rakeshadr commented on code in PR #3444: URL: https://github.com/apache/ozone/pull/3444#discussion_r882321732
########## hadoop-ozone/ozone-manager/src/main/java/org/apache/hadoop/ozone/om/OzoneListStatusHelper.java: ########## @@ -0,0 +1,534 @@ +/** + * 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 + * <p> + * http://www.apache.org/licenses/LICENSE-2.0 + * <p> + * 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.hadoop.ozone.om; + +import com.google.common.base.Preconditions; +import com.google.common.base.Strings; +import org.apache.commons.lang3.StringUtils; +import org.apache.hadoop.hdds.utils.db.Table; +import org.apache.hadoop.hdds.utils.db.TableIterator; +import org.apache.hadoop.hdds.utils.db.cache.CacheKey; +import org.apache.hadoop.hdds.utils.db.cache.CacheValue; +import org.apache.hadoop.ozone.om.helpers.OzoneFileStatus; +import org.apache.hadoop.ozone.om.helpers.OzoneFSUtils; +import org.apache.hadoop.ozone.om.helpers.OmKeyArgs; +import org.apache.hadoop.ozone.om.helpers.OmBucketInfo; +import org.apache.hadoop.ozone.om.helpers.OmKeyInfo; +import org.apache.hadoop.ozone.om.helpers.BucketLayout; +import org.apache.hadoop.ozone.om.helpers.OmDirectoryInfo; +import org.apache.hadoop.ozone.om.helpers.WithParentObjectId; +import org.apache.hadoop.ozone.om.request.file.OMFileRequest; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.Closeable; +import java.io.IOException; +import java.util.ArrayList; +import java.util.Iterator; +import java.util.TreeMap; +import java.util.Map; +import java.util.PriorityQueue; +import java.util.NoSuchElementException; +import java.util.Collection; +import java.util.Collections; + + +import static org.apache.hadoop.ozone.om.lock. + OzoneManagerLock.Resource.BUCKET_LOCK; + +/** + * Helper class for fetching List Status for a path. + */ +public class OzoneListStatusHelper { + /** + * Interface to get the File Status for a path. + */ + @FunctionalInterface + public interface GetFileStatusHelper { + OzoneFileStatus apply(OmKeyArgs args, String clientAddress, + boolean skipFileNotFoundError) throws IOException; + } + + /** + * Interface for iteration of Heap Entries. + */ + public interface ClosableIterator extends Iterator<HeapEntry>, Closeable { + + } + + private static final Logger LOG = + LoggerFactory.getLogger(OzoneListStatusHelper.class); + + private final OMMetadataManager metadataManager; + private final long scmBlockSize; + private final GetFileStatusHelper getStatusHelper; + + OzoneListStatusHelper(OMMetadataManager metadataManager, long scmBlockSize, + GetFileStatusHelper func) { + this.metadataManager = metadataManager; + this.scmBlockSize = scmBlockSize; + this.getStatusHelper = func; + } + + public Collection<OzoneFileStatus> listStatusFSO(OmKeyArgs args, + String startKey, long numEntries, String clientAddress) + throws IOException { + Preconditions.checkNotNull(args, "Key args can not be null"); + + boolean listKeysMode = false; + final String volumeName = args.getVolumeName(); + final String bucketName = args.getBucketName(); + String keyName = args.getKeyName(); + String prefixKey = keyName; + + String bucketKey = metadataManager.getBucketKey(volumeName, bucketName); + OmBucketInfo omBucketInfo = + metadataManager.getBucketTable().get(bucketKey); + if (omBucketInfo == null) { + if (LOG.isDebugEnabled()) { + LOG.debug("Volume:{} Bucket:{} does not exist", + volumeName, bucketName); + } + return new ArrayList<>(); + } + + // Determine if the prefixKey is determined from the startKey + // if the keyName is null + if (StringUtils.isNotBlank(startKey)) { + if (StringUtils.isNotBlank(keyName)) { + if (!listKeysMode && + !StringUtils.startsWith(startKey, keyName) && + !OzoneFSUtils.isImmediateChild(keyName, startKey)) { + if (LOG.isDebugEnabled()) { + LOG.debug("StartKey {} is not an immediate child of keyName {}. " + + "Returns empty list", startKey, keyName); + } + return new ArrayList<>(); + } + } else { + keyName = OzoneFSUtils.getParentDir(startKey); + prefixKey = keyName; + args = args.toBuilder() + .setKeyName(keyName) + .setSortDatanodesInPipeline(false) + .build(); + } + } + + OzoneFileStatus fileStatus = + getStatusHelper.apply(args, clientAddress, listKeysMode); + + String dbPrefixKey; + if (fileStatus == null) { + // if the file status is null, prefix is a not a valid filesystem path + // this should only work in list keys mode. + // fetch the db key based on the prefix path. + dbPrefixKey = getDbKey(keyName, args, omBucketInfo); + prefixKey = OzoneFSUtils.getParentDir(keyName); + } else { + // If the keyname is a file just return one entry + if (fileStatus.isFile()) { + return Collections.singletonList(fileStatus); + } + + // fetch the db key based on parent prefix id. + long id = getId(fileStatus, omBucketInfo); + dbPrefixKey = metadataManager.getOzonePathKey(id, ""); + } + + // Determine startKeyPrefix for DB iteration + String startKeyPrefix = + Strings.isNullOrEmpty(startKey) ? "" : + getDbKey(startKey, args, omBucketInfo); + + TreeMap<String, OzoneFileStatus> map = new TreeMap<>(); + + BucketLayout bucketLayout = omBucketInfo.getBucketLayout(); + + // fetch the sorted output using a min heap iterator where + // every remove from the heap will give the smallest entry. + try (MinHeapIterator heapIterator = new MinHeapIterator(metadataManager, + dbPrefixKey, bucketLayout, startKeyPrefix, volumeName, bucketName)) { + + while (map.size() < numEntries && heapIterator.hasNext()) { + HeapEntry entry = heapIterator.next(); + OzoneFileStatus status = entry.getStatus(prefixKey, + scmBlockSize, volumeName, bucketName); + map.put(entry.key, status); + } + } + + return map.values(); + } + + private String getDbKey(String key, OmKeyArgs args, + OmBucketInfo omBucketInfo) throws IOException { + long startKeyParentId; + OzoneFileStatus fileStatusInfo = getFileStatus(key, args); + if (fileStatusInfo == null || fileStatusInfo.isFile()) { + String parent = OzoneFSUtils.getParentDir(key); + + fileStatusInfo = getFileStatus(parent, args); + + // the keyname is not a valid filesystem path. + // determine the parent prefix by fetching the + // prefix id of the parent directory + Preconditions.checkNotNull(fileStatusInfo); Review Comment: checkNotNull can throw NPE, which is a RuntimeException and can leads to retries. Instead of that, can you throw OMException explicitly. ``` 2022-05-26 10:37:31,235 [Time-limited test] INFO retry.RetryInvocationHandler (RetryInvocationHandler.java:log(411)) - com.google.protobuf.ServiceException: org.apache.hadoop.ipc.RemoteException(java.lang.NullPointerException): java.lang.NullPointerException at com.google.common.base.Preconditions.checkNotNull(Preconditions.java:889) at org.apache.hadoop.ozone.om.OzoneListStatusHelper.getDbKey(OzoneListStatusHelper.java:) ``` ``` public static <T> T checkNotNull(@CheckForNull T reference) { if (reference == null) { throw new NullPointerException(); } else { return reference; } } ``` -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
