* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu-common.h"
-#include "migration.h"
-#include "monitor.h"
-#include "buffered_file.h"
-#include "sysemu.h"
-#include "block.h"
-#include "qemu_socket.h"
-#include "block-migration.h"
-#include "qemu-objects.h"
+#include "migration/migration.h"
+#include "monitor/monitor.h"
+#include "migration/qemu-file.h"
+#include "sysemu/sysemu.h"
+#include "block/block.h"
+#include "qemu/sockets.h"
+#include "migration/block.h"
+#include "qemu/thread.h"
+#include "qmp-commands.h"
+#include "trace.h"
//#define DEBUG_MIGRATION
do { } while (0)
#endif
-/* Migration speed throttling */
-static int64_t max_throttle = (32 << 20);
+enum {
+ MIG_STATE_ERROR = -1,
+ MIG_STATE_NONE,
+ MIG_STATE_SETUP,
+ MIG_STATE_CANCELLED,
+ MIG_STATE_ACTIVE,
+ MIG_STATE_COMPLETED,
+};
-static MigrationState *current_migration;
+#define MAX_THROTTLE (32 << 20) /* Migration speed throttling */
+
+/* Amount of time to allocate to each "chunk" of bandwidth-throttled
+ * data. */
+#define BUFFER_DELAY 100
+#define XFER_LIMIT_RATIO (1000 / BUFFER_DELAY)
+
+/* Migration XBZRLE default cache size */
+#define DEFAULT_MIGRATE_CACHE_SIZE (64 * 1024 * 1024)
static NotifierList migration_state_notifiers =
NOTIFIER_LIST_INITIALIZER(migration_state_notifiers);
-int qemu_start_incoming_migration(const char *uri)
+/* When we add fault tolerance, we could have several
+ migrations at once. For now we don't need to add
+ dynamic creation of migration */
+
+MigrationState *migrate_get_current(void)
+{
+ static MigrationState current_migration = {
+ .state = MIG_STATE_NONE,
+ .bandwidth_limit = MAX_THROTTLE,
+ .xbzrle_cache_size = DEFAULT_MIGRATE_CACHE_SIZE,
+ .mbps = -1,
+ };
+
+ return ¤t_migration;
+}
+
+void qemu_start_incoming_migration(const char *uri, Error **errp)
{
const char *p;
- int ret;
if (strstart(uri, "tcp:", &p))
- ret = tcp_start_incoming_migration(p);
+ tcp_start_incoming_migration(p, errp);
+#ifdef CONFIG_RDMA
+ else if (strstart(uri, "x-rdma:", &p))
+ rdma_start_incoming_migration(p, errp);
+#endif
#if !defined(WIN32)
else if (strstart(uri, "exec:", &p))
- ret = exec_start_incoming_migration(p);
+ exec_start_incoming_migration(p, errp);
else if (strstart(uri, "unix:", &p))
- ret = unix_start_incoming_migration(p);
+ unix_start_incoming_migration(p, errp);
else if (strstart(uri, "fd:", &p))
- ret = fd_start_incoming_migration(p);
+ fd_start_incoming_migration(p, errp);
#endif
else {
- fprintf(stderr, "unknown migration protocol: %s\n", uri);
- ret = -EPROTONOSUPPORT;
+ error_setg(errp, "unknown migration protocol: %s", uri);
}
- return ret;
}
-void process_incoming_migration(QEMUFile *f)
+static void process_incoming_migration_co(void *opaque)
{
- if (qemu_loadvm_state(f) < 0) {
+ QEMUFile *f = opaque;
+ int ret;
+
+ ret = qemu_loadvm_state(f);
+ qemu_fclose(f);
+ if (ret < 0) {
fprintf(stderr, "load of migration failed\n");
- exit(0);
+ exit(EXIT_FAILURE);
}
qemu_announce_self();
DPRINTF("successfully loaded vm state\n");
- incoming_expected = false;
+ bdrv_clear_incoming_migration_all();
+ /* Make sure all file formats flush their mutable metadata */
+ bdrv_invalidate_cache_all();
- if (autostart)
+ if (autostart) {
vm_start();
-}
-
-int do_migrate(Monitor *mon, const QDict *qdict, QObject **ret_data)
-{
- MigrationState *s = NULL;
- const char *p;
- int detach = qdict_get_try_bool(qdict, "detach", 0);
- int blk = qdict_get_try_bool(qdict, "blk", 0);
- int inc = qdict_get_try_bool(qdict, "inc", 0);
- const char *uri = qdict_get_str(qdict, "uri");
-
- if (current_migration &&
- current_migration->get_status(current_migration) == MIG_STATE_ACTIVE) {
- monitor_printf(mon, "migration already in progress\n");
- return -1;
- }
-
- if (qemu_savevm_state_blocked(mon)) {
- return -1;
- }
-
- if (strstart(uri, "tcp:", &p)) {
- s = tcp_start_outgoing_migration(mon, p, max_throttle, detach,
- blk, inc);
-#if !defined(WIN32)
- } else if (strstart(uri, "exec:", &p)) {
- s = exec_start_outgoing_migration(mon, p, max_throttle, detach,
- blk, inc);
- } else if (strstart(uri, "unix:", &p)) {
- s = unix_start_outgoing_migration(mon, p, max_throttle, detach,
- blk, inc);
- } else if (strstart(uri, "fd:", &p)) {
- s = fd_start_outgoing_migration(mon, p, max_throttle, detach,
- blk, inc);
-#endif
} else {
- monitor_printf(mon, "unknown migration protocol: %s\n", uri);
- return -1;
- }
-
- if (s == NULL) {
- monitor_printf(mon, "migration failed\n");
- return -1;
+ runstate_set(RUN_STATE_PAUSED);
}
-
- if (current_migration) {
- current_migration->release(current_migration);
- }
-
- current_migration = s;
- notifier_list_notify(&migration_state_notifiers);
- return 0;
}
-int do_migrate_cancel(Monitor *mon, const QDict *qdict, QObject **ret_data)
-{
- MigrationState *s = current_migration;
-
- if (s)
- s->cancel(s);
-
- return 0;
-}
-
-int do_migrate_set_speed(Monitor *mon, const QDict *qdict, QObject **ret_data)
+void process_incoming_migration(QEMUFile *f)
{
- int64_t d;
- FdMigrationState *s;
-
- d = qdict_get_int(qdict, "value");
- if (d < 0) {
- d = 0;
- }
- max_throttle = d;
-
- s = migrate_to_fms(current_migration);
- if (s && s->file) {
- qemu_file_set_rate_limit(s->file, max_throttle);
- }
+ Coroutine *co = qemu_coroutine_create(process_incoming_migration_co);
+ int fd = qemu_get_fd(f);
- return 0;
+ assert(fd != -1);
+ qemu_set_nonblock(fd);
+ qemu_coroutine_enter(co, f);
}
/* amount of nanoseconds we are willing to wait for migration to be down.
return max_downtime;
}
-int do_migrate_set_downtime(Monitor *mon, const QDict *qdict,
- QObject **ret_data)
+MigrationCapabilityStatusList *qmp_query_migrate_capabilities(Error **errp)
{
- double d;
+ MigrationCapabilityStatusList *head = NULL;
+ MigrationCapabilityStatusList *caps;
+ MigrationState *s = migrate_get_current();
+ int i;
+
+ for (i = 0; i < MIGRATION_CAPABILITY_MAX; i++) {
+ if (head == NULL) {
+ head = g_malloc0(sizeof(*caps));
+ caps = head;
+ } else {
+ caps->next = g_malloc0(sizeof(*caps));
+ caps = caps->next;
+ }
+ caps->value =
+ g_malloc(sizeof(*caps->value));
+ caps->value->capability = i;
+ caps->value->state = s->enabled_capabilities[i];
+ }
- d = qdict_get_double(qdict, "value") * 1e9;
- d = MAX(0, MIN(UINT64_MAX, d));
- max_downtime = (uint64_t)d;
+ return head;
+}
- return 0;
+static void get_xbzrle_cache_stats(MigrationInfo *info)
+{
+ if (migrate_use_xbzrle()) {
+ info->has_xbzrle_cache = true;
+ info->xbzrle_cache = g_malloc0(sizeof(*info->xbzrle_cache));
+ info->xbzrle_cache->cache_size = migrate_xbzrle_cache_size();
+ info->xbzrle_cache->bytes = xbzrle_mig_bytes_transferred();
+ info->xbzrle_cache->pages = xbzrle_mig_pages_transferred();
+ info->xbzrle_cache->cache_miss = xbzrle_mig_pages_cache_miss();
+ info->xbzrle_cache->overflow = xbzrle_mig_pages_overflow();
+ }
}
-static void migrate_print_status(Monitor *mon, const char *name,
- const QDict *status_dict)
+MigrationInfo *qmp_query_migrate(Error **errp)
{
- QDict *qdict;
+ MigrationInfo *info = g_malloc0(sizeof(*info));
+ MigrationState *s = migrate_get_current();
+
+ switch (s->state) {
+ case MIG_STATE_NONE:
+ /* no migration has happened ever */
+ break;
+ case MIG_STATE_SETUP:
+ info->has_status = true;
+ info->status = g_strdup("setup");
+ info->has_total_time = false;
+ break;
+ case MIG_STATE_ACTIVE:
+ info->has_status = true;
+ info->status = g_strdup("active");
+ info->has_total_time = true;
+ info->total_time = qemu_get_clock_ms(rt_clock)
+ - 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();
+ }
- qdict = qobject_to_qdict(qdict_get(status_dict, name));
+ get_xbzrle_cache_stats(info);
+ break;
+ case MIG_STATE_COMPLETED:
+ get_xbzrle_cache_stats(info);
+
+ info->has_status = true;
+ info->status = g_strdup("completed");
+ info->has_total_time = true;
+ info->total_time = s->total_time;
+ info->has_downtime = true;
+ info->downtime = s->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 = 0;
+ 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->mbps = s->mbps;
+ break;
+ case MIG_STATE_ERROR:
+ info->has_status = true;
+ info->status = g_strdup("failed");
+ break;
+ case MIG_STATE_CANCELLED:
+ info->has_status = true;
+ info->status = g_strdup("cancelled");
+ break;
+ }
- monitor_printf(mon, "transferred %s: %" PRIu64 " kbytes\n", name,
- qdict_get_int(qdict, "transferred") >> 10);
- monitor_printf(mon, "remaining %s: %" PRIu64 " kbytes\n", name,
- qdict_get_int(qdict, "remaining") >> 10);
- monitor_printf(mon, "total %s: %" PRIu64 " kbytes\n", name,
- qdict_get_int(qdict, "total") >> 10);
+ return info;
}
-void do_info_migrate_print(Monitor *mon, const QObject *data)
+void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params,
+ Error **errp)
{
- QDict *qdict;
+ MigrationState *s = migrate_get_current();
+ MigrationCapabilityStatusList *cap;
- qdict = qobject_to_qdict(data);
-
- monitor_printf(mon, "Migration status: %s\n",
- qdict_get_str(qdict, "status"));
-
- if (qdict_haskey(qdict, "ram")) {
- migrate_print_status(mon, "ram", qdict);
+ if (s->state == MIG_STATE_ACTIVE || s->state == MIG_STATE_SETUP) {
+ error_set(errp, QERR_MIGRATION_ACTIVE);
+ return;
}
- if (qdict_haskey(qdict, "disk")) {
- migrate_print_status(mon, "disk", qdict);
+ for (cap = params; cap; cap = cap->next) {
+ s->enabled_capabilities[cap->value->capability] = cap->value->state;
}
}
-static void migrate_put_status(QDict *qdict, const char *name,
- uint64_t trans, uint64_t rem, uint64_t total)
-{
- QObject *obj;
-
- obj = qobject_from_jsonf("{ 'transferred': %" PRId64 ", "
- "'remaining': %" PRId64 ", "
- "'total': %" PRId64 " }", trans, rem, total);
- qdict_put_obj(qdict, name, obj);
-}
+/* shared migration helpers */
-void do_info_migrate(Monitor *mon, QObject **ret_data)
+static void migrate_fd_cleanup(void *opaque)
{
- QDict *qdict;
- MigrationState *s = current_migration;
+ MigrationState *s = opaque;
- if (s) {
- switch (s->get_status(s)) {
- case MIG_STATE_ACTIVE:
- qdict = qdict_new();
- qdict_put(qdict, "status", qstring_from_str("active"));
+ qemu_bh_delete(s->cleanup_bh);
+ s->cleanup_bh = NULL;
- migrate_put_status(qdict, "ram", ram_bytes_transferred(),
- ram_bytes_remaining(), ram_bytes_total());
+ if (s->file) {
+ DPRINTF("closing file\n");
+ qemu_mutex_unlock_iothread();
+ qemu_thread_join(&s->thread);
+ qemu_mutex_lock_iothread();
- if (blk_mig_active()) {
- migrate_put_status(qdict, "disk", blk_mig_bytes_transferred(),
- blk_mig_bytes_remaining(),
- blk_mig_bytes_total());
- }
+ qemu_fclose(s->file);
+ s->file = NULL;
+ }
- *ret_data = QOBJECT(qdict);
- break;
- case MIG_STATE_COMPLETED:
- *ret_data = qobject_from_jsonf("{ 'status': 'completed' }");
- break;
- case MIG_STATE_ERROR:
- *ret_data = qobject_from_jsonf("{ 'status': 'failed' }");
- break;
- case MIG_STATE_CANCELLED:
- *ret_data = qobject_from_jsonf("{ 'status': 'cancelled' }");
- break;
- }
+ assert(s->state != MIG_STATE_ACTIVE);
+
+ if (s->state != MIG_STATE_COMPLETED) {
+ qemu_savevm_state_cancel();
}
-}
-/* shared migration helpers */
+ notifier_list_notify(&migration_state_notifiers, s);
+}
-void migrate_fd_monitor_suspend(FdMigrationState *s, Monitor *mon)
+static void migrate_set_state(MigrationState *s, int old_state, int new_state)
{
- s->mon = mon;
- if (monitor_suspend(mon) == 0) {
- DPRINTF("suspending monitor\n");
- } else {
- monitor_printf(mon, "terminal does not allow synchronous "
- "migration, continuing detached\n");
+ if (atomic_cmpxchg(&s->state, old_state, new_state) == new_state) {
+ trace_migrate_set_state(new_state);
}
}
-void migrate_fd_error(FdMigrationState *s)
+void migrate_fd_error(MigrationState *s)
{
DPRINTF("setting error state\n");
+ assert(s->file == NULL);
s->state = MIG_STATE_ERROR;
- notifier_list_notify(&migration_state_notifiers);
- migrate_fd_cleanup(s);
+ trace_migrate_set_state(MIG_STATE_ERROR);
+ notifier_list_notify(&migration_state_notifiers, s);
}
-int migrate_fd_cleanup(FdMigrationState *s)
+static void migrate_fd_cancel(MigrationState *s)
{
- int ret = 0;
-
- qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
-
- if (s->file) {
- DPRINTF("closing file\n");
- if (qemu_fclose(s->file) != 0) {
- ret = -1;
- }
- s->file = NULL;
- }
-
- if (s->fd != -1)
- close(s->fd);
+ DPRINTF("cancelling migration\n");
- /* Don't resume monitor until we've flushed all of the buffers */
- if (s->mon) {
- monitor_resume(s->mon);
- }
+ migrate_set_state(s, s->state, MIG_STATE_CANCELLED);
+}
- s->fd = -1;
+void add_migration_state_change_notifier(Notifier *notify)
+{
+ notifier_list_add(&migration_state_notifiers, notify);
+}
- return ret;
+void remove_migration_state_change_notifier(Notifier *notify)
+{
+ notifier_remove(notify);
}
-void migrate_fd_put_notify(void *opaque)
+bool migration_in_setup(MigrationState *s)
{
- FdMigrationState *s = opaque;
+ return s->state == MIG_STATE_SETUP;
+}
- qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
- qemu_file_put_notify(s->file);
+bool migration_has_finished(MigrationState *s)
+{
+ return s->state == MIG_STATE_COMPLETED;
}
-ssize_t migrate_fd_put_buffer(void *opaque, const void *data, size_t size)
+bool migration_has_failed(MigrationState *s)
{
- FdMigrationState *s = opaque;
- ssize_t ret;
+ return (s->state == MIG_STATE_CANCELLED ||
+ s->state == MIG_STATE_ERROR);
+}
- do {
- ret = s->write(s, data, size);
- } while (ret == -1 && ((s->get_error(s)) == EINTR));
+static 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;
+
+ memcpy(enabled_capabilities, s->enabled_capabilities,
+ sizeof(enabled_capabilities));
+
+ memset(s, 0, sizeof(*s));
+ s->params = *params;
+ memcpy(s->enabled_capabilities, enabled_capabilities,
+ sizeof(enabled_capabilities));
+ s->xbzrle_cache_size = xbzrle_cache_size;
+
+ s->bandwidth_limit = bandwidth_limit;
+ s->state = MIG_STATE_SETUP;
+ trace_migrate_set_state(MIG_STATE_SETUP);
+
+ s->total_time = qemu_get_clock_ms(rt_clock);
+ return s;
+}
- if (ret == -1)
- ret = -(s->get_error(s));
+static GSList *migration_blockers;
- if (ret == -EAGAIN) {
- qemu_set_fd_handler2(s->fd, NULL, NULL, migrate_fd_put_notify, s);
- } else if (ret < 0) {
- if (s->mon) {
- monitor_resume(s->mon);
- }
- s->state = MIG_STATE_ERROR;
- notifier_list_notify(&migration_state_notifiers);
- }
+void migrate_add_blocker(Error *reason)
+{
+ migration_blockers = g_slist_prepend(migration_blockers, reason);
+}
- return ret;
+void migrate_del_blocker(Error *reason)
+{
+ migration_blockers = g_slist_remove(migration_blockers, reason);
}
-void migrate_fd_connect(FdMigrationState *s)
+void qmp_migrate(const char *uri, bool has_blk, bool blk,
+ bool has_inc, bool inc, bool has_detach, bool detach,
+ Error **errp)
{
- int ret;
+ Error *local_err = NULL;
+ MigrationState *s = migrate_get_current();
+ MigrationParams params;
+ const char *p;
- s->file = qemu_fopen_ops_buffered(s,
- s->bandwidth_limit,
- migrate_fd_put_buffer,
- migrate_fd_put_ready,
- migrate_fd_wait_for_unfreeze,
- migrate_fd_close);
+ params.blk = has_blk && blk;
+ params.shared = has_inc && inc;
- DPRINTF("beginning savevm\n");
- ret = qemu_savevm_state_begin(s->mon, s->file, s->mig_state.blk,
- s->mig_state.shared);
- if (ret < 0) {
- DPRINTF("failed, %d\n", ret);
- migrate_fd_error(s);
+ if (s->state == MIG_STATE_ACTIVE || s->state == MIG_STATE_SETUP) {
+ error_set(errp, QERR_MIGRATION_ACTIVE);
return;
}
-
- migrate_fd_put_ready(s);
-}
-void migrate_fd_put_ready(void *opaque)
-{
- FdMigrationState *s = opaque;
+ if (qemu_savevm_state_blocked(errp)) {
+ return;
+ }
- if (s->state != MIG_STATE_ACTIVE) {
- DPRINTF("put_ready returning because of non-active state\n");
+ if (migration_blockers) {
+ *errp = error_copy(migration_blockers->data);
return;
}
- DPRINTF("iterate\n");
- if (qemu_savevm_state_iterate(s->mon, s->file) == 1) {
- int state;
- int old_vm_running = vm_running;
+ s = migrate_init(¶ms);
- DPRINTF("done iterating\n");
- vm_stop(0);
+ if (strstart(uri, "tcp:", &p)) {
+ tcp_start_outgoing_migration(s, p, &local_err);
+#ifdef CONFIG_RDMA
+ } else if (strstart(uri, "x-rdma:", &p)) {
+ rdma_start_outgoing_migration(s, p, &local_err);
+#endif
+#if !defined(WIN32)
+ } else if (strstart(uri, "exec:", &p)) {
+ exec_start_outgoing_migration(s, p, &local_err);
+ } else if (strstart(uri, "unix:", &p)) {
+ unix_start_outgoing_migration(s, p, &local_err);
+ } else if (strstart(uri, "fd:", &p)) {
+ fd_start_outgoing_migration(s, p, &local_err);
+#endif
+ } else {
+ error_set(errp, QERR_INVALID_PARAMETER_VALUE, "uri", "a valid migration protocol");
+ return;
+ }
- if ((qemu_savevm_state_complete(s->mon, s->file)) < 0) {
- if (old_vm_running) {
- vm_start();
- }
- state = MIG_STATE_ERROR;
- } else {
- state = MIG_STATE_COMPLETED;
- }
- if (migrate_fd_cleanup(s) < 0) {
- if (old_vm_running) {
- vm_start();
- }
- state = MIG_STATE_ERROR;
- }
- s->state = state;
- notifier_list_notify(&migration_state_notifiers);
+ if (local_err) {
+ migrate_fd_error(s);
+ error_propagate(errp, local_err);
+ return;
}
}
-int migrate_fd_get_status(MigrationState *mig_state)
+void qmp_migrate_cancel(Error **errp)
{
- FdMigrationState *s = migrate_to_fms(mig_state);
- return s->state;
+ migrate_fd_cancel(migrate_get_current());
}
-void migrate_fd_cancel(MigrationState *mig_state)
+void qmp_migrate_set_cache_size(int64_t value, Error **errp)
{
- FdMigrationState *s = migrate_to_fms(mig_state);
+ MigrationState *s = migrate_get_current();
- if (s->state != MIG_STATE_ACTIVE)
+ /* Check for truncation */
+ if (value != (size_t)value) {
+ error_set(errp, QERR_INVALID_PARAMETER_VALUE, "cache size",
+ "exceeding address space");
return;
+ }
- DPRINTF("cancelling migration\n");
-
- s->state = MIG_STATE_CANCELLED;
- notifier_list_notify(&migration_state_notifiers);
- qemu_savevm_state_cancel(s->mon, s->file);
+ s->xbzrle_cache_size = xbzrle_cache_resize(value);
+}
- migrate_fd_cleanup(s);
+int64_t qmp_query_migrate_cache_size(Error **errp)
+{
+ return migrate_xbzrle_cache_size();
}
-void migrate_fd_release(MigrationState *mig_state)
+void qmp_migrate_set_speed(int64_t value, Error **errp)
{
- FdMigrationState *s = migrate_to_fms(mig_state);
+ MigrationState *s;
- DPRINTF("releasing state\n");
-
- if (s->state == MIG_STATE_ACTIVE) {
- s->state = MIG_STATE_CANCELLED;
- notifier_list_notify(&migration_state_notifiers);
- migrate_fd_cleanup(s);
+ if (value < 0) {
+ value = 0;
+ }
+ if (value > SIZE_MAX) {
+ value = SIZE_MAX;
+ }
+
+ s = migrate_get_current();
+ s->bandwidth_limit = value;
+ if (s->file) {
+ qemu_file_set_rate_limit(s->file, s->bandwidth_limit / XFER_LIMIT_RATIO);
}
- qemu_free(s);
}
-void migrate_fd_wait_for_unfreeze(void *opaque)
+void qmp_migrate_set_downtime(double value, Error **errp)
{
- FdMigrationState *s = opaque;
- int ret;
+ value *= 1e9;
+ value = MAX(0, MIN(UINT64_MAX, value));
+ max_downtime = (uint64_t)value;
+}
- DPRINTF("wait for unfreeze\n");
- if (s->state != MIG_STATE_ACTIVE)
- return;
+bool migrate_rdma_pin_all(void)
+{
+ MigrationState *s;
+
+ s = migrate_get_current();
+
+ return s->enabled_capabilities[MIGRATION_CAPABILITY_X_RDMA_PIN_ALL];
+}
- do {
- fd_set wfds;
+bool migrate_auto_converge(void)
+{
+ MigrationState *s;
- FD_ZERO(&wfds);
- FD_SET(s->fd, &wfds);
+ s = migrate_get_current();
- ret = select(s->fd + 1, NULL, &wfds, NULL, NULL);
- } while (ret == -1 && (s->get_error(s)) == EINTR);
+ return s->enabled_capabilities[MIGRATION_CAPABILITY_AUTO_CONVERGE];
}
-int migrate_fd_close(void *opaque)
+bool migrate_zero_blocks(void)
{
- FdMigrationState *s = opaque;
+ MigrationState *s;
+
+ s = migrate_get_current();
- qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
- return s->close(s);
+ return s->enabled_capabilities[MIGRATION_CAPABILITY_ZERO_BLOCKS];
}
-void add_migration_state_change_notifier(Notifier *notify)
+int migrate_use_xbzrle(void)
{
- notifier_list_add(&migration_state_notifiers, notify);
+ MigrationState *s;
+
+ s = migrate_get_current();
+
+ return s->enabled_capabilities[MIGRATION_CAPABILITY_XBZRLE];
}
-void remove_migration_state_change_notifier(Notifier *notify)
+int64_t migrate_xbzrle_cache_size(void)
{
- notifier_list_remove(&migration_state_notifiers, notify);
+ MigrationState *s;
+
+ s = migrate_get_current();
+
+ return s->xbzrle_cache_size;
}
-int get_migration_state(void)
+/* migration thread support */
+
+static void *migration_thread(void *opaque)
{
- if (current_migration) {
- return migrate_fd_get_status(current_migration);
+ MigrationState *s = opaque;
+ int64_t initial_time = qemu_get_clock_ms(rt_clock);
+ int64_t setup_start = qemu_get_clock_ms(host_clock);
+ 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_get_clock_ms(host_clock) - 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 %lu max %lu\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_get_clock_ms(rt_clock);
+ 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, INT_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_get_clock_ms(rt_clock);
+ 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_get_clock_ms(rt_clock);
+ s->total_time = end_time - s->total_time;
+ s->downtime = end_time - start_time;
+ runstate_set(RUN_STATE_POSTMIGRATE);
} else {
- return MIG_STATE_ERROR;
+ if (old_vm_running) {
+ vm_start();
+ }
}
+ qemu_bh_schedule(s->cleanup_bh);
+ qemu_mutex_unlock_iothread();
+
+ return NULL;
+}
+
+void migrate_fd_connect(MigrationState *s)
+{
+ s->state = MIG_STATE_SETUP;
+ trace_migrate_set_state(MIG_STATE_SETUP);
+
+ /* This is a best 1st approximation. ns to ms */
+ s->expected_downtime = max_downtime/1000000;
+ s->cleanup_bh = qemu_bh_new(migrate_fd_cleanup, s);
+
+ qemu_file_set_rate_limit(s->file,
+ s->bandwidth_limit / XFER_LIMIT_RATIO);
+
+ /* Notify before starting migration thread */
+ notifier_list_notify(&migration_state_notifiers, s);
+
+ qemu_thread_create(&s->thread, migration_thread, s,
+ QEMU_THREAD_JOINABLE);
}
projects / external / qemu.git / blobdiff