From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57787) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fPLDk-0008HR-TG for qemu-devel@nongnu.org; Sun, 03 Jun 2018 01:06:26 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fPLDj-0000kI-KO for qemu-devel@nongnu.org; Sun, 03 Jun 2018 01:06:24 -0400 Received: from mail-pf0-x242.google.com ([2607:f8b0:400e:c00::242]:38897) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1fPLDj-0000k8-Cw for qemu-devel@nongnu.org; Sun, 03 Jun 2018 01:06:23 -0400 Received: by mail-pf0-x242.google.com with SMTP id b74-v6so10906796pfl.5 for ; Sat, 02 Jun 2018 22:06:23 -0700 (PDT) From: Zhang Chen Date: Sun, 3 Jun 2018 13:05:34 +0800 Message-Id: <20180603050546.6827-6-zhangckid@gmail.com> In-Reply-To: <20180603050546.6827-1-zhangckid@gmail.com> References: <20180603050546.6827-1-zhangckid@gmail.com> Subject: [Qemu-devel] [PATCH V8 05/17] COLO: Add block replication into colo process List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org, Paolo Bonzini , Juan Quintela , "Dr . David Alan Gilbert" , Jason Wang , Eric Blake , Markus Armbruster Cc: Zhang Chen , zhanghailiang , Li Zhijian Make sure master start block replication after slave's block replication started. Besides, we need to activate VM's blocks before goes into COLO state. Signed-off-by: zhanghailiang Signed-off-by: Li Zhijian Signed-off-by: Zhang Chen --- migration/colo.c | 43 +++++++++++++++++++++++++++++++++++++++++++ migration/migration.c | 9 +++++++++ 2 files changed, 52 insertions(+) diff --git a/migration/colo.c b/migration/colo.c index 081df1835f..e06640c3d6 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -27,6 +27,7 @@ #include "replication.h" #include "net/colo-compare.h" #include "net/colo.h" +#include "block/block.h" static bool vmstate_loading; static Notifier packets_compare_notifier; @@ -56,6 +57,7 @@ static void secondary_vm_do_failover(void) { int old_state; MigrationIncomingState *mis = migration_incoming_get_current(); + Error *local_err = NULL; /* Can not do failover during the process of VM's loading VMstate, Or * it will break the secondary VM. @@ -73,6 +75,11 @@ static void secondary_vm_do_failover(void) migrate_set_state(&mis->state, MIGRATION_STATUS_COLO, MIGRATION_STATUS_COMPLETED); + replication_stop_all(true, &local_err); + if (local_err) { + error_report_err(local_err); + } + if (!autostart) { error_report("\"-S\" qemu option will be ignored in secondary side"); /* recover runstate to normal migration finish state */ @@ -110,6 +117,7 @@ static void primary_vm_do_failover(void) { MigrationState *s = migrate_get_current(); int old_state; + Error *local_err = NULL; migrate_set_state(&s->state, MIGRATION_STATUS_COLO, MIGRATION_STATUS_COMPLETED); @@ -133,6 +141,13 @@ static void primary_vm_do_failover(void) FailoverStatus_str(old_state)); return; } + + replication_stop_all(true, &local_err); + if (local_err) { + error_report_err(local_err); + local_err = NULL; + } + /* Notify COLO thread that failover work is finished */ qemu_sem_post(&s->colo_exit_sem); } @@ -356,6 +371,11 @@ static int colo_do_checkpoint_transaction(MigrationState *s, qemu_savevm_state_header(fb); qemu_savevm_state_setup(fb); qemu_mutex_lock_iothread(); + replication_do_checkpoint_all(&local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } qemu_savevm_state_complete_precopy(fb, false, false); qemu_mutex_unlock_iothread(); @@ -446,6 +466,12 @@ static void colo_process_checkpoint(MigrationState *s) object_unref(OBJECT(bioc)); qemu_mutex_lock_iothread(); + replication_start_all(REPLICATION_MODE_PRIMARY, &local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + vm_start(); qemu_mutex_unlock_iothread(); trace_colo_vm_state_change("stop", "run"); @@ -585,6 +611,11 @@ void *colo_process_incoming_thread(void *opaque) object_unref(OBJECT(bioc)); qemu_mutex_lock_iothread(); + replication_start_all(REPLICATION_MODE_SECONDARY, &local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } vm_start(); trace_colo_vm_state_change("stop", "run"); qemu_mutex_unlock_iothread(); @@ -665,6 +696,18 @@ void *colo_process_incoming_thread(void *opaque) goto out; } + replication_get_error_all(&local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + /* discard colo disk buffer */ + replication_do_checkpoint_all(&local_err); + if (local_err) { + qemu_mutex_unlock_iothread(); + goto out; + } + vmstate_loading = false; vm_start(); trace_colo_vm_state_change("stop", "run"); diff --git a/migration/migration.c b/migration/migration.c index 59aab11f4a..0dfdeecf0f 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -360,6 +360,7 @@ static void process_incoming_migration_co(void *opaque) MigrationIncomingState *mis = migration_incoming_get_current(); PostcopyState ps; int ret; + Error *local_err = NULL; assert(mis->from_src_file); mis->largest_page_size = qemu_ram_pagesize_largest(); @@ -391,6 +392,14 @@ static void process_incoming_migration_co(void *opaque) /* we get COLO info, and know if we are in COLO mode */ if (!ret && migration_incoming_enable_colo()) { + /* Make sure all file formats flush their mutable metadata */ + bdrv_invalidate_cache_all(&local_err); + if (local_err) { + migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, + MIGRATION_STATUS_FAILED); + error_report_err(local_err); + exit(EXIT_FAILURE); + } mis->migration_incoming_co = qemu_coroutine_self(); qemu_thread_create(&mis->colo_incoming_thread, "COLO incoming", colo_process_incoming_thread, mis, QEMU_THREAD_JOINABLE); -- 2.17.GIT