate_handle_rp_req_pages(ms, (char *)&buf[13], start, len);
+ break;
+
default:
break;
}
}
- if (rp && qemu_file_get_error(rp)) {
+ if (qemu_file_get_error(rp)) {
trace_source_return_path_thread_bad_end();
mark_source_rp_bad(ms);
}
return NULL;
}
-__attribute__ (( unused )) /* Until later in patch series */
static int open_return_path_on_source(MigrationState *ms)
{
- ms->rp_state.from_dst_file = qemu_file_get_return_path(ms->file);
+ ms->rp_state.from_dst_file = qemu_file_get_return_path(ms->to_dst_file);
if (!ms->rp_state.from_dst_file) {
return -1;
}
return 0;
}
-__attribute__ (( unused )) /* Until later in patch series */
/* Returns 0 if the RP was ok, otherwise there was an error on the RP */
static int await_return_path_close_on_source(MigrationState *ms)
{
* rp_thread will exit, however if there's an error we need to cause
* it to exit.
*/
- if (qemu_file_get_error(ms->file) && ms->rp_state.from_dst_file) {
+ if (qemu_file_get_error(ms->to_dst_file) && ms->rp_state.from_dst_file) {
/*
* shutdown(2), if we have it, will cause it to unblock if it's stuck
* waiting for the destination.
return ms->rp_state.error;
}
+/*
+ * Switch from normal iteration to postcopy
+ * Returns non-0 on error
+ */
+static int postcopy_start(MigrationState *ms, bool *old_vm_running)
+{
+ int ret;
+ const QEMUSizedBuffer *qsb;
+ int64_t time_at_stop = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+ migrate_set_state(&ms->state, MIGRATION_STATUS_ACTIVE,
+ MIGRATION_STATUS_POSTCOPY_ACTIVE);
+
+ trace_postcopy_start();
+ qemu_mutex_lock_iothread();
+ trace_postcopy_start_set_run();
+
+ qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER);
+ *old_vm_running = runstate_is_running();
+ global_state_store();
+ ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ ret = bdrv_inactivate_all();
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /*
+ * Cause any non-postcopiable, but iterative devices to
+ * send out their final data.
+ */
+ qemu_savevm_state_complete_precopy(ms->to_dst_file, true);
+
+ /*
+ * in Finish migrate and with the io-lock held everything should
+ * be quiet, but we've potentially still got dirty pages and we
+ * need to tell the destination to throw any pages it's already received
+ * that are dirty
+ */
+ if (ram_postcopy_send_discard_bitmap(ms)) {
+ error_report("postcopy send discard bitmap failed");
+ goto fail;
+ }
+
+ /*
+ * send rest of state - note things that are doing postcopy
+ * will notice we're in POSTCOPY_ACTIVE and not actually
+ * wrap their state up here
+ */
+ qemu_file_set_rate_limit(ms->to_dst_file, INT64_MAX);
+ /* Ping just for debugging, helps line traces up */
+ qemu_savevm_send_ping(ms->to_dst_file, 2);
+
+ /*
+ * While loading the device state we may trigger page transfer
+ * requests and the fd must be free to process those, and thus
+ * the destination must read the whole device state off the fd before
+ * it starts processing it. Unfortunately the ad-hoc migration format
+ * doesn't allow the destination to know the size to read without fully
+ * parsing it through each devices load-state code (especially the open
+ * coded devices that use get/put).
+ * So we wrap the device state up in a package with a length at the start;
+ * to do this we use a qemu_buf to hold the whole of the device state.
+ */
+ QEMUFile *fb = qemu_bufopen("w", NULL);
+ if (!fb) {
+ error_report("Failed to create buffered file");
+ goto fail;
+ }
+
+ /*
+ * Make sure the receiver can get incoming pages before we send the rest
+ * of the state
+ */
+ qemu_savevm_send_postcopy_listen(fb);
+
+ qemu_savevm_state_complete_precopy(fb, false);
+ qemu_savevm_send_ping(fb, 3);
+
+ qemu_savevm_send_postcopy_run(fb);
+
+ /* <><> end of stuff going into the package */
+ qsb = qemu_buf_get(fb);
+
+ /* Now send that blob */
+ if (qemu_savevm_send_packaged(ms->to_dst_file, qsb)) {
+ goto fail_closefb;
+ }
+ qemu_fclose(fb);
+ ms->downtime = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) - time_at_stop;
+
+ qemu_mutex_unlock_iothread();
+
+ /*
+ * Although this ping is just for debug, it could potentially be
+ * used for getting a better measurement of downtime at the source.
+ */
+ qemu_savevm_send_ping(ms->to_dst_file, 4);
+
+ ret = qemu_file_get_error(ms->to_dst_file);
+ if (ret) {
+ error_report("postcopy_start: Migration stream errored");
+ migrate_set_state(&ms->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
+ MIGRATION_STATUS_FAILED);
+ }
+
+ return ret;
+
+fail_closefb:
+ qemu_fclose(fb);
+fail:
+ migrate_set_state(&ms->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
+ MIGRATION_STATUS_FAILED);
+ qemu_mutex_unlock_iothread();
+ return -1;
+}
+
/**
* migration_completion: Used by migration_thread when there's not much left.
* The caller 'breaks' the loop when this returns.
*
* @s: Current migration state
+ * @current_active_state: The migration state we expect to be in
* @*old_vm_running: Pointer to old_vm_running flag
* @*start_time: Pointer to time to update
*/
-static void migration_completion(MigrationState *s, bool *old_vm_running,
+static void migration_completion(MigrationState *s, int current_active_state,
+ bool *old_vm_running,
int64_t *start_time)
{
int ret;
- 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();
+ if (s->state == MIGRATION_STATUS_ACTIVE) {
+ 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 = global_state_store();
+
+ if (!ret) {
+ ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
+ if (ret >= 0) {
+ ret = bdrv_inactivate_all();
+ }
+ if (ret >= 0) {
+ qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX);
+ qemu_savevm_state_complete_precopy(s->to_dst_file, false);
+ }
+ }
+ qemu_mutex_unlock_iothread();
- ret = global_state_store();
- if (!ret) {
- 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_precopy(s->file);
+ if (ret < 0) {
+ goto fail;
}
+ } else if (s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) {
+ trace_migration_completion_postcopy_end();
+
+ qemu_savevm_state_complete_postcopy(s->to_dst_file);
+ trace_migration_completion_postcopy_end_after_complete();
}
- qemu_mutex_unlock_iothread();
- if (ret < 0) {
- goto fail;
+ /*
+ * If rp was opened we must clean up the thread before
+ * cleaning everything else up (since if there are no failures
+ * it will wait for the destination to send it's status in
+ * a SHUT command).
+ * Postcopy opens rp if enabled (even if it's not avtivated)
+ */
+ if (migrate_postcopy_ram()) {
+ int rp_error;
+ trace_migration_completion_postcopy_end_before_rp();
+ rp_error = await_return_path_close_on_source(s);
+ trace_migration_completion_postcopy_end_after_rp(rp_error);
+ if (rp_error) {
+ goto fail;
+ }
}
- if (qemu_file_get_error(s->file)) {
+ if (qemu_file_get_error(s->to_dst_file)) {
trace_migration_completion_file_err();
goto fail;
}
- migrate_set_state(s, MIGRATION_STATUS_ACTIVE, MIGRATION_STATUS_COMPLETED);
+ migrate_set_state(&s->state, current_active_state,
+ MIGRATION_STATUS_COMPLETED);
return;
fail:
- migrate_set_state(s, MIGRATION_STATUS_ACTIVE, MIGRATION_STATUS_FAILED);
+ migrate_set_state(&s->state, current_active_state,
+ MIGRATION_STATUS_FAILED);
}
/*
static void *migration_thread(void *opaque)
{
MigrationState *s = opaque;
+ /* Used by the bandwidth calcs, updated later */
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 start_time = initial_time;
int64_t end_time;
bool old_vm_running = false;
+ bool entered_postcopy = false;
+ /* The active state we expect to be in; ACTIVE or POSTCOPY_ACTIVE */
+ enum MigrationStatus current_active_state = MIGRATION_STATUS_ACTIVE;
rcu_register_thread();
- qemu_savevm_state_header(s->file);
- qemu_savevm_state_begin(s->file, &s->params);
+ qemu_savevm_state_header(s->to_dst_file);
+
+ if (migrate_postcopy_ram()) {
+ /* Now tell the dest that it should open its end so it can reply */
+ qemu_savevm_send_open_return_path(s->to_dst_file);
+
+ /* And do a ping that will make stuff easier to debug */
+ qemu_savevm_send_ping(s->to_dst_file, 1);
+
+ /*
+ * Tell the destination that we *might* want to do postcopy later;
+ * if the other end can't do postcopy it should fail now, nice and
+ * early.
+ */
+ qemu_savevm_send_postcopy_advise(s->to_dst_file);
+ }
+
+ qemu_savevm_state_begin(s->to_dst_file, &s->params);
s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
- migrate_set_state(s, MIGRATION_STATUS_SETUP, MIGRATION_STATUS_ACTIVE);
+ current_active_state = MIGRATION_STATUS_ACTIVE;
+ migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
+ MIGRATION_STATUS_ACTIVE);
+
+ trace_migration_thread_setup_complete();
- while (s->state == MIGRATION_STATUS_ACTIVE) {
+ while (s->state == MIGRATION_STATUS_ACTIVE ||
+ s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) {
int64_t current_time;
uint64_t pending_size;
- if (!qemu_file_rate_limit(s->file)) {
+ if (!qemu_file_rate_limit(s->to_dst_file)) {
uint64_t pend_post, pend_nonpost;
- qemu_savevm_state_pending(s->file, max_size, &pend_nonpost,
+ qemu_savevm_state_pending(s->to_dst_file, max_size, &pend_nonpost,
&pend_post);
pending_size = pend_nonpost + pend_post;
trace_migrate_pending(pending_size, max_size,
pend_post, pend_nonpost);
if (pending_size && pending_size >= max_size) {
- qemu_savevm_state_iterate(s->file);
+ /* Still a significant amount to transfer */
+
+ if (migrate_postcopy_ram() &&
+ s->state != MIGRATION_STATUS_POSTCOPY_ACTIVE &&
+ pend_nonpost <= max_size &&
+ atomic_read(&s->start_postcopy)) {
+
+ if (!postcopy_start(s, &old_vm_running)) {
+ current_active_state = MIGRATION_STATUS_POSTCOPY_ACTIVE;
+ entered_postcopy = true;
+ }
+
+ continue;
+ }
+ /* Just another iteration step */
+ qemu_savevm_state_iterate(s->to_dst_file, entered_postcopy);
} else {
trace_migration_thread_low_pending(pending_size);
- migration_completion(s, &old_vm_running, &start_time);
+ migration_completion(s, current_active_state,
+ &old_vm_running, &start_time);
break;
}
}
- if (qemu_file_get_error(s->file)) {
- migrate_set_state(s, MIGRATION_STATUS_ACTIVE,
+ if (qemu_file_get_error(s->to_dst_file)) {
+ migrate_set_state(&s->state, current_active_state,
MIGRATION_STATUS_FAILED);
+ trace_migration_thread_file_err();
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 transferred_bytes = qemu_ftell(s->to_dst_file) -
+ initial_bytes;
uint64_t time_spent = current_time - initial_time;
- double bandwidth = transferred_bytes / time_spent;
+ double bandwidth = (double)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;
+ s->mbps = (((double) transferred_bytes * 8.0) /
+ ((double) time_spent / 1000.0)) / 1000.0 / 1000.0;
trace_migrate_transferred(transferred_bytes, time_spent,
bandwidth, max_size);
s->expected_downtime = s->dirty_bytes_rate / bandwidth;
}
- qemu_file_reset_rate_limit(s->file);
+ qemu_file_reset_rate_limit(s->to_dst_file);
initial_time = current_time;
- initial_bytes = qemu_ftell(s->file);
+ initial_bytes = qemu_ftell(s->to_dst_file);
}
- if (qemu_file_rate_limit(s->file)) {
+ if (qemu_file_rate_limit(s->to_dst_file)) {
/* usleep expects microseconds */
g_usleep((initial_time + BUFFER_DELAY - current_time)*1000);
}
}
+ trace_migration_thread_after_loop();
/* If we enabled cpu throttling for auto-converge, turn it off. */
cpu_throttle_stop();
end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
qemu_mutex_lock_iothread();
qemu_savevm_state_cleanup();
if (s->state == MIGRATION_STATUS_COMPLETED) {
- uint64_t transferred_bytes = qemu_ftell(s->file);
+ uint64_t transferred_bytes = qemu_ftell(s->to_dst_file);
s->total_time = end_time - s->total_time;
- s->downtime = end_time - start_time;
+ if (!entered_postcopy) {
+ s->downtime = end_time - start_time;
+ }
if (s->total_time) {
s->mbps = (((double) transferred_bytes * 8.0) /
((double) s->total_time)) / 1000;
}
runstate_set(RUN_STATE_POSTMIGRATE);
} else {
- if (old_vm_running) {
+ if (old_vm_running && !entered_postcopy) {
vm_start();
}
}
s->expected_downtime = max_downtime/1000000;
s->cleanup_bh = qemu_bh_new(migrate_fd_cleanup, s);
- qemu_file_set_rate_limit(s->file,
+ qemu_file_set_rate_limit(s->to_dst_file,
s->bandwidth_limit / XFER_LIMIT_RATIO);
/* Notify before starting migration thread */
notifier_list_notify(&migration_state_notifiers, s);
+ /*
+ * Open the return path; currently for postcopy but other things might
+ * also want it.
+ */
+ if (migrate_postcopy_ram()) {
+ if (open_return_path_on_source(s)) {
+ error_report("Unable to open return-path for postcopy");
+ migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
+ MIGRATION_STATUS_FAILED);
+ migrate_fd_cleanup(s);
+ return;
+ }
+ }
+
migrate_compress_threads_create();
qemu_thread_create(&s->thread, "migration", migration_thread, s,
QEMU_THREAD_JOINABLE);
+ s->migration_thread_running = true;
}
PostcopyState postcopy_state_get(void)
projects / mirror_qemu.git / blobdiff