When there is IO error on the incoming channel (e.g., network down),
instead of bailing out immediately, we allow the dst vm to switch to the
new POSTCOPY_PAUSE state. Currently it is still simple - it waits the
new semaphore, until someone poke it for another attempt.
Signed-off-by: Peter Xu <pet...@redhat.com>
---
migration/migration.c | 1 +
migration/migration.h | 3 +++
migration/savevm.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
migration/trace-events | 2 ++
4 files changed, 51 insertions(+)
diff --git a/migration/migration.c b/migration/migration.c
index 0bc70c8..c729c5a 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -146,6 +146,7 @@ MigrationIncomingState *migration_incoming_get_current(void)
memset(&mis_current, 0, sizeof(MigrationIncomingState));
qemu_mutex_init(&mis_current.rp_mutex);
qemu_event_init(&mis_current.main_thread_load_event, false);
+ qemu_sem_init(&mis_current.postcopy_pause_sem_dst, 0);
once = true;
}
return &mis_current;
diff --git a/migration/migration.h b/migration/migration.h
index 24cdaf6..08b90e8 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -60,6 +60,9 @@ struct MigrationIncomingState {
/* The coroutine we should enter (back) after failover */
Coroutine *migration_incoming_co;
QemuSemaphore colo_incoming_sem;
+
+ /* notify PAUSED postcopy incoming migrations to try to continue */
+ QemuSemaphore postcopy_pause_sem_dst;
};
MigrationIncomingState *migration_incoming_get_current(void);
diff --git a/migration/savevm.c b/migration/savevm.c
index 13ae9d6..1f62268 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -1954,11 +1954,41 @@ void qemu_loadvm_state_cleanup(void)
}
}
+/* Return true if we should continue the migration, or false. */
+static bool postcopy_pause_incoming(MigrationIncomingState *mis)
+{
+ trace_postcopy_pause_incoming();
+
+ migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
+ MIGRATION_STATUS_POSTCOPY_PAUSED);
+
+ assert(mis->from_src_file);
+ qemu_file_shutdown(mis->from_src_file);
+ qemu_fclose(mis->from_src_file);
+ mis->from_src_file = NULL;
+
+ assert(mis->to_src_file);
+ qemu_mutex_lock(&mis->rp_mutex);
+ qemu_file_shutdown(mis->to_src_file);
+ qemu_fclose(mis->to_src_file);
+ mis->to_src_file = NULL;
+ qemu_mutex_unlock(&mis->rp_mutex);
+
+ while (mis->state == MIGRATION_STATUS_POSTCOPY_PAUSED) {
+ qemu_sem_wait(&mis->postcopy_pause_sem_dst);
+ }
+
+ trace_postcopy_pause_incoming_continued();
+
+ return true;
+}
+
static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis)
{
uint8_t section_type;
int ret = 0;
+retry:
while (true) {
section_type = qemu_get_byte(f);
@@ -2004,6 +2034,21 @@ static int qemu_loadvm_state_main(QEMUFile *f,
MigrationIncomingState *mis)
out:
if (ret < 0) {
qemu_file_set_error(f, ret);
+
+ /*
+ * Detect whether it is:
+ *
+ * 1. postcopy running
+ * 2. network failure (-EIO)
+ *
+ * If so, we try to wait for a recovery.
+ */
+ if (mis->state == MIGRATION_STATUS_POSTCOPY_ACTIVE &&
+ ret == -EIO && postcopy_pause_incoming(mis)) {
+ /* Reset f to point to the newly created channel */
+ f = mis->from_src_file;
+ goto retry;
+ }
}
return ret;
}
diff --git a/migration/trace-events b/migration/trace-events
index 2211acc..22a629e 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -99,6 +99,8 @@ open_return_path_on_source(void) ""
open_return_path_on_source_continue(void) ""
postcopy_start(void) ""
postcopy_pause_continued(void) ""
+postcopy_pause_incoming(void) ""
+postcopy_pause_incoming_continued(void) ""
postcopy_start_set_run(void) ""
source_return_path_thread_bad_end(void) ""
source_return_path_thread_end(void) ""
--
2.7.4
