* zhanghailiang (zhang.zhanghaili...@huawei.com) wrote:
> We need communications protocol of user-defined to control the checkpoint
> process.
> 
> The new checkpoint 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.zhanghaili...@huawei.com>
> Signed-off-by: Li Zhijian <lizhij...@cn.fujitsu.com>
> Signed-off-by: Gonglei <arei.gong...@huawei.com>
> Cc: Eric Blake <ebl...@redhat.com>
> Cc: Markus Armbruster <arm...@redhat.com>
> Cc: Dr. David Alan Gilbert <dgilb...@redhat.com>
> ---
> 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 | 201 
> ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
>  qapi-schema.json |  25 +++++++
>  trace-events     |   2 +
>  3 files changed, 226 insertions(+), 2 deletions(-)
> 
> diff --git a/migration/colo.c b/migration/colo.c
> index 65ac0c9..c76e1fa 100644
> --- a/migration/colo.c
> +++ b/migration/colo.c
> @@ -10,6 +10,7 @@
>   * later.  See the COPYING file in the top-level directory.
>   */
>  
> +#include <unistd.h>
>  #include "sysemu/sysemu.h"
>  #include "migration/colo.h"
>  #include "trace.h"
> @@ -34,22 +35,147 @@ bool migration_incoming_in_colo_state(void)
>      return mis && (mis->state == MIGRATION_STATUS_COLO);
>  }
>  
> +static void colo_put_cmd(QEMUFile *f, COLOCommand cmd,
> +                         Error **errp)
> +{
> +    int ret;
> +
> +    if (cmd >= COLO_COMMAND__MAX) {
> +        error_setg(errp, "%s: Invalid cmd", __func__);
> +        return;
> +    }
> +    qemu_put_be32(f, cmd);
> +    qemu_fflush(f);
> +
> +    ret = qemu_file_get_error(f);
> +    if (ret < 0) {
> +        error_setg_errno(errp, -ret, "Can't put COLO command");
> +    }
> +    trace_colo_put_cmd(COLOCommand_lookup[cmd]);
> +}
> +
> +static COLOCommand colo_get_cmd(QEMUFile *f, Error **errp)
> +{
> +    COLOCommand cmd;
> +    int ret;
> +
> +    cmd = qemu_get_be32(f);
> +    ret = qemu_file_get_error(f);
> +    if (ret < 0) {
> +        error_setg_errno(errp, -ret, "Can't get COLO command");
> +        return cmd;
> +    }
> +    if (cmd >= COLO_COMMAND__MAX) {

I'm not sure this is guaranteed to do the right thing if the value
read was negative and converted to the enum;  it seems to depend
a bit on the compiler as to whether an enum is signed or not;
but it seems the normal behaviour is for the enum to be unsigned
as long as there are no negative values when it's declared; so it looks
safe in practice.

Reviewed-by: Dr. David Alan Gilbert <dgilb...@redhat.com>

> +        error_setg(errp, "%s: Invalid cmd", __func__);
> +        return cmd;
> +    }
> +    trace_colo_get_cmd(COLOCommand_lookup[cmd]);
> +    return cmd;
> +}
> +
> +static void colo_get_check_cmd(QEMUFile *f, COLOCommand expect_cmd,
> +                               Error **errp)
> +{
> +    COLOCommand cmd;
> +    Error *local_err = NULL;
> +
> +    cmd = colo_get_cmd(f, &local_err);
> +    if (local_err) {
> +        error_propagate(errp, local_err);
> +        return;
> +    }
> +    if (cmd != expect_cmd) {
> +        error_setg(errp, "Unexpected COLO command %d, expected %d",
> +                          expect_cmd, cmd);
> +    }
> +}
> +
> +static int colo_do_checkpoint_transaction(MigrationState *s)
> +{
> +    Error *local_err = NULL;
> +
> +    colo_put_cmd(s->to_dst_file, COLO_COMMAND_CHECKPOINT_REQUEST,
> +                 &local_err);
> +    if (local_err) {
> +        goto out;
> +    }
> +
> +    colo_get_check_cmd(s->rp_state.from_dst_file,
> +                       COLO_COMMAND_CHECKPOINT_REPLY, &local_err);
> +    if (local_err) {
> +        goto out;
> +    }
> +
> +    /* TODO: suspend and save vm state to colo buffer */
> +
> +    colo_put_cmd(s->to_dst_file, COLO_COMMAND_VMSTATE_SEND, &local_err);
> +    if (local_err) {
> +        goto out;
> +    }
> +
> +    /* TODO: send vmstate to Secondary */
> +
> +    colo_get_check_cmd(s->rp_state.from_dst_file,
> +                       COLO_COMMAND_VMSTATE_RECEIVED, &local_err);
> +    if (local_err) {
> +        goto out;
> +    }
> +
> +    colo_get_check_cmd(s->rp_state.from_dst_file,
> +                       COLO_COMMAND_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_get_check_cmd(s->rp_state.from_dst_file,
> +                       COLO_COMMAND_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) {
> +        /* start a colo checkpoint */
> +        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);
>  
> @@ -67,9 +193,33 @@ void migrate_start_colo_process(MigrationState *s)
>      qemu_mutex_lock_iothread();
>  }
>  
> +static void colo_wait_handle_cmd(QEMUFile *f, int *checkpoint_request,
> +                                 Error **errp)
> +{
> +    COLOCommand cmd;
> +    Error *local_err = NULL;
> +
> +    cmd = colo_get_cmd(f, &local_err);
> +    if (local_err) {
> +        error_propagate(errp, local_err);
> +        return;
> +    }
> +
> +    switch (cmd) {
> +    case COLO_COMMAND_CHECKPOINT_REQUEST:
> +        *checkpoint_request = 1;
> +        break;
> +    default:
> +        *checkpoint_request = 0;
> +        error_setg(errp, "Got unknown COLO command: %d", cmd);
> +        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);
> @@ -85,9 +235,56 @@ void *colo_process_incoming_thread(void *opaque)
>      */
>      qemu_file_set_blocking(mis->from_src_file, true);
>  
> -    /* TODO: COLO checkpoint restore loop */
> +    colo_put_cmd(mis->to_src_file, COLO_COMMAND_CHECKPOINT_READY,
> +                 &local_err);
> +    if (local_err) {
> +        goto out;
> +    }
> +
> +    while (mis->state == MIGRATION_STATUS_COLO) {
> +        int request;
> +
> +        colo_wait_handle_cmd(mis->from_src_file, &request, &local_err);
> +        if (local_err) {
> +            goto out;
> +        }
> +        assert(request);
> +        /* FIXME: This is unnecessary for periodic checkpoint mode */
> +        colo_put_cmd(mis->to_src_file, COLO_COMMAND_CHECKPOINT_REPLY,
> +                     &local_err);
> +        if (local_err) {
> +            goto out;
> +        }
> +
> +        colo_get_check_cmd(mis->from_src_file,
> +                           COLO_COMMAND_VMSTATE_SEND, &local_err);
> +        if (local_err) {
> +            goto out;
> +        }
> +
> +        /* TODO: read migration data into colo buffer */
> +
> +        colo_put_cmd(mis->to_src_file, COLO_COMMAND_VMSTATE_RECEIVED,
> +                     &local_err);
> +        if (local_err) {
> +            goto out;
> +        }
> +
> +        /* TODO: load vm state */
> +
> +        colo_put_cmd(mis->to_src_file, COLO_COMMAND_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);
>      }
> diff --git a/qapi-schema.json b/qapi-schema.json
> index 6eefad2..4ea4108 100644
> --- a/qapi-schema.json
> +++ b/qapi-schema.json
> @@ -718,6 +718,31 @@
>  { 'command': 'migrate-start-postcopy' }
>  
>  ##
> +# @COLOCommand
> +#
> +# The commands for COLO fault tolerance
> +#
> +# @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: 2.6
> +##
> +{ 'enum': 'COLOCommand',
> +  'data': [ 'checkpoint-ready', 'checkpoint-request', 'checkpoint-reply',
> +            'vmstate-send', 'vmstate-size', 'vmstate-received',
> +            'vmstate-loaded' ] }
> +
>  # @MouseInfo:
>  #
>  # Information about a mouse device.
> diff --git a/trace-events b/trace-events
> index 57ddc8f..51b2305 100644
> --- a/trace-events
> +++ b/trace-events
> @@ -1581,6 +1581,8 @@ postcopy_ram_incoming_cleanup_join(void) ""
>  
>  # migration/colo.c
>  colo_vm_state_change(const char *old, const char *new) "Change '%s' => '%s'"
> +colo_put_cmd(const char *msg) "Send '%s' cmd"
> +colo_get_cmd(const char *msg) "Receive '%s' cmd"
>  
>  # kvm-all.c
>  kvm_ioctl(int type, void *arg) "type 0x%x, arg %p"
> -- 
> 1.8.3.1
> 
> 
--
Dr. David Alan Gilbert / dgilb...@redhat.com / Manchester, UK

Reply via email to