solr4.7分片shard对应的range值变为null异常问题处理(bug)

solr分片shard对应的range值变为null异常问题处理

转贴请声明原文： http://blog.csdn.net/duck_genuine/article/details/52984082

选 用的solr是solr4.7版本！

solr分片突然发现多个collections上某些shard对应的range值变为null,而且还多一个parent:null

由于solr文档的分发到不同shard是通过主键hash后，分到不同的范围值取对应的shard，所以上面这个问题会

导致索引不了，且搜索到某个分片取对应文档也有问题，最关键在solrcloud图上并没有显示有任务的异常问题，只有在logging上不断抛出下面的异常！

org.apache.solr.common.SolrException: No active slice servicing hash code b8951b39 in DocCollection(audio_tags)={  "shards":{    "shard2":{      "range":"0-7fffffff",      "state":"active",      "replicas":{        "core_node4":{          "state":"active",          "base_url":"http://192.168.1.14:11111/solr",          "core":"audio_tags_shard2_replica2",          "node_name":"192.168.1.14:11111_solr"},        "core_node5":{          "state":"active",          "base_url":"http://192.168.1.13:11112/solr",          "core":"audio_tags_shard2_replica1",          "node_name":"192.168.1.13:11112_solr",          "leader":"true"}}},    "shard1":{      "range":null,      "state":"active",      "parent":null,      "replicas":{        "core_node6":{          "state":"active",          "base_url":"http://192.168.1.11:11111/solr",          "core":"audio_tags_shard1_replica4",          "node_name":"192.168.1.11:11111_solr",          "leader":"true"},        "core_node7":{          "state":"active",          "base_url":"http://192.168.1.3:11111/solr",          "core":"audio_tags_shard1_replica4",          "node_name":"192.168.1.3:11111_solr"}}}},  "maxShardsPerNode":"1",  "router":{"name":"compositeId"},  "replicationFactor":"3"}at org.apache.solr.common.cloud.HashBasedRouter.hashToSlice(HashBasedRouter.java:60)at org.apache.solr.common.cloud.HashBasedRouter.getTargetSlice(HashBasedRouter.java:34)at org.apache.solr.update.processor.DistributedUpdateProcessor.setupRequest(DistributedUpdateProcessor.java:218)at org.apache.solr.update.processor.DistributedUpdateProcessor.processAdd(DistributedUpdateProcessor.java:550)at org.apache.solr.update.processor.LogUpdateProcessor.processAdd(LogUpdateProcessorFactory.java:100)at org.apache.solr.handler.loader.JavabinLoader$1.update(JavabinLoader.java:96)at org.apache.solr.client.solrj.request.JavaBinUpdateRequestCodec$1.readOuterMostDocIterator(JavaBinUpdateRequestCodec.java:166)at org.apache.solr.client.solrj.request.JavaBinUpdateRequestCodec$1.readIterator(JavaBinUpdateRequestCodec.java:136)at org.apache.solr.common.util.JavaBinCodec.readVal(JavaBinCodec.java:225)at org.apache.solr.client.solrj.request.JavaBinUpdateRequestCodec$1.readNamedList(JavaBinUpdateRequestCodec.java:121)at org.apache.solr.common.util.JavaBinCodec.readVal(JavaBinCodec.java:190)at org.apache.solr.common.util.JavaBinCodec.unmarshal(JavaBinCodec.java:116)at org.apache.solr.client.solrj.request.JavaBinUpdateRequestCodec.unmarshal(JavaBinUpdateRequestCodec.java:173)at org.apache.solr.handler.loader.JavabinLoader.parseAndLoadDocs(JavabinLoader.java:106)at org.apache.solr.handler.loader.JavabinLoader.load(JavabinLoader.java:58)at org.apache.solr.handler.UpdateRequestHandler$1.load(UpdateRequestHandler.java:92)at org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(ContentStreamHandlerBase.java:74)at org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBase.java:135)at org.apache.solr.core.SolrCore.execute(SolrCore.java:1916)at org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java:768)at org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:415)at org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:205)at org.eclipse.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1419)at org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:455)at org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:137)at org.eclipse.jetty.security.SecurityHandler.handle(SecurityHandler.java:557)at org.eclipse.jetty.server.session.SessionHandler.doHandle(SessionHandler.java:231)at org.eclipse.jetty.server.handler.ContextHandler.doHandle(ContextHandler.java:1075)at org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:384)at org.eclipse.jetty.server.session.SessionHandler.doScope(SessionHandler.java:193)at org.eclipse.jetty.server.handler.ContextHandler.doScope(ContextHandler.java:1009)at org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:135)at org.eclipse.jetty.server.handler.ContextHandlerCollection.handle(ContextHandlerCollection.java:255)at org.eclipse.jetty.server.handler.HandlerCollection.handle(HandlerCollection.java:154)at org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:116)at org.eclipse.jetty.server.Server.handle(Server.java:368)at org.eclipse.jetty.server.AbstractHttpConnection.handleRequest(AbstractHttpConnection.java:489)at org.eclipse.jetty.server.BlockingHttpConnection.handleRequest(BlockingHttpConnection.java:53)at org.eclipse.jetty.server.AbstractHttpConnection.content(AbstractHttpConnection.java:953)at org.eclipse.jetty.server.AbstractHttpConnection$RequestHandler.content(AbstractHttpConnection.java:1014)at org.eclipse.jetty.http.HttpParser.parseNext(HttpParser.java:861)at org.eclipse.jetty.http.HttpParser.parseAvailable(HttpParser.java:235)at org.eclipse.jetty.server.BlockingHttpConnection.handle(BlockingHttpConnection.java:72)at org.eclipse.jetty.server.bio.SocketConnector$ConnectorEndPoint.run(SocketConnector.java:264)at org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:608)at org.eclipse.jetty.util.thread.QueuedThreadPool$3.run(QueuedThreadPool.java:543)at java.lang.Thread.run(Thread.java:745)

这应该是个bug,不过要重现应该不容易，所以只能找解决方案。马上想到的是修改 /clusterstate.json

为了安全起见，不直接去zk上修改该结点内容。而是写了个小程序去修改

import java.util.Collections;import java.util.HashMap;import java.util.List;import java.util.Map;import org.apache.solr.client.solrj.impl.CloudSolrServer;import org.apache.solr.common.cloud.ClusterState;import org.apache.solr.common.cloud.CompositeIdRouter;import org.apache.solr.common.cloud.DocCollection;import org.apache.solr.common.cloud.DocRouter;import org.apache.solr.common.cloud.DocRouter.Range;import org.apache.solr.common.cloud.Slice;import org.apache.solr.common.cloud.ZkNodeProps;import org.apache.solr.common.cloud.ZkStateReader;public class UpdateClusterstat {/**取分片对应hash范围值 * @param totalShardNum 总共有多少分片 * @param shardNum  第几个分片 ，1开始 * @return */public static  String getRange(int totalShardNum, int shardNum) {DocRouter hp = DocRouter.DEFAULT;List<Range> ranges;ranges = hp.partitionRange(totalShardNum, hp.fullRange());int index = shardNum - 1;Range r = ranges.get(index);return r.toString();}public static void main(String[] args) {System.out.println("###");try {// testSliceStateUpdate("audio_comment", "shard2",// "d5550000-2aa9ffff");// testSliceStateUpdate("audio_tags", "shard1",// "80000000-ffffffff");// testSliceStateUpdate("audio", "shard2", "0-7fffffff");//testSliceStateUpdate("DeviceIDFA", "shard1", "80000000-7fffffff");//testSliceStateUpdate("analzyerword", "shard1", "80000000-7fffffff");String range = getRange(2,2);testSliceStateUpdate("DeviceIDFA", "shard1", range);System.out.println(range);} catch (Exception e) {// TODO Auto-generated catch blocke.printStackTrace();}}public static void testSliceStateUpdate(String collection, String shard,String range) throws Exception {String zkHost = "zookeeper:2181/new_on_lizhi_search";int zkClientTimeout = 2000;int zkConnectTimeout = 2000;CloudSolrServer solrServer = CloudSolrServerFactory.getInstance(zkHost,zkClientTimeout, zkConnectTimeout, collection);ClusterState cluster = solrServer.getZkStateReader().getClusterState();Map<String, Slice> slicesMap = cluster.getSlicesMap(collection);Slice slice = slicesMap.get(shard);Map<String, Object> prop = slice.getProperties();prop.put("range", range);prop.remove("parent");Slice newSlice = new Slice(slice.getName(), slice.getReplicasMap(),prop);slicesMap.put(newSlice.getName(), newSlice);Map<String, Object> props = new HashMap<String, Object>(1);props.put(DocCollection.DOC_ROUTER,ZkNodeProps.makeMap("name", CompositeIdRouter.NAME));DocCollection coll = new DocCollection(collection, slicesMap, props,DocRouter.DEFAULT);ClusterState newState = cluster.copyWith(Collections.singletonMap(coll.getName(), coll));solrServer.getZkStateReader().getZkClient().setData(ZkStateReader.CLUSTER_STATE,ZkStateReader.toJSON(newState), true);}}

处理后，测试已没有问题。