diff mbox series

[RFC,v3,1/2] migration: Update error description whenever migration fails

Message ID 20230518062308.90631-2-tejus.gk@nutanix.com (mailing list archive)
State New, archived
Headers show
Series migration: Update error description whenever migration fails | expand

Commit Message

Tejus GK May 18, 2023, 6:23 a.m. UTC
There are places in migration.c where the migration is marked failed with
MIGRATION_STATUS_FAILED, but the failure reason is never updated. Hence
libvirt doesn't know why the migration failed when it queries for it.

Signed-off-by: Tejus GK <tejus.gk@nutanix.com>
---
 migration/migration.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

Comments

Juan Quintela May 18, 2023, 11:50 a.m. UTC | #1
Tejus GK <tejus.gk@nutanix.com> wrote:
> There are places in migration.c where the migration is marked failed with
> MIGRATION_STATUS_FAILED, but the failure reason is never updated. Hence
> libvirt doesn't know why the migration failed when it queries for it.
>
> Signed-off-by: Tejus GK <tejus.gk@nutanix.com>

Reviewed-by: Juan Quintela <quintela@redhat.com>


> ---
>  migration/migration.c | 23 ++++++++++++-----------
>  1 file changed, 12 insertions(+), 11 deletions(-)
>
> diff --git a/migration/migration.c b/migration/migration.c
> index 00d8ba8da0..864150d01d 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -1683,15 +1683,11 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
>      } else if (strstart(uri, "fd:", &p)) {
>          fd_start_outgoing_migration(s, p, &local_err);
>      } else {
> -        if (!(has_resume && resume)) {
> -            yank_unregister_instance(MIGRATION_YANK_INSTANCE);
> -        }
> -        error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "uri",
> +        error_setg(&local_err, QERR_INVALID_PARAMETER_VALUE, "uri",
>                     "a valid migration protocol");
>          migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
>                            MIGRATION_STATUS_FAILED);
>          block_cleanup_parameters();
> -        return;

If you have to respin, please split the removal of the yan_unregister()
and return in one patch, and let of this patch the error bits.

>      }
>  
>      if (local_err) {
> @@ -2073,7 +2069,7 @@ migration_wait_main_channel(MigrationState *ms)
>   * Switch from normal iteration to postcopy
>   * Returns non-0 on error
>   */
> -static int postcopy_start(MigrationState *ms)
> +static int postcopy_start(MigrationState *ms, Error **errp)
>  {
>      int ret;
>      QIOChannelBuffer *bioc;
> @@ -2183,7 +2179,7 @@ static int postcopy_start(MigrationState *ms)
>       */
>      ret = qemu_file_get_error(ms->to_dst_file);
>      if (ret) {
> -        error_report("postcopy_start: Migration stream errored (pre package)");
> +        error_setg(errp, "postcopy_start: Migration stream errored (pre package)");
>          goto fail_closefb;
>      }
>  
> @@ -2220,7 +2216,7 @@ static int postcopy_start(MigrationState *ms)
>  
>      ret = qemu_file_get_error(ms->to_dst_file);
>      if (ret) {
> -        error_report("postcopy_start: Migration stream errored");
> +        error_setg(errp, "postcopy_start: Migration stream errored");
>          migrate_set_state(&ms->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
>                                MIGRATION_STATUS_FAILED);
>      }
> @@ -2741,6 +2737,7 @@ typedef enum {
>  static MigIterateState migration_iteration_run(MigrationState *s)
>  {
>      uint64_t must_precopy, can_postcopy;
> +    Error *local_err = NULL;
>      bool in_postcopy = s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE;
>  
>      qemu_savevm_state_pending_estimate(&must_precopy, &can_postcopy);
> @@ -2763,8 +2760,9 @@ static MigIterateState migration_iteration_run(MigrationState *s)
>      /* Still a significant amount to transfer */
>      if (!in_postcopy && must_precopy <= s->threshold_size &&
>          qatomic_read(&s->start_postcopy)) {
> -        if (postcopy_start(s)) {
> -            error_report("%s: postcopy failed to start", __func__);
> +        if (postcopy_start(s, &local_err)) {
> +            migrate_set_error(s, local_err);
> +            error_report_err(local_err);

Not your fault.
But the interface of migrate_set_error() is a mess.  It is followed
sometimes from error_report_err() another from error_free() and another
by ...
Daniel P. Berrangé May 18, 2023, 12:24 p.m. UTC | #2
On Thu, May 18, 2023 at 06:23:07AM +0000, Tejus GK wrote:
> There are places in migration.c where the migration is marked failed with
> MIGRATION_STATUS_FAILED, but the failure reason is never updated. Hence
> libvirt doesn't know why the migration failed when it queries for it.
> 
> Signed-off-by: Tejus GK <tejus.gk@nutanix.com>
> ---
>  migration/migration.c | 23 ++++++++++++-----------
>  1 file changed, 12 insertions(+), 11 deletions(-)

Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>


With regards,
Daniel
diff mbox series

Patch

diff --git a/migration/migration.c b/migration/migration.c
index 00d8ba8da0..864150d01d 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1683,15 +1683,11 @@  void qmp_migrate(const char *uri, bool has_blk, bool blk,
     } else if (strstart(uri, "fd:", &p)) {
         fd_start_outgoing_migration(s, p, &local_err);
     } else {
-        if (!(has_resume && resume)) {
-            yank_unregister_instance(MIGRATION_YANK_INSTANCE);
-        }
-        error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "uri",
+        error_setg(&local_err, QERR_INVALID_PARAMETER_VALUE, "uri",
                    "a valid migration protocol");
         migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
                           MIGRATION_STATUS_FAILED);
         block_cleanup_parameters();
-        return;
     }
 
     if (local_err) {
@@ -2073,7 +2069,7 @@  migration_wait_main_channel(MigrationState *ms)
  * Switch from normal iteration to postcopy
  * Returns non-0 on error
  */
-static int postcopy_start(MigrationState *ms)
+static int postcopy_start(MigrationState *ms, Error **errp)
 {
     int ret;
     QIOChannelBuffer *bioc;
@@ -2183,7 +2179,7 @@  static int postcopy_start(MigrationState *ms)
      */
     ret = qemu_file_get_error(ms->to_dst_file);
     if (ret) {
-        error_report("postcopy_start: Migration stream errored (pre package)");
+        error_setg(errp, "postcopy_start: Migration stream errored (pre package)");
         goto fail_closefb;
     }
 
@@ -2220,7 +2216,7 @@  static int postcopy_start(MigrationState *ms)
 
     ret = qemu_file_get_error(ms->to_dst_file);
     if (ret) {
-        error_report("postcopy_start: Migration stream errored");
+        error_setg(errp, "postcopy_start: Migration stream errored");
         migrate_set_state(&ms->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
                               MIGRATION_STATUS_FAILED);
     }
@@ -2741,6 +2737,7 @@  typedef enum {
 static MigIterateState migration_iteration_run(MigrationState *s)
 {
     uint64_t must_precopy, can_postcopy;
+    Error *local_err = NULL;
     bool in_postcopy = s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE;
 
     qemu_savevm_state_pending_estimate(&must_precopy, &can_postcopy);
@@ -2763,8 +2760,9 @@  static MigIterateState migration_iteration_run(MigrationState *s)
     /* Still a significant amount to transfer */
     if (!in_postcopy && must_precopy <= s->threshold_size &&
         qatomic_read(&s->start_postcopy)) {
-        if (postcopy_start(s)) {
-            error_report("%s: postcopy failed to start", __func__);
+        if (postcopy_start(s, &local_err)) {
+            migrate_set_error(s, local_err);
+            error_report_err(local_err);
         }
         return MIG_ITERATE_SKIP;
     }
@@ -3250,8 +3248,10 @@  void migrate_fd_connect(MigrationState *s, Error *error_in)
      */
     if (migrate_postcopy_ram() || migrate_return_path()) {
         if (open_return_path_on_source(s, !resume)) {
-            error_report("Unable to open return-path for postcopy");
+            error_setg(&local_err, "Unable to open return-path for postcopy");
             migrate_set_state(&s->state, s->state, MIGRATION_STATUS_FAILED);
+            migrate_set_error(s, local_err);
+            error_report_err(local_err);
             migrate_fd_cleanup(s);
             return;
         }
@@ -3275,6 +3275,7 @@  void migrate_fd_connect(MigrationState *s, Error *error_in)
     }
 
     if (multifd_save_setup(&local_err) != 0) {
+        migrate_set_error(s, local_err);
         error_report_err(local_err);
         migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
                           MIGRATION_STATUS_FAILED);