qemu/migration.c
Juan Quintela 7aa939af39 migration: move total_time from ram stats to migration info
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
2012-08-21 15:06:24 -03:00

594 lines
15 KiB
C

/*
* QEMU live migration
*
* Copyright IBM, Corp. 2008
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* 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 "qmp-commands.h"
//#define DEBUG_MIGRATION
#ifdef DEBUG_MIGRATION
#define DPRINTF(fmt, ...) \
do { printf("migration: " fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
do { } while (0)
#endif
enum {
MIG_STATE_ERROR,
MIG_STATE_SETUP,
MIG_STATE_CANCELLED,
MIG_STATE_ACTIVE,
MIG_STATE_COMPLETED,
};
#define MAX_THROTTLE (32 << 20) /* Migration speed throttling */
/* Migration XBZRLE default cache size */
#define DEFAULT_MIGRATE_CACHE_SIZE (64 * 1024 * 1024)
static NotifierList migration_state_notifiers =
NOTIFIER_LIST_INITIALIZER(migration_state_notifiers);
/* When we add fault tolerance, we could have several
migrations at once. For now we don't need to add
dynamic creation of migration */
static MigrationState *migrate_get_current(void)
{
static MigrationState current_migration = {
.state = MIG_STATE_SETUP,
.bandwidth_limit = MAX_THROTTLE,
.xbzrle_cache_size = DEFAULT_MIGRATE_CACHE_SIZE,
};
return &current_migration;
}
int 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, errp);
#if !defined(WIN32)
else if (strstart(uri, "exec:", &p))
ret = exec_start_incoming_migration(p);
else if (strstart(uri, "unix:", &p))
ret = unix_start_incoming_migration(p);
else if (strstart(uri, "fd:", &p))
ret = fd_start_incoming_migration(p);
#endif
else {
fprintf(stderr, "unknown migration protocol: %s\n", uri);
ret = -EPROTONOSUPPORT;
}
return ret;
}
void process_incoming_migration(QEMUFile *f)
{
if (qemu_loadvm_state(f) < 0) {
fprintf(stderr, "load of migration failed\n");
exit(0);
}
qemu_announce_self();
DPRINTF("successfully loaded vm state\n");
bdrv_clear_incoming_migration_all();
/* Make sure all file formats flush their mutable metadata */
bdrv_invalidate_cache_all();
if (autostart) {
vm_start();
} else {
runstate_set(RUN_STATE_PRELAUNCH);
}
}
/* amount of nanoseconds we are willing to wait for migration to be down.
* the choice of nanoseconds is because it is the maximum resolution that
* get_clock() can achieve. It is an internal measure. All user-visible
* units must be in seconds */
static uint64_t max_downtime = 30000000;
uint64_t migrate_max_downtime(void)
{
return max_downtime;
}
MigrationCapabilityStatusList *qmp_query_migrate_capabilities(Error **errp)
{
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];
}
return head;
}
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();
}
}
MigrationInfo *qmp_query_migrate(Error **errp)
{
MigrationInfo *info = g_malloc0(sizeof(*info));
MigrationState *s = migrate_get_current();
switch (s->state) {
case MIG_STATE_SETUP:
/* no migration has happened ever */
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_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->normal = norm_mig_pages_transferred();
info->ram->normal_bytes = norm_mig_bytes_transferred();
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 MIG_STATE_COMPLETED:
get_xbzrle_cache_stats(info);
info->has_status = true;
info->status = g_strdup("completed");
info->total_time = s->total_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->normal = norm_mig_pages_transferred();
info->ram->normal_bytes = norm_mig_bytes_transferred();
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;
}
return info;
}
void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params,
Error **errp)
{
MigrationState *s = migrate_get_current();
MigrationCapabilityStatusList *cap;
if (s->state == MIG_STATE_ACTIVE) {
error_set(errp, QERR_MIGRATION_ACTIVE);
return;
}
for (cap = params; cap; cap = cap->next) {
s->enabled_capabilities[cap->value->capability] = cap->value->state;
}
}
/* shared migration helpers */
static int migrate_fd_cleanup(MigrationState *s)
{
int ret = 0;
qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
if (s->file) {
DPRINTF("closing file\n");
ret = qemu_fclose(s->file);
s->file = NULL;
}
if (s->fd != -1) {
close(s->fd);
s->fd = -1;
}
return ret;
}
void migrate_fd_error(MigrationState *s)
{
DPRINTF("setting error state\n");
s->state = MIG_STATE_ERROR;
notifier_list_notify(&migration_state_notifiers, s);
migrate_fd_cleanup(s);
}
static void migrate_fd_completed(MigrationState *s)
{
DPRINTF("setting completed state\n");
if (migrate_fd_cleanup(s) < 0) {
s->state = MIG_STATE_ERROR;
} else {
s->state = MIG_STATE_COMPLETED;
runstate_set(RUN_STATE_POSTMIGRATE);
}
notifier_list_notify(&migration_state_notifiers, s);
}
static void migrate_fd_put_notify(void *opaque)
{
MigrationState *s = opaque;
qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
qemu_file_put_notify(s->file);
if (s->file && qemu_file_get_error(s->file)) {
migrate_fd_error(s);
}
}
static ssize_t migrate_fd_put_buffer(void *opaque, const void *data,
size_t size)
{
MigrationState *s = opaque;
ssize_t ret;
if (s->state != MIG_STATE_ACTIVE) {
return -EIO;
}
do {
ret = s->write(s, data, size);
} while (ret == -1 && ((s->get_error(s)) == EINTR));
if (ret == -1)
ret = -(s->get_error(s));
if (ret == -EAGAIN) {
qemu_set_fd_handler2(s->fd, NULL, NULL, migrate_fd_put_notify, s);
}
return ret;
}
static void migrate_fd_put_ready(void *opaque)
{
MigrationState *s = opaque;
int ret;
if (s->state != MIG_STATE_ACTIVE) {
DPRINTF("put_ready returning because of non-active state\n");
return;
}
DPRINTF("iterate\n");
ret = qemu_savevm_state_iterate(s->file);
if (ret < 0) {
migrate_fd_error(s);
} else if (ret == 1) {
int old_vm_running = runstate_is_running();
DPRINTF("done iterating\n");
qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER);
vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
if (qemu_savevm_state_complete(s->file) < 0) {
migrate_fd_error(s);
} else {
migrate_fd_completed(s);
}
s->total_time = qemu_get_clock_ms(rt_clock) - s->total_time;
if (s->state != MIG_STATE_COMPLETED) {
if (old_vm_running) {
vm_start();
}
}
}
}
static void migrate_fd_cancel(MigrationState *s)
{
if (s->state != MIG_STATE_ACTIVE)
return;
DPRINTF("cancelling migration\n");
s->state = MIG_STATE_CANCELLED;
notifier_list_notify(&migration_state_notifiers, s);
qemu_savevm_state_cancel(s->file);
migrate_fd_cleanup(s);
}
static void migrate_fd_wait_for_unfreeze(void *opaque)
{
MigrationState *s = opaque;
int ret;
DPRINTF("wait for unfreeze\n");
if (s->state != MIG_STATE_ACTIVE)
return;
do {
fd_set wfds;
FD_ZERO(&wfds);
FD_SET(s->fd, &wfds);
ret = select(s->fd + 1, NULL, &wfds, NULL, NULL);
} while (ret == -1 && (s->get_error(s)) == EINTR);
if (ret == -1) {
qemu_file_set_error(s->file, -s->get_error(s));
}
}
static int migrate_fd_close(void *opaque)
{
MigrationState *s = opaque;
qemu_set_fd_handler2(s->fd, NULL, NULL, NULL, NULL);
return s->close(s);
}
void add_migration_state_change_notifier(Notifier *notify)
{
notifier_list_add(&migration_state_notifiers, notify);
}
void remove_migration_state_change_notifier(Notifier *notify)
{
notifier_remove(notify);
}
bool migration_is_active(MigrationState *s)
{
return s->state == MIG_STATE_ACTIVE;
}
bool migration_has_finished(MigrationState *s)
{
return s->state == MIG_STATE_COMPLETED;
}
bool migration_has_failed(MigrationState *s)
{
return (s->state == MIG_STATE_CANCELLED ||
s->state == MIG_STATE_ERROR);
}
void migrate_fd_connect(MigrationState *s)
{
int ret;
s->state = MIG_STATE_ACTIVE;
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);
DPRINTF("beginning savevm\n");
ret = qemu_savevm_state_begin(s->file, &s->params);
if (ret < 0) {
DPRINTF("failed, %d\n", ret);
migrate_fd_error(s);
return;
}
migrate_fd_put_ready(s);
}
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->bandwidth_limit = bandwidth_limit;
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;
s->total_time = qemu_get_clock_ms(rt_clock);
return s;
}
static GSList *migration_blockers;
void migrate_add_blocker(Error *reason)
{
migration_blockers = g_slist_prepend(migration_blockers, reason);
}
void migrate_del_blocker(Error *reason)
{
migration_blockers = g_slist_remove(migration_blockers, reason);
}
void qmp_migrate(const char *uri, bool has_blk, bool blk,
bool has_inc, bool inc, bool has_detach, bool detach,
Error **errp)
{
MigrationState *s = migrate_get_current();
MigrationParams params;
const char *p;
int ret;
params.blk = blk;
params.shared = inc;
if (s->state == MIG_STATE_ACTIVE) {
error_set(errp, QERR_MIGRATION_ACTIVE);
return;
}
if (qemu_savevm_state_blocked(errp)) {
return;
}
if (migration_blockers) {
*errp = error_copy(migration_blockers->data);
return;
}
s = migrate_init(&params);
if (strstart(uri, "tcp:", &p)) {
ret = tcp_start_outgoing_migration(s, p, errp);
#if !defined(WIN32)
} else if (strstart(uri, "exec:", &p)) {
ret = exec_start_outgoing_migration(s, p);
} else if (strstart(uri, "unix:", &p)) {
ret = unix_start_outgoing_migration(s, p);
} else if (strstart(uri, "fd:", &p)) {
ret = fd_start_outgoing_migration(s, p);
#endif
} else {
error_set(errp, QERR_INVALID_PARAMETER_VALUE, "uri", "a valid migration protocol");
return;
}
if (ret < 0) {
if (!error_is_set(errp)) {
DPRINTF("migration failed: %s\n", strerror(-ret));
/* FIXME: we should return meaningful errors */
error_set(errp, QERR_UNDEFINED_ERROR);
}
return;
}
notifier_list_notify(&migration_state_notifiers, s);
}
void qmp_migrate_cancel(Error **errp)
{
migrate_fd_cancel(migrate_get_current());
}
void qmp_migrate_set_cache_size(int64_t value, Error **errp)
{
MigrationState *s = migrate_get_current();
/* Check for truncation */
if (value != (size_t)value) {
error_set(errp, QERR_INVALID_PARAMETER_VALUE, "cache size",
"exceeding address space");
return;
}
s->xbzrle_cache_size = xbzrle_cache_resize(value);
}
int64_t qmp_query_migrate_cache_size(Error **errp)
{
return migrate_xbzrle_cache_size();
}
void qmp_migrate_set_speed(int64_t value, Error **errp)
{
MigrationState *s;
if (value < 0) {
value = 0;
}
s = migrate_get_current();
s->bandwidth_limit = value;
qemu_file_set_rate_limit(s->file, s->bandwidth_limit);
}
void qmp_migrate_set_downtime(double value, Error **errp)
{
value *= 1e9;
value = MAX(0, MIN(UINT64_MAX, value));
max_downtime = (uint64_t)value;
}
int migrate_use_xbzrle(void)
{
MigrationState *s;
s = migrate_get_current();
return s->enabled_capabilities[MIGRATION_CAPABILITY_XBZRLE];
}
int64_t migrate_xbzrle_cache_size(void)
{
MigrationState *s;
s = migrate_get_current();
return s->xbzrle_cache_size;
}