From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:46942) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1db0J4-0000wR-9Y for qemu-devel@nongnu.org; Fri, 28 Jul 2017 04:07:35 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1db0J3-0001ET-GU for qemu-devel@nongnu.org; Fri, 28 Jul 2017 04:07:34 -0400 Received: from mx1.redhat.com ([209.132.183.28]:34514) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1db0J3-0001Ds-8P for qemu-devel@nongnu.org; Fri, 28 Jul 2017 04:07:33 -0400 From: Peter Xu Date: Fri, 28 Jul 2017 16:06:21 +0800 Message-Id: <1501229198-30588-13-git-send-email-peterx@redhat.com> In-Reply-To: <1501229198-30588-1-git-send-email-peterx@redhat.com> References: <1501229198-30588-1-git-send-email-peterx@redhat.com> Subject: [Qemu-devel] [RFC 12/29] migration: allow dst vm pause on postcopy List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: Laurent Vivier , Alexey Perevalov , Juan Quintela , Andrea Arcangeli , "Dr . David Alan Gilbert" , peterx@redhat.com 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 --- 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