1、3台solr服务器，采用主从复制的策略实现索引文件的同步，主从就是设置集群中一台server为主，另外为从服务器，从服务器定时从主服务器中同步数据

主服务器的solr配置（solrconfig.xml）

<?xml version="1.0" encoding="UTF-8" ?>  <!--   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.  -->    <!--   This is a stripped down config file used for a simple example...     It is *not* a good example to work from.   -->  <config>    <luceneMatchVersion>4.9</luceneMatchVersion>         <!-- A 'dir' option by itself adds any files found in the directory          to the classpath, this is useful for including all jars in a         directory.           When a 'regex' is specified in addition to a 'dir', only the         files in that directory which completely match the regex         (anchored on both ends) will be included.           If a 'dir' option (with or without a regex) is used and nothing         is found that matches, a warning will be logged.           The examples below can be used to load some solr-contribs along          with their external dependencies.      -->          <!--  The DirectoryFactory to use for indexes.          solr.StandardDirectoryFactory, the default, is filesystem based.          solr.RAMDirectoryFactory is memory based, not persistent, and doesn't work with replication. -->    <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>      <dataDir>${solr.core0.data.dir:}</dataDir>      <!-- To enable dynamic schema REST APIs, use the following for <schemaFactory>:             <schemaFactory class="ManagedIndexSchemaFactory">           <bool name="mutable">true</bool>           <str name="managedSchemaResourceName">managed-schema</str>         </schemaFactory>                  When ManagedIndexSchemaFactory is specified, Solr will load the schema from         he resource named in 'managedSchemaResourceName', rather than from schema.xml.         Note that the managed schema resource CANNOT be named schema.xml.  If the managed         schema does not exist, Solr will create it after reading schema.xml, then rename         'schema.xml' to 'schema.xml.bak'.                   Do NOT hand edit the managed schema - external modifications will be ignored and         overwritten as a result of schema modification REST API calls.           When ManagedIndexSchemaFactory is specified with mutable = true, schema         modification REST API calls will be allowed; otherwise, error responses will be         sent back for these requests.     -->    <schemaFactory class="ClassicIndexSchemaFactory"/>      <updateHandler class="solr.DirectUpdateHandler2">      <updateLog>        <str name="dir">${solr.core0.data.dir:}</str>      </updateLog>    </updateHandler>      <!-- realtime get handler, guaranteed to return the latest stored fields       of any document, without the need to commit or open a new searcher. The current       implementation relies on the updateLog feature being enabled. -->    <requestHandler name="/get" class="solr.RealTimeGetHandler">      <lst name="defaults">        <str name="omitHeader">true</str>      </lst>    </requestHandler>         <requestHandler name="/replication" class="solr.ReplicationHandler" >       <lst name="master">          <!--Replicate on 'startup' and 'commit'. 'optimize' is also a valid value for replicateAfter. -->          <str name="replicateAfter">startup</str>          <str name="replicateAfter">commit</str>          <str name="replicateAfter">optimize</str>                   <!--Create a backup after 'optimize'. Other values can be 'commit', 'startup'. It is possible to have multiple entries of this config string.  Note that this is just for backup, replication does not require this. -->          <!-- <str name="backupAfter">optimize</str> -->            <!--If configuration files need to be replicated give the names here, separated by comma -->          <str name="confFiles">schema.xml,stopwords.txt</str>                 <!--The default value of reservation is 10 secs.See the documentation below . Normally , you should not need to specify this -->          <str name="commitReserveDuration">00:00:10</str>              </lst>              </requestHandler>        <requestDispatcher handleSelect="true" >      <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" formdataUploadLimitInKB="2048" />    </requestDispatcher>        <requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />    <requestHandler name="/analysis/field" startup="lazy" class="solr.FieldAnalysisRequestHandler" />    <requestHandler name="/update" class="solr.UpdateRequestHandler"  />    <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />   <!--     <requestHandler name="/admin/ping" class="solr.PingRequestHandler">      <lst name="invariants">        <str name="q">solrpingquery</str>      </lst>      <lst name="defaults">        <str name="echoParams">all</str>      </lst>    </requestHandler>   -->     <queryResultWindowSize>1500</queryResultWindowSize>  <queryResultMaxDocsCached>150</queryResultMaxDocsCached>    <queryResultCache  class="solr.LRUCache"  size="15000"  initialSize="15000"  autowarmCount="1500"/>             <!-- config for the admin interface -->     <admin>      <defaultQuery>solr</defaultQuery>    </admin>    </config>

<?xml version="1.0" encoding="UTF-8" ?>  <!--   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.  -->    <!--   This is a stripped down config file used for a simple example...     It is *not* a good example to work from.   -->  <config>    <luceneMatchVersion>4.9</luceneMatchVersion>         <!-- A 'dir' option by itself adds any files found in the directory          to the classpath, this is useful for including all jars in a         directory.           When a 'regex' is specified in addition to a 'dir', only the         files in that directory which completely match the regex         (anchored on both ends) will be included.           If a 'dir' option (with or without a regex) is used and nothing         is found that matches, a warning will be logged.           The examples below can be used to load some solr-contribs along          with their external dependencies.      -->           <!--  The DirectoryFactory to use for indexes.          solr.StandardDirectoryFactory, the default, is filesystem based.          solr.RAMDirectoryFactory is memory based, not persistent, and doesn't work with replication. -->    <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>      <dataDir>${solr.core0.data.dir:}</dataDir>      <!-- To enable dynamic schema REST APIs, use the following for <schemaFactory>:             <schemaFactory class="ManagedIndexSchemaFactory">           <bool name="mutable">true</bool>           <str name="managedSchemaResourceName">managed-schema</str>         </schemaFactory>                  When ManagedIndexSchemaFactory is specified, Solr will load the schema from         he resource named in 'managedSchemaResourceName', rather than from schema.xml.         Note that the managed schema resource CANNOT be named schema.xml.  If the managed         schema does not exist, Solr will create it after reading schema.xml, then rename         'schema.xml' to 'schema.xml.bak'.                   Do NOT hand edit the managed schema - external modifications will be ignored and         overwritten as a result of schema modification REST API calls.           When ManagedIndexSchemaFactory is specified with mutable = true, schema         modification REST API calls will be allowed; otherwise, error responses will be         sent back for these requests.     -->    <schemaFactory class="ClassicIndexSchemaFactory"/>      <updateHandler class="solr.DirectUpdateHandler2">      <updateLog>        <str name="dir">${solr.core0.data.dir:}</str>      </updateLog>    </updateHandler>      <!-- realtime get handler, guaranteed to return the latest stored fields       of any document, without the need to commit or open a new searcher. The current       implementation relies on the updateLog feature being enabled. -->    <requestHandler name="/get" class="solr.RealTimeGetHandler">      <lst name="defaults">        <str name="omitHeader">true</str>      </lst>    </requestHandler>            <requestHandler name="/replication" class="solr.ReplicationHandler" startup="lazy" >        <lst name="slave">            <!--fully qualified url for the replication handler of master . It is possible to pass on this as a request param for the fetchindex command-->          <str name="masterUrl">http://10.10.53.235:8080/solr/core0/replication</str>            <!--Interval in which the slave should poll master .Format is HH:mm:ss . If this is absent slave does not poll automatically.                        But a fetchindex can be triggered from the admin or the http API -->          <str name="pollInterval">00:10:00</str>                  <!-- THE FOLLOWING PARAMETERS ARE USUALLY NOT REQUIRED-->          <!--to use compression while transferring the index files. The possible values are internal|external                        if the value is 'external' make sure that your master Solr has the settings to honour the accept-encoding header.                                 see here for details http://wiki.apache.org/solr/SolrHttpCompression                                          If it is 'internal' everything will be taken care of automatically.                                                   USE THIS ONLY IF YOUR BANDWIDTH IS LOW . THIS CAN ACTUALLY SLOWDOWN REPLICATION IN A LAN-->          <str name="compression">internal</str>                  <!--The following values are used when the slave connects to the master to download the index files.                                Default values implicitly set as 5000ms and 10000ms respectively. The user DOES NOT need to specify                                         these unless the bandwidth is extremely low or if there is an extremely high latency-->          <str name="httpConnTimeout">5000</str>                  <str name="httpReadTimeout">10000</str>            <!-- If HTTP Basic authentication is enabled on the master, then the slave can be configured with the following -->       </lst>       </requestHandler>        <requestDispatcher handleSelect="true" >      <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" formdataUploadLimitInKB="2048" />    </requestDispatcher>        <requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />    <requestHandler name="/analysis/field" startup="lazy" class="solr.FieldAnalysisRequestHandler" />    <requestHandler name="/update" class="solr.UpdateRequestHandler"  />    <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />           <requestHandler name="/admin/ping" class="solr.PingRequestHandler">      <lst name="invariants">        <str name="q">solrpingquery</str>      </lst>      <lst name="defaults">        <str name="echoParams">all</str>      </lst>    </requestHandler>          <queryResultWindowSize>1500</queryResultWindowSize>  <queryResultMaxDocsCached>150</queryResultMaxDocsCached>  <queryResultCache  class="solr.LRUCache"  size="15000"  initialSize="15000"  autowarmCount="1500"/>             <!-- config for the admin interface -->     <admin>      <defaultQuery>solr</defaultQuery>    </admin>    </config>

2、solrj实现索引创建和查询

由于采用了主从架构，所以创建直接在主服务器上完成就可以，从服务器会自动同步

查询时前端用nginx做代理，达到负载均衡的效果

nginx的配置如下：

upstream localhost{     server 10.10.53.177:8080;     server 10.16.15.121:8080;     server 10.10.53.235:8080;      }        server   {      listen       80;      server_name  10.10.53.235;        root        /home/html;      charset     utf-8;      include     proxy.conf;        #   location ~ ^/getAllPlaybill.json$   #   {   #   if ($query_string ~* "playbillDate=(.*)&mdv=(.*)$") {  #       set $playbillDate $1;  #         rewrite  ^/getAllPlaybill\.json  http://10.10.53.235/getAllPlaybill_$playbillDate.txt break;     #  }         # }          location ~ /      {          proxy_pass   http://localhost;       }          # Add expires header for static comtent      location ~ .*\.(gif|jpg|jpeg|png|bmp|swf)$      {            access_log   off;            expires      10d;      }        location ~ .*\.(js|css)$      {          access_log   off;          expires      1h;      }   }

upstream localhost{     server 10.10.53.177:8080;     server 10.16.15.121:8080;     //server 10.10.53.235:8080; 注释即可      }

来自：http://my.oschina.net/gaowm/blog/349334