[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [RFC v2 09/33] migration: implement "postcopy-pause" src lo
From: |
Peter Xu |
Subject: |
[Qemu-devel] [RFC v2 09/33] migration: implement "postcopy-pause" src logic |
Date: |
Wed, 30 Aug 2017 16:32:06 +0800 |
Now when network down for postcopy, the source side will not fail the
migration. Instead we convert the status into this new paused state, and
we will try to wait for a rescue in the future.
If a recovery is detected, migration_thread() will reset its local
variables to prepare for that.
Signed-off-by: Peter Xu <address@hidden>
---
migration/migration.c | 98 +++++++++++++++++++++++++++++++++++++++++++++++---
migration/migration.h | 3 ++
migration/trace-events | 1 +
3 files changed, 98 insertions(+), 4 deletions(-)
diff --git a/migration/migration.c b/migration/migration.c
index f6130db..8d26ea8 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -993,6 +993,8 @@ static void migrate_fd_cleanup(void *opaque)
notifier_list_notify(&migration_state_notifiers, s);
block_cleanup_parameters(s);
+
+ qemu_sem_destroy(&s->postcopy_pause_sem);
}
void migrate_fd_error(MigrationState *s, const Error *error)
@@ -1136,6 +1138,7 @@ MigrationState *migrate_init(void)
s->migration_thread_running = false;
error_free(s->error);
s->error = NULL;
+ qemu_sem_init(&s->postcopy_pause_sem, 0);
migrate_set_state(&s->state, MIGRATION_STATUS_NONE,
MIGRATION_STATUS_SETUP);
@@ -1938,6 +1941,80 @@ bool migrate_colo_enabled(void)
return s->enabled_capabilities[MIGRATION_CAPABILITY_X_COLO];
}
+typedef enum MigThrError {
+ /* No error detected */
+ MIG_THR_ERR_NONE = 0,
+ /* Detected error, but resumed successfully */
+ MIG_THR_ERR_RECOVERED = 1,
+ /* Detected fatal error, need to exit */
+ MIG_THR_ERR_FATAL = 2,
+} MigThrError;
+
+/*
+ * We don't return until we are in a safe state to continue current
+ * postcopy migration. Returns MIG_THR_ERR_RECOVERED if recovered, or
+ * MIG_THR_ERR_FATAL if unrecovery failure happened.
+ */
+static MigThrError postcopy_pause(MigrationState *s)
+{
+ assert(s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE);
+ migrate_set_state(&s->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
+ MIGRATION_STATUS_POSTCOPY_PAUSED);
+
+ /* Current channel is possibly broken. Release it. */
+ assert(s->to_dst_file);
+ qemu_file_shutdown(s->to_dst_file);
+ qemu_fclose(s->to_dst_file);
+ s->to_dst_file = NULL;
+
+ error_report("Detected IO failure for postcopy. "
+ "Migration paused.");
+
+ /*
+ * We wait until things fixed up. Then someone will setup the
+ * status back for us.
+ */
+ while (s->state == MIGRATION_STATUS_POSTCOPY_PAUSED) {
+ qemu_sem_wait(&s->postcopy_pause_sem);
+ }
+
+ trace_postcopy_pause_continued();
+
+ return MIG_THR_ERR_RECOVERED;
+}
+
+static MigThrError migration_detect_error(MigrationState *s)
+{
+ int ret;
+
+ /* Try to detect any file errors */
+ ret = qemu_file_get_error(s->to_dst_file);
+
+ if (!ret) {
+ /* Everything is fine */
+ return MIG_THR_ERR_NONE;
+ }
+
+ if (s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE && ret == -EIO) {
+ /*
+ * For postcopy, we allow the network to be down for a
+ * while. After that, it can be continued by a
+ * recovery phase.
+ */
+ return postcopy_pause(s);
+ } else {
+ /*
+ * For precopy (or postcopy with error outside IO), we fail
+ * with no time.
+ */
+ migrate_set_state(&s->state, s->state, MIGRATION_STATUS_FAILED);
+ trace_migration_thread_file_err();
+
+ /* Time to stop the migration, now. */
+ return MIG_THR_ERR_FATAL;
+ }
+}
+
/*
* Master migration thread on the source VM.
* It drives the migration and pumps the data down the outgoing channel.
@@ -1962,6 +2039,7 @@ static void *migration_thread(void *opaque)
/* The active state we expect to be in; ACTIVE or POSTCOPY_ACTIVE */
enum MigrationStatus current_active_state = MIGRATION_STATUS_ACTIVE;
bool enable_colo = migrate_colo_enabled();
+ MigThrError thr_error;
rcu_register_thread();
@@ -2034,12 +2112,24 @@ static void *migration_thread(void *opaque)
}
}
- if (qemu_file_get_error(s->to_dst_file)) {
- migrate_set_state(&s->state, current_active_state,
- MIGRATION_STATUS_FAILED);
- trace_migration_thread_file_err();
+ /*
+ * Try to detect any kind of failures, and see whether we
+ * should stop the migration now.
+ */
+ thr_error = migration_detect_error(s);
+ if (thr_error == MIG_THR_ERR_FATAL) {
+ /* Stop migration */
break;
+ } else if (thr_error == MIG_THR_ERR_RECOVERED) {
+ /*
+ * Just recovered from a e.g. network failure, reset all
+ * the local variables. This is important to avoid
+ * breaking transferred_bytes and bandwidth calculation
+ */
+ initial_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+ initial_bytes = 0;
}
+
current_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
if (current_time >= initial_time + BUFFER_DELAY) {
uint64_t transferred_bytes = qemu_ftell(s->to_dst_file) -
diff --git a/migration/migration.h b/migration/migration.h
index 70e3094..0c957c9 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -149,6 +149,9 @@ struct MigrationState
bool send_configuration;
/* Whether we send section footer during migration */
bool send_section_footer;
+
+ /* Needed by postcopy-pause state */
+ QemuSemaphore postcopy_pause_sem;
};
void migrate_set_state(int *state, int old_state, int new_state);
diff --git a/migration/trace-events b/migration/trace-events
index d2910a6..907564b 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -98,6 +98,7 @@ migration_thread_setup_complete(void) ""
open_return_path_on_source(void) ""
open_return_path_on_source_continue(void) ""
postcopy_start(void) ""
+postcopy_pause_continued(void) ""
postcopy_start_set_run(void) ""
source_return_path_thread_bad_end(void) ""
source_return_path_thread_end(void) ""
--
2.7.4
- [Qemu-devel] [RFC v2 00/33] Migration: postcopy failure recovery, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 01/33] bitmap: remove BITOP_WORD(), Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 02/33] bitmap: introduce bitmap_count_one(), Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 03/33] bitmap: provide to_le/from_le helpers, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 04/33] migration: dump str in migrate_set_state trace, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 05/33] migration: better error handling with QEMUFile, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 06/33] migration: reuse mis->userfault_quit_fd, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 07/33] migration: provide postcopy_fault_thread_notify(), Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 09/33] migration: implement "postcopy-pause" src logic,
Peter Xu <=
- [Qemu-devel] [RFC v2 08/33] migration: new postcopy-pause state, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 10/33] migration: allow dst vm pause on postcopy, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 11/33] migration: allow src return path to pause, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 12/33] migration: allow send_rq to fail, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 13/33] migration: allow fault thread to pause, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 14/33] qmp: hmp: add migrate "resume" option, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 15/33] migration: pass MigrationState to migrate_init(), Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 16/33] migration: rebuild channel on source, Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 17/33] migration: new state "postcopy-recover", Peter Xu, 2017/08/30
- [Qemu-devel] [RFC v2 18/33] migration: wakeup dst ram-load-thread for recover, Peter Xu, 2017/08/30