@@ -15,6 +15,7 @@
#include "migration/colo.h"
#include "trace.h"
#include "qemu/error-report.h"
+#include "qapi/error.h"
bool colo_supported(void)
{
@@ -35,22 +36,146 @@ bool migration_incoming_in_colo_state(void)
return mis && (mis->state == MIGRATION_STATUS_COLO);
}
+static void colo_send_message(QEMUFile *f, COLOMessage msg,
+ Error **errp)
+{
+ int ret;
+
+ if (msg >= COLO_MESSAGE__MAX) {
+ error_setg(errp, "%s: Invalid message", __func__);
+ return;
+ }
+ qemu_put_be32(f, msg);
+ qemu_fflush(f);
+
+ ret = qemu_file_get_error(f);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Can't send COLO message");
+ }
+ trace_colo_send_message(COLOMessage_lookup[msg]);
+}
+
+static COLOMessage colo_receive_message(QEMUFile *f, Error **errp)
+{
+ COLOMessage msg;
+ int ret;
+
+ msg = qemu_get_be32(f);
+ ret = qemu_file_get_error(f);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Can't receive COLO message");
+ return msg;
+ }
+ if (msg >= COLO_MESSAGE__MAX) {
+ error_setg(errp, "%s: Invalid message", __func__);
+ return msg;
+ }
+ trace_colo_receive_message(COLOMessage_lookup[msg]);
+ return msg;
+}
+
+static void colo_receive_check_message(QEMUFile *f, COLOMessage expect_msg,
+ Error **errp)
+{
+ COLOMessage msg;
+ Error *local_err = NULL;
+
+ msg = colo_receive_message(f, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ return;
+ }
+ if (msg != expect_msg) {
+ error_setg(errp, "Unexpected COLO message %d, expected %d",
+ msg, expect_msg);
+ }
+}
+
+static int colo_do_checkpoint_transaction(MigrationState *s)
+{
+ Error *local_err = NULL;
+
+ colo_send_message(s->to_dst_file, COLO_MESSAGE_CHECKPOINT_REQUEST,
+ &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ colo_receive_check_message(s->rp_state.from_dst_file,
+ COLO_MESSAGE_CHECKPOINT_REPLY, &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ /* TODO: suspend and save vm state to colo buffer */
+
+ colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ /* TODO: send vmstate to Secondary */
+
+ colo_receive_check_message(s->rp_state.from_dst_file,
+ COLO_MESSAGE_VMSTATE_RECEIVED, &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ colo_receive_check_message(s->rp_state.from_dst_file,
+ COLO_MESSAGE_VMSTATE_LOADED, &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ /* TODO: resume Primary */
+
+ return 0;
+out:
+ if (local_err) {
+ error_report_err(local_err);
+ }
+ return -EINVAL;
+}
+
static void colo_process_checkpoint(MigrationState *s)
{
+ Error *local_err = NULL;
+ int ret;
+
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");
goto out;
}
+ /*
+ * Wait for Secondary finish loading VM states and enter COLO
+ * restore.
+ */
+ colo_receive_check_message(s->rp_state.from_dst_file,
+ COLO_MESSAGE_CHECKPOINT_READY, &local_err);
+ if (local_err) {
+ goto out;
+ }
+
qemu_mutex_lock_iothread();
vm_start();
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
- /* TODO: COLO checkpoint savevm loop */
+ while (s->state == MIGRATION_STATUS_COLO) {
+ ret = colo_do_checkpoint_transaction(s);
+ if (ret < 0) {
+ goto out;
+ }
+ }
out:
+ /* Throw the unreported error message after exited from loop */
+ if (local_err) {
+ error_report_err(local_err);
+ }
migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
MIGRATION_STATUS_COMPLETED);
@@ -68,9 +193,33 @@ void migrate_start_colo_process(MigrationState *s)
qemu_mutex_lock_iothread();
}
+static void colo_wait_handle_message(QEMUFile *f, int *checkpoint_request,
+ Error **errp)
+{
+ COLOMessage msg;
+ Error *local_err = NULL;
+
+ msg = colo_receive_message(f, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ return;
+ }
+
+ switch (msg) {
+ case COLO_MESSAGE_CHECKPOINT_REQUEST:
+ *checkpoint_request = 1;
+ break;
+ default:
+ *checkpoint_request = 0;
+ error_setg(errp, "Got unknown COLO message: %d", msg);
+ break;
+ }
+}
+
void *colo_process_incoming_thread(void *opaque)
{
MigrationIncomingState *mis = opaque;
+ Error *local_err = NULL;
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COLO);
@@ -87,9 +236,56 @@ void *colo_process_incoming_thread(void *opaque)
*/
qemu_file_set_blocking(mis->from_src_file, true);
- /* TODO: COLO checkpoint restore loop */
+ colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY,
+ &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ while (mis->state == MIGRATION_STATUS_COLO) {
+ int request;
+
+ colo_wait_handle_message(mis->from_src_file, &request, &local_err);
+ if (local_err) {
+ goto out;
+ }
+ assert(request);
+ /* FIXME: This is unnecessary for periodic checkpoint mode */
+ colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY,
+ &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ colo_receive_check_message(mis->from_src_file,
+ COLO_MESSAGE_VMSTATE_SEND, &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ /* TODO: read migration data into colo buffer */
+
+ colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED,
+ &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ /* TODO: load vm state */
+
+ colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED,
+ &local_err);
+ if (local_err) {
+ goto out;
+ }
+ }
out:
+ /* Throw the unreported error message after exited from loop */
+ if (local_err) {
+ error_report_err(local_err);
+ }
+
if (mis->to_src_file) {
qemu_fclose(mis->to_src_file);
}
@@ -210,3 +210,5 @@ migration_tls_incoming_handshake_complete(void) ""
# migration/colo.c
colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'"
+colo_send_message(const char *msg) "Send '%s' message"
+colo_receive_message(const char *msg) "Receive '%s' message"
@@ -800,6 +800,31 @@
{ 'command': 'migrate-start-postcopy' }
##
+# @COLOMessage
+#
+# The message transmission between PVM and SVM
+#
+# @checkpoint-ready: SVM is ready for checkpointing
+#
+# @checkpoint-request: PVM tells SVM to prepare for new checkpointing
+#
+# @checkpoint-reply: SVM gets PVM's checkpoint request
+#
+# @vmstate-send: VM's state will be sent by PVM.
+#
+# @vmstate-size: The total size of VMstate.
+#
+# @vmstate-received: VM's state has been received by SVM.
+#
+# @vmstate-loaded: VM's state has been loaded by SVM.
+#
+# Since: 2.8
+##
+{ 'enum': 'COLOMessage',
+ 'data': [ 'checkpoint-ready', 'checkpoint-request', 'checkpoint-reply',
+ 'vmstate-send', 'vmstate-size', 'vmstate-received',
+ 'vmstate-loaded' ] }
+
# @MouseInfo:
#
# Information about a mouse device.
We need communications protocol of user-defined to control the checkpointing process. The new checkpointing request is started by Primary VM, and the interactive process like below: Checkpoint synchronizing points: Primary Secondary initial work 'checkpoint-ready' <-------------------- @ 'checkpoint-request' @ --------------------> Suspend (Only in hybrid mode) 'checkpoint-reply' <-------------------- @ Suspend&Save state 'vmstate-send' @ --------------------> Send state Receive state 'vmstate-received' <-------------------- @ Release packets Load state 'vmstate-load' <-------------------- @ Resume Resume (Only in hybrid mode) Start Comparing (Only in hybrid mode) NOTE: 1) '@' who sends the message 2) Every sync-point is synchronized by two sides with only one handshake(single direction) for low-latency. If more strict synchronization is required, a opposite direction sync-point should be added. 3) Since sync-points are single direction, the remote side may go forward a lot when this side just receives the sync-point. 4) For now, we only support 'periodic' checkpoint, for which the Secondary VM is not running, later we will support 'hybrid' mode. Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com> Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com> Signed-off-by: Gonglei <arei.gonglei@huawei.com> Cc: Eric Blake <eblake@redhat.com> Cc: Markus Armbruster <armbru@redhat.com> Cc: Dr. David Alan Gilbert <dgilbert@redhat.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> --- v19: - fix title and comments v16: - Rename 'colo_put/get[_check]_cmd()' to 'colo_send/receive[_check]_message()' v14: - Rename 'COLOCommand' to 'COLOMessage'. (Markus's suggestion) - Add Reviewd-by tag v13: - Refactor colo command related helper functions, use 'Error **errp' parameter instead of return value to indicate success or failure. - Fix some other comments from Markus. v12: - Rename colo_ctl_put() to colo_put_cmd() - Rename colo_ctl_get() to colo_get_check_cmd() and drop the third parameter - Rename colo_ctl_get_cmd() to colo_get_cmd() - Remove useless 'invalid' member for COLOcommand enum. v11: - Add missing 'checkpoint-ready' communication in comment. - Use parameter to return 'value' for colo_ctl_get() (Dave's suggestion) - Fix trace for colo_ctl_get() to trace command and value both v10: - Rename enum COLOCmd to COLOCommand (Eric's suggestion). - Remove unused 'ram-steal' --- migration/colo.c | 200 ++++++++++++++++++++++++++++++++++++++++++++++++- migration/trace-events | 2 + qapi-schema.json | 25 +++++++ 3 files changed, 225 insertions(+), 2 deletions(-)