LUCENE-864: set svn:eol-style=native.

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@529511 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Doron Cohen 2007-04-17 07:11:04 +00:00
parent 1877f9e3dc
commit 33694c7d86
13 changed files with 1323 additions and 1323 deletions

View File

@ -1,137 +1,137 @@
<?xml version="1.0"?>
<project name="benchmark" default="default">
<description>
Lucene Benchmarking Contributions
</description>
<import file="../contrib-build.xml"/>
<property name="working.dir" value="work"/>
<target name="check-files">
<available file="temp/news20.tar.gz" property="news20.exists"/>
<available file="${working.dir}/20_newsgroup" property="news20.expanded"/>
<available file="temp/reuters21578.tar.gz" property="reuters.exists"/>
<available file="${working.dir}/reuters" property="reuters.expanded"/>
<available file="${working.dir}/reuters-out" property="reuters.extracted"/>
<available file="temp/20news-18828.tar.gz" property="20news-18828.exists"/>
<available file="${working.dir}/20news-18828" property="20news-18828.expanded"/>
<available file="${working.dir}/mini_newsgroups" property="mini.expanded"/>
</target>
<target name="get-news-20" unless="20news-18828.exists">
<get src="http://www-2.cs.cmu.edu/afs/cs.cmu.edu/project/theo-20/www/data/news20.tar.gz"
dest="temp/news20.tar.gz"/>
</target>
<target name="get-reuters" unless="reuters.exists">
<get src="http://www.daviddlewis.com/resources/testcollections/reuters21578/reuters21578.tar.gz"
dest="temp/reuters21578.tar.gz"/>
</target>
<target name="expand-news-20" unless="news20.expanded">
<gunzip src="temp/news20.tar.gz" dest="temp"/>
<untar src="temp/news20.tar" dest="${working.dir}"/>
</target>
<target name="expand-reuters" unless="reuters.expanded">
<gunzip src="temp/reuters21578.tar.gz" dest="temp"/>
<mkdir dir="${working.dir}/reuters"/>
<untar src="temp/reuters21578.tar" dest="${working.dir}/reuters"/>
<delete >
<fileset dir="${working.dir}/reuters">
<include name="*.txt"/>
</fileset>
</delete>
</target>
<target name="extract-reuters" depends="check-files" unless="reuters.extracted">
<mkdir dir="${working.dir}/reuters-out"/>
<java classname="org.apache.lucene.benchmark.utils.ExtractReuters" maxmemory="1024M" fork="true">
<classpath refid="run.classpath"/>
<arg line="${working.dir}/reuters ${working.dir}/reuters-out"/>
</java>
</target>
<target name="get-20news-18828" unless="20news-18828.exists">
<get src="http://people.csail.mit.edu/u/j/jrennie/public_html/20Newsgroups/20news-18828.tar.gz"
dest="temp/20news-18828.tar.gz"/>
</target>
<target name="expand-20news-18828" unless="20news-18828.expanded">
<gunzip src="temp/20news-18828.tar.gz" dest="temp"/>
<untar src="temp/20news-18828.tar" dest="${working.dir}"/>
</target>
<target name="get-mini-news" unless="mini.exists">
<get src="http://kdd.ics.uci.edu/databases/20newsgroups/mini_newsgroups.tar.gz"
dest="temp/mini_newsgroups.tar.gz"/>
</target>
<target name="expand-mini-news" unless="mini.expanded">
<gunzip src="temp/mini_newsgroups.tar.gz" dest="temp"/>
<untar src="temp/mini_newsgroups.tar" dest="${working.dir}"/>
</target>
<target name="get-files" depends="check-files">
<mkdir dir="temp"/>
<antcall target="get-reuters"/>
<antcall target="expand-reuters"/>
<antcall target="extract-reuters"/>
</target>
<property name="digester.jar" value="commons-digester-1.7.jar"/>
<property name="collections.jar" value="commons-collections-3.1.jar"/>
<property name="logging.jar" value="commons-logging-1.0.4.jar"/>
<property name="bean-utils.jar" value="commons-beanutils-1.7.0.jar"/>
<path id="classpath">
<pathelement path="${common.dir}/build/classes/java"/>
<pathelement path="${common.dir}/build/classes/demo"/>
<pathelement path="${basedir}/lib/${digester.jar}"/>
<pathelement path="${basedir}/lib/${collections.jar}"/>
<pathelement path="${basedir}/lib/${logging.jar}"/>
<pathelement path="${basedir}/lib/${bean-utils.jar}"/>
</path>
<path id="run.classpath">
<path refid="classpath"/>
<pathelement location="${build.dir}/classes/java"/>
<pathelement location="${benchmark.ext.classpath}"/>
</path>
<target name="run-standard" depends="compile,check-files,get-files" description="Run the standard baseline">
<echo>Working Directory: ${working.dir}</echo>
<java classname="org.apache.lucene.benchmark.Driver" maxmemory="1024M" fork="true">
<classpath refid="run.classpath"/>
<arg line="${working.dir} ${basedir}/conf/standard-config.xml"/>
</java>
</target>
<target name="run-micro-standard" depends="compile,check-files,get-files" description="Run the standard baseline">
<echo>Working Directory: ${working.dir}</echo>
<java classname="org.apache.lucene.benchmark.Driver" maxmemory="1024M" fork="true">
<classpath refid="run.classpath"/>
<arg line="${working.dir} ${basedir}/conf/micro-standard-config.xml"/>
</java>
</target>
<property name="task.alg" value="${basedir}/conf/micro-standard.alg"/>
<property name="task.mem" value="140M"/>
<target name="run-task" depends="compile,check-files,get-files" description="Run compound penalty perf test">
<echo>Working Directory: ${working.dir}</echo>
<java classname="org.apache.lucene.benchmark.byTask.Benchmark" maxmemory="${task.mem}" fork="true">
<classpath refid="run.classpath"/>
<arg line="${task.alg}"/>
</java>
</target>
<target name="compile-demo">
<subant target="compile-demo">
<fileset dir="${common.dir}" includes="build.xml"/>
</subant>
</target>
<target name="init" depends="common.init,compile-demo,check-files"/>
</project>
<?xml version="1.0"?>
<project name="benchmark" default="default">
<description>
Lucene Benchmarking Contributions
</description>
<import file="../contrib-build.xml"/>
<property name="working.dir" value="work"/>
<target name="check-files">
<available file="temp/news20.tar.gz" property="news20.exists"/>
<available file="${working.dir}/20_newsgroup" property="news20.expanded"/>
<available file="temp/reuters21578.tar.gz" property="reuters.exists"/>
<available file="${working.dir}/reuters" property="reuters.expanded"/>
<available file="${working.dir}/reuters-out" property="reuters.extracted"/>
<available file="temp/20news-18828.tar.gz" property="20news-18828.exists"/>
<available file="${working.dir}/20news-18828" property="20news-18828.expanded"/>
<available file="${working.dir}/mini_newsgroups" property="mini.expanded"/>
</target>
<target name="get-news-20" unless="20news-18828.exists">
<get src="http://www-2.cs.cmu.edu/afs/cs.cmu.edu/project/theo-20/www/data/news20.tar.gz"
dest="temp/news20.tar.gz"/>
</target>
<target name="get-reuters" unless="reuters.exists">
<get src="http://www.daviddlewis.com/resources/testcollections/reuters21578/reuters21578.tar.gz"
dest="temp/reuters21578.tar.gz"/>
</target>
<target name="expand-news-20" unless="news20.expanded">
<gunzip src="temp/news20.tar.gz" dest="temp"/>
<untar src="temp/news20.tar" dest="${working.dir}"/>
</target>
<target name="expand-reuters" unless="reuters.expanded">
<gunzip src="temp/reuters21578.tar.gz" dest="temp"/>
<mkdir dir="${working.dir}/reuters"/>
<untar src="temp/reuters21578.tar" dest="${working.dir}/reuters"/>
<delete >
<fileset dir="${working.dir}/reuters">
<include name="*.txt"/>
</fileset>
</delete>
</target>
<target name="extract-reuters" depends="check-files" unless="reuters.extracted">
<mkdir dir="${working.dir}/reuters-out"/>
<java classname="org.apache.lucene.benchmark.utils.ExtractReuters" maxmemory="1024M" fork="true">
<classpath refid="run.classpath"/>
<arg line="${working.dir}/reuters ${working.dir}/reuters-out"/>
</java>
</target>
<target name="get-20news-18828" unless="20news-18828.exists">
<get src="http://people.csail.mit.edu/u/j/jrennie/public_html/20Newsgroups/20news-18828.tar.gz"
dest="temp/20news-18828.tar.gz"/>
</target>
<target name="expand-20news-18828" unless="20news-18828.expanded">
<gunzip src="temp/20news-18828.tar.gz" dest="temp"/>
<untar src="temp/20news-18828.tar" dest="${working.dir}"/>
</target>
<target name="get-mini-news" unless="mini.exists">
<get src="http://kdd.ics.uci.edu/databases/20newsgroups/mini_newsgroups.tar.gz"
dest="temp/mini_newsgroups.tar.gz"/>
</target>
<target name="expand-mini-news" unless="mini.expanded">
<gunzip src="temp/mini_newsgroups.tar.gz" dest="temp"/>
<untar src="temp/mini_newsgroups.tar" dest="${working.dir}"/>
</target>
<target name="get-files" depends="check-files">
<mkdir dir="temp"/>
<antcall target="get-reuters"/>
<antcall target="expand-reuters"/>
<antcall target="extract-reuters"/>
</target>
<property name="digester.jar" value="commons-digester-1.7.jar"/>
<property name="collections.jar" value="commons-collections-3.1.jar"/>
<property name="logging.jar" value="commons-logging-1.0.4.jar"/>
<property name="bean-utils.jar" value="commons-beanutils-1.7.0.jar"/>
<path id="classpath">
<pathelement path="${common.dir}/build/classes/java"/>
<pathelement path="${common.dir}/build/classes/demo"/>
<pathelement path="${basedir}/lib/${digester.jar}"/>
<pathelement path="${basedir}/lib/${collections.jar}"/>
<pathelement path="${basedir}/lib/${logging.jar}"/>
<pathelement path="${basedir}/lib/${bean-utils.jar}"/>
</path>
<path id="run.classpath">
<path refid="classpath"/>
<pathelement location="${build.dir}/classes/java"/>
<pathelement location="${benchmark.ext.classpath}"/>
</path>
<target name="run-standard" depends="compile,check-files,get-files" description="Run the standard baseline">
<echo>Working Directory: ${working.dir}</echo>
<java classname="org.apache.lucene.benchmark.Driver" maxmemory="1024M" fork="true">
<classpath refid="run.classpath"/>
<arg line="${working.dir} ${basedir}/conf/standard-config.xml"/>
</java>
</target>
<target name="run-micro-standard" depends="compile,check-files,get-files" description="Run the standard baseline">
<echo>Working Directory: ${working.dir}</echo>
<java classname="org.apache.lucene.benchmark.Driver" maxmemory="1024M" fork="true">
<classpath refid="run.classpath"/>
<arg line="${working.dir} ${basedir}/conf/micro-standard-config.xml"/>
</java>
</target>
<property name="task.alg" value="${basedir}/conf/micro-standard.alg"/>
<property name="task.mem" value="140M"/>
<target name="run-task" depends="compile,check-files,get-files" description="Run compound penalty perf test">
<echo>Working Directory: ${working.dir}</echo>
<java classname="org.apache.lucene.benchmark.byTask.Benchmark" maxmemory="${task.mem}" fork="true">
<classpath refid="run.classpath"/>
<arg line="${task.alg}"/>
</java>
</target>
<target name="compile-demo">
<subant target="compile-demo">
<fileset dir="${common.dir}" includes="build.xml"/>
</subant>
</target>
<target name="init" depends="common.init,compile-demo,check-files"/>
</project>

View File

@ -1,93 +1,93 @@
#/**
# * 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.
# */
# --------------------------------------------------------
# Compound: what is the cost of compound format in indexing?
# It does twice as much IO, is it twice slower? (no)
# --------------------------------------------------------
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
merge.factor=mrg:10
max.buffered=buf:10
compound=compnd:true:false
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=stored:true:true:false:false
doc.tokenized=true
doc.term.vector=vector:true:true:false:false
doc.add.log.step=500
doc.delete.log.step=100
docs.dir=reuters-out
#docs.dir=reuters-111
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=1
log.queries=false
# -------------------------------------------------------------------------------------
ResetSystemErase
{ "Round"
CreateIndex
{ "AddDocs" AddDoc > : 10000
CloseIndex
OpenReader
{ "SearchSameRdr" Search > : 500
CloseReader
{ "WarmNewRdr" Warm > : 50
{ "SrchNewRdr" Search > : 500
{ "SrchTrvNewRdr" SearchTrav > : 300
{ "SrchTrvRetNewRdr" SearchTravRet > : 100
[ "WarmNewRdr" Warm > : 50
[ "SrchNewRdr" Search > : 500
[ "SrchTrvNewRdr" SearchTrav > : 300
[ "SrchTrvRetNewRdr" SearchTravRet > : 100
ResetInputs
RepSumByName
NewRound
} : 4
RepSumByName
RepSumByNameRound
RepSumByPrefRound AddDocs
RepSumByPrefRound SearchSameRdr
RepSumByPrefRound WarmNewRdr
RepSumByPrefRound SrchTrvNewRdr
RepSumByPrefRound SrchTrvRetNewRdr
#/**
# * 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.
# */
# --------------------------------------------------------
# Compound: what is the cost of compound format in indexing?
# It does twice as much IO, is it twice slower? (no)
# --------------------------------------------------------
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
merge.factor=mrg:10
max.buffered=buf:10
compound=compnd:true:false
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=stored:true:true:false:false
doc.tokenized=true
doc.term.vector=vector:true:true:false:false
doc.add.log.step=500
doc.delete.log.step=100
docs.dir=reuters-out
#docs.dir=reuters-111
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=1
log.queries=false
# -------------------------------------------------------------------------------------
ResetSystemErase
{ "Round"
CreateIndex
{ "AddDocs" AddDoc > : 10000
CloseIndex
OpenReader
{ "SearchSameRdr" Search > : 500
CloseReader
{ "WarmNewRdr" Warm > : 50
{ "SrchNewRdr" Search > : 500
{ "SrchTrvNewRdr" SearchTrav > : 300
{ "SrchTrvRetNewRdr" SearchTravRet > : 100
[ "WarmNewRdr" Warm > : 50
[ "SrchNewRdr" Search > : 500
[ "SrchTrvNewRdr" SearchTrav > : 300
[ "SrchTrvRetNewRdr" SearchTravRet > : 100
ResetInputs
RepSumByName
NewRound
} : 4
RepSumByName
RepSumByNameRound
RepSumByPrefRound AddDocs
RepSumByPrefRound SearchSameRdr
RepSumByPrefRound WarmNewRdr
RepSumByPrefRound SrchTrvNewRdr
RepSumByPrefRound SrchTrvRetNewRdr

View File

@ -1,70 +1,70 @@
#/**
# * 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.
# */
# --------------------------------------------------------
# Deletes: what is the cost of deleting documents?
# --------------------------------------------------------
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
merge.factor=mrg:10
max.buffered=buf:100
compound=true
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=true
doc.tokenized=true
doc.term.vector=false
doc.add.log.step=10000
doc.delete.log.step=100
docs.dir=reuters-out
#docs.dir=reuters-111
doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=1
log.queries=false
# -------------------------------------------------------------------------------------
ResetSystemErase
CreateIndex
CloseIndex
{ "Populate"
OpenIndex
{ AddDoc(10) > : 200000
Optimize
CloseIndex
>
{ "Deletions"
OpenReader DeleteDoc CloseReader
} : 4000
RepSumByName
#/**
# * 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.
# */
# --------------------------------------------------------
# Deletes: what is the cost of deleting documents?
# --------------------------------------------------------
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
merge.factor=mrg:10
max.buffered=buf:100
compound=true
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=true
doc.tokenized=true
doc.term.vector=false
doc.add.log.step=10000
doc.delete.log.step=100
docs.dir=reuters-out
#docs.dir=reuters-111
doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=1
log.queries=false
# -------------------------------------------------------------------------------------
ResetSystemErase
CreateIndex
CloseIndex
{ "Populate"
OpenIndex
{ AddDoc(10) > : 200000
Optimize
CloseIndex
>
{ "Deletions"
OpenReader DeleteDoc CloseReader
} : 4000
RepSumByName

View File

@ -1,76 +1,76 @@
#/**
# * 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.
# */
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
merge.factor=mrg:10:100:10:100
max.buffered=buf:10:10:100:100
compound=true
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=true
doc.tokenized=true
doc.term.vector=false
doc.add.log.step=500
docs.dir=reuters-out
#docs.dir=reuters-111
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=2
log.queries=true
# -------------------------------------------------------------------------------------
{ "Rounds"
ResetSystemErase
{ "Populate"
CreateIndex
{ "MAddDocs" AddDoc > : 2000
Optimize
CloseIndex
}
OpenReader
{ "SearchSameRdr" Search > : 5000
CloseReader
{ "WarmNewRdr" Warm > : 50
{ "SrchNewRdr" Search > : 500
{ "SrchTrvNewRdr" SearchTrav(1000) > : 300
{ "SrchTrvRetNewRdr" SearchTravRet(2000) > : 100
NewRound
} : 4
RepSumByName
RepSumByPrefRound MAddDocs
#/**
# * 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.
# */
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
merge.factor=mrg:10:100:10:100
max.buffered=buf:10:10:100:100
compound=true
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=true
doc.tokenized=true
doc.term.vector=false
doc.add.log.step=500
docs.dir=reuters-out
#docs.dir=reuters-111
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=2
log.queries=true
# -------------------------------------------------------------------------------------
{ "Rounds"
ResetSystemErase
{ "Populate"
CreateIndex
{ "MAddDocs" AddDoc > : 2000
Optimize
CloseIndex
}
OpenReader
{ "SearchSameRdr" Search > : 5000
CloseReader
{ "WarmNewRdr" Warm > : 50
{ "SrchNewRdr" Search > : 500
{ "SrchTrvNewRdr" SearchTrav(1000) > : 300
{ "SrchTrvRetNewRdr" SearchTravRet(2000) > : 100
NewRound
} : 4
RepSumByName
RepSumByPrefRound MAddDocs

View File

@ -1,85 +1,85 @@
#/**
# * 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.
# */
# --------------------------------------------------------
#
# Sample: what is the effect of doc size on indexing time?
#
# There are two parts in this test:
# - PopulateShort adds 2N documents of length L
# - PopulateLong adds N documents of length 2L
# Which one would be faster?
# The comparison is done twice.
#
# --------------------------------------------------------
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
merge.factor=mrg:10:20
max.buffered=buf:100:1000
compound=true
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=true
doc.tokenized=true
doc.term.vector=false
doc.add.log.step=500
docs.dir=reuters-out
#docs.dir=reuters-111
doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=2
log.queries=false
# -------------------------------------------------------------------------------------
{
{ "PopulateShort"
CreateIndex
{ AddDoc(4000) > : 20000
Optimize
CloseIndex
>
ResetSystemErase
{ "PopulateLong"
CreateIndex
{ AddDoc(8000) > : 10000
Optimize
CloseIndex
>
ResetSystemErase
NewRound
} : 2
RepSumByName
RepSelectByPref Populate
#/**
# * 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.
# */
# --------------------------------------------------------
#
# Sample: what is the effect of doc size on indexing time?
#
# There are two parts in this test:
# - PopulateShort adds 2N documents of length L
# - PopulateLong adds N documents of length 2L
# Which one would be faster?
# The comparison is done twice.
#
# --------------------------------------------------------
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
merge.factor=mrg:10:20
max.buffered=buf:100:1000
compound=true
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=true
doc.tokenized=true
doc.term.vector=false
doc.add.log.step=500
docs.dir=reuters-out
#docs.dir=reuters-111
doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=2
log.queries=false
# -------------------------------------------------------------------------------------
{
{ "PopulateShort"
CreateIndex
{ AddDoc(4000) > : 20000
Optimize
CloseIndex
>
ResetSystemErase
{ "PopulateLong"
CreateIndex
{ AddDoc(8000) > : 10000
Optimize
CloseIndex
>
ResetSystemErase
NewRound
} : 2
RepSumByName
RepSelectByPref Populate

View File

@ -1,74 +1,74 @@
#/**
# * 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.
# */
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
max.buffered=100
merge.factor=10
compound=true
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=false
doc.tokenized=true
doc.term.vector=false
doc.add.log.step=500
docs.dir=reuters-out
#docs.dir=reuters-111
doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleSloppyPhraseQueryMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=1
log.queries=false
# -------------------------------------------------------------------------------------
ResetSystemErase
{ "Populate"
CreateIndex
{ "MAddDocs" AddDoc(2000) > : 20000
Optimize
CloseIndex
}
{ "Round"
OpenReader
{ "SearchSameRdr" Search > : 6000
CloseReader
ResetInputs
RepSumByName
NewRound
} : 4
RepSumByPrefRound MAddDocs
RepSumByName
RepSumByPrefRound Search
#/**
# * 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.
# */
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
max.buffered=100
merge.factor=10
compound=true
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=false
doc.tokenized=true
doc.term.vector=false
doc.add.log.step=500
docs.dir=reuters-out
#docs.dir=reuters-111
doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleSloppyPhraseQueryMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=1
log.queries=false
# -------------------------------------------------------------------------------------
ResetSystemErase
{ "Populate"
CreateIndex
{ "MAddDocs" AddDoc(2000) > : 20000
Optimize
CloseIndex
}
{ "Round"
OpenReader
{ "SearchSameRdr" Search > : 6000
CloseReader
ResetInputs
RepSumByName
NewRound
} : 4
RepSumByPrefRound MAddDocs
RepSumByName
RepSumByPrefRound Search

View File

@ -1,91 +1,91 @@
#/**
# * 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.
# */
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
merge.factor=mrg:10:100:10:100:10:100:10:100
max.buffered=buf:10:10:100:100:10:10:100:100
compound=cmpnd:true:true:true:true:false:false:false:false
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=true
doc.tokenized=true
doc.term.vector=false
doc.add.log.step=2000
docs.dir=reuters-out
#docs.dir=reuters-111
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=2
log.queries=true
# -------------------------------------------------------------------------------------
{ "Rounds"
ResetSystemErase
{ "Populate"
CreateIndex
{ "MAddDocs" AddDoc } : 20000
Optimize
CloseIndex
}
OpenReader
{ "SearchSameRdr" Search > : 5000
CloseReader
{ "WarmNewRdr" Warm > : 50
{ "SrchNewRdr" Search > : 500
{ "SrchTrvNewRdr" SearchTrav > : 300
{ "SrchTrvRetNewRdr" SearchTravRet > : 100
OpenReader
[ "SearchSameRdr" Search > : 5000 : 2500
CloseReader
[ "WarmNewRdr" Warm > : 50 : 25
[ "SrchNewRdr" Search > : 50 : 25
[ "SrchTrvNewRdr" SearchTrav > : 300 : 150
[ "SrchTrvRetNewRdr" SearchTravRet > : 100 : 50
RepSumByPref MAddDocs
NewRound
} : 8
RepSumByNameRound
RepSumByName
RepSumByPrefRound MAddDocs
#/**
# * 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.
# */
# -------------------------------------------------------------------------------------
# multi val params are iterated by NewRound's, added to reports, start with column name.
merge.factor=mrg:10:100:10:100:10:100:10:100
max.buffered=buf:10:10:100:100:10:10:100:100
compound=cmpnd:true:true:true:true:false:false:false:false
analyzer=org.apache.lucene.analysis.standard.StandardAnalyzer
directory=FSDirectory
#directory=RamDirectory
doc.stored=true
doc.tokenized=true
doc.term.vector=false
doc.add.log.step=2000
docs.dir=reuters-out
#docs.dir=reuters-111
#doc.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleDocMaker
doc.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersDocMaker
#query.maker=org.apache.lucene.benchmark.byTask.feeds.SimpleQueryMaker
query.maker=org.apache.lucene.benchmark.byTask.feeds.ReutersQueryMaker
# task at this depth or less would print when they start
task.max.depth.log=2
log.queries=true
# -------------------------------------------------------------------------------------
{ "Rounds"
ResetSystemErase
{ "Populate"
CreateIndex
{ "MAddDocs" AddDoc } : 20000
Optimize
CloseIndex
}
OpenReader
{ "SearchSameRdr" Search > : 5000
CloseReader
{ "WarmNewRdr" Warm > : 50
{ "SrchNewRdr" Search > : 500
{ "SrchTrvNewRdr" SearchTrav > : 300
{ "SrchTrvRetNewRdr" SearchTravRet > : 100
OpenReader
[ "SearchSameRdr" Search > : 5000 : 2500
CloseReader
[ "WarmNewRdr" Warm > : 50 : 25
[ "SrchNewRdr" Search > : 50 : 25
[ "SrchTrvNewRdr" SearchTrav > : 300 : 150
[ "SrchTrvRetNewRdr" SearchTravRet > : 100 : 50
RepSumByPref MAddDocs
NewRound
} : 8
RepSumByNameRound
RepSumByName
RepSumByPrefRound MAddDocs

View File

@ -1,6 +1,6 @@
<html>
<body>
Sources for benchmark inputs: documents and queries.
</body>
</html>
<html>
<body>
Sources for benchmark inputs: documents and queries.
</body>
</html>

View File

@ -1,5 +1,5 @@
<html>
<body>
Sample performance test written programatically - no algorithm file is needed here.
</body>
<html>
<body>
Sample performance test written programatically - no algorithm file is needed here.
</body>
</html>

View File

@ -1,5 +1,5 @@
<html>
<body>
Statistics maintained when running benchmark tasks.
</body>
</html>
<html>
<body>
Statistics maintained when running benchmark tasks.
</body>
</html>

View File

@ -1,9 +1,9 @@
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<meta name="Author" content="Doron Cohen">
</head>
<body>
Extendable benchmark tasks.
</body>
</html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<meta name="Author" content="Doron Cohen">
</head>
<body>
Extendable benchmark tasks.
</body>
</html>

View File

@ -1,5 +1,5 @@
<html>
<body>
Utilities used for the benchmark, and for the reports.
</body>
</html>
<html>
<body>
Utilities used for the benchmark, and for the reports.
</body>
</html>