wuchong commented on code in PR #20196: URL: https://github.com/apache/flink/pull/20196#discussion_r935204581
########## flink-table/flink-table-common/src/main/java/org/apache/flink/table/connector/source/lookup/cache/DefaultLookupCache.java: ########## @@ -0,0 +1,263 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.flink.table.connector.source.lookup.cache; + +import org.apache.flink.annotation.PublicEvolving; +import org.apache.flink.annotation.VisibleForTesting; +import org.apache.flink.configuration.ReadableConfig; +import org.apache.flink.metrics.Counter; +import org.apache.flink.metrics.ThreadSafeSimpleCounter; +import org.apache.flink.metrics.groups.CacheMetricGroup; +import org.apache.flink.table.data.RowData; +import org.apache.flink.util.clock.Clock; + +import org.apache.flink.shaded.guava30.com.google.common.base.Ticker; +import org.apache.flink.shaded.guava30.com.google.common.cache.Cache; +import org.apache.flink.shaded.guava30.com.google.common.cache.CacheBuilder; + +import javax.annotation.Nullable; + +import java.time.Duration; +import java.util.Collection; + +import static org.apache.flink.table.connector.source.lookup.LookupOptions.CACHE_TYPE; +import static org.apache.flink.table.connector.source.lookup.LookupOptions.LookupCacheType.PARTIAL; +import static org.apache.flink.table.connector.source.lookup.LookupOptions.PARTIAL_CACHE_CACHE_MISSING_KEY; +import static org.apache.flink.table.connector.source.lookup.LookupOptions.PARTIAL_CACHE_EXPIRE_AFTER_ACCESS; +import static org.apache.flink.table.connector.source.lookup.LookupOptions.PARTIAL_CACHE_EXPIRE_AFTER_WRITE; +import static org.apache.flink.table.connector.source.lookup.LookupOptions.PARTIAL_CACHE_MAX_ROWS; +import static org.apache.flink.util.Preconditions.checkArgument; +import static org.apache.flink.util.Preconditions.checkNotNull; + +/** Default implementation of {@link LookupCache}. */ +@PublicEvolving +public class DefaultLookupCache implements LookupCache { + private static final long serialVersionUID = 1L; + + // Configurations of the cache + private final Duration expireAfterAccessDuration; + private final Duration expireAfterWriteDuration; + private final Long maximumSize; + private final boolean cacheMissingKey; + + // The underlying Guava cache implementation + private transient Cache<RowData, Collection<RowData>> guavaCache; + + // Guava Ticker for testing expiration + private transient Ticker ticker; + + // For tracking cache metrics + private final transient Counter hitCounter; + private final transient Counter missCounter; + + private DefaultLookupCache( + Duration expireAfterAccessDuration, + Duration expireAfterWriteDuration, + Long maximumSize, + boolean cacheMissingKey) { + this.expireAfterAccessDuration = expireAfterAccessDuration; + this.expireAfterWriteDuration = expireAfterWriteDuration; + this.maximumSize = maximumSize; + this.cacheMissingKey = cacheMissingKey; + sanityCheck(); Review Comment: I'm fine with adding the sanity check in the constructor. But would be better to add checks in `DefaultLookupCache#fromConfig` as well to indicate to users **which configuration is missed to configure**. I'm afraid the current exception is useless for users. It can't help users fix their pipelines. ########## flink-table/flink-table-common/src/main/java/org/apache/flink/table/connector/source/lookup/cache/DefaultLookupCache.java: ########## @@ -0,0 +1,263 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.flink.table.connector.source.lookup.cache; + +import org.apache.flink.annotation.PublicEvolving; +import org.apache.flink.annotation.VisibleForTesting; +import org.apache.flink.configuration.ReadableConfig; +import org.apache.flink.metrics.Counter; +import org.apache.flink.metrics.ThreadSafeSimpleCounter; +import org.apache.flink.metrics.groups.CacheMetricGroup; +import org.apache.flink.table.data.RowData; +import org.apache.flink.util.clock.Clock; + +import org.apache.flink.shaded.guava30.com.google.common.base.Ticker; +import org.apache.flink.shaded.guava30.com.google.common.cache.Cache; +import org.apache.flink.shaded.guava30.com.google.common.cache.CacheBuilder; + +import javax.annotation.Nullable; + +import java.time.Duration; +import java.util.Collection; + +import static org.apache.flink.table.connector.source.lookup.LookupOptions.CACHE_TYPE; +import static org.apache.flink.table.connector.source.lookup.LookupOptions.LookupCacheType.PARTIAL; +import static org.apache.flink.table.connector.source.lookup.LookupOptions.PARTIAL_CACHE_CACHE_MISSING_KEY; +import static org.apache.flink.table.connector.source.lookup.LookupOptions.PARTIAL_CACHE_EXPIRE_AFTER_ACCESS; +import static org.apache.flink.table.connector.source.lookup.LookupOptions.PARTIAL_CACHE_EXPIRE_AFTER_WRITE; +import static org.apache.flink.table.connector.source.lookup.LookupOptions.PARTIAL_CACHE_MAX_ROWS; +import static org.apache.flink.util.Preconditions.checkArgument; +import static org.apache.flink.util.Preconditions.checkNotNull; + +/** Default implementation of {@link LookupCache}. */ +@PublicEvolving +public class DefaultLookupCache implements LookupCache { + private static final long serialVersionUID = 1L; + + // Configurations of the cache + private final Duration expireAfterAccessDuration; + private final Duration expireAfterWriteDuration; + private final Long maximumSize; + private final boolean cacheMissingKey; + + // The underlying Guava cache implementation + private transient Cache<RowData, Collection<RowData>> guavaCache; + + // Guava Ticker for testing expiration + private transient Ticker ticker; + + // For tracking cache metrics + private final transient Counter hitCounter; + private final transient Counter missCounter; + + private DefaultLookupCache( + Duration expireAfterAccessDuration, + Duration expireAfterWriteDuration, + Long maximumSize, + boolean cacheMissingKey) { + this.expireAfterAccessDuration = expireAfterAccessDuration; + this.expireAfterWriteDuration = expireAfterWriteDuration; + this.maximumSize = maximumSize; + this.cacheMissingKey = cacheMissingKey; + sanityCheck(); + hitCounter = new ThreadSafeSimpleCounter(); + missCounter = new ThreadSafeSimpleCounter(); Review Comment: I think this is problematic. When the cache is shipped to cluster for running, the `hitCounter` and `missCounter` are null. It, of course, will run into NPE during `get` and `put`. I think we can turn `testCacheSerialization` into a test before method. Every tests should run on a deserialized cache object. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
