diff options
Diffstat (limited to 'migration')
| -rw-r--r-- | migration/block-dirty-bitmap.c | 130 | ||||
| -rw-r--r-- | migration/colo.c | 39 | ||||
| -rw-r--r-- | migration/migration.c | 4 | ||||
| -rw-r--r-- | migration/migration.h | 4 | ||||
| -rw-r--r-- | migration/ram.c | 5 | ||||
| -rw-r--r-- | migration/ram.h | 1 | ||||
| -rw-r--r-- | migration/rdma.c | 12 |
7 files changed, 137 insertions, 58 deletions
diff --git a/migration/block-dirty-bitmap.c b/migration/block-dirty-bitmap.c index 7eafface61..47bc0f650c 100644 --- a/migration/block-dirty-bitmap.c +++ b/migration/block-dirty-bitmap.c @@ -268,57 +268,118 @@ static void dirty_bitmap_mig_cleanup(void) } /* Called with iothread lock taken. */ -static int init_dirty_bitmap_migration(void) +static int add_bitmaps_to_list(BlockDriverState *bs, const char *bs_name) { - BlockDriverState *bs; BdrvDirtyBitmap *bitmap; DirtyBitmapMigBitmapState *dbms; Error *local_err = NULL; + bitmap = bdrv_dirty_bitmap_first(bs); + if (!bitmap) { + return 0; + } + + if (!bs_name || strcmp(bs_name, "") == 0) { + error_report("Bitmap '%s' in unnamed node can't be migrated", + bdrv_dirty_bitmap_name(bitmap)); + return -1; + } + + if (bs_name[0] == '#') { + error_report("Bitmap '%s' in a node with auto-generated " + "name '%s' can't be migrated", + bdrv_dirty_bitmap_name(bitmap), bs_name); + return -1; + } + + FOR_EACH_DIRTY_BITMAP(bs, bitmap) { + if (!bdrv_dirty_bitmap_name(bitmap)) { + continue; + } + + if (bdrv_dirty_bitmap_check(bitmap, BDRV_BITMAP_DEFAULT, &local_err)) { + error_report_err(local_err); + return -1; + } + + bdrv_ref(bs); + bdrv_dirty_bitmap_set_busy(bitmap, true); + + dbms = g_new0(DirtyBitmapMigBitmapState, 1); + dbms->bs = bs; + dbms->node_name = bs_name; + dbms->bitmap = bitmap; + dbms->total_sectors = bdrv_nb_sectors(bs); + dbms->sectors_per_chunk = CHUNK_SIZE * 8 * + bdrv_dirty_bitmap_granularity(bitmap) >> BDRV_SECTOR_BITS; + if (bdrv_dirty_bitmap_enabled(bitmap)) { + dbms->flags |= DIRTY_BITMAP_MIG_START_FLAG_ENABLED; + } + if (bdrv_dirty_bitmap_get_persistence(bitmap)) { + dbms->flags |= DIRTY_BITMAP_MIG_START_FLAG_PERSISTENT; + } + + QSIMPLEQ_INSERT_TAIL(&dirty_bitmap_mig_state.dbms_list, + dbms, entry); + } + + return 0; +} + +/* Called with iothread lock taken. */ +static int init_dirty_bitmap_migration(void) +{ + BlockDriverState *bs; + DirtyBitmapMigBitmapState *dbms; + GHashTable *handled_by_blk = g_hash_table_new(NULL, NULL); + BlockBackend *blk; + dirty_bitmap_mig_state.bulk_completed = false; dirty_bitmap_mig_state.prev_bs = NULL; dirty_bitmap_mig_state.prev_bitmap = NULL; dirty_bitmap_mig_state.no_bitmaps = false; - for (bs = bdrv_next_all_states(NULL); bs; bs = bdrv_next_all_states(bs)) { - const char *name = bdrv_get_device_or_node_name(bs); + /* + * Use blockdevice name for direct (or filtered) children of named block + * backends. + */ + for (blk = blk_next(NULL); blk; blk = blk_next(blk)) { + const char *name = blk_name(blk); - FOR_EACH_DIRTY_BITMAP(bs, bitmap) { - if (!bdrv_dirty_bitmap_name(bitmap)) { - continue; - } + if (!name || strcmp(name, "") == 0) { + continue; + } - if (!name || strcmp(name, "") == 0) { - error_report("Found bitmap '%s' in unnamed node %p. It can't " - "be migrated", bdrv_dirty_bitmap_name(bitmap), bs); - goto fail; + bs = blk_bs(blk); + + /* Skip filters without bitmaps */ + while (bs && bs->drv && bs->drv->is_filter && + !bdrv_has_named_bitmaps(bs)) + { + if (bs->backing) { + bs = bs->backing->bs; + } else if (bs->file) { + bs = bs->file->bs; + } else { + bs = NULL; } + } - if (bdrv_dirty_bitmap_check(bitmap, BDRV_BITMAP_DEFAULT, - &local_err)) { - error_report_err(local_err); + if (bs && bs->drv && !bs->drv->is_filter) { + if (add_bitmaps_to_list(bs, name)) { goto fail; } + g_hash_table_add(handled_by_blk, bs); + } + } - bdrv_ref(bs); - bdrv_dirty_bitmap_set_busy(bitmap, true); - - dbms = g_new0(DirtyBitmapMigBitmapState, 1); - dbms->bs = bs; - dbms->node_name = name; - dbms->bitmap = bitmap; - dbms->total_sectors = bdrv_nb_sectors(bs); - dbms->sectors_per_chunk = CHUNK_SIZE * 8 * - bdrv_dirty_bitmap_granularity(bitmap) >> BDRV_SECTOR_BITS; - if (bdrv_dirty_bitmap_enabled(bitmap)) { - dbms->flags |= DIRTY_BITMAP_MIG_START_FLAG_ENABLED; - } - if (bdrv_dirty_bitmap_get_persistence(bitmap)) { - dbms->flags |= DIRTY_BITMAP_MIG_START_FLAG_PERSISTENT; - } + for (bs = bdrv_next_all_states(NULL); bs; bs = bdrv_next_all_states(bs)) { + if (g_hash_table_contains(handled_by_blk, bs)) { + continue; + } - QSIMPLEQ_INSERT_TAIL(&dirty_bitmap_mig_state.dbms_list, - dbms, entry); + if (add_bitmaps_to_list(bs, bdrv_get_node_name(bs))) { + goto fail; } } @@ -331,9 +392,12 @@ static int init_dirty_bitmap_migration(void) dirty_bitmap_mig_state.no_bitmaps = true; } + g_hash_table_destroy(handled_by_blk); + return 0; fail: + g_hash_table_destroy(handled_by_blk); dirty_bitmap_mig_cleanup(); return -1; diff --git a/migration/colo.c b/migration/colo.c index d015d4f84e..ea7d1e9d4e 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -436,11 +436,6 @@ static int colo_do_checkpoint_transaction(MigrationState *s, goto out; } - colo_notify_compares_event(NULL, COLO_EVENT_CHECKPOINT, &local_err); - if (local_err) { - goto out; - } - /* Disable block migration */ migrate_set_block_enabled(false, &local_err); if (local_err) { @@ -502,6 +497,12 @@ static int colo_do_checkpoint_transaction(MigrationState *s, goto out; } + qemu_event_reset(&s->colo_checkpoint_event); + colo_notify_compares_event(NULL, COLO_EVENT_CHECKPOINT, &local_err); + if (local_err) { + goto out; + } + colo_receive_check_message(s->rp_state.from_dst_file, COLO_MESSAGE_VMSTATE_LOADED, &local_err); if (local_err) { @@ -589,7 +590,7 @@ static void colo_process_checkpoint(MigrationState *s) goto out; } - qemu_sem_wait(&s->colo_checkpoint_sem); + qemu_event_wait(&s->colo_checkpoint_event); if (s->state != MIGRATION_STATUS_COLO) { goto out; @@ -637,7 +638,7 @@ out: colo_compare_unregister_notifier(&packets_compare_notifier); timer_del(s->colo_delay_timer); timer_free(s->colo_delay_timer); - qemu_sem_destroy(&s->colo_checkpoint_sem); + qemu_event_destroy(&s->colo_checkpoint_event); /* * Must be called after failover BH is completed, @@ -654,7 +655,7 @@ void colo_checkpoint_notify(void *opaque) MigrationState *s = opaque; int64_t next_notify_time; - qemu_sem_post(&s->colo_checkpoint_sem); + qemu_event_set(&s->colo_checkpoint_event); s->colo_checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST); next_notify_time = s->colo_checkpoint_time + s->parameters.x_checkpoint_delay; @@ -664,7 +665,7 @@ void colo_checkpoint_notify(void *opaque) void migrate_start_colo_process(MigrationState *s) { qemu_mutex_unlock_iothread(); - qemu_sem_init(&s->colo_checkpoint_sem, 0); + qemu_event_init(&s->colo_checkpoint_event, false); s->colo_delay_timer = timer_new_ms(QEMU_CLOCK_HOST, colo_checkpoint_notify, s); @@ -704,7 +705,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis, } qemu_mutex_lock_iothread(); - cpu_synchronize_all_pre_loadvm(); + cpu_synchronize_all_states(); ret = qemu_loadvm_state_main(mis->from_src_file, mis); qemu_mutex_unlock_iothread(); @@ -747,9 +748,11 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis, qemu_mutex_lock_iothread(); vmstate_loading = true; + colo_flush_ram_cache(); ret = qemu_load_device_state(fb); if (ret < 0) { error_setg(errp, "COLO: load device state failed"); + vmstate_loading = false; qemu_mutex_unlock_iothread(); return; } @@ -758,6 +761,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis, replication_get_error_all(&local_err); if (local_err) { error_propagate(errp, local_err); + vmstate_loading = false; qemu_mutex_unlock_iothread(); return; } @@ -766,6 +770,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis, replication_do_checkpoint_all(&local_err); if (local_err) { error_propagate(errp, local_err); + vmstate_loading = false; qemu_mutex_unlock_iothread(); return; } @@ -777,6 +782,7 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis, if (local_err) { error_propagate(errp, local_err); + vmstate_loading = false; qemu_mutex_unlock_iothread(); return; } @@ -787,9 +793,6 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis, qemu_mutex_unlock_iothread(); if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) { - failover_set_state(FAILOVER_STATUS_RELAUNCH, - FAILOVER_STATUS_NONE); - failover_request_active(NULL); return; } @@ -888,6 +891,14 @@ void *colo_process_incoming_thread(void *opaque) error_report_err(local_err); break; } + + if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) { + failover_set_state(FAILOVER_STATUS_RELAUNCH, + FAILOVER_STATUS_NONE); + failover_request_active(NULL); + break; + } + if (failover_get_state() != FAILOVER_STATUS_NONE) { error_report("failover request"); break; @@ -895,8 +906,6 @@ void *colo_process_incoming_thread(void *opaque) } out: - vmstate_loading = false; - /* * There are only two reasons we can get here, some error happened * or the user triggered failover. diff --git a/migration/migration.c b/migration/migration.c index 0bb042a0f7..b63ad91d34 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -3361,6 +3361,10 @@ bool migration_rate_limit(void) bool urgent = false; migration_update_counters(s, now); if (qemu_file_rate_limit(s->to_dst_file)) { + + if (qemu_file_get_error(s->to_dst_file)) { + return false; + } /* * Wait for a delay to do rate limiting OR * something urgent to post the semaphore. diff --git a/migration/migration.h b/migration/migration.h index 507284e563..f617960522 100644 --- a/migration/migration.h +++ b/migration/migration.h @@ -215,8 +215,8 @@ struct MigrationState /* The semaphore is used to notify COLO thread that failover is finished */ QemuSemaphore colo_exit_sem; - /* The semaphore is used to notify COLO thread to do checkpoint */ - QemuSemaphore colo_checkpoint_sem; + /* The event is used to notify COLO thread to do checkpoint */ + QemuEvent colo_checkpoint_event; int64_t colo_checkpoint_time; QEMUTimer *colo_delay_timer; diff --git a/migration/ram.c b/migration/ram.c index 859f835f1a..41cc530d9d 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -3360,7 +3360,7 @@ static bool postcopy_is_running(void) * Flush content of RAM cache into SVM's memory. * Only flush the pages that be dirtied by PVM or SVM or both. */ -static void colo_flush_ram_cache(void) +void colo_flush_ram_cache(void) { RAMBlock *block = NULL; void *dst_host; @@ -3632,9 +3632,6 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id) } trace_ram_load_complete(ret, seq_iter); - if (!ret && migration_incoming_in_colo_state()) { - colo_flush_ram_cache(); - } return ret; } diff --git a/migration/ram.h b/migration/ram.h index 5ceaff7cb4..2eeaacfa13 100644 --- a/migration/ram.h +++ b/migration/ram.h @@ -65,6 +65,7 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb); /* ram cache */ int colo_init_ram_cache(void); +void colo_flush_ram_cache(void); void colo_release_ram_cache(void); void colo_incoming_start_dirty_log(void); diff --git a/migration/rdma.c b/migration/rdma.c index 967fda5b0c..ec45d33ba3 100644 --- a/migration/rdma.c +++ b/migration/rdma.c @@ -4056,7 +4056,9 @@ void rdma_start_incoming_migration(const char *host_port, Error **errp) return; err: error_propagate(errp, local_err); - g_free(rdma->host); + if (rdma) { + g_free(rdma->host); + } g_free(rdma); g_free(rdma_return_path); } @@ -4092,20 +4094,20 @@ void rdma_start_outgoing_migration(void *opaque, rdma_return_path = qemu_rdma_data_init(host_port, errp); if (rdma_return_path == NULL) { - goto err; + goto return_path_err; } ret = qemu_rdma_source_init(rdma_return_path, s->enabled_capabilities[MIGRATION_CAPABILITY_RDMA_PIN_ALL], errp); if (ret) { - goto err; + goto return_path_err; } ret = qemu_rdma_connect(rdma_return_path, errp); if (ret) { - goto err; + goto return_path_err; } rdma->return_path = rdma_return_path; @@ -4118,6 +4120,8 @@ void rdma_start_outgoing_migration(void *opaque, s->to_dst_file = qemu_fopen_rdma(rdma, "wb"); migrate_fd_connect(s, NULL); return; +return_path_err: + qemu_rdma_cleanup(rdma); err: g_free(rdma); g_free(rdma_return_path); |