[
https://issues.apache.org/jira/browse/DRILL-7745?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17182826#comment-17182826
]
ASF GitHub Bot commented on DRILL-7745:
---------------------------------------
vvysotskyi commented on a change in pull request #2084:
URL: https://github.com/apache/drill/pull/2084#discussion_r475253606
##########
File path:
contrib/storage-ipfs/src/main/java/org/apache/drill/exec/store/ipfs/IPFSGroupScan.java
##########
@@ -0,0 +1,452 @@
+/*
+ * 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.drill.exec.store.ipfs;
+
+
+import com.fasterxml.jackson.annotation.JacksonInject;
+import com.fasterxml.jackson.annotation.JsonCreator;
+import com.fasterxml.jackson.annotation.JsonIgnore;
+import com.fasterxml.jackson.annotation.JsonProperty;
+import com.fasterxml.jackson.annotation.JsonTypeName;
+import io.ipfs.api.MerkleNode;
+import io.ipfs.cid.Cid;
+import io.ipfs.multihash.Multihash;
+import org.apache.drill.common.PlanStringBuilder;
+import org.apache.drill.common.exceptions.UserException;
+import org.apache.drill.common.expression.SchemaPath;
+import org.apache.drill.common.util.DrillVersionInfo;
+import org.apache.drill.exec.coord.ClusterCoordinator;
+import org.apache.drill.exec.physical.EndpointAffinity;
+import org.apache.drill.exec.physical.base.AbstractGroupScan;
+import org.apache.drill.exec.physical.base.PhysicalOperator;
+import org.apache.drill.exec.physical.base.ScanStats;
+import org.apache.drill.exec.proto.CoordinationProtos.DrillbitEndpoint;
+import org.apache.drill.exec.store.StoragePluginRegistry;
+import org.apache.drill.exec.store.schedule.AffinityCreator;
+import org.apache.drill.exec.store.schedule.AssignmentCreator;
+import org.apache.drill.exec.store.schedule.CompleteWork;
+import org.apache.drill.exec.store.schedule.EndpointByteMap;
+import org.apache.drill.exec.store.schedule.EndpointByteMapImpl;
+import org.apache.drill.shaded.guava.com.google.common.base.Preconditions;
+import org.apache.drill.shaded.guava.com.google.common.base.Stopwatch;
+import org.apache.drill.shaded.guava.com.google.common.cache.LoadingCache;
+import
org.apache.drill.shaded.guava.com.google.common.collect.ArrayListMultimap;
+import org.apache.drill.shaded.guava.com.google.common.collect.ImmutableList;
+import org.apache.drill.shaded.guava.com.google.common.collect.ListMultimap;
+import org.apache.drill.shaded.guava.com.google.common.collect.Lists;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.LinkedHashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Optional;
+import java.util.Random;
+import java.util.concurrent.ForkJoinPool;
+import java.util.concurrent.RecursiveTask;
+import java.util.concurrent.TimeUnit;
+import java.util.stream.Collectors;
+
+
+@JsonTypeName("ipfs-scan")
+public class IPFSGroupScan extends AbstractGroupScan {
+ private static final Logger logger =
LoggerFactory.getLogger(IPFSGroupScan.class);
+ private final IPFSContext ipfsContext;
+ private final IPFSScanSpec ipfsScanSpec;
+ private final IPFSStoragePluginConfig config;
+ private List<SchemaPath> columns;
+
+ private static final long DEFAULT_NODE_SIZE = 1000L;
+ public static final int DEFAULT_USER_PORT = 31010;
+ public static final int DEFAULT_CONTROL_PORT = 31011;
+ public static final int DEFAULT_DATA_PORT = 31012;
+ public static final int DEFAULT_HTTP_PORT = 8047;
+
+ private ListMultimap<Integer, IPFSWork> assignments;
+ private List<IPFSWork> ipfsWorkList = Lists.newArrayList();
+ private ListMultimap<String, IPFSWork> endpointWorksMap;
+ private List<EndpointAffinity> affinities;
+
+ @JsonCreator
+ public IPFSGroupScan(@JsonProperty("IPFSScanSpec") IPFSScanSpec ipfsScanSpec,
+ @JsonProperty("IPFSStoragePluginConfig")
IPFSStoragePluginConfig ipfsStoragePluginConfig,
+ @JsonProperty("columns") List<SchemaPath> columns,
+ @JacksonInject StoragePluginRegistry pluginRegistry) {
+ this(
+ pluginRegistry.resolve(ipfsStoragePluginConfig,
IPFSStoragePlugin.class).getIPFSContext(),
+ ipfsScanSpec,
+ columns
+ );
+ }
+
+ public IPFSGroupScan(IPFSContext ipfsContext,
+ IPFSScanSpec ipfsScanSpec,
+ List<SchemaPath> columns) {
+ super((String) null);
+ this.ipfsContext = ipfsContext;
+ this.ipfsScanSpec = ipfsScanSpec;
+ this.config = ipfsContext.getStoragePluginConfig();
+ logger.debug("GroupScan constructor called with columns {}", columns);
+ this.columns = columns == null || columns.size() == 0? ALL_COLUMNS :
columns;
+ init();
+ }
+
+ private void init() {
+ IPFSHelper ipfsHelper = ipfsContext.getIPFSHelper();
+ endpointWorksMap = ArrayListMultimap.create();
+
+ Multihash topHash = ipfsScanSpec.getTargetHash(ipfsHelper);
+ try {
+ Map<Multihash, String> leafAddrMap = getLeafAddrMappings(topHash);
+ logger.debug("Iterating on {} leaves...", leafAddrMap.size());
+ ClusterCoordinator coordinator =
ipfsContext.getStoragePlugin().getContext().getClusterCoordinator();
+ for (Multihash leaf : leafAddrMap.keySet()) {
+ String peerHostname = leafAddrMap.get(leaf);
+
+ Optional<DrillbitEndpoint> oep = coordinator.getAvailableEndpoints()
+ .stream()
+ .filter(a -> a.getAddress().equals(peerHostname))
+ .findAny();
+ DrillbitEndpoint ep;
+ if (oep.isPresent()) {
+ ep = oep.get();
+ logger.debug("Using existing endpoint {}", ep.getAddress());
+ } else {
+ logger.debug("created new endpoint on the fly {}", peerHostname);
+ //DRILL-7754: read ports & version info from IPFS instead of
hard-coded
+ ep = DrillbitEndpoint.newBuilder()
+ .setAddress(peerHostname)
+ .setUserPort(DEFAULT_USER_PORT)
+ .setControlPort(DEFAULT_CONTROL_PORT)
+ .setDataPort(DEFAULT_DATA_PORT)
+ .setHttpPort(DEFAULT_HTTP_PORT)
+ .setVersion(DrillVersionInfo.getVersion())
+ .setState(DrillbitEndpoint.State.ONLINE)
+ .build();
+ //DRILL-7777: how to safely remove endpoints that are no longer
needed once the query is completed?
+ ClusterCoordinator.RegistrationHandle handle =
coordinator.register(ep);
Review comment:
@dbw9580, the case I mentioned may be reproduced in the cluster with
several nodes when the endpoint for this plugin is registered for the node with
no running drillbit that belongs to the current Drill cluster. In this case,
the endpoint for that node will be registered. Assume at this time, another
query is submitted. Drill will try to send the plan fragment to this node, and
this will cause problems since actually Drillbit is not running there.
Please take a look at the logic in `BlockMapBuilder`, where it decides which
drillbit will execute specific `CompleteWork` instance.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
> Add storage plugin for IPFS
> ---------------------------
>
> Key: DRILL-7745
> URL: https://issues.apache.org/jira/browse/DRILL-7745
> Project: Apache Drill
> Issue Type: New Feature
> Components: Storage - Other
> Affects Versions: 1.18.0
> Reporter: Bowen Ding
> Assignee: Bowen Ding
> Priority: Major
>
> See introduction here: [https://github.com/bdchain/Minerva]
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
