summaryrefslogtreecommitdiffstats
path: root/migration
diff options
context:
space:
mode:
authorPeter Xu2022-07-07 20:55:09 +0200
committerDr. David Alan Gilbert2022-07-20 13:15:08 +0200
commitd0edb8a173b54cae4571c9040c88cf0c5a1c6e12 (patch)
tree70b58da0cff5c250872f3e336d6bec18a9be45cf /migration
parentmigration: Postcopy recover with preempt enabled (diff)
downloadqemu-d0edb8a173b54cae4571c9040c88cf0c5a1c6e12.tar.gz
qemu-d0edb8a173b54cae4571c9040c88cf0c5a1c6e12.tar.xz
qemu-d0edb8a173b54cae4571c9040c88cf0c5a1c6e12.zip
migration: Create the postcopy preempt channel asynchronously
This patch allows the postcopy preempt channel to be created asynchronously. The benefit is that when the connection is slow, we won't take the BQL (and potentially block all things like QMP) for a long time without releasing. A function postcopy_preempt_wait_channel() is introduced, allowing the migration thread to be able to wait on the channel creation. The channel is always created by the main thread, in which we'll kick a new semaphore to tell the migration thread that the channel has created. We'll need to wait for the new channel in two places: (1) when there's a new postcopy migration that is starting, or (2) when there's a postcopy migration to resume. For the start of migration, we don't need to wait for this channel until when we want to start postcopy, aka, postcopy_start(). We'll fail the migration if we found that the channel creation failed (which should probably not happen at all in 99% of the cases, because the main channel is using the same network topology). For a postcopy recovery, we'll need to wait in postcopy_pause(). In that case if the channel creation failed, we can't fail the migration or we'll crash the VM, instead we keep in PAUSED state, waiting for yet another recovery. Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Reviewed-by: Manish Mishra <manish.mishra@nutanix.com> Signed-off-by: Peter Xu <peterx@redhat.com> Message-Id: <20220707185509.27311-1-peterx@redhat.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Diffstat (limited to 'migration')
-rw-r--r--migration/migration.c16
-rw-r--r--migration/migration.h7
-rw-r--r--migration/postcopy-ram.c56
-rw-r--r--migration/postcopy-ram.h1
4 files changed, 68 insertions, 12 deletions
diff --git a/migration/migration.c b/migration/migration.c
index 3119bd2e4b..427d4de185 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -3053,6 +3053,12 @@ static int postcopy_start(MigrationState *ms)
int64_t bandwidth = migrate_max_postcopy_bandwidth();
bool restart_block = false;
int cur_state = MIGRATION_STATUS_ACTIVE;
+
+ if (postcopy_preempt_wait_channel(ms)) {
+ migrate_set_state(&ms->state, ms->state, MIGRATION_STATUS_FAILED);
+ return -1;
+ }
+
if (!migrate_pause_before_switchover()) {
migrate_set_state(&ms->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_POSTCOPY_ACTIVE);
@@ -3534,6 +3540,14 @@ static MigThrError postcopy_pause(MigrationState *s)
if (s->state == MIGRATION_STATUS_POSTCOPY_RECOVER) {
/* Woken up by a recover procedure. Give it a shot */
+ if (postcopy_preempt_wait_channel(s)) {
+ /*
+ * Preempt enabled, and new channel create failed; loop
+ * back to wait for another recovery.
+ */
+ continue;
+ }
+
/*
* Firstly, let's wake up the return path now, with a new
* return path channel.
@@ -4398,6 +4412,7 @@ static void migration_instance_finalize(Object *obj)
qemu_sem_destroy(&ms->postcopy_pause_sem);
qemu_sem_destroy(&ms->postcopy_pause_rp_sem);
qemu_sem_destroy(&ms->rp_state.rp_sem);
+ qemu_sem_destroy(&ms->postcopy_qemufile_src_sem);
error_free(ms->error);
}
@@ -4444,6 +4459,7 @@ static void migration_instance_init(Object *obj)
qemu_sem_init(&ms->rp_state.rp_sem, 0);
qemu_sem_init(&ms->rate_limit_sem, 0);
qemu_sem_init(&ms->wait_unplug_sem, 0);
+ qemu_sem_init(&ms->postcopy_qemufile_src_sem, 0);
qemu_mutex_init(&ms->qemu_file_lock);
}
diff --git a/migration/migration.h b/migration/migration.h
index 9220cec6bd..ae4ffd3454 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -219,6 +219,13 @@ struct MigrationState {
QEMUFile *to_dst_file;
/* Postcopy specific transfer channel */
QEMUFile *postcopy_qemufile_src;
+ /*
+ * It is posted when the preempt channel is established. Note: this is
+ * used for both the start or recover of a postcopy migration. We'll
+ * post to this sem every time a new preempt channel is created in the
+ * main thread, and we keep post() and wait() in pair.
+ */
+ QemuSemaphore postcopy_qemufile_src_sem;
QIOChannelBuffer *bioc;
/*
* Protects to_dst_file/from_dst_file pointers. We need to make sure we
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 84f7b1526e..70b21e9d51 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -1552,10 +1552,50 @@ bool postcopy_preempt_new_channel(MigrationIncomingState *mis, QEMUFile *file)
return true;
}
-int postcopy_preempt_setup(MigrationState *s, Error **errp)
+static void
+postcopy_preempt_send_channel_new(QIOTask *task, gpointer opaque)
{
- QIOChannel *ioc;
+ MigrationState *s = opaque;
+ QIOChannel *ioc = QIO_CHANNEL(qio_task_get_source(task));
+ Error *local_err = NULL;
+
+ if (qio_task_propagate_error(task, &local_err)) {
+ /* Something wrong happened.. */
+ migrate_set_error(s, local_err);
+ error_free(local_err);
+ } else {
+ migration_ioc_register_yank(ioc);
+ s->postcopy_qemufile_src = qemu_file_new_output(ioc);
+ trace_postcopy_preempt_new_channel();
+ }
+
+ /*
+ * Kick the waiter in all cases. The waiter should check upon
+ * postcopy_qemufile_src to know whether it failed or not.
+ */
+ qemu_sem_post(&s->postcopy_qemufile_src_sem);
+ object_unref(OBJECT(ioc));
+}
+/* Returns 0 if channel established, -1 for error. */
+int postcopy_preempt_wait_channel(MigrationState *s)
+{
+ /* If preempt not enabled, no need to wait */
+ if (!migrate_postcopy_preempt()) {
+ return 0;
+ }
+
+ /*
+ * We need the postcopy preempt channel to be established before
+ * starting doing anything.
+ */
+ qemu_sem_wait(&s->postcopy_qemufile_src_sem);
+
+ return s->postcopy_qemufile_src ? 0 : -1;
+}
+
+int postcopy_preempt_setup(MigrationState *s, Error **errp)
+{
if (!migrate_postcopy_preempt()) {
return 0;
}
@@ -1566,16 +1606,8 @@ int postcopy_preempt_setup(MigrationState *s, Error **errp)
return -1;
}
- ioc = socket_send_channel_create_sync(errp);
-
- if (ioc == NULL) {
- return -1;
- }
-
- migration_ioc_register_yank(ioc);
- s->postcopy_qemufile_src = qemu_file_new_output(ioc);
-
- trace_postcopy_preempt_new_channel();
+ /* Kick an async task to connect */
+ socket_send_channel_create(postcopy_preempt_send_channel_new, s);
return 0;
}
diff --git a/migration/postcopy-ram.h b/migration/postcopy-ram.h
index 34b1080cde..6147bf7d1d 100644
--- a/migration/postcopy-ram.h
+++ b/migration/postcopy-ram.h
@@ -192,5 +192,6 @@ enum PostcopyChannels {
bool postcopy_preempt_new_channel(MigrationIncomingState *mis, QEMUFile *file);
int postcopy_preempt_setup(MigrationState *s, Error **errp);
+int postcopy_preempt_wait_channel(MigrationState *s);
#endif