*/
#include "qemu/osdep.h"
+#include "qemu/timer.h"
#include "sysemu/sysemu.h"
#include "migration/colo.h"
#include "io/channel-buffer.h"
#include "trace.h"
#include "qemu/error-report.h"
#include "qapi/error.h"
+#include "migration/failover.h"
+#include "replication.h"
+#include "qmp-commands.h"
+
+static bool vmstate_loading;
#define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024)
bool colo_supported(void)
{
- return false;
+ return true;
}
bool migration_in_colo_state(void)
return mis && (mis->state == MIGRATION_STATUS_COLO);
}
+static bool colo_runstate_is_stopped(void)
+{
+ return runstate_check(RUN_STATE_COLO) || !runstate_is_running();
+}
+
+static void secondary_vm_do_failover(void)
+{
+ int old_state;
+ MigrationIncomingState *mis = migration_incoming_get_current();
+
+ /* Can not do failover during the process of VM's loading VMstate, Or
+ * it will break the secondary VM.
+ */
+ if (vmstate_loading) {
+ old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
+ FAILOVER_STATUS_RELAUNCH);
+ if (old_state != FAILOVER_STATUS_ACTIVE) {
+ error_report("Unknown error while do failover for secondary VM,"
+ "old_state: %s", FailoverStatus_lookup[old_state]);
+ }
+ return;
+ }
+
+ migrate_set_state(&mis->state, MIGRATION_STATUS_COLO,
+ MIGRATION_STATUS_COMPLETED);
+
+ if (!autostart) {
+ error_report("\"-S\" qemu option will be ignored in secondary side");
+ /* recover runstate to normal migration finish state */
+ autostart = true;
+ }
+ /*
+ * Make sure COLO incoming thread not block in recv or send,
+ * If mis->from_src_file and mis->to_src_file use the same fd,
+ * The second shutdown() will return -1, we ignore this value,
+ * It is harmless.
+ */
+ if (mis->from_src_file) {
+ qemu_file_shutdown(mis->from_src_file);
+ }
+ if (mis->to_src_file) {
+ qemu_file_shutdown(mis->to_src_file);
+ }
+
+ old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
+ FAILOVER_STATUS_COMPLETED);
+ if (old_state != FAILOVER_STATUS_ACTIVE) {
+ error_report("Incorrect state (%s) while doing failover for "
+ "secondary VM", FailoverStatus_lookup[old_state]);
+ return;
+ }
+ /* Notify COLO incoming thread that failover work is finished */
+ qemu_sem_post(&mis->colo_incoming_sem);
+ /* For Secondary VM, jump to incoming co */
+ if (mis->migration_incoming_co) {
+ qemu_coroutine_enter(mis->migration_incoming_co);
+ }
+}
+
+static void primary_vm_do_failover(void)
+{
+ MigrationState *s = migrate_get_current();
+ int old_state;
+
+ migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
+ MIGRATION_STATUS_COMPLETED);
+
+ /*
+ * Wake up COLO thread which may blocked in recv() or send(),
+ * The s->rp_state.from_dst_file and s->to_dst_file may use the
+ * same fd, but we still shutdown the fd for twice, it is harmless.
+ */
+ if (s->to_dst_file) {
+ qemu_file_shutdown(s->to_dst_file);
+ }
+ if (s->rp_state.from_dst_file) {
+ qemu_file_shutdown(s->rp_state.from_dst_file);
+ }
+
+ old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
+ FAILOVER_STATUS_COMPLETED);
+ if (old_state != FAILOVER_STATUS_ACTIVE) {
+ error_report("Incorrect state (%s) while doing failover for Primary VM",
+ FailoverStatus_lookup[old_state]);
+ return;
+ }
+ /* Notify COLO thread that failover work is finished */
+ qemu_sem_post(&s->colo_exit_sem);
+}
+
+void colo_do_failover(MigrationState *s)
+{
+ /* Make sure VM stopped while failover happened. */
+ if (!colo_runstate_is_stopped()) {
+ vm_stop_force_state(RUN_STATE_COLO);
+ }
+
+ if (get_colo_mode() == COLO_MODE_PRIMARY) {
+ primary_vm_do_failover();
+ } else {
+ secondary_vm_do_failover();
+ }
+}
+
+void qmp_xen_set_replication(bool enable, bool primary,
+ bool has_failover, bool failover,
+ Error **errp)
+{
+ ReplicationMode mode = primary ?
+ REPLICATION_MODE_PRIMARY :
+ REPLICATION_MODE_SECONDARY;
+
+ if (has_failover && enable) {
+ error_setg(errp, "Parameter 'failover' is only for"
+ " stopping replication");
+ return;
+ }
+
+ if (enable) {
+ replication_start_all(mode, errp);
+ } else {
+ if (!has_failover) {
+ failover = NULL;
+ }
+ replication_stop_all(failover, failover ? NULL : errp);
+ }
+}
+
+ReplicationStatus *qmp_query_xen_replication_status(Error **errp)
+{
+ Error *err = NULL;
+ ReplicationStatus *s = g_new0(ReplicationStatus, 1);
+
+ replication_get_error_all(&err);
+ if (err) {
+ s->error = true;
+ s->has_desc = true;
+ s->desc = g_strdup(error_get_pretty(err));
+ } else {
+ s->error = false;
+ }
+
+ error_free(err);
+ return s;
+}
+
+void qmp_xen_colo_do_checkpoint(Error **errp)
+{
+ replication_do_checkpoint_all(errp);
+}
+
static void colo_send_message(QEMUFile *f, COLOMessage msg,
Error **errp)
{
}
}
+static uint64_t colo_receive_message_value(QEMUFile *f, uint32_t expect_msg,
+ Error **errp)
+{
+ Error *local_err = NULL;
+ uint64_t value;
+ int ret;
+
+ colo_receive_check_message(f, expect_msg, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ return 0;
+ }
+
+ value = qemu_get_be64(f);
+ ret = qemu_file_get_error(f);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Failed to get value for COLO message: %s",
+ COLOMessage_lookup[expect_msg]);
+ }
+ return value;
+}
+
static int colo_do_checkpoint_transaction(MigrationState *s,
QIOChannelBuffer *bioc,
QEMUFile *fb)
bioc->usage = 0;
qemu_mutex_lock_iothread();
+ if (failover_get_state() != FAILOVER_STATUS_NONE) {
+ qemu_mutex_unlock_iothread();
+ goto out;
+ }
vm_stop_force_state(RUN_STATE_COLO);
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("run", "stop");
+ /*
+ * Failover request bh could be called after vm_stop_force_state(),
+ * So we need check failover_request_is_active() again.
+ */
+ if (failover_get_state() != FAILOVER_STATUS_NONE) {
+ goto out;
+ }
/* Disable block migration */
s->params.blk = 0;
{
QIOChannelBuffer *bioc;
QEMUFile *fb = NULL;
+ int64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
Error *local_err = NULL;
int ret;
+ failover_init_state();
+
s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file);
if (!s->rp_state.from_dst_file) {
error_report("Open QEMUFile from_dst_file failed");
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
+ timer_mod(s->colo_delay_timer,
+ current_time + s->parameters.x_checkpoint_delay);
+
while (s->state == MIGRATION_STATUS_COLO) {
+ if (failover_get_state() != FAILOVER_STATUS_NONE) {
+ error_report("failover request");
+ goto out;
+ }
+
+ qemu_sem_wait(&s->colo_checkpoint_sem);
+
ret = colo_do_checkpoint_transaction(s, bioc, fb);
if (ret < 0) {
goto out;
qemu_fclose(fb);
}
+ timer_del(s->colo_delay_timer);
+
+ /* Hope this not to be too long to wait here */
+ qemu_sem_wait(&s->colo_exit_sem);
+ qemu_sem_destroy(&s->colo_exit_sem);
+ /*
+ * Must be called after failover BH is completed,
+ * Or the failover BH may shutdown the wrong fd that
+ * re-used by other threads after we release here.
+ */
if (s->rp_state.from_dst_file) {
qemu_fclose(s->rp_state.from_dst_file);
}
}
+void colo_checkpoint_notify(void *opaque)
+{
+ MigrationState *s = opaque;
+ int64_t next_notify_time;
+
+ qemu_sem_post(&s->colo_checkpoint_sem);
+ s->colo_checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
+ next_notify_time = s->colo_checkpoint_time +
+ s->parameters.x_checkpoint_delay;
+ timer_mod(s->colo_delay_timer, next_notify_time);
+}
+
void migrate_start_colo_process(MigrationState *s)
{
qemu_mutex_unlock_iothread();
+ qemu_sem_init(&s->colo_checkpoint_sem, 0);
+ s->colo_delay_timer = timer_new_ms(QEMU_CLOCK_HOST,
+ colo_checkpoint_notify, s);
+
+ qemu_sem_init(&s->colo_exit_sem, 0);
migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COLO);
colo_process_checkpoint(s);
void *colo_process_incoming_thread(void *opaque)
{
MigrationIncomingState *mis = opaque;
+ QEMUFile *fb = NULL;
+ QIOChannelBuffer *bioc = NULL; /* Cache incoming device state */
+ uint64_t total_size;
+ uint64_t value;
Error *local_err = NULL;
+ qemu_sem_init(&mis->colo_incoming_sem, 0);
+
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COLO);
+ failover_init_state();
+
mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
if (!mis->to_src_file) {
error_report("COLO incoming thread: Open QEMUFile to_src_file failed");
*/
qemu_file_set_blocking(mis->from_src_file, true);
+ bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
+ fb = qemu_fopen_channel_input(QIO_CHANNEL(bioc));
+ object_unref(OBJECT(bioc));
+
colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY,
&local_err);
if (local_err) {
}
while (mis->state == MIGRATION_STATUS_COLO) {
- int request;
+ int request = 0;
colo_wait_handle_message(mis->from_src_file, &request, &local_err);
if (local_err) {
goto out;
}
assert(request);
+ if (failover_get_state() != FAILOVER_STATUS_NONE) {
+ error_report("failover request");
+ goto out;
+ }
+
/* FIXME: This is unnecessary for periodic checkpoint mode */
colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY,
&local_err);
goto out;
}
- /* TODO: read migration data into colo buffer */
+ value = colo_receive_message_value(mis->from_src_file,
+ COLO_MESSAGE_VMSTATE_SIZE, &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ /*
+ * Read VM device state data into channel buffer,
+ * It's better to re-use the memory allocated.
+ * Here we need to handle the channel buffer directly.
+ */
+ if (value > bioc->capacity) {
+ bioc->capacity = value;
+ bioc->data = g_realloc(bioc->data, bioc->capacity);
+ }
+ total_size = qemu_get_buffer(mis->from_src_file, bioc->data, value);
+ if (total_size != value) {
+ error_report("Got %" PRIu64 " VMState data, less than expected"
+ " %" PRIu64, total_size, value);
+ goto out;
+ }
+ bioc->usage = total_size;
+ qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL);
colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED,
&local_err);
goto out;
}
- /* TODO: load vm state */
+ qemu_mutex_lock_iothread();
+ qemu_system_reset(VMRESET_SILENT);
+ vmstate_loading = true;
+ if (qemu_loadvm_state(fb) < 0) {
+ error_report("COLO: loadvm failed");
+ qemu_mutex_unlock_iothread();
+ goto out;
+ }
+
+ vmstate_loading = false;
+ qemu_mutex_unlock_iothread();
+
+ if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
+ failover_set_state(FAILOVER_STATUS_RELAUNCH,
+ FAILOVER_STATUS_NONE);
+ failover_request_active(NULL);
+ goto out;
+ }
colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED,
&local_err);
}
out:
+ vmstate_loading = false;
/* Throw the unreported error message after exited from loop */
if (local_err) {
error_report_err(local_err);
}
+ if (fb) {
+ qemu_fclose(fb);
+ }
+
+ /* Hope this not to be too long to loop here */
+ qemu_sem_wait(&mis->colo_incoming_sem);
+ qemu_sem_destroy(&mis->colo_incoming_sem);
+ /* Must be called after failover BH is completed */
if (mis->to_src_file) {
qemu_fclose(mis->to_src_file);
}
projects / mirror_qemu.git / blobdiff