diff mbox series

[v7,20/23] qmp/migration: new command migrate-recover

Message ID 20180309091535.13315-21-peterx@redhat.com
State New
Headers show
Series Migration: postcopy failure recovery | expand

Commit Message

Peter Xu March 9, 2018, 9:15 a.m. UTC
The first allow-oob=true command.  It's used on destination side when
the postcopy migration is paused and ready for a recovery.  After
execution, a new migration channel will be established for postcopy to
continue.

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 migration/migration.c | 24 ++++++++++++++++++++++++
 migration/migration.h |  1 +
 migration/savevm.c    |  3 +++
 qapi/migration.json   | 20 ++++++++++++++++++++
 4 files changed, 48 insertions(+)

Comments

Dr. David Alan Gilbert March 12, 2018, 5:33 p.m. UTC | #1
* Peter Xu (peterx@redhat.com) wrote:
> The first allow-oob=true command.  It's used on destination side when
> the postcopy migration is paused and ready for a recovery.  After
> execution, a new migration channel will be established for postcopy to
> continue.
> 
> Signed-off-by: Peter Xu <peterx@redhat.com>

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

> ---
>  migration/migration.c | 24 ++++++++++++++++++++++++
>  migration/migration.h |  1 +
>  migration/savevm.c    |  3 +++
>  qapi/migration.json   | 20 ++++++++++++++++++++
>  4 files changed, 48 insertions(+)
> 
> diff --git a/migration/migration.c b/migration/migration.c
> index af00cfe04f..180552329c 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -1424,6 +1424,30 @@ void qmp_migrate_incoming(const char *uri, Error **errp)
>      once = false;
>  }
>  
> +void qmp_migrate_recover(const char *uri, Error **errp)
> +{
> +    MigrationIncomingState *mis = migration_incoming_get_current();
> +
> +    if (mis->state != MIGRATION_STATUS_POSTCOPY_PAUSED) {
> +        error_setg(errp, "Migrate recover can only be run "
> +                   "when postcopy is paused.");
> +        return;
> +    }
> +
> +    if (atomic_cmpxchg(&mis->postcopy_recover_triggered,
> +                       false, true) == true) {
> +        error_setg(errp, "Migrate recovery is triggered already");
> +        return;
> +    }
> +
> +    /*
> +     * Note that this call will never start a real migration; it will
> +     * only re-setup the migration stream and poke existing migration
> +     * to continue using that newly established channel.
> +     */
> +    qemu_start_incoming_migration(uri, errp);
> +}
> +
>  bool migration_is_blocked(Error **errp)
>  {
>      if (qemu_savevm_state_blocked(errp)) {
> diff --git a/migration/migration.h b/migration/migration.h
> index 8f64b43584..c549859cc3 100644
> --- a/migration/migration.h
> +++ b/migration/migration.h
> @@ -65,6 +65,7 @@ struct MigrationIncomingState {
>      QemuSemaphore colo_incoming_sem;
>  
>      /* notify PAUSED postcopy incoming migrations to try to continue */
> +    bool postcopy_recover_triggered;
>      QemuSemaphore postcopy_pause_sem_dst;
>      QemuSemaphore postcopy_pause_sem_fault;
>  };
> diff --git a/migration/savevm.c b/migration/savevm.c
> index 7f4899ae9c..3e660dfca6 100644
> --- a/migration/savevm.c
> +++ b/migration/savevm.c
> @@ -2166,6 +2166,9 @@ static bool postcopy_pause_incoming(MigrationIncomingState *mis)
>  {
>      trace_postcopy_pause_incoming();
>  
> +    /* Clear the triggered bit to allow one recovery */
> +    mis->postcopy_recover_triggered = false;
> +
>      migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
>                        MIGRATION_STATUS_POSTCOPY_PAUSED);
>  
> diff --git a/qapi/migration.json b/qapi/migration.json
> index 152fb8e51e..451d8c572b 100644
> --- a/qapi/migration.json
> +++ b/qapi/migration.json
> @@ -1174,3 +1174,23 @@
>  # Since: 2.9
>  ##
>  { 'command': 'xen-colo-do-checkpoint' }
> +
> +##
> +# @migrate-recover:
> +#
> +# Provide a recovery migration stream URI.
> +#
> +# @uri: the URI to be used for the recovery of migration stream.
> +#
> +# Returns: nothing.
> +#
> +# Example:
> +#
> +# -> { "execute": "migrate-recover",
> +#      "arguments": { "uri": "tcp:192.168.1.200:12345" } }
> +# <- { "return": {} }
> +#
> +# Since: 2.12
> +##
> +{ 'command': 'migrate-recover', 'data': { 'uri': 'str' },
> +  'allow-oob': true }
> -- 
> 2.14.3
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
diff mbox series

Patch

diff --git a/migration/migration.c b/migration/migration.c
index af00cfe04f..180552329c 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1424,6 +1424,30 @@  void qmp_migrate_incoming(const char *uri, Error **errp)
     once = false;
 }
 
+void qmp_migrate_recover(const char *uri, Error **errp)
+{
+    MigrationIncomingState *mis = migration_incoming_get_current();
+
+    if (mis->state != MIGRATION_STATUS_POSTCOPY_PAUSED) {
+        error_setg(errp, "Migrate recover can only be run "
+                   "when postcopy is paused.");
+        return;
+    }
+
+    if (atomic_cmpxchg(&mis->postcopy_recover_triggered,
+                       false, true) == true) {
+        error_setg(errp, "Migrate recovery is triggered already");
+        return;
+    }
+
+    /*
+     * Note that this call will never start a real migration; it will
+     * only re-setup the migration stream and poke existing migration
+     * to continue using that newly established channel.
+     */
+    qemu_start_incoming_migration(uri, errp);
+}
+
 bool migration_is_blocked(Error **errp)
 {
     if (qemu_savevm_state_blocked(errp)) {
diff --git a/migration/migration.h b/migration/migration.h
index 8f64b43584..c549859cc3 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -65,6 +65,7 @@  struct MigrationIncomingState {
     QemuSemaphore colo_incoming_sem;
 
     /* notify PAUSED postcopy incoming migrations to try to continue */
+    bool postcopy_recover_triggered;
     QemuSemaphore postcopy_pause_sem_dst;
     QemuSemaphore postcopy_pause_sem_fault;
 };
diff --git a/migration/savevm.c b/migration/savevm.c
index 7f4899ae9c..3e660dfca6 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -2166,6 +2166,9 @@  static bool postcopy_pause_incoming(MigrationIncomingState *mis)
 {
     trace_postcopy_pause_incoming();
 
+    /* Clear the triggered bit to allow one recovery */
+    mis->postcopy_recover_triggered = false;
+
     migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
                       MIGRATION_STATUS_POSTCOPY_PAUSED);
 
diff --git a/qapi/migration.json b/qapi/migration.json
index 152fb8e51e..451d8c572b 100644
--- a/qapi/migration.json
+++ b/qapi/migration.json
@@ -1174,3 +1174,23 @@ 
 # Since: 2.9
 ##
 { 'command': 'xen-colo-do-checkpoint' }
+
+##
+# @migrate-recover:
+#
+# Provide a recovery migration stream URI.
+#
+# @uri: the URI to be used for the recovery of migration stream.
+#
+# Returns: nothing.
+#
+# Example:
+#
+# -> { "execute": "migrate-recover",
+#      "arguments": { "uri": "tcp:192.168.1.200:12345" } }
+# <- { "return": {} }
+#
+# Since: 2.12
+##
+{ 'command': 'migrate-recover', 'data': { 'uri': 'str' },
+  'allow-oob': true }