summaryrefslogtreecommitdiff
path: root/defaults/solr
diff options
context:
space:
mode:
authorMichael Peter Christen <mc@yacy.net>2014-05-21 11:48:08 +0200
committerMichael Peter Christen <mc@yacy.net>2014-05-21 11:48:08 +0200
commitd4157184ec43ed7d37e1dc1375e414b44b4a6896 (patch)
tree3360709b513b0bf8941d3c79c1dc4cd745f811cb /defaults/solr
parent49e344e8d9b7068ccd38f391d238783a424f6c01 (diff)
migration to Solr 4.8.1
This includes also an update to zookeeper 3.4.6 and a new library that Solr initializes by default: org.restlet from http://restlet.com/download/current#release=stable&edition=jse&distribution=zip which is included in version 2.2.1 from may 6th 2014
Diffstat (limited to 'defaults/solr')
-rw-r--r--defaults/solr/solrconfig.xml897
1 files changed, 480 insertions, 417 deletions
diff --git a/defaults/solr/solrconfig.xml b/defaults/solr/solrconfig.xml
index 375420cd8..405d50b8c 100644
--- a/defaults/solr/solrconfig.xml
+++ b/defaults/solr/solrconfig.xml
@@ -6,57 +6,57 @@
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
-
+
+ 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.
- -->
+-->
-<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
- -->
+<!--
+ For more details about configurations options that may appear in
+ this file, see http://wiki.apache.org/solr/SolrConfigXml.
+-->
<config>
- <!-- In all configuration below, a prefix of "solr." for class names
- is an alias that causes solr to search appropriate packages,
- including org.apache.solr.(search|update|request|core|analysis)
-
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
-
- <!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
- -->
- <luceneMatchVersion>4.7</luceneMatchVersion>
-
- <!-- <lib/> directives can be used to instruct Solr to load an Jars
- identified and use them to resolve any "plugins" specified in
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
- Handlers, etc...).
-
- All directories and paths are resolved relative to the
- instanceDir.
-
- Please note that <lib/> directives are processed in the order
- that they appear in your solrconfig.xml file, and are "stacked"
- on top of each other when building a ClassLoader - so if you have
- plugin jars with dependencies on other jars, the "lower level"
- dependency jars should be loaded first.
-
- If a "./lib" directory exists in your instanceDir, all files
- found in it are included as if you had used the following
- syntax...
-
- <lib dir="./lib" />
- -->
+ <!-- In all configuration below, a prefix of "solr." for class names
+ is an alias that causes solr to search appropriate packages,
+ including org.apache.solr.(search|update|request|core|analysis)
+
+ You may also specify a fully qualified Java classname if you
+ have your own custom plugins.
+ -->
+
+ <!-- Controls what version of Lucene various components of Solr
+ adhere to. Generally, you want to use the latest version to
+ get all bug fixes and improvements. It is highly recommended
+ that you fully re-index after changing this setting as it can
+ affect both how text is indexed and queried.
+ -->
+ <luceneMatchVersion>4.7</luceneMatchVersion>
+
+ <!-- <lib/> directives can be used to instruct Solr to load an Jars
+ identified and use them to resolve any "plugins" specified in
+ your solrconfig.xml or schema.xml (ie: Analyzers, Request
+ Handlers, etc...).
+
+ All directories and paths are resolved relative to the
+ instanceDir.
+
+ Please note that <lib/> directives are processed in the order
+ that they appear in your solrconfig.xml file, and are "stacked"
+ on top of each other when building a ClassLoader - so if you have
+ plugin jars with dependencies on other jars, the "lower level"
+ dependency jars should be loaded first.
+
+ If a "./lib" directory exists in your instanceDir, all files
+ found in it are included as if you had used the following
+ syntax...
+
+ <lib dir="./lib" />
+ -->
<!-- A 'dir' option by itself adds any files found in the directory
to the classpath, this is useful for including all jars in a
@@ -102,322 +102,383 @@
<!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory is filesystem
- based and tries to pick the best implementation for the current
- JVM and platform. solr.NRTCachingDirectoryFactory, the default,
- wraps solr.StandardDirectoryFactory and caches small files in memory
- for better NRT performance.
-
- One can force a particular implementation via solr.MMapDirectoryFactory,
- solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
-
- solr.RAMDirectoryFactory is memory based, not
- persistent, and doesn't work with replication.
- -->
- <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
- <!-- <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.MMapDirectoryFactory}"/> -->
- <!-- using MMapDirectoryFactory as solution for ClosedChannelException given in https://issues.apache.org/jira/browse/SOLR-2247
- this feature is now switched on in the startYACY.sh file using a -D option -->
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Index Config - These settings control low-level behavior of indexing
- Most example settings here show the default value, but are commented
- out, to more easily see where customizations have been made.
-
- Note: This replaces <indexDefaults> and <mainIndex> from older versions
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <indexConfig>
- <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
- LimitTokenCountFilterFactory in your fieldType definition. E.g.
- <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
- -->
- <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
- <writeLockTimeout>20000</writeLockTimeout>
+
+ solr.StandardDirectoryFactory is filesystem
+ based and tries to pick the best implementation for the current
+ JVM and platform. solr.NRTCachingDirectoryFactory, the default,
+ wraps solr.StandardDirectoryFactory and caches small files in memory
+ for better NRT performance.
+
+ One can force a particular implementation via solr.MMapDirectoryFactory,
+ solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
+
+ solr.RAMDirectoryFactory is memory based, not
+ persistent, and doesn't work with replication.
+ -->
+ <directoryFactory name="DirectoryFactory"
+ class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}">
+
+
+ <!-- These will be used if you are using the solr.HdfsDirectoryFactory,
+ otherwise they will be ignored. If you don't plan on using hdfs,
+ you can safely remove this section. -->
+ <!-- The root directory that collection data should be written to. -->
+ <str name="solr.hdfs.home">${solr.hdfs.home:}</str>
+ <!-- The hadoop configuration files to use for the hdfs client. -->
+ <str name="solr.hdfs.confdir">${solr.hdfs.confdir:}</str>
+ <!-- Enable/Disable the hdfs cache. -->
+ <str name="solr.hdfs.blockcache.enabled">${solr.hdfs.blockcache.enabled:true}</str>
+
+ </directoryFactory>
+
+ <!-- The CodecFactory for defining the format of the inverted index.
+ The default implementation is SchemaCodecFactory, which is the official Lucene
+ index format, but hooks into the schema to provide per-field customization of
+ the postings lists and per-document values in the fieldType element
+ (postingsFormat/docValuesFormat). Note that most of the alternative implementations
+ are experimental, so if you choose to customize the index format, its a good
+ idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
+ before upgrading to a newer version to avoid unnecessary reindexing.
+ -->
+ <codecFactory class="solr.SchemaCodecFactory"/>
+
+ <!-- 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"/>
+
+ <!-- using MMapDirectoryFactory as solution for ClosedChannelException
+ given in https://issues.apache.org/jira/browse/SOLR-2247
+ this feature is now switched on in the startYACY.sh file using a -D option
+ -->
+
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Index Config - These settings control low-level behavior of indexing
+ Most example settings here show the default value, but are commented
+ out, to more easily see where customizations have been made.
+
+ Note: This replaces <indexDefaults> and <mainIndex> from older versions
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+ <indexConfig>
+ <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
+ LimitTokenCountFilterFactory in your fieldType definition. E.g.
+ <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
+ -->
+ <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
+ <writeLockTimeout>20000</writeLockTimeout>
- <!-- Expert: Enabling compound file will use less files for the index,
- using fewer file descriptors on the expense of performance decrease.
+ <!-- The maximum number of simultaneous threads that may be
+ indexing documents at once in IndexWriter; if more than this
+ many threads arrive they will wait for others to finish.
+ Default in Solr/Lucene is 8. -->
+ <!-- <maxIndexingThreads>8</maxIndexingThreads> -->
+
+ <!-- Expert: Enabling compound file will use less files for the index,
+ using fewer file descriptors on the expense of performance decrease.
Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
- <!-- <useCompoundFile>true</useCompoundFile> -->
+ <useCompoundFile>true</useCompoundFile>
- <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+ <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
indexing for buffering added documents and deletions before they are
flushed to the Directory.
maxBufferedDocs sets a limit on the number of documents buffered
before flushing.
If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first. -->
- <!-- <ramBufferSizeMB>32</ramBufferSizeMB> -->
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
+ Lucene will flush based on whichever limit is hit first.
+ The default is 100 MB. -->
+ <ramBufferSizeMB>32</ramBufferSizeMB>
+ <maxBufferedDocs>100</maxBufferedDocs>
- <!-- Expert: Merge Policy
+ <!-- Expert: Merge Policy
The Merge Policy in Lucene controls how merging of segments is done.
The default since Solr/Lucene 3.3 is TieredMergePolicy.
The default since Lucene 2.3 was the LogByteSizeMergePolicy,
Even older versions of Lucene used LogDocMergePolicy.
- -->
- <!--
- <mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
- <int name="maxMergeAtOnce">10</int>
- <int name="segmentsPerTier">10</int>
- </mergePolicy>
- -->
-
- <!-- Merge Factor
+ -->
+ <!--
+ <mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
+ <int name="maxMergeAtOnce">10</int>
+ <int name="segmentsPerTier">10</int>
+ </mergePolicy>
+ -->
+
+ <!-- Merge Factor
The merge factor controls how many segments will get merged at a time.
For TieredMergePolicy, mergeFactor is a convenience parameter which
will set both MaxMergeAtOnce and SegmentsPerTier at once.
For LogByteSizeMergePolicy, mergeFactor decides how many new segments
will be allowed before they are merged into one.
Default is 10 for both merge policies.
- -->
- <mergeFactor>5</mergeFactor>
+ -->
+ <!--
+ <mergeFactor>10</mergeFactor>
+ -->
- <!-- Expert: Merge Scheduler
+ <!-- Expert: Merge Scheduler
The Merge Scheduler in Lucene controls how merges are
performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
can perform merges in the background using separate threads.
The SerialMergeScheduler (Lucene 2.2 default) does not.
- -->
- <!--
- <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
- -->
-
- <!-- LockFactory
-
+ -->
+ <!--
+ <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+ -->
+
+ <!-- LockFactory
+
This option specifies which Lucene LockFactory implementation
to use.
-
+
single = SingleInstanceLockFactory - suggested for a
- read-only index or when there is no possibility of
- another process trying to modify the index.
+ read-only index or when there is no possibility of
+ another process trying to modify the index.
native = NativeFSLockFactory - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
+ Do not use when multiple solr webapps in the same
+ JVM are attempting to share a single index.
simple = SimpleFSLockFactory - uses a plain file for locking
-
+
Defaults: 'native' is default for Solr3.6 and later, otherwise
- 'simple' is the default
-
+ 'simple' is the default
+
More details on the nuances of each LockFactory...
http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <!-- <lockType>native</lockType> -->
-
- <!-- Unlock On Startup
-
+ -->
+ <lockType>${solr.lock.type:native}</lockType>
+
+ <!-- Unlock On Startup
+
If true, unlock any held write or commit locks on startup.
This defeats the locking mechanism that allows multiple
processes to safely access a lucene index, and should be used
with care. Default is "false".
-
- This is not needed if lock type is 'none' or 'single'
- -->
- <!--
- <unlockOnStartup>false</unlockOnStartup>
- -->
-
- <!-- Expert: Controls how often Lucene loads terms into memory
+
+ This is not needed if lock type is 'single'
+ -->
+ <!--
+ <unlockOnStartup>false</unlockOnStartup>
+ -->
+
+ <!-- Expert: Controls how often Lucene loads terms into memory
Default is 128 and is likely good for most everyone.
- -->
- <!-- <termIndexInterval>128</termIndexInterval> -->
-
- <!-- If true, IndexReaders will be reopened (often more efficient)
- instead of closed and then opened. Default: true
- -->
- <!--
- <reopenReaders>true</reopenReaders>
- -->
-
- <!-- Commit Deletion Policy
-
+ -->
+ <!-- <termIndexInterval>128</termIndexInterval> -->
+
+ <!-- If true, IndexReaders will be opened/reopened from the IndexWriter
+ instead of from the Directory. Hosts in a master/slave setup
+ should have this set to false while those in a SolrCloud
+ cluster need to be set to true. Default: true
+ -->
+ <!--
+ <nrtMode>true</nrtMode>
+ -->
+
+ <!-- Commit Deletion Policy
Custom deletion policies can be specified here. The class must
implement org.apache.lucene.index.IndexDeletionPolicy.
-
- http://lucene.apache.org/java/3_5_0/api/core/org/apache/lucene/index/IndexDeletionPolicy.html
-
+
The default Solr IndexDeletionPolicy implementation supports
deleting index commit points on number of commits, age of
commit point and optimized status.
The latest commit point should always be preserved regardless
of the criteria.
- -->
- <!--
- <deletionPolicy class="solr.SolrDeletionPolicy">
- -->
- <!-- The number of commit points to be kept -->
- <!-- <str name="maxCommitsToKeep">1</str> -->
- <!-- The number of optimized commit points to be kept -->
- <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
+ -->
+ <!--
+ <deletionPolicy class="solr.SolrDeletionPolicy">
+ -->
+ <!-- The number of commit points to be kept -->
+ <!-- <str name="maxCommitsToKeep">1</str> -->
+ <!-- The number of optimized commit points to be kept -->
+ <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
+ <!--
+ Delete all commit points once they have reached the given age.
+ Supports DateMathParser syntax e.g.
+ -->
+ <!--
<str name="maxCommitAge">30MINUTES</str>
<str name="maxCommitAge">1DAY</str>
- -->
- <!--
- </deletionPolicy>
- -->
+ -->
+ <!--
+ </deletionPolicy>
+ -->
- <!-- Lucene Infostream
-
+ <!-- Lucene Infostream
+
To aid in advanced debugging, Lucene provides an "InfoStream"
of detailed information when indexing.
-
- Setting The value to true will instruct the underlying Lucene
- IndexWriter to write its debugging info the specified file
- -->
- <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
- </indexConfig>
-
-
- <!-- JMX
-
- This example enables JMX if and only if an existing MBeanServer
- is found, use this if you want to configure JMX through JVM
- parameters. Remove this to disable exposing Solr configuration
- and statistics to JMX.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
+
+ Setting the value to true will instruct the underlying Lucene
+ IndexWriter to write its info stream to solr's log. By default,
+ this is enabled here, and controlled through log4j.properties.
+ -->
+ <infoStream>true</infoStream>
+ </indexConfig>
+
+
+ <!-- JMX
+
+ This example enables JMX if and only if an existing MBeanServer
+ is found, use this if you want to configure JMX through JVM
+ parameters. Remove this to disable exposing Solr configuration
+ and statistics to JMX.
+
+ For more details see http://wiki.apache.org/solr/SolrJmx
+ -->
+ <jmx />
+ <!-- If you want to connect to a particular server, specify the
+ agentId
+ -->
+ <!-- <jmx agentId="myAgent" /> -->
+ <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
+ <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+ -->
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- AutoCommit
-
+ <!-- The default high-performance update handler -->
+ <updateHandler class="solr.DirectUpdateHandler2">
+
+ <!-- Enables a transaction log, used for real-time get, durability, and
+ and solr cloud replica recovery. The log can grow as big as
+ uncommitted changes to the index, so use of a hard autoCommit
+ is recommended (see below).
+ "dir" - the target directory for transaction logs, defaults to the
+ solr data directory. -->
+ <updateLog>
+ <str name="dir">${solr.ulog.dir:}</str>
+ </updateLog>
+
+ <!-- AutoCommit
+
Perform a hard commit automatically under certain conditions.
Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
+ when adding documents.
+
http://wiki.apache.org/solr/UpdateXmlMessages
-
+
maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
+ commit before automatically triggering a new commit.
+
maxTime - Maximum amount of time in ms that is allowed to pass
- since a document was added before automaticly
- triggering a new commit.
+ since a document was added before automatically
+ triggering a new commit.
openSearcher - if false, the commit causes recent index changes
- to be flushed to stable storage, but does not cause a new
- searcher to be opened to make those changes visible.
- -->
- <autoCommit>
- <maxTime>180000</maxTime>
- <openSearcher>false</openSearcher>
- </autoCommit>
-
- <!-- softAutoCommit is like autoCommit except it causes a
+ to be flushed to stable storage, but does not cause a new
+ searcher to be opened to make those changes visible.
+
+ If the updateLog is enabled, then it's highly recommended to
+ have some sort of hard autoCommit to limit the log size.
+ -->
+ <autoCommit>
+ <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
+ <openSearcher>true</openSearcher>
+ </autoCommit>
+
+ <!-- softAutoCommit is like autoCommit except it causes a
'soft' commit which only ensures that changes are visible
but does not ensure that data is synced to disk. This is
faster and more near-realtime friendly than a hard commit.
- -->
- <!--
- <autoSoftCommit>
- <maxTime>3000</maxTime>
- </autoSoftCommit>
- -->
-
- <!-- Update Related Event Listeners
+ -->
+
+ <autoSoftCommit>
+ <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
+ </autoSoftCommit>
+
+ <!-- Update Related Event Listeners
Various IndexWriter related events can trigger Listeners to
take actions.
-
+
postCommit - fired after every commit or optimize command
postOptimize - fired after every optimize command
- -->
- <!-- The RunExecutableListener executes an external command from a
+ -->
+ <!-- The RunExecutableListener executes an external command from a
hook such as postCommit or postOptimize.
exe - the name of the executable to run
dir - dir to use as the current working directory. (default=".")
- wait - the calling thread waits until the executable returns.
- (default="true")
+ wait - the calling thread waits until the executable returns.
+ (default="true")
args - the arguments to pass to the program. (default is none)
env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
+ -->
+ <!-- This example shows how RunExecutableListener could be used
with the script based replication...
http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <listener event="postCommit" class="solr.RunExecutableListener">
+ -->
+ <!--
+ <listener event="postCommit" class="solr.RunExecutableListener">
<str name="exe">solr/bin/snapshooter</str>
<str name="dir">.</str>
<bool name="wait">true</bool>
<arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
<arr name="env"> <str>MYVAR=val1</str> </arr>
- </listener>
- -->
-
- <!-- Enables a transaction log, currently used for real-time get.
- "dir" - the target directory for transaction logs, defaults to the
- solr data directory. -->
- <!--
- <updateLog>
- <str name="dir">${solr.data.dir:}</str>
- </updateLog>
- -->
-
- </updateHandler>
+ </listener>
+ -->
+
+ </updateHandler>
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
- <!-- By explicitly declaring the Factory, the termIndexDivisor can
- be specified.
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory"
- class="solr.StandardIndexReaderFactory">
- <int name="setTermIndexDivisor">12</int>
+ <!-- IndexReaderFactory
+
+ Use the following format to specify a custom IndexReaderFactory,
+ which allows for alternate IndexReader implementations.
+
+ ** Experimental Feature **
+
+ Please note - Using a custom IndexReaderFactory may prevent
+ certain other features from working. The API to
+ IndexReaderFactory may change without warning or may even be
+ removed from future releases if the problems cannot be
+ resolved.
+
+
+ ** Features that may not work with custom IndexReaderFactory **
+
+ The ReplicationHandler assumes a disk-resident index. Using a
+ custom IndexReader implementation may cause incompatibility
+ with ReplicationHandler and may cause replication to not work
+ correctly. See SOLR-1366 for details.
+
+ -->
+ <!--
+ <indexReaderFactory name="IndexReaderFactory" class="package.class">
+ <str name="someArg">Some Value</str>
+ </indexReaderFactory >
+ -->
+ <!-- By explicitly declaring the Factory, the termIndexDivisor can
+ be specified.
+ -->
+ <!--
+ <indexReaderFactory name="IndexReaderFactory"
+ class="solr.StandardIndexReaderFactory">
+ <int name="setTermIndexDivisor">12</int>
</indexReaderFactory >
- -->
+ -->
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Query section - these settings control query time things like caches
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <query>
- <!-- Max Boolean Clauses
-
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Query section - these settings control query time things like caches
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+ <query>
+ <!-- Max Boolean Clauses
+
Maximum number of clauses in each BooleanQuery, an exception
is thrown if exceeded.
-
+
** WARNING **
This option actually modifies a global Lucene property that
@@ -425,24 +486,24 @@
disagree on this property, the value at any given moment will
be based on the last SolrCore to be initialized.
- -->
- <maxBooleanClauses>1024</maxBooleanClauses>
-
-
- <!-- Solr Internal Query Caches
-
+ -->
+ <maxBooleanClauses>1024</maxBooleanClauses>
+
+
+ <!-- Solr Internal Query Caches
+
There are two implementations of cache available for Solr,
LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
+ FastLRUCache, based on a ConcurrentHashMap.
+
FastLRUCache has faster gets and slower puts in single
threaded operation and thus is generally faster than LRUCache
when the hit ratio of the cache is high (> 75%), and may be
faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
+ -->
+
+ <!-- Filter Cache
+
Cache used by SolrIndexSearcher for filters (DocSets),
unordered sets of *all* documents that match a query. When a
new searcher is opened, its caches may be prepopulated or
@@ -450,155 +511,157 @@
autowarmCount is the number of items to prepopulate. For
LRUCache, the autowarmed items will be the most recently
accessed items.
-
+
Parameters:
- class - the SolrCache implementation LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- initialSize - the initial capacity (number of entries) of
- the cache. (see java.util.HashMap)
- autowarmCount - the number of entries to prepopulate from
- and old cache.
- -->
- <filterCache class="solr.FastLRUCache"
- size="64"
- initialSize="64"
- autowarmCount="0"
- cleanupThread="true"/>
+ class - the SolrCache implementation LRUCache or
+ (LRUCache or FastLRUCache)
+ size - the maximum number of entries in the cache
+ initialSize - the initial capacity (number of entries) of
+ the cache. (see java.util.HashMap)
+ autowarmCount - the number of entries to prepopulate from
+ and old cache.
+ -->
+ <filterCache class="solr.FastLRUCache"
+ size="100"
+ initialSize="100"
+ autowarmCount="0"/>
- <!-- Query Result Cache
+ <!-- Query Result Cache
Caches results of searches - ordered lists of document ids
- (DocList) based on a query, a sort, and the range of documents requested.
- -->
- <queryResultCache class="solr.FastLRUCache"
- size="64"
- initialSize="64"
- autowarmCount="0"
- cleanupThread="true"/>
-
- <!-- Document Cache
-
+ (DocList) based on a query, a sort, and the range of documents requested.
+ -->
+ <queryResultCache class="solr.LRUCache"
+ size="100"
+ initialSize="100"
+ autowarmCount="0"/>
+
+ <!-- Document Cache
+
Caches Lucene Document objects (the stored fields for each
document). Since Lucene internal document ids are transient,
- this cache will not be autowarmed.
- -->
- <documentCache class="solr.FastLRUCache"
- size="64"
- initialSize="64"
- autowarmCount="0"
- cleanupThread="true"/>
-
- <!-- Field Value Cache
+ this cache will not be autowarmed.
+ -->
+ <documentCache class="solr.LRUCache"
+ size="64"
+ initialSize="64"
+ autowarmCount="0"/>
+
+ <!-- custom cache currently used by block join -->
+ <cache name="perSegFilter"
+ class="solr.search.LRUCache"
+ size="10"
+ initialSize="0"
+ autowarmCount="10"
+ regenerator="solr.NoOpRegenerator" />
+
+ <!-- Field Value Cache
Cache used to hold field values that are quickly accessible
by document id. The fieldValueCache is created by default
even if not configured here.
- -->
- <fieldValueCache class="solr.FastLRUCache"
- size="64"
- autowarmCount="0"
- showItems="32"
- cleanupThread="true"/>
-
- <!-- Custom Cache
-
+ -->
+ <fieldValueCache class="solr.FastLRUCache"
+ size="64"
+ autowarmCount="0"
+ showItems="32" />
+
+ <!-- Custom Cache
+
Example of a generic cache. These caches may be accessed by
name through SolrIndexSearcher.getCache(),cacheLookup(), and
cacheInsert(). The purpose is to enable easy caching of
user/application level data. The regenerator argument should
- be specified as an implementation of solr.CacheRegenerator
- if autowarming is desired.
- -->
- <!--
- <cache name="myUserCache"
- class="solr.FastLRUCache"
- size="64"
- initialSize="64"
- autowarmCount="0"
- regenerator="com.mycompany.MyRegenerator"
- cleanupThread="true"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
+ be specified as an implementation of solr.CacheRegenerator
+ if autowarming is desired.
+ -->
+ <!--
+ <cache name="myUserCache"
+ class="solr.LRUCache"
+ size="4096"
+ initialSize="1024"
+ autowarmCount="1024"
+ regenerator="com.mycompany.MyRegenerator"
+ />
+ -->
+
+ <!-- Lazy Field Loading
+
If true, stored fields that are not requested will be loaded
lazily. This can result in a significant speed improvement
if the usual case is to not load all stored fields,
especially if the skipped fields are large compressed text
fields.
- -->
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
-
- <!-- Use Filter For Sorted Query
-
- A possible optimization that attempts to use a filter to
- satisfy a search. If the requested sort does not include
- score, then the filterCache will be checked for a filter
- matching the query. If found, the filter will be used as the
- source of document ids, and then the sort will be applied to
- that.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- are collected. For example, if a search for a particular query
- requests matching documents 10 through 19, and queryWindowSize is 50,
- then documents 0 through 49 will be collected and cached. Any further
- requests in that range can be satisfied via the cache.
- -->
- <queryResultWindowSize>20</queryResultWindowSize>
+ -->
+ <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+ <!-- Use Filter For Sorted Query
+
+ A possible optimization that attempts to use a filter to
+ satisfy a search. If the requested sort does not include
+ score, then the filterCache will be checked for a filter
+ matching the query. If found, the filter will be used as the
+ source of document ids, and then the sort will be applied to
+ that.
+
+ For most situations, this will not be useful unless you
+ frequently get the same search repeatedly with different sort
+ options, and none of them ever use "score"
+ -->
+ <!--
+ <useFilterForSortedQuery>true</useFilterForSortedQuery>
+ -->
+
+ <!-- Result Window Size
+
+ An optimization for use with the queryResultCache. When a search
+ is requested, a superset of the requested number of document ids
+ are collected. For example, if a search for a particular query
+ requests matching documents 10 through 19, and queryWindowSize is 50,
+ then documents 0 through 49 will be collected and cached. Any further
+ requests in that range can be satisfied via the cache.
+ -->
+ <queryResultWindowSize>1</queryResultWindowSize>
+
+ <!-- Maximum number of documents to cache for any entry in the
+ queryResultCache.
+ -->
+ <queryResultMaxDocsCached>100</queryResultMaxDocsCached>
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+ <!-- Query Related Event Listeners
+
+ Various IndexSearcher related events can trigger Listeners to
+ take actions.
+
+ newSearcher - fired whenever a new searcher is being prepared
+ and there is a current searcher handling requests (aka
+ registered). It can be used to prime certain caches to
+ prevent long request times for certain requests.
+
+ firstSearcher - fired whenever a new searcher is being
+ prepared but there is no current registered searcher to handle
+ requests or to gain autowarming data from.
+
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- prepared but there is no current registered searcher to handle
- requests or to gain autowarming data from.
-
-
- -->
- <!-- QuerySenderListener takes an array of NamedList and executes a
- local query request for each NamedList in sequence.
- -->
- <listener event="newSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- </arr>
- </listener>
+ -->
+ <!-- QuerySenderListener takes an array of NamedList and executes a
+ local query request for each NamedList in sequence.
+ -->
+ <listener event="newSearcher" class="solr.QuerySenderListener">
+ <arr name="queries">
+ <!--
+ <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
+ <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
+ -->
+ </arr>
+ </listener>
+ <listener event="firstSearcher" class="solr.QuerySenderListener">
+ <arr name="queries">
+ <lst>
+ <str name="q">static firstSearcher warming in solrconfig.xml</str>
+ </lst>
+ </arr>
+ </listener>
<!-- Use Cold Searcher