Commit 0b827d5e authored by zhanghailiang's avatar zhanghailiang Committed by Amit Shah
Browse files

migration: Enter into COLO mode after migration if COLO is enabled 



Add a new migration state: MIGRATION_STATUS_COLO. Migration source side
enters this state after the first live migration successfully finished
if COLO is enabled by command 'migrate_set_capability x-colo on'.

We reuse migration thread, so the process of checkpointing will be handled
in migration thread.

Signed-off-by: default avatarzhanghailiang <zhang.zhanghailiang@huawei.com>
Signed-off-by: default avatarLi Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: default avatarGonglei <arei.gonglei@huawei.com>
Reviewed-by: default avatarDr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: default avatarAmit Shah <amit.shah@redhat.com>
Signed-off-by: default avatarAmit Shah <amit@amitshah.net>
parent 5821ebf9

include/migration/colo.h

+3 −0
Original line number Diff line number Diff line
@@ -19,4 +19,7 @@ 
bool colo_supported(void);

void colo_info_init(void);



void migrate_start_colo_process(MigrationState *s);

bool migration_in_colo_state(void);



#endif

migration/colo.c

+29 −0
Original line number Diff line number Diff line
@@ -11,9 +11,38 @@ 
 */



#include "qemu/osdep.h"

#include "sysemu/sysemu.h"

#include "migration/colo.h"

#include "trace.h"



bool colo_supported(void)

{

    return false;

}



bool migration_in_colo_state(void)

{

    MigrationState *s = migrate_get_current();



    return (s->state == MIGRATION_STATUS_COLO);

}



static void colo_process_checkpoint(MigrationState *s)

{

    qemu_mutex_lock_iothread();

    vm_start();

    qemu_mutex_unlock_iothread();

    trace_colo_vm_state_change("stop", "run");



    /* TODO: COLO checkpoint savevm loop */



}



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();

}

migration/migration.c

+33 −5
Original line number Diff line number Diff line
@@ -695,6 +695,10 @@ MigrationInfo *qmp_query_migrate(Error **errp) 


        get_xbzrle_cache_stats(info);

        break;

    case MIGRATION_STATUS_COLO:

        info->has_status = true;

        /* TODO: display COLO specific information (checkpoint info etc.) */

        break;

    case MIGRATION_STATUS_COMPLETED:

        get_xbzrle_cache_stats(info);
@@ -1113,7 +1117,8 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk, 
    params.shared = has_inc && inc;



    if (migration_is_setup_or_active(s->state) ||

        s->state == MIGRATION_STATUS_CANCELLING) {

        s->state == MIGRATION_STATUS_CANCELLING ||

        s->state == MIGRATION_STATUS_COLO) {

        error_setg(errp, QERR_MIGRATION_ACTIVE);

        return;

    }
@@ -1661,7 +1666,11 @@ static void migration_completion(MigrationState *s, int current_active_state, 


        if (!ret) {

            ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);

            if (ret >= 0) {

            /*

             * Don't mark the image with BDRV_O_INACTIVE flag if

             * we will go into COLO stage later.

             */

            if (ret >= 0 && !migrate_colo_enabled()) {

                ret = bdrv_inactivate_all();

            }

            if (ret >= 0) {
@@ -1703,8 +1712,11 @@ static void migration_completion(MigrationState *s, int current_active_state, 
        goto fail_invalidate;

    }



    if (!migrate_colo_enabled()) {

        migrate_set_state(&s->state, current_active_state,

                          MIGRATION_STATUS_COMPLETED);

    }



    return;



fail_invalidate:
@@ -1749,6 +1761,7 @@ static void *migration_thread(void *opaque) 
    bool entered_postcopy = false;

    /* The active state we expect to be in; ACTIVE or POSTCOPY_ACTIVE */

    enum MigrationStatus current_active_state = MIGRATION_STATUS_ACTIVE;

    bool enable_colo = migrate_colo_enabled();



    rcu_register_thread();
@@ -1857,7 +1870,13 @@ static void *migration_thread(void *opaque) 
    end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);



    qemu_mutex_lock_iothread();

    /*

     * The resource has been allocated by migration will be reused in COLO

     * process, so don't release them.

     */

    if (!enable_colo) {

        qemu_savevm_state_cleanup();

    }

    if (s->state == MIGRATION_STATUS_COMPLETED) {

        uint64_t transferred_bytes = qemu_ftell(s->to_dst_file);

        s->total_time = end_time - s->total_time;
@@ -1870,6 +1889,15 @@ static void *migration_thread(void *opaque) 
        }

        runstate_set(RUN_STATE_POSTMIGRATE);

    } else {

        if (s->state == MIGRATION_STATUS_ACTIVE && enable_colo) {

            migrate_start_colo_process(s);

            qemu_savevm_state_cleanup();

            /*

            * Fixme: we will run VM in COLO no matter its old running state.

            * After exited COLO, we will keep running.

            */

            old_vm_running = true;

        }

        if (old_vm_running && !entered_postcopy) {

            vm_start();

        } else {

migration/trace-events

+3 −0
Original line number Diff line number Diff line
@@ -207,3 +207,6 @@ migration_tls_outgoing_handshake_complete(void) "" 
migration_tls_incoming_handshake_start(void) ""

migration_tls_incoming_handshake_error(const char *err) "err=%s"

migration_tls_incoming_handshake_complete(void) ""



# migration/colo.c

colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'"

qapi-schema.json

+3 −1
Original line number Diff line number Diff line
@@ -459,12 +459,14 @@ 
#

# @failed: some error occurred during migration process.

#

# @colo: VM is in the process of fault tolerance. (since 2.8)

#

# Since: 2.3

#

##

{ 'enum': 'MigrationStatus',

  'data': [ 'none', 'setup', 'cancelling', 'cancelled',

            'active', 'postcopy-active', 'completed', 'failed' ] }

            'active', 'postcopy-active', 'completed', 'failed', 'colo' ] }



##

# @MigrationInfo