| Message ID | 20180514165424.12884-6-zhangckid@gmail.com |
|---|---|
| State | New |
| Headers | show |
| Series | COLO: integrate colo frame with block replication and COLO proxy | expand |
* Zhang Chen (zhangckid@gmail.com) wrote: > 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. Stefan: This looks mostly OK to me, how does it look from the block side? The only thing I'd like to be convinced of is that the replication_do_checkpoint_all() is synchronous enough to know that the destination has received all disk IO for one checkpoint before the primary starts running the next one. Also, in the 'colo_do_checkpoint_transaction' the replication is called near the start; is that the right point or should it be after any of the device saves (could they spit out one last write?) Dave > Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com> > Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com> > Signed-off-by: Zhang Chen <zhangckid@gmail.com> > --- > 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 bca187275a..ddd0c4b988 100644 > --- a/migration/migration.c > +++ b/migration/migration.c > @@ -357,6 +357,7 @@ 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(); > @@ -388,6 +389,14 @@ 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); > -- > 2.17.0 > -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
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 bca187275a..ddd0c4b988 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -357,6 +357,7 @@ 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(); @@ -388,6 +389,14 @@ 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);