[libvirt PATCH v2 03/81] Introduce VIR_DOMAIN_RUNNING_POSTCOPY_FAILED

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



This new "post-copy failed" reason for the running state will be used on
the destination host when post-copy migration fails while the domain is
already running there.

Signed-off-by: Jiri Denemark <jdenemar@xxxxxxxxxx>
---

Notes:
    Version 2:
    - documented both VIR_DOMAIN_RUNNING_POSTCOPY_FAILED and
      VIR_DOMAIN_PAUSED_POSTCOPY_FAILED possibilities on the destination

 examples/c/misc/event-test.c     |  3 +++
 include/libvirt/libvirt-domain.h |  2 ++
 src/conf/domain_conf.c           |  1 +
 src/libvirt-domain.c             | 26 +++++++++++++++++++-------
 src/qemu/qemu_domain.c           |  3 +++
 tools/virsh-domain-event.c       |  3 ++-
 tools/virsh-domain-monitor.c     |  1 +
 7 files changed, 31 insertions(+), 8 deletions(-)

diff --git a/examples/c/misc/event-test.c b/examples/c/misc/event-test.c
index 1165469a65..64652b0153 100644
--- a/examples/c/misc/event-test.c
+++ b/examples/c/misc/event-test.c
@@ -196,6 +196,9 @@ eventDetailToString(int event,
             case VIR_DOMAIN_EVENT_RESUMED_POSTCOPY:
                 return "Post-copy";
 
+            case VIR_DOMAIN_EVENT_RESUMED_POSTCOPY_FAILED:
+                return "Post-copy Error";
+
             case VIR_DOMAIN_EVENT_RESUMED_LAST:
                 break;
             }
diff --git a/include/libvirt/libvirt-domain.h b/include/libvirt/libvirt-domain.h
index 24846046aa..caf99d41bc 100644
--- a/include/libvirt/libvirt-domain.h
+++ b/include/libvirt/libvirt-domain.h
@@ -108,6 +108,7 @@ typedef enum {
                                                wakeup event (Since: 0.9.11) */
     VIR_DOMAIN_RUNNING_CRASHED = 9,         /* resumed from crashed (Since: 1.1.1) */
     VIR_DOMAIN_RUNNING_POSTCOPY = 10,       /* running in post-copy migration mode (Since: 1.3.3) */
+    VIR_DOMAIN_RUNNING_POSTCOPY_FAILED = 11, /* running in failed post-copy migration (Since: 8.5.0) */
 
 # ifdef VIR_ENUM_SENTINELS
     VIR_DOMAIN_RUNNING_LAST /* (Since: 0.9.10) */
@@ -3801,6 +3802,7 @@ typedef enum {
     VIR_DOMAIN_EVENT_RESUMED_FROM_SNAPSHOT = 2, /* Resumed from snapshot (Since: 0.9.5) */
     VIR_DOMAIN_EVENT_RESUMED_POSTCOPY = 3,   /* Resumed, but migration is still
                                                 running in post-copy mode (Since: 1.3.3) */
+    VIR_DOMAIN_EVENT_RESUMED_POSTCOPY_FAILED = 4, /* Running, but migration failed in post-copy (Since: 8.5.0) */
 
 # ifdef VIR_ENUM_SENTINELS
     VIR_DOMAIN_EVENT_RESUMED_LAST /* (Since: 0.9.10) */
diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c
index 6e1bb36ba8..58ca3c7c75 100644
--- a/src/conf/domain_conf.c
+++ b/src/conf/domain_conf.c
@@ -1106,6 +1106,7 @@ VIR_ENUM_IMPL(virDomainRunningReason,
               "wakeup",
               "crashed",
               "post-copy",
+              "post-copy failed",
 );
 
 VIR_ENUM_IMPL(virDomainBlockedReason,
diff --git a/src/libvirt-domain.c b/src/libvirt-domain.c
index e3ced700b8..b9f1d73d5a 100644
--- a/src/libvirt-domain.c
+++ b/src/libvirt-domain.c
@@ -9764,10 +9764,16 @@ virDomainMigrateGetMaxSpeed(virDomainPtr domain,
  * at most once no matter how fast it changes. On the other hand once the
  * guest is running on the destination host, the migration can no longer be
  * rolled back because none of the hosts has complete state. If this happens,
- * libvirt will leave the domain paused on both hosts with
- * VIR_DOMAIN_PAUSED_POSTCOPY_FAILED reason. It's up to the upper layer to
- * decide what to do in such case. Because of this, libvirt will refuse to
- * cancel post-copy migration via virDomainAbortJob.
+ * libvirt will leave the domain paused on the source host with
+ * VIR_DOMAIN_PAUSED_POSTCOPY_FAILED reason. The domain on the destination host
+ * will either remain running with VIR_DOMAIN_RUNNING_POSTCOPY_FAILED reason if
+ * libvirt loses control over the migration (e.g., the daemon is restarted or
+ * libvirt connection is broken) while QEMU is still able to continue migrating
+ * memory pages from the source to the destination or it will be paused with
+ * VIR_DOMAIN_PAUSED_POSTCOPY_FAILED if even the connection between QEMU
+ * processes gets broken. It's up to the upper layer to decide what to do in
+ * such case. Because of this, libvirt will refuse to cancel post-copy
+ * migration via virDomainAbortJob.
  *
  * The following domain life cycle events are emitted during post-copy
  * migration:
@@ -9781,9 +9787,15 @@ virDomainMigrateGetMaxSpeed(virDomainPtr domain,
  *  VIR_DOMAIN_EVENT_RESUMED_MIGRATED (on the destination),
  *  VIR_DOMAIN_EVENT_STOPPED_MIGRATED (on the source) -- migration finished
  *      successfully and the destination host holds a complete guest state.
- *  VIR_DOMAIN_EVENT_SUSPENDED_POSTCOPY_FAILED (on the destination) -- emitted
- *      when migration fails in post-copy mode and it's unclear whether any
- *      of the hosts has a complete guest state.
+ *  VIR_DOMAIN_EVENT_SUSPENDED_POSTCOPY_FAILED (on the source),
+ *  VIR_DOMAIN_EVENT_RESUMED_POSTCOPY_FAILED (on the destination) -- emitted
+ *      when migration fails in post-copy mode from libvirt's point of view
+ *      and it's unclear whether any of the hosts has a complete guest state.
+ *      This happens when libvirt loses control over the migration. Virtual
+ *      CPUs on the destination are still running.
+ *  VIR_DOMAIN_EVENT_SUSPENDED_POSTCOPY_FAILED (on the destination) -- QEMU is
+ *      not able to keep migration running in post-copy mode (i.e., its
+ *      connection is broken) and libvirt stops virtual CPUs on the destination.
  *
  * The progress of a post-copy migration can be monitored normally using
  * virDomainGetJobStats on the source host. Fetching statistics of a completed
diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
index 8ebf152d95..6f358466c5 100644
--- a/src/qemu/qemu_domain.c
+++ b/src/qemu/qemu_domain.c
@@ -11145,6 +11145,9 @@ qemuDomainRunningReasonToResumeEvent(virDomainRunningReason reason)
     case VIR_DOMAIN_RUNNING_POSTCOPY:
         return VIR_DOMAIN_EVENT_RESUMED_POSTCOPY;
 
+    case VIR_DOMAIN_RUNNING_POSTCOPY_FAILED:
+        return VIR_DOMAIN_EVENT_RESUMED_POSTCOPY_FAILED;
+
     case VIR_DOMAIN_RUNNING_UNKNOWN:
     case VIR_DOMAIN_RUNNING_SAVE_CANCELED:
     case VIR_DOMAIN_RUNNING_BOOTED:
diff --git a/tools/virsh-domain-event.c b/tools/virsh-domain-event.c
index 6dbb64a655..2d6db5f881 100644
--- a/tools/virsh-domain-event.c
+++ b/tools/virsh-domain-event.c
@@ -93,7 +93,8 @@ VIR_ENUM_IMPL(virshDomainEventResumed,
               N_("Unpaused"),
               N_("Migrated"),
               N_("Snapshot"),
-              N_("Post-copy"));
+              N_("Post-copy"),
+              N_("Post-copy Error"));
 
 VIR_ENUM_DECL(virshDomainEventStopped);
 VIR_ENUM_IMPL(virshDomainEventStopped,
diff --git a/tools/virsh-domain-monitor.c b/tools/virsh-domain-monitor.c
index 246e8a16c0..dc5fe13e49 100644
--- a/tools/virsh-domain-monitor.c
+++ b/tools/virsh-domain-monitor.c
@@ -166,6 +166,7 @@ VIR_ENUM_IMPL(virshDomainRunningReason,
               N_("event wakeup"),
               N_("crashed"),
               N_("post-copy"),
+              N_("post-copy failed"),
 );
 
 VIR_ENUM_DECL(virshDomainBlockedReason);
-- 
2.35.1




[Index of Archives]     [Virt Tools]     [Libvirt Users]     [Lib OS Info]     [Fedora Users]     [Fedora Desktop]     [Fedora SELinux]     [Big List of Linux Books]     [Yosemite News]     [KDE Users]     [Fedora Tools]

  Powered by Linux