qemu-e2k/migration/colo.c

670 lines
19 KiB
C
Raw Normal View History

/*
* 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 "qemu-file-channel.h"
#include "migration.h"
#include "qemu-file.h"
#include "savevm.h"
#include "migration/colo.h"
#include "block.h"
#include "io/channel-buffer.h"
#include "trace.h"
#include "qemu/error-report.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 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 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_str(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_str(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_str(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)
{
#ifdef CONFIG_REPLICATION
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);
}
#else
abort();
#endif
}
ReplicationStatus *qmp_query_xen_replication_status(Error **errp)
{
#ifdef CONFIG_REPLICATION
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;
#else
abort();
#endif
}
void qmp_xen_colo_do_checkpoint(Error **errp)
{
#ifdef CONFIG_REPLICATION
replication_do_checkpoint_all(errp);
#else
abort();
#endif
}
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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_str(msg));
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
}
static void colo_send_message_value(QEMUFile *f, COLOMessage msg,
uint64_t value, Error **errp)
{
Error *local_err = NULL;
int ret;
colo_send_message(f, msg, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
qemu_put_be64(f, value);
qemu_fflush(f);
ret = qemu_file_get_error(f);
if (ret < 0) {
error_setg_errno(errp, -ret, "Failed to send value for message:%s",
COLOMessage_str(msg));
}
}
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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_str(msg));
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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 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_str(expect_msg));
}
return value;
}
static int colo_do_checkpoint_transaction(MigrationState *s,
QIOChannelBuffer *bioc,
QEMUFile *fb)
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
{
Error *local_err = NULL;
int ret = -1;
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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;
}
/* Reset channel-buffer directly */
qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL);
bioc->usage = 0;
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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 */
migrate_set_block_enabled(false, &local_err);
qemu_savevm_state_header(fb);
qemu_savevm_state_setup(fb);
qemu_mutex_lock_iothread();
qemu_savevm_state_complete_precopy(fb, false, false);
qemu_mutex_unlock_iothread();
qemu_fflush(fb);
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
if (local_err) {
goto out;
}
/*
* We need the size of the VMstate data in Secondary side,
* With which we can decide how much data should be read.
*/
colo_send_message_value(s->to_dst_file, COLO_MESSAGE_VMSTATE_SIZE,
bioc->usage, &local_err);
if (local_err) {
goto out;
}
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
qemu_put_buffer(s->to_dst_file, bioc->data, bioc->usage);
qemu_fflush(s->to_dst_file);
ret = qemu_file_get_error(s->to_dst_file);
if (ret < 0) {
goto out;
}
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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;
}
ret = 0;
qemu_mutex_lock_iothread();
vm_start();
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
out:
if (local_err) {
error_report_err(local_err);
}
return ret;
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
}
static void colo_process_checkpoint(MigrationState *s)
{
QIOChannelBuffer *bioc;
QEMUFile *fb = NULL;
int64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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");
goto out;
}
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
/*
* 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;
}
bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
fb = qemu_fopen_channel_output(QIO_CHANNEL(bioc));
object_unref(OBJECT(bioc));
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
qemu_mutex_lock_iothread();
vm_start();
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("stop", "run");
timer_mod(s->colo_delay_timer,
current_time + s->parameters.x_checkpoint_delay);
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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);
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
if (ret < 0) {
goto out;
}
}
out:
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
/* Throw the unreported error message after exited from loop */
if (local_err) {
error_report_err(local_err);
}
if (fb) {
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);
qemu_mutex_lock_iothread();
}
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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;
QEMUFile *fb = NULL;
QIOChannelBuffer *bioc = NULL; /* Cache incoming device state */
uint64_t total_size;
uint64_t value;
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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");
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);
bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
fb = qemu_fopen_channel_input(QIO_CHANNEL(bioc));
object_unref(OBJECT(bioc));
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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 = 0;
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
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;
}
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
/* 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;
}
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: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED,
&local_err);
if (local_err) {
goto out;
}
qemu_mutex_lock_iothread();
shutdown: Prepare for use of an enum in reset/shutdown_request We want to track why a guest was shutdown; in particular, being able to tell the difference between a guest request (such as ACPI request) and host request (such as SIGINT) will prove useful to libvirt. Since all requests eventually end up changing shutdown_requested in vl.c, the logical change is to make that value track the reason, rather than its current 0/1 contents. Since command-line options control whether a reset request is turned into a shutdown request instead, the same treatment is given to reset_requested. This patch adds an internal enum ShutdownCause that describes reasons that a shutdown can be requested, and changes qemu_system_reset() to pass the reason through, although for now nothing is actually changed with regards to what gets reported. The enum could be exported via QAPI at a later date, if deemed necessary, but for now, there has not been a request to expose that much detail to end clients. For the most part, we turn 0 into SHUTDOWN_CAUSE_NONE, and 1 into SHUTDOWN_CAUSE_HOST_ERROR; the only specific case where we have enough information right now to use a different value is when we are reacting to a host signal. It will take a further patch to edit all call-sites that can trigger a reset or shutdown request to properly pass in any other reasons; this patch includes TODOs to point such places out. qemu_system_reset() trades its 'bool report' parameter for a 'ShutdownCause reason', with all non-zero values having the same effect; this lets us get rid of the weird #defines for VMRESET_* as synonyms for bools. Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <20170515214114.15442-3-eblake@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com>
2017-05-15 23:41:11 +02:00
qemu_system_reset(SHUTDOWN_CAUSE_NONE);
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();
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
failover_set_state(FAILOVER_STATUS_RELAUNCH,
FAILOVER_STATUS_NONE);
failover_request_active(NULL);
goto out;
}
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED,
&local_err);
if (local_err) {
goto out;
}
}
out:
vmstate_loading = false;
COLO: Introduce checkpointing protocol 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>
2016-10-27 08:42:57 +02:00
/* 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);
}
migration_incoming_exit_colo();
return NULL;
}