From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:44979) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1euE8O-0003s8-KP for qemu-devel@nongnu.org; Fri, 09 Mar 2018 04:16:17 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1euE8J-0005yH-EK for qemu-devel@nongnu.org; Fri, 09 Mar 2018 04:16:16 -0500 Received: from mx3-rdu2.redhat.com ([66.187.233.73]:45400 helo=mx1.redhat.com) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1euE8J-0005y3-8Y for qemu-devel@nongnu.org; Fri, 09 Mar 2018 04:16:11 -0500 From: Peter Xu Date: Fri, 9 Mar 2018 17:15:21 +0800 Message-Id: <20180309091535.13315-10-peterx@redhat.com> In-Reply-To: <20180309091535.13315-1-peterx@redhat.com> References: <20180309091535.13315-1-peterx@redhat.com> Subject: [Qemu-devel] [PATCH v7 09/23] migration: new state "postcopy-recover" List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: Andrea Arcangeli , "Daniel P . Berrange" , Juan Quintela , Alexey Perevalov , "Dr . David Alan Gilbert" , peterx@redhat.com Introducing new migration state "postcopy-recover". If a migration procedure is paused and the connection is rebuilt afterward successfully, we'll switch the source VM state from "postcopy-paused" to the new state "postcopy-recover", then we'll do the resume logic in the migration thread (along with the return path thread). This patch only do the state switch on source side. Another following up patch will handle the state switching on destination side using the same status bit. Reviewed-by: Dr. David Alan Gilbert Signed-off-by: Peter Xu --- migration/migration.c | 76 ++++++++++++++++++++++++++++++++++++++------------- qapi/migration.json | 4 ++- 2 files changed, 60 insertions(+), 20 deletions(-) diff --git a/migration/migration.c b/migration/migration.c index 0b31468552..322d5ad79b 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -561,6 +561,7 @@ static bool migration_is_setup_or_active(int state) case MIGRATION_STATUS_ACTIVE: case MIGRATION_STATUS_POSTCOPY_ACTIVE: case MIGRATION_STATUS_POSTCOPY_PAUSED: + case MIGRATION_STATUS_POSTCOPY_RECOVER: case MIGRATION_STATUS_SETUP: case MIGRATION_STATUS_PRE_SWITCHOVER: case MIGRATION_STATUS_DEVICE: @@ -641,6 +642,7 @@ MigrationInfo *qmp_query_migrate(Error **errp) case MIGRATION_STATUS_PRE_SWITCHOVER: case MIGRATION_STATUS_DEVICE: case MIGRATION_STATUS_POSTCOPY_PAUSED: + case MIGRATION_STATUS_POSTCOPY_RECOVER: /* TODO add some postcopy stats */ info->has_status = true; info->has_total_time = true; @@ -2247,6 +2249,13 @@ typedef enum MigThrError { MIG_THR_ERR_FATAL = 2, } MigThrError; +/* Return zero if success, or <0 for error */ +static int postcopy_do_resume(MigrationState *s) +{ + /* TODO: do the resume logic */ + return 0; +} + /* * We don't return until we are in a safe state to continue current * postcopy migration. Returns MIG_THR_ERR_RECOVERED if recovered, or @@ -2255,29 +2264,55 @@ typedef enum MigThrError { 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; + while (true) { + migrate_set_state(&s->state, s->state, + MIGRATION_STATUS_POSTCOPY_PAUSED); - error_report("Detected IO failure for postcopy. " - "Migration 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; - /* - * 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); - } + error_report("Detected IO failure for postcopy. " + "Migration paused."); - trace_postcopy_pause_continued(); + /* + * 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); + } + + if (s->state == MIGRATION_STATUS_POSTCOPY_RECOVER) { + /* Woken up by a recover procedure. Give it a shot */ - return MIG_THR_ERR_RECOVERED; + /* + * Firstly, let's wake up the return path now, with a new + * return path channel. + */ + qemu_sem_post(&s->postcopy_pause_rp_sem); + + /* Do the resume logic */ + if (postcopy_do_resume(s) == 0) { + /* Let's continue! */ + trace_postcopy_pause_continued(); + return MIG_THR_ERR_RECOVERED; + } else { + /* + * Something wrong happened during the recovery, let's + * pause again. Pause is always better than throwing + * data away. + */ + continue; + } + } else { + /* This is not right... Time to quit. */ + return MIG_THR_ERR_FATAL; + } + } } static MigThrError migration_detect_error(MigrationState *s) @@ -2597,7 +2632,10 @@ void migrate_fd_connect(MigrationState *s, Error *error_in) } if (resume) { - /* TODO: do the resume logic */ + /* Wakeup the main migration thread to do the recovery */ + migrate_set_state(&s->state, MIGRATION_STATUS_POSTCOPY_PAUSED, + MIGRATION_STATUS_POSTCOPY_RECOVER); + qemu_sem_post(&s->postcopy_pause_sem); return; } diff --git a/qapi/migration.json b/qapi/migration.json index 11e0736f67..152fb8e51e 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -91,6 +91,8 @@ # # @postcopy-paused: during postcopy but paused. (since 2.12) # +# @postcopy-recover: trying to recover from a paused postcopy. (since 2.11) +# # @completed: migration is finished. # # @failed: some error occurred during migration process. @@ -109,7 +111,7 @@ { 'enum': 'MigrationStatus', 'data': [ 'none', 'setup', 'cancelling', 'cancelled', 'active', 'postcopy-active', 'postcopy-paused', - 'completed', 'failed', 'colo', + 'postcopy-recover', 'completed', 'failed', 'colo', 'pre-switchover', 'device' ] } ## -- 2.14.3