qemu: Cancel migration if guest encoutners I/O error while migrating

During a live migration the guest may receive a disk access I/O error.
In this state the guest is unable to continue running on a remote host
after migration as some state may be present in the kernel and not
migrated.

With this patch, the migration is canceled in such case so it can either
continue on the source if the I/O issues are recovered or has to be
destroyed anyways.

diff --git a/src/qemu/qemu_migration.c b/src/qemu/qemu_migration.c
index ff803caa486567f04b47c997ce8040ecbfb5f5e6..4115ca2aa7dfe2dff8d42a2c82ec25f9a14a9027 100644 (file)
--- a/src/qemu/qemu_migration.c
+++ b/src/qemu/qemu_migration.c
@@ -1686,6 +1686,7 @@ qemuMigrationWaitForCompletion(virQEMUDriverPtr driver, virDomainObjPtr vm,
 {
     qemuDomainObjPrivatePtr priv = vm->privateData;
     const char *job;
+    int pauseReason;
 
     switch (priv->job.asyncJob) {
     case QEMU_ASYNC_JOB_MIGRATION_OUT:
@@ -1707,6 +1708,12 @@ qemuMigrationWaitForCompletion(virQEMUDriverPtr driver, virDomainObjPtr vm,
         /* Poll every 50ms for progress & to allow cancellation */
         struct timespec ts = { .tv_sec = 0, .tv_nsec = 50 * 1000 * 1000ull };
 
+        /* cancel migration if disk I/O error is emitted while migrating */
+        if (priv->job.asyncJob == QEMU_ASYNC_JOB_MIGRATION_OUT &&
+            virDomainObjGetState(vm, &pauseReason) == VIR_DOMAIN_PAUSED &&
+            pauseReason == VIR_DOMAIN_PAUSED_IOERROR)
+            goto cancel;
+
         if (qemuMigrationUpdateJobStatus(driver, vm, job, asyncJob) < 0)
             goto cleanup;
 
@@ -1728,6 +1735,20 @@ cleanup:
         return 0;
     else
         return -1;
+
+cancel:
+    if (virDomainObjIsActive(vm)) {
+        if (qemuDomainObjEnterMonitorAsync(driver, vm,
+                                           priv->job.asyncJob) == 0) {
+            qemuMonitorMigrateCancel(priv->mon);
+            qemuDomainObjExitMonitor(driver, vm);
+        }
+    }
+
+    priv->job.info.type = VIR_DOMAIN_JOB_FAILED;
+    virReportError(VIR_ERR_OPERATION_FAILED,
+                   _("%s: %s"), job, _("failed due to I/O error"));
+    return -1;
 }