mirror of
https://github.com/qemu/qemu.git
synced 2024-11-27 05:43:47 +08:00
4f97558e10
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> Reviewed-by: Amit Shah <amit.shah@redhat.com> Signed-off-by: Amit Shah <amit@amitshah.net>
295 lines
7.4 KiB
C
295 lines
7.4 KiB
C
/*
|
|
* COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO)
|
|
* (a.k.a. Fault Tolerance or Continuous Replication)
|
|
*
|
|
* Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD.
|
|
* Copyright (c) 2016 FUJITSU LIMITED
|
|
* Copyright (c) 2016 Intel Corporation
|
|
*
|
|
* This work is licensed under the terms of the GNU GPL, version 2 or
|
|
* later. See the COPYING file in the top-level directory.
|
|
*/
|
|
|
|
#include "qemu/osdep.h"
|
|
#include "sysemu/sysemu.h"
|
|
#include "migration/colo.h"
|
|
#include "trace.h"
|
|
#include "qemu/error-report.h"
|
|
#include "qapi/error.h"
|
|
|
|
bool colo_supported(void)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
bool migration_in_colo_state(void)
|
|
{
|
|
MigrationState *s = migrate_get_current();
|
|
|
|
return (s->state == MIGRATION_STATUS_COLO);
|
|
}
|
|
|
|
bool migration_incoming_in_colo_state(void)
|
|
{
|
|
MigrationIncomingState *mis = migration_incoming_get_current();
|
|
|
|
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");
|
|
|
|
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);
|
|
}
|
|
|
|
if (s->rp_state.from_dst_file) {
|
|
qemu_fclose(s->rp_state.from_dst_file);
|
|
}
|
|
}
|
|
|
|
void migrate_start_colo_process(MigrationState *s)
|
|
{
|
|
qemu_mutex_unlock_iothread();
|
|
migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
|
|
MIGRATION_STATUS_COLO);
|
|
colo_process_checkpoint(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);
|
|
|
|
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");
|
|
goto out;
|
|
}
|
|
/*
|
|
* Note: the communication between Primary side and Secondary side
|
|
* should be sequential, we set the fd to unblocked in migration incoming
|
|
* coroutine, and here we are in the COLO incoming thread, so it is ok to
|
|
* set the fd back to blocked.
|
|
*/
|
|
qemu_file_set_blocking(mis->from_src_file, true);
|
|
|
|
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);
|
|
}
|
|
migration_incoming_exit_colo();
|
|
|
|
return NULL;
|
|
}
|