diff mbox series

[v5,5/5] qapi: introduce exit-on-error parameter for migrate-incoming

Message ID 20240429191426.2327225-6-vsementsov@yandex-team.ru (mailing list archive)
State New, archived
Headers show
Series migration: do not exit on incoming failure | expand

Commit Message

Vladimir Sementsov-Ogievskiy April 29, 2024, 7:14 p.m. UTC 
Now we do set MIGRATION_FAILED state, but don't give a chance to
orchestrator to query migration state and get the error.

Let's provide a possibility for QMP-based orchestrators to get an error
like with outgoing migration.

For hmp_migrate_incoming(), let's enable the new behavior: HMP is not
and ABI, it's mostly intended to use by developer and it makes sense
not to stop the process.

For x-exit-preconfig, let's keep the old behavior:
 - it's called from init(), so here we want to keep current behavior by
   default
 - it does exit on error by itself as well
So, if we want to change the behavior of x-exit-preconfig, it should be
another patch.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Acked-by: Markus Armbruster <armbru@redhat.com>
---
 migration/migration-hmp-cmds.c |  2 +-
 migration/migration.c          | 38 +++++++++++++++++++++++++++-------
 migration/migration.h          |  3 +++
 qapi/migration.json            |  7 ++++++-
 system/vl.c                    |  3 ++-
 5 files changed, 43 insertions(+), 10 deletions(-)

Comments

Peter Xu April 29, 2024, 7:41 p.m. UTC | #1 
On Mon, Apr 29, 2024 at 10:14:26PM +0300, Vladimir Sementsov-Ogievskiy wrote:
> Now we do set MIGRATION_FAILED state, but don't give a chance to
> orchestrator to query migration state and get the error.
> 
> Let's provide a possibility for QMP-based orchestrators to get an error
> like with outgoing migration.
> 
> For hmp_migrate_incoming(), let's enable the new behavior: HMP is not
> and ABI, it's mostly intended to use by developer and it makes sense
> not to stop the process.
> 
> For x-exit-preconfig, let's keep the old behavior:
>  - it's called from init(), so here we want to keep current behavior by
>    default
>  - it does exit on error by itself as well
> So, if we want to change the behavior of x-exit-preconfig, it should be
> another patch.
> 
> Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
> Acked-by: Markus Armbruster <armbru@redhat.com>
> ---
>  migration/migration-hmp-cmds.c |  2 +-
>  migration/migration.c          | 38 +++++++++++++++++++++++++++-------
>  migration/migration.h          |  3 +++
>  qapi/migration.json            |  7 ++++++-
>  system/vl.c                    |  3 ++-
>  5 files changed, 43 insertions(+), 10 deletions(-)
> 
> diff --git a/migration/migration-hmp-cmds.c b/migration/migration-hmp-cmds.c
> index 7e96ae6ffd..23181bbee1 100644
> --- a/migration/migration-hmp-cmds.c
> +++ b/migration/migration-hmp-cmds.c
> @@ -466,7 +466,7 @@ void hmp_migrate_incoming(Monitor *mon, const QDict *qdict)
>      }
>      QAPI_LIST_PREPEND(caps, g_steal_pointer(&channel));
>  
> -    qmp_migrate_incoming(NULL, true, caps, &err);
> +    qmp_migrate_incoming(NULL, true, caps, true, false, &err);
>      qapi_free_MigrationChannelList(caps);
>  
>  end:
> diff --git a/migration/migration.c b/migration/migration.c
> index 5489ff96df..09f762c99e 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -72,6 +72,8 @@
>  #define NOTIFIER_ELEM_INIT(array, elem)    \
>      [elem] = NOTIFIER_WITH_RETURN_LIST_INITIALIZER((array)[elem])
>  
> +#define INMIGRATE_DEFAULT_EXIT_ON_ERROR true
> +
>  static NotifierWithReturnList migration_state_notifiers[] = {
>      NOTIFIER_ELEM_INIT(migration_state_notifiers, MIG_MODE_NORMAL),
>      NOTIFIER_ELEM_INIT(migration_state_notifiers, MIG_MODE_CPR_REBOOT),
> @@ -234,6 +236,8 @@ void migration_object_init(void)
>      qemu_cond_init(&current_incoming->page_request_cond);
>      current_incoming->page_requested = g_tree_new(page_request_addr_cmp);
>  
> +    current_incoming->exit_on_error = INMIGRATE_DEFAULT_EXIT_ON_ERROR;
> +
>      migration_object_check(current_migration, &error_fatal);
>  
>      blk_mig_init();
> @@ -806,14 +810,19 @@ fail:
>                        MIGRATION_STATUS_FAILED);
>      migration_incoming_state_destroy();
>  
> -    if (migrate_has_error(s)) {
> -        WITH_QEMU_LOCK_GUARD(&s->error_mutex) {
> -            error_report_err(error_copy(s->error));
> +    if (mis->exit_on_error) {
> +        if (migrate_has_error(s)) {
> +            WITH_QEMU_LOCK_GUARD(&s->error_mutex) {
> +                error_report_err(error_copy(s->error));
> +            }
>          }
> +        error_report_err(local_err);
> +        migrate_error_free(s);
> +        exit(EXIT_FAILURE);
> +    } else {
> +        migrate_set_error(s, local_err);
> +        error_free(local_err);
>      }
> -    error_report_err(local_err);
> -    migrate_error_free(s);
> -    exit(EXIT_FAILURE);
>  }

(Please see my reply in previous patch)

>  
>  /**
> @@ -1322,6 +1331,15 @@ static void fill_destination_migration_info(MigrationInfo *info)
>          break;
>      }
>      info->status = mis->state;
> +
> +    if (!info->error_desc) {

This will also guarantee to happen?  Can drop the check too if so.

Other than that looks good, thanks.

> +        MigrationState *s = migrate_get_current();
> +        QEMU_LOCK_GUARD(&s->error_mutex);
> +
> +        if (s->error) {
> +            info->error_desc = g_strdup(error_get_pretty(s->error));
> +        }
> +    }
>  }
>  
>  MigrationInfo *qmp_query_migrate(Error **errp)
> @@ -1796,10 +1814,13 @@ void migrate_del_blocker(Error **reasonp)
>  }
>  
>  void qmp_migrate_incoming(const char *uri, bool has_channels,
> -                          MigrationChannelList *channels, Error **errp)
> +                          MigrationChannelList *channels,
> +                          bool has_exit_on_error, bool exit_on_error,
> +                          Error **errp)
>  {
>      Error *local_err = NULL;
>      static bool once = true;
> +    MigrationIncomingState *mis = migration_incoming_get_current();
>  
>      if (!once) {
>          error_setg(errp, "The incoming migration has already been started");
> @@ -1814,6 +1835,9 @@ void qmp_migrate_incoming(const char *uri, bool has_channels,
>          return;
>      }
>  
> +    mis->exit_on_error =
> +        has_exit_on_error ? exit_on_error : INMIGRATE_DEFAULT_EXIT_ON_ERROR;
> +
>      qemu_start_incoming_migration(uri, has_channels, channels, &local_err);
>  
>      if (local_err) {
> diff --git a/migration/migration.h b/migration/migration.h
> index 8045e39c26..95995a818e 100644
> --- a/migration/migration.h
> +++ b/migration/migration.h
> @@ -227,6 +227,9 @@ struct MigrationIncomingState {
>       * is needed as this field is updated serially.
>       */
>      unsigned int switchover_ack_pending_num;
> +
> +    /* Do exit on incoming migration failure */
> +    bool exit_on_error;
>  };
>  
>  MigrationIncomingState *migration_incoming_get_current(void);
> diff --git a/qapi/migration.json b/qapi/migration.json
> index 8c65b90328..9feed413b5 100644
> --- a/qapi/migration.json
> +++ b/qapi/migration.json
> @@ -1837,6 +1837,10 @@
>  # @channels: list of migration stream channels with each stream in the
>  #     list connected to a destination interface endpoint.
>  #
> +# @exit-on-error: Exit on incoming migration failure.  Default true.
> +#     When set to false, the failure triggers a MIGRATION event, and
> +#     error details could be retrieved with query-migrate.  (since 9.1)
> +#
>  # Since: 2.3
>  #
>  # Notes:
> @@ -1889,7 +1893,8 @@
>  ##
>  { 'command': 'migrate-incoming',
>               'data': {'*uri': 'str',
> -                      '*channels': [ 'MigrationChannel' ] } }
> +                      '*channels': [ 'MigrationChannel' ],
> +                      '*exit-on-error': 'bool' } }
>  
>  ##
>  # @xen-save-devices-state:
> diff --git a/system/vl.c b/system/vl.c
> index 7756eac81e..79cd498395 100644
> --- a/system/vl.c
> +++ b/system/vl.c
> @@ -2723,7 +2723,8 @@ void qmp_x_exit_preconfig(Error **errp)
>      if (incoming) {
>          Error *local_err = NULL;
>          if (strcmp(incoming, "defer") != 0) {
> -            qmp_migrate_incoming(incoming, false, NULL, &local_err);
> +            qmp_migrate_incoming(incoming, false, NULL, true, true,
> +                                 &local_err);
>              if (local_err) {
>                  error_reportf_err(local_err, "-incoming %s: ", incoming);
>                  exit(1);
> -- 
> 2.34.1
>
diff mbox series

Patch

diff --git a/migration/migration-hmp-cmds.c b/migration/migration-hmp-cmds.c
index 7e96ae6ffd..23181bbee1 100644
--- a/migration/migration-hmp-cmds.c
+++ b/migration/migration-hmp-cmds.c
@@ -466,7 +466,7 @@  void hmp_migrate_incoming(Monitor *mon, const QDict *qdict)
     }
     QAPI_LIST_PREPEND(caps, g_steal_pointer(&channel));
 
-    qmp_migrate_incoming(NULL, true, caps, &err);
+    qmp_migrate_incoming(NULL, true, caps, true, false, &err);
     qapi_free_MigrationChannelList(caps);
 
 end:
diff --git a/migration/migration.c b/migration/migration.c
index 5489ff96df..09f762c99e 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -72,6 +72,8 @@ 
 #define NOTIFIER_ELEM_INIT(array, elem)    \
     [elem] = NOTIFIER_WITH_RETURN_LIST_INITIALIZER((array)[elem])
 
+#define INMIGRATE_DEFAULT_EXIT_ON_ERROR true
+
 static NotifierWithReturnList migration_state_notifiers[] = {
     NOTIFIER_ELEM_INIT(migration_state_notifiers, MIG_MODE_NORMAL),
     NOTIFIER_ELEM_INIT(migration_state_notifiers, MIG_MODE_CPR_REBOOT),
@@ -234,6 +236,8 @@  void migration_object_init(void)
     qemu_cond_init(&current_incoming->page_request_cond);
     current_incoming->page_requested = g_tree_new(page_request_addr_cmp);
 
+    current_incoming->exit_on_error = INMIGRATE_DEFAULT_EXIT_ON_ERROR;
+
     migration_object_check(current_migration, &error_fatal);
 
     blk_mig_init();
@@ -806,14 +810,19 @@  fail:
                       MIGRATION_STATUS_FAILED);
     migration_incoming_state_destroy();
 
-    if (migrate_has_error(s)) {
-        WITH_QEMU_LOCK_GUARD(&s->error_mutex) {
-            error_report_err(error_copy(s->error));
+    if (mis->exit_on_error) {
+        if (migrate_has_error(s)) {
+            WITH_QEMU_LOCK_GUARD(&s->error_mutex) {
+                error_report_err(error_copy(s->error));
+            }
         }
+        error_report_err(local_err);
+        migrate_error_free(s);
+        exit(EXIT_FAILURE);
+    } else {
+        migrate_set_error(s, local_err);
+        error_free(local_err);
     }
-    error_report_err(local_err);
-    migrate_error_free(s);
-    exit(EXIT_FAILURE);
 }
 
 /**
@@ -1322,6 +1331,15 @@  static void fill_destination_migration_info(MigrationInfo *info)
         break;
     }
     info->status = mis->state;
+
+    if (!info->error_desc) {
+        MigrationState *s = migrate_get_current();
+        QEMU_LOCK_GUARD(&s->error_mutex);
+
+        if (s->error) {
+            info->error_desc = g_strdup(error_get_pretty(s->error));
+        }
+    }
 }
 
 MigrationInfo *qmp_query_migrate(Error **errp)
@@ -1796,10 +1814,13 @@  void migrate_del_blocker(Error **reasonp)
 }
 
 void qmp_migrate_incoming(const char *uri, bool has_channels,
-                          MigrationChannelList *channels, Error **errp)
+                          MigrationChannelList *channels,
+                          bool has_exit_on_error, bool exit_on_error,
+                          Error **errp)
 {
     Error *local_err = NULL;
     static bool once = true;
+    MigrationIncomingState *mis = migration_incoming_get_current();
 
     if (!once) {
         error_setg(errp, "The incoming migration has already been started");
@@ -1814,6 +1835,9 @@  void qmp_migrate_incoming(const char *uri, bool has_channels,
         return;
     }
 
+    mis->exit_on_error =
+        has_exit_on_error ? exit_on_error : INMIGRATE_DEFAULT_EXIT_ON_ERROR;
+
     qemu_start_incoming_migration(uri, has_channels, channels, &local_err);
 
     if (local_err) {
diff --git a/migration/migration.h b/migration/migration.h
index 8045e39c26..95995a818e 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -227,6 +227,9 @@  struct MigrationIncomingState {
      * is needed as this field is updated serially.
      */
     unsigned int switchover_ack_pending_num;
+
+    /* Do exit on incoming migration failure */
+    bool exit_on_error;
 };
 
 MigrationIncomingState *migration_incoming_get_current(void);
diff --git a/qapi/migration.json b/qapi/migration.json
index 8c65b90328..9feed413b5 100644
--- a/qapi/migration.json
+++ b/qapi/migration.json
@@ -1837,6 +1837,10 @@ 
 # @channels: list of migration stream channels with each stream in the
 #     list connected to a destination interface endpoint.
 #
+# @exit-on-error: Exit on incoming migration failure.  Default true.
+#     When set to false, the failure triggers a MIGRATION event, and
+#     error details could be retrieved with query-migrate.  (since 9.1)
+#
 # Since: 2.3
 #
 # Notes:
@@ -1889,7 +1893,8 @@ 
 ##
 { 'command': 'migrate-incoming',
              'data': {'*uri': 'str',
-                      '*channels': [ 'MigrationChannel' ] } }
+                      '*channels': [ 'MigrationChannel' ],
+                      '*exit-on-error': 'bool' } }
 
 ##
 # @xen-save-devices-state:
diff --git a/system/vl.c b/system/vl.c
index 7756eac81e..79cd498395 100644
--- a/system/vl.c
+++ b/system/vl.c
@@ -2723,7 +2723,8 @@  void qmp_x_exit_preconfig(Error **errp)
     if (incoming) {
         Error *local_err = NULL;
         if (strcmp(incoming, "defer") != 0) {
-            qmp_migrate_incoming(incoming, false, NULL, &local_err);
+            qmp_migrate_incoming(incoming, false, NULL, true, true,
+                                 &local_err);
             if (local_err) {
                 error_reportf_err(local_err, "-incoming %s: ", incoming);
                 exit(1);