[
https://issues.apache.org/jira/browse/BEAM-13015?focusedWorklogId=697067&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-697067
]
ASF GitHub Bot logged work on BEAM-13015:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 16/Dec/21 05:03
Start Date: 16/Dec/21 05:03
Worklog Time Spent: 10m
Work Description: lukecwik commented on a change in pull request #16130:
URL: https://github.com/apache/beam/pull/16130#discussion_r770226746
##########
File path:
sdks/java/harness/src/main/java/org/apache/beam/fn/harness/Caches.java
##########
@@ -0,0 +1,285 @@
+/*
+ * 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.beam.fn.harness;
+
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.Objects;
+import java.util.Set;
+import java.util.function.Function;
+import org.apache.beam.sdk.options.PipelineOptions;
+import org.apache.beam.sdk.options.SdkHarnessOptions;
+import
org.apache.beam.vendor.guava.v26_0_jre.com.google.common.annotations.VisibleForTesting;
+import org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.Sets;
+import
org.apache.beam.vendor.guava.v26_0_jre.com.google.common.util.concurrent.MoreExecutors;
+import org.cache2k.Cache2kBuilder;
+import org.cache2k.operation.Weigher;
+import org.github.jamm.MemoryMeter;
+
+/** Utility methods used to instantiate and operate over cache instances. */
+@SuppressWarnings("nullness")
+public final class Caches {
+
+ /** A cache that never stores any values. */
+ public static <K, V> Cache<K, V> noop() {
+ return new SubCacheable<K, V>() {
+ @Override
+ public V peek(K key) {
+ return null;
+ }
+
+ @Override
+ public V computeIfAbsent(K key, Function<K, V> loadingFunction) {
+ return loadingFunction.apply(key);
+ }
+
+ @Override
+ public void put(K key, V value) {}
+
+ @Override
+ public void clear() {}
+
+ @Override
+ public void remove(K key) {}
+
+ @Override
+ public Set<K> keys() {
+ return Collections.emptySet();
+ }
+ };
+ }
+
+ /**
+ * Uses the specified {@link PipelineOptions} to configure and return a
cache instance based upon
+ * parameters within {@link SdkHarnessOptions}.
+ */
+ public static <K, V> Cache<K, V> fromOptions(PipelineOptions options) {
+ // We specifically use cache2k since it allows for recursive
computeIfAbsent calls
+ // preventing deadlock from occurring when a loading function mutates the
underlying cache
+ org.cache2k.Cache<Object, Object> cache =
+ Cache2kBuilder.forUnknownTypes()
+ .maximumWeight(
+ options.as(SdkHarnessOptions.class).getMaxCacheMemoryUsageMb()
* 1024L * 1024L)
+ .weigher(
+ new Weigher<Object, Object>() {
+ private final MemoryMeter memoryMeter =
MemoryMeter.builder().build();
+
+ @Override
+ public int weigh(Object key, Object value) {
+ long size = memoryMeter.measureDeep(key) +
memoryMeter.measureDeep(value);
+ return size > Integer.MAX_VALUE ? Integer.MAX_VALUE :
(int) size;
+ }
+ })
+ .storeByReference(true)
+ .executor(MoreExecutors.directExecutor())
+ .build();
+
+ return (Cache<K, V>) forCache(cache);
+ }
+
+ /**
+ * Returns a view of a cache that operates on keys with a specified key
prefix.
+ *
+ * <p>All lookups, insertions, and removals into the parent {@link Cache}
will be prefixed by the
+ * specified prefixes.
+ *
+ * <p>Operations which operate over the entire caches contents such as
{@link Cache#clear} only
+ * operate over keys with the specified prefixes.
+ */
+ public static <K, V> Cache<K, V> subCache(
+ Cache<?, ?> cache, Object keyPrefix, Object... additionalKeyPrefix) {
+ if (cache instanceof SubCache) {
+ return new SubCache<>(
+ ((SubCache<?, ?>) cache).cache,
+ ((SubCache<?, ?>) cache).keyPrefix.subKey(keyPrefix,
additionalKeyPrefix));
+ } else if (cache instanceof SubCacheable) {
+ return new SubCache<>((SubCacheable<?, ?>) cache,
CompositeKey.ROOT.subKey(keyPrefix));
+ }
+ throw new UnsupportedOperationException("An unsupported type of cache was
passed.");
+ }
+
+ /** A cache that never evicts any values. */
+ public static <K, V> Cache<K, V> eternal() {
+ // We specifically use cache2k since it allows for recursive
computeIfAbsent calls
Review comment:
The swap to use guava cache is in
https://github.com/apache/beam/pull/16252
--
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: github-unsubscr...@beam.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
Issue Time Tracking
-------------------
Worklog Id: (was: 697067)
Time Spent: 24h 20m (was: 24h 10m)
> Optimize Java SDK harness
> -------------------------
>
> Key: BEAM-13015
> URL: https://issues.apache.org/jira/browse/BEAM-13015
> Project: Beam
> Issue Type: Improvement
> Components: sdk-java-harness
> Reporter: Luke Cwik
> Assignee: Luke Cwik
> Priority: P2
> Time Spent: 24h 20m
> Remaining Estimate: 0h
>
> Use profiling tools to remove bundle processing overhead in the SDK harness.
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
