起源
事情的起源是在1.6.2的版本上，釘友發現了一個Bug，在TTL state snapshot的時，此處會拋IllegalArgumentException：
protected CompositeSerializer<TtlValue<T>> createSerializerInstance(
PrecomputedParameters precomputed,
TypeSerializer<?> ... originalSerializers) {
Preconditions.checkNotNull(originalSerializers);
//異常，length爲1，原因在緊接的一行中
Preconditions.checkArgument(originalSerializers.length == 2);
//duplicate的時候只取了fieldSerializer，丟棄了TTL中timestamp的LongSerializer
return new TtlSerializer<>(precomputed, (TypeSerializer<T>) originalSerializers[1]);
}
上述BUG已經在Flink 1.6.3版本修復，在定位過程中反覆跟蹤和閱讀了State的註冊和使用源碼，在此進行記錄。
State 存儲結構
存儲結構層次如下：
- 在AbstractKeyedStateBackend中以StateDescriptor name爲key存儲State
// From AbstractKeyedStateBackend.java private final HashMap<String, InternalKvState<K, ?, ?>> keyValueStatesByName; - InternalKvState中以三元組的形式存儲保存數據，具體保存方式和store的類型相關，以heap方式爲例：
//From AbstractHeapState.java protected final StateTable<K, N, SV> stateTable; - StateTable的具體實現方式有兩種，CopyOnWriteStateTable和NestedMapsStateTable，兩者的主要區別是一種是flat的方式存儲，一種是嵌套map的方式存儲。重點看看CopyOnWriteStateTable的數據保存方式：
此處有兩個StateTableEntry的數據，和CopyOnWriteTable的實現相關，不用太關注。// From CopyOnWriteStateTable.java /** * This is the primary entry array (hash directory) of the state table. If no incremental rehash is ongoing, this * is the only used table. **/ private StateTableEntry<K, N, S>[] primaryTable; /** * We maintain a secondary entry array while performing an incremental rehash. The purpose is to slowly migrate * entries from the primary table to this resized table array. When all entries are migrated, this becomes the new * primary table. */ private StateTableEntry<K, N, S>[] incrementalRehashTable; - StateTableEntry就是state的封裝類了，其中還包括一些hash、衝突鏈next指針等信息，和CopyOnWriteTable的實現強相關，是一種類hashMap的處理。
需要強調的是不同的State在具體的實現上有些差異。
State 註冊過程
1. 註冊時機
StreamTask在run前會先open所有的operator，operator的open方法中，我們通常會通過StateDescription 來初始化State。沒錯，就在此時註冊。一個MapState註冊的調用棧：
2. 關鍵過程
-
靜態註冊StateFactory
//From TtlStateFactory @SuppressWarnings("deprecation") private Map<Class<? extends StateDescriptor>, SupplierWithException<IS, Exception>> createStateFactories() { return Stream.of( Tuple2.of(ValueStateDescriptor.class, (SupplierWithException<IS, Exception>) this::createValueState), Tuple2.of(ListStateDescriptor.class, (SupplierWithException<IS, Exception>) this::createListState), Tuple2.of(MapStateDescriptor.class, (SupplierWithException<IS, Exception>) this::createMapState), Tuple2.of(ReducingStateDescriptor.class, (SupplierWithException<IS, Exception>) this::createReducingState), Tuple2.of(AggregatingStateDescriptor.class, (SupplierWithException<IS, Exception>) this::createAggregatingState), Tuple2.of(FoldingStateDescriptor.class, (SupplierWithException<IS, Exception>) this::createFoldingState) ).collect(Collectors.toMap(t -> t.f0, t -> t.f1)); } -
創建 KeyedState
// From AbstractKeyedStateBackend.java public <N, S extends State, V> S getOrCreateKeyedState( final TypeSerializer<N> namespaceSerializer, StateDescriptor<S, V> stateDescriptor) throws Exception { checkNotNull(namespaceSerializer, "Namespace serializer"); checkNotNull(keySerializer, "State key serializer has not been configured in the config. " + "This operation cannot use partitioned state."); InternalKvState<K, ?, ?> kvState = keyValueStatesByName.get(stateDescriptor.getName()); if (kvState == null) { if (!stateDescriptor.isSerializerInitialized()) { // 將Tyepinfo轉爲Serializer，上面一句判空應該是冗餘的 stateDescriptor.initializeSerializerUnlessSet(executionConfig); } // 通過KeyedStateFactory創建KVState // 用TTLStateFactory進行包裝，未enale TTL的情況，就直接使用this kvState = TtlStateFactory.createStateAndWrapWithTtlIfEnabled( namespaceSerializer, stateDescriptor, this, ttlTimeProvider); //以Descriptor的名稱爲key keyValueStatesByName.put(stateDescriptor.getName(), kvState); publishQueryableStateIfEnabled(stateDescriptor, kvState); } return (S) kvState; } -
以MapState爲例看具體創建代碼
private <UK, UV> IS createMapState() throws Exception { MapStateDescriptor<UK, UV> mapStateDesc = (MapStateDescriptor<UK, UV>) stateDesc; //這裏重新包裝了descriptor，是因爲除了mapstate之外，還需要記錄timemstap，用於判斷TTL MapStateDescriptor<UK, TtlValue<UV>> ttlDescriptor = new MapStateDescriptor<>( stateDesc.getName(), mapStateDesc.getKeySerializer(), new TtlSerializer<>(mapStateDesc.getValueSerializer())); //創建MapState return (IS) new TtlMapState<>( originalStateFactory.createInternalState(namespaceSerializer, ttlDescriptor, getSnapshotTransformFactory()), ttlConfig, timeProvider, mapStateDesc.getSerializer()); } -
對於heap backend，創建internalState的code：
// From heapKeyedStateBackend.java public <N, SV, SEV, S extends State, IS extends S> IS createInternalState( @Nonnull TypeSerializer<N> namespaceSerializer, @Nonnull StateDescriptor<S, SV> stateDesc, @Nonnull StateSnapshotTransformFactory<SEV> snapshotTransformFactory) throws Exception { //STATE_FACTORIES的定義見後文 StateFactory stateFactory = STATE_FACTORIES.get(stateDesc.getClass()); if (stateFactory == null) { String message = String.format("State %s is not supported by %s", stateDesc.getClass(), this.getClass()); throw new FlinkRuntimeException(message); } StateTable<K, N, SV> stateTable = tryRegisterStateTable( namespaceSerializer, stateDesc, getStateSnapshotTransformer(stateDesc, snapshotTransformFactory)); return stateFactory.createState(stateDesc, stateTable, keySerializer); } // 註冊state private <N, V> StateTable<K, N, V> tryRegisterStateTable( TypeSerializer<N> namespaceSerializer, StateDescriptor<?, V> stateDesc, StateSnapshotTransformer<V> snapshotTransformer) throws StateMigrationException { @SuppressWarnings("unchecked") // 以descriptor的名稱爲key, StateTable爲value StateTable<K, N, V> stateTable = (StateTable<K, N, V>) registeredKVStates.get(stateDesc.getName()); RegisteredKeyValueStateBackendMetaInfo<N, V> newMetaInfo; if (stateTable != null) { @SuppressWarnings("unchecked") StateMetaInfoSnapshot restoredMetaInfoSnapshot = restoredStateMetaInfo.get( StateUID.of(stateDesc.getName(), StateMetaInfoSnapshot.BackendStateType.KEY_VALUE)); Preconditions.checkState( restoredMetaInfoSnapshot != null, "Requested to check compatibility of a restored RegisteredKeyedBackendStateMetaInfo," + " but its corresponding restored snapshot cannot be found."); newMetaInfo = RegisteredKeyValueStateBackendMetaInfo.resolveKvStateCompatibility( restoredMetaInfoSnapshot, namespaceSerializer, stateDesc, snapshotTransformer); stateTable.setMetaInfo(newMetaInfo); } else { newMetaInfo = new RegisteredKeyValueStateBackendMetaInfo<>( stateDesc.getType(), stateDesc.getName(), namespaceSerializer, stateDesc.getSerializer(), snapshotTransformer); // 創建StateTable stateTable = snapshotStrategy.newStateTable(newMetaInfo); registeredKVStates.put(stateDesc.getName(), stateTable); } return stateTable; }
鏈路有點長，需要點耐心，希望上述記錄可以作爲看該過程代碼的roadmap。