10:21 a.m.
So far migration could only be completed while a migration API was
running and waiting for the migration to finish. In case such API could
not be called (the connection that initiated the migration is broken)
the migration would just be aborted or left in a "don't know what to do"
state. But this will change soon and we will be able to successfully
complete such migration once we get the corresponding event from QEMU.
This is specific to post-copy migration when vCPUs are already running
on the destination and we're only waiting for all memory pages to be
transferred. Such post-copy migration (which no-one is actively
watching) is called unattended migration.
Signed-off-by: Jiri Denemark <jdenemar(a)redhat.com>
---
src/qemu/qemu_domain.c | 1 +
src/qemu/qemu_domain.h | 1 +
src/qemu/qemu_driver.c | 5 +++++
src/qemu/qemu_migration.c | 43 +++++++++++++++++++++++++++++++++++++--
src/qemu/qemu_migration.h | 6 ++++++
src/qemu/qemu_process.c | 18 ++++++++++++++++
6 files changed, 72 insertions(+), 2 deletions(-)
diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
index 7ad84f7080..00e1f0c94e 100644
--- a/src/qemu/qemu_domain.c
+++ b/src/qemu/qemu_domain.c
@@ -11074,6 +11074,7 @@ qemuProcessEventFree(struct qemuProcessEvent *event)
qemuMonitorMemoryDeviceSizeChangeFree(event->data);
break;
case QEMU_PROCESS_EVENT_PR_DISCONNECT:
+ case QEMU_PROCESS_EVENT_UNATTENDED_MIGRATION:
case QEMU_PROCESS_EVENT_LAST:
break;
}
diff --git a/src/qemu/qemu_domain.h b/src/qemu/qemu_domain.h
index 3ea0426c7e..94520ac97e 100644
--- a/src/qemu/qemu_domain.h
+++ b/src/qemu/qemu_domain.h
@@ -410,6 +410,7 @@ typedef enum {
QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED,
QEMU_PROCESS_EVENT_GUEST_CRASHLOADED,
QEMU_PROCESS_EVENT_MEMORY_DEVICE_SIZE_CHANGE,
+ QEMU_PROCESS_EVENT_UNATTENDED_MIGRATION,
QEMU_PROCESS_EVENT_LAST
} qemuProcessEventType;
diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c
index d19115473a..e268d3a478 100644
--- a/src/qemu/qemu_driver.c
+++ b/src/qemu/qemu_driver.c
@@ -4279,6 +4279,11 @@ static void qemuProcessEventHandler(void *data, void *opaque)
case QEMU_PROCESS_EVENT_MEMORY_DEVICE_SIZE_CHANGE:
processMemoryDeviceSizeChange(driver, vm, processEvent->data);
break;
+ case QEMU_PROCESS_EVENT_UNATTENDED_MIGRATION:
+ qemuMigrationProcessUnattended(driver, vm,
+ processEvent->action,
+ processEvent->status);
+ break;
case QEMU_PROCESS_EVENT_LAST:
break;
}
diff --git a/src/qemu/qemu_migration.c b/src/qemu/qemu_migration.c
index 6938e0fafc..dacea63610 100644
--- a/src/qemu/qemu_migration.c
+++ b/src/qemu/qemu_migration.c
@@ -5842,8 +5842,11 @@ qemuMigrationDstComplete(virQEMUDriver *driver,
qemuDomainSaveStatus(vm);
- /* Guest is successfully running, so cancel previous auto destroy */
- qemuProcessAutoDestroyRemove(driver, vm);
+ /* Guest is successfully running, so cancel previous auto destroy. There's
+ * nothing to remove when we are resuming post-copy migration.
+ */
+ if (!virDomainObjIsFailedPostcopy(vm))
+ qemuProcessAutoDestroyRemove(driver, vm);
/* Remove completed stats for post-copy, everything but timing fields
* is obsolete anyway.
@@ -6212,6 +6215,42 @@ qemuMigrationDstFinish(virQEMUDriver *driver,
}
+void
+qemuMigrationProcessUnattended(virQEMUDriver *driver,
+ virDomainObj *vm,
+ virDomainAsyncJob job,
+ qemuMonitorMigrationStatus status)
+{
+ qemuDomainObjPrivate *priv = vm->privateData;
+ qemuMigrationJobPhase phase;
+
+ if (!qemuMigrationJobIsActive(vm, job) ||
+ status != QEMU_MONITOR_MIGRATION_STATUS_COMPLETED)
+ return;
+
+ VIR_DEBUG("Unattended %s migration of domain %s successfully finished",
+ job == VIR_ASYNC_JOB_MIGRATION_IN ? "incoming" :
"outgoing",
+ vm->def->name);
+
+ if (job == VIR_ASYNC_JOB_MIGRATION_IN)
+ phase = QEMU_MIGRATION_PHASE_FINISH3;
+ else
+ phase = QEMU_MIGRATION_PHASE_CONFIRM3;
+
+ qemuMigrationJobStartPhase(vm, phase);
+
+ if (job == VIR_ASYNC_JOB_MIGRATION_IN)
+ qemuMigrationDstComplete(driver, vm, true, job, &priv->job);
+ else
+ qemuMigrationSrcComplete(driver, vm, job);
+
+ qemuMigrationJobFinish(vm);
+
+ if (!virDomainObjIsActive(vm))
+ qemuDomainRemoveInactive(driver, vm);
+}
+
+
/* Helper function called while vm is active. */
int
qemuMigrationSrcToFile(virQEMUDriver *driver, virDomainObj *vm,
diff --git a/src/qemu/qemu_migration.h b/src/qemu/qemu_migration.h
index c099cf99cf..eeb69a52bf 100644
--- a/src/qemu/qemu_migration.h
+++ b/src/qemu/qemu_migration.h
@@ -211,6 +211,12 @@ qemuMigrationSrcComplete(virQEMUDriver *driver,
virDomainObj *vm,
virDomainAsyncJob asyncJob);
+void
+qemuMigrationProcessUnattended(virQEMUDriver *driver,
+ virDomainObj *vm,
+ virDomainAsyncJob job,
+ qemuMonitorMigrationStatus status);
+
bool
qemuMigrationSrcIsAllowed(virQEMUDriver *driver,
virDomainObj *vm,
diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c
index d92cd8cb5e..7b347a9061 100644
--- a/src/qemu/qemu_process.c
+++ b/src/qemu/qemu_process.c
@@ -1619,6 +1619,24 @@ qemuProcessHandleMigrationStatus(qemuMonitor *mon G_GNUC_UNUSED,
qemuDomainSaveStatus(vm);
}
+ /* A post-copy migration marked as failed when reconnecting to a domain
+ * with running migration may actually still be running, but we're not
+ * watching it in any thread. Let's make sure the migration is properly
+ * finished in case we get a "completed" event.
+ */
+ if (virDomainObjIsFailedPostcopy(vm) &&
+ priv->job.asyncOwner == 0 &&
+ status == QEMU_MONITOR_MIGRATION_STATUS_COMPLETED) {
+ struct qemuProcessEvent *proc = g_new0(struct qemuProcessEvent, 1);
+
+ proc->eventType = QEMU_PROCESS_EVENT_UNATTENDED_MIGRATION;
+ proc->action = priv->job.asyncJob;
+ proc->status = status;
+ proc->vm = virObjectRef(vm);
+
+ qemuProcessEventSubmit(driver, &proc);
+ }
+
cleanup:
virObjectUnlock(vm);
virObjectEventStateQueue(driver->domainEventState, event);
--
2.35.1