mirror of
https://github.com/honeymoose/OpenSearch.git
synced 2025-02-06 13:08:29 +00:00
fadbe0de08
Today we require users to prepare their indices for split operations. Yet, we can do this automatically when an index is created which would make the split feature a much more appealing option since it doesn't have any 3rd party prerequisites anymore. This change automatically sets the number of routinng shards such that an index is guaranteed to be able to split once into twice as many shards. The number of routing shards is scaled towards the default shard limit per index such that indices with a smaller amount of shards can be split more often than larger ones. For instance an index with 1 or 2 shards can be split 10x (until it approaches 1024 shards) while an index created with 128 shards can only be split 3x by a factor of 2. Please note this is just a default value and users can still prepare their indices with `index.number_of_routing_shards` for custom splitting. NOTE: this change has an impact on the document distribution since we are changing the hash space. Documents are still uniformly distributed across all shards but since we are artificually changing the number of buckets in the consistent hashign space document might be hashed into different shards compared to previous versions. This is a 7.0 only change.
522 lines
16 KiB
Groovy
522 lines
16 KiB
Groovy
/*
|
|
* Licensed to Elasticsearch under one or more contributor
|
|
* license agreements. See the NOTICE file distributed with
|
|
* this work for additional information regarding copyright
|
|
* ownership. Elasticsearch 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.
|
|
*/
|
|
|
|
apply plugin: 'elasticsearch.docs-test'
|
|
|
|
integTestCluster {
|
|
/* Enable regexes in painless so our tests don't complain about example
|
|
* snippets that use them. */
|
|
setting 'script.painless.regex.enabled', 'true'
|
|
Closure configFile = {
|
|
extraConfigFile it, "src/test/cluster/config/$it"
|
|
}
|
|
configFile 'analysis/example_word_list.txt'
|
|
configFile 'analysis/hyphenation_patterns.xml'
|
|
configFile 'analysis/synonym.txt'
|
|
configFile 'analysis/stemmer_override.txt'
|
|
configFile 'userdict_ja.txt'
|
|
configFile 'KeywordTokenizer.rbbi'
|
|
extraConfigFile 'hunspell/en_US/en_US.aff', '../core/src/test/resources/indices/analyze/conf_dir/hunspell/en_US/en_US.aff'
|
|
extraConfigFile 'hunspell/en_US/en_US.dic', '../core/src/test/resources/indices/analyze/conf_dir/hunspell/en_US/en_US.dic'
|
|
// Whitelist reindexing from the local node so we can test it.
|
|
setting 'reindex.remote.whitelist', '127.0.0.1:*'
|
|
}
|
|
|
|
// Build the cluster with all plugins
|
|
|
|
project.rootProject.subprojects.findAll { it.parent.path == ':plugins' }.each { subproj ->
|
|
/* Skip repositories. We just aren't going to be able to test them so it
|
|
* doesn't make sense to waste time installing them. */
|
|
if (subproj.path.startsWith(':plugins:repository-')) {
|
|
return
|
|
}
|
|
subproj.afterEvaluate { // need to wait until the project has been configured
|
|
integTestCluster {
|
|
plugin subproj.path
|
|
}
|
|
}
|
|
}
|
|
|
|
buildRestTests.docs = fileTree(projectDir) {
|
|
// No snippets in here!
|
|
exclude 'build.gradle'
|
|
// That is where the snippets go, not where they come from!
|
|
exclude 'build'
|
|
}
|
|
|
|
Closure setupTwitter = { String name, int count ->
|
|
buildRestTests.setups[name] = '''
|
|
- do:
|
|
indices.create:
|
|
index: twitter
|
|
body:
|
|
settings:
|
|
number_of_shards: 1
|
|
number_of_replicas: 1
|
|
mappings:
|
|
tweet:
|
|
properties:
|
|
user:
|
|
type: keyword
|
|
doc_values: true
|
|
date:
|
|
type: date
|
|
likes:
|
|
type: long
|
|
- do:
|
|
bulk:
|
|
index: twitter
|
|
type: tweet
|
|
refresh: true
|
|
body: |'''
|
|
for (int i = 0; i < count; i++) {
|
|
String user, text
|
|
if (i == 0) {
|
|
user = 'kimchy'
|
|
text = 'trying out Elasticsearch'
|
|
} else {
|
|
user = 'test'
|
|
text = "some message with the number $i"
|
|
}
|
|
buildRestTests.setups[name] += """
|
|
{"index":{"_id": "$i"}}
|
|
{"user": "$user", "message": "$text", "date": "2009-11-15T14:12:12", "likes": $i}"""
|
|
}
|
|
}
|
|
setupTwitter('twitter', 5)
|
|
setupTwitter('big_twitter', 120)
|
|
setupTwitter('huge_twitter', 1200)
|
|
|
|
buildRestTests.setups['host'] = '''
|
|
# Fetch the http host. We use the host of the master because we know there will always be a master.
|
|
- do:
|
|
cluster.state: {}
|
|
- set: { master_node: master }
|
|
- do:
|
|
nodes.info:
|
|
metric: [ http, transport ]
|
|
- is_true: nodes.$master.http.publish_address
|
|
- set: {nodes.$master.http.publish_address: host}
|
|
- set: {nodes.$master.transport.publish_address: transport_host}
|
|
'''
|
|
|
|
buildRestTests.setups['node'] = '''
|
|
# Fetch the node name. We use the host of the master because we know there will always be a master.
|
|
- do:
|
|
cluster.state: {}
|
|
- is_true: master_node
|
|
- set: { master_node: node_name }
|
|
'''
|
|
|
|
// Used by scripted metric docs
|
|
buildRestTests.setups['ledger'] = '''
|
|
- do:
|
|
indices.create:
|
|
index: ledger
|
|
body:
|
|
settings:
|
|
number_of_shards: 2
|
|
number_of_replicas: 1
|
|
mappings:
|
|
sale:
|
|
properties:
|
|
type:
|
|
type: keyword
|
|
amount:
|
|
type: double
|
|
- do:
|
|
bulk:
|
|
index: ledger
|
|
type: sale
|
|
refresh: true
|
|
body: |
|
|
{"index":{}}
|
|
{"date": "2015/01/01 00:00:00", "amount": 200, "type": "sale", "description": "something"}
|
|
{"index":{}}
|
|
{"date": "2015/01/01 00:00:00", "amount": 10, "type": "expense", "decription": "another thing"}
|
|
{"index":{}}
|
|
{"date": "2015/01/01 00:00:00", "amount": 150, "type": "sale", "description": "blah"}
|
|
{"index":{}}
|
|
{"date": "2015/01/01 00:00:00", "amount": 50, "type": "expense", "description": "cost of blah"}
|
|
{"index":{}}
|
|
{"date": "2015/01/01 00:00:00", "amount": 50, "type": "expense", "description": "advertisement"}'''
|
|
|
|
// Used by aggregation docs
|
|
buildRestTests.setups['sales'] = '''
|
|
- do:
|
|
indices.create:
|
|
index: sales
|
|
body:
|
|
settings:
|
|
number_of_shards: 2
|
|
number_of_replicas: 1
|
|
mappings:
|
|
sale:
|
|
properties:
|
|
type:
|
|
type: keyword
|
|
- do:
|
|
bulk:
|
|
index: sales
|
|
type: sale
|
|
refresh: true
|
|
body: |
|
|
{"index":{}}
|
|
{"date": "2015/01/01 00:00:00", "price": 200, "promoted": true, "rating": 1, "type": "hat"}
|
|
{"index":{}}
|
|
{"date": "2015/01/01 00:00:00", "price": 200, "promoted": true, "rating": 1, "type": "t-shirt"}
|
|
{"index":{}}
|
|
{"date": "2015/01/01 00:00:00", "price": 150, "promoted": true, "rating": 5, "type": "bag"}
|
|
{"index":{}}
|
|
{"date": "2015/02/01 00:00:00", "price": 50, "promoted": false, "rating": 1, "type": "hat"}
|
|
{"index":{}}
|
|
{"date": "2015/02/01 00:00:00", "price": 10, "promoted": true, "rating": 4, "type": "t-shirt"}
|
|
{"index":{}}
|
|
{"date": "2015/03/01 00:00:00", "price": 200, "promoted": true, "rating": 1, "type": "hat"}
|
|
{"index":{}}
|
|
{"date": "2015/03/01 00:00:00", "price": 175, "promoted": false, "rating": 2, "type": "t-shirt"}'''
|
|
|
|
// Dummy bank account data used by getting-started.asciidoc
|
|
buildRestTests.setups['bank'] = '''
|
|
- do:
|
|
indices.create:
|
|
index: bank
|
|
body:
|
|
settings:
|
|
number_of_shards: 5
|
|
number_of_routing_shards: 5
|
|
- do:
|
|
bulk:
|
|
index: bank
|
|
type: account
|
|
refresh: true
|
|
body: |
|
|
#bank_data#
|
|
'''
|
|
/* Load the actual accounts only if we're going to use them. This complicates
|
|
* dependency checking but that is a small price to pay for not building a
|
|
* 400kb string every time we start the build. */
|
|
File accountsFile = new File("$projectDir/src/test/resources/accounts.json")
|
|
buildRestTests.inputs.file(accountsFile)
|
|
buildRestTests.doFirst {
|
|
String accounts = accountsFile.getText('UTF-8')
|
|
// Indent like a yaml test needs
|
|
accounts = accounts.replaceAll('(?m)^', ' ')
|
|
buildRestTests.setups['bank'] =
|
|
buildRestTests.setups['bank'].replace('#bank_data#', accounts)
|
|
}
|
|
|
|
buildRestTests.setups['range_index'] = '''
|
|
- do :
|
|
indices.create:
|
|
index: range_index
|
|
body:
|
|
settings:
|
|
number_of_shards: 2
|
|
number_of_replicas: 1
|
|
mappings:
|
|
my_type:
|
|
properties:
|
|
expected_attendees:
|
|
type: integer_range
|
|
time_frame:
|
|
type: date_range
|
|
format: yyyy-MM-dd HH:mm:ss||yyyy-MM-dd||epoch_millis
|
|
- do:
|
|
bulk:
|
|
index: range_index
|
|
type: my_type
|
|
refresh: true
|
|
body: |
|
|
{"index":{"_id": 1}}
|
|
{"expected_attendees": {"gte": 10, "lte": 20}, "time_frame": {"gte": "2015-10-31 12:00:00", "lte": "2015-11-01"}}'''
|
|
|
|
// Used by index boost doc
|
|
buildRestTests.setups['index_boost'] = '''
|
|
- do:
|
|
indices.create:
|
|
index: index1
|
|
- do:
|
|
indices.create:
|
|
index: index2
|
|
|
|
- do:
|
|
indices.put_alias:
|
|
index: index1
|
|
name: alias1
|
|
'''
|
|
// Used by sampler and diversified-sampler aggregation docs
|
|
buildRestTests.setups['stackoverflow'] = '''
|
|
- do:
|
|
indices.create:
|
|
index: stackoverflow
|
|
body:
|
|
settings:
|
|
number_of_shards: 1
|
|
number_of_replicas: 1
|
|
mappings:
|
|
question:
|
|
properties:
|
|
author:
|
|
type: keyword
|
|
tags:
|
|
type: keyword
|
|
- do:
|
|
bulk:
|
|
index: stackoverflow
|
|
type: question
|
|
refresh: true
|
|
body: |'''
|
|
|
|
// Make Kibana strongly connected to elasticsearch and logstash
|
|
// Make Kibana rarer (and therefore higher-ranking) than Javascript
|
|
// Make Javascript strongly connected to jquery and angular
|
|
// Make Cabana strongly connected to elasticsearch but only as a result of a single author
|
|
|
|
for (int i = 0; i < 150; i++) {
|
|
buildRestTests.setups['stackoverflow'] += """
|
|
{"index":{}}
|
|
{"author": "very_relevant_$i", "tags": ["elasticsearch", "kibana"]}"""
|
|
}
|
|
for (int i = 0; i < 50; i++) {
|
|
buildRestTests.setups['stackoverflow'] += """
|
|
{"index":{}}
|
|
{"author": "very_relevant_$i", "tags": ["logstash", "kibana"]}"""
|
|
}
|
|
for (int i = 0; i < 200; i++) {
|
|
buildRestTests.setups['stackoverflow'] += """
|
|
{"index":{}}
|
|
{"author": "partially_relevant_$i", "tags": ["javascript", "jquery"]}"""
|
|
}
|
|
for (int i = 0; i < 200; i++) {
|
|
buildRestTests.setups['stackoverflow'] += """
|
|
{"index":{}}
|
|
{"author": "partially_relevant_$i", "tags": ["javascript", "angular"]}"""
|
|
}
|
|
for (int i = 0; i < 50; i++) {
|
|
buildRestTests.setups['stackoverflow'] += """
|
|
{"index":{}}
|
|
{"author": "noisy author", "tags": ["elasticsearch", "cabana"]}"""
|
|
}
|
|
buildRestTests.setups['stackoverflow'] += """
|
|
"""
|
|
// Used by significant_text aggregation docs
|
|
buildRestTests.setups['news'] = '''
|
|
- do:
|
|
indices.create:
|
|
index: news
|
|
body:
|
|
settings:
|
|
number_of_shards: 1
|
|
number_of_replicas: 1
|
|
mappings:
|
|
question:
|
|
properties:
|
|
source:
|
|
type: keyword
|
|
content:
|
|
type: text
|
|
- do:
|
|
bulk:
|
|
index: news
|
|
type: article
|
|
refresh: true
|
|
body: |'''
|
|
|
|
// Make h5n1 strongly connected to bird flu
|
|
|
|
for (int i = 0; i < 100; i++) {
|
|
buildRestTests.setups['news'] += """
|
|
{"index":{}}
|
|
{"source": "very_relevant_$i", "content": "bird flu h5n1"}"""
|
|
}
|
|
for (int i = 0; i < 100; i++) {
|
|
buildRestTests.setups['news'] += """
|
|
{"index":{}}
|
|
{"source": "filler_$i", "content": "bird dupFiller "}"""
|
|
}
|
|
for (int i = 0; i < 100; i++) {
|
|
buildRestTests.setups['news'] += """
|
|
{"index":{}}
|
|
{"source": "filler_$i", "content": "flu dupFiller "}"""
|
|
}
|
|
for (int i = 0; i < 20; i++) {
|
|
buildRestTests.setups['news'] += """
|
|
{"index":{}}
|
|
{"source": "partially_relevant_$i", "content": "elasticsearch dupFiller dupFiller dupFiller dupFiller pozmantier"}"""
|
|
}
|
|
for (int i = 0; i < 10; i++) {
|
|
buildRestTests.setups['news'] += """
|
|
{"index":{}}
|
|
{"source": "partially_relevant_$i", "content": "elasticsearch logstash kibana"}"""
|
|
}
|
|
buildRestTests.setups['news'] += """
|
|
"""
|
|
|
|
// Used by some aggregations
|
|
buildRestTests.setups['exams'] = '''
|
|
- do:
|
|
indices.create:
|
|
index: exams
|
|
body:
|
|
settings:
|
|
number_of_shards: 1
|
|
number_of_replicas: 1
|
|
mappings:
|
|
exam:
|
|
properties:
|
|
grade:
|
|
type: byte
|
|
- do:
|
|
bulk:
|
|
index: exams
|
|
type: exam
|
|
refresh: true
|
|
body: |
|
|
{"index":{}}
|
|
{"grade": 100}
|
|
{"index":{}}
|
|
{"grade": 50}'''
|
|
|
|
buildRestTests.setups['stored_example_script'] = '''
|
|
# Simple script to load a field. Not really a good example, but a simple one.
|
|
- do:
|
|
put_script:
|
|
id: "my_script"
|
|
body: { "script": { "lang": "painless", "source": "doc[params.field].value" } }
|
|
- match: { acknowledged: true }
|
|
'''
|
|
|
|
buildRestTests.setups['stored_scripted_metric_script'] = '''
|
|
- do:
|
|
put_script:
|
|
id: "my_init_script"
|
|
body: { "script": { "lang": "painless", "source": "params._agg.transactions = []" } }
|
|
- match: { acknowledged: true }
|
|
|
|
- do:
|
|
put_script:
|
|
id: "my_map_script"
|
|
body: { "script": { "lang": "painless", "source": "params._agg.transactions.add(doc.type.value == 'sale' ? doc.amount.value : -1 * doc.amount.value)" } }
|
|
- match: { acknowledged: true }
|
|
|
|
- do:
|
|
put_script:
|
|
id: "my_combine_script"
|
|
body: { "script": { "lang": "painless", "source": "double profit = 0;for (t in params._agg.transactions) { profit += t; } return profit" } }
|
|
- match: { acknowledged: true }
|
|
|
|
- do:
|
|
put_script:
|
|
id: "my_reduce_script"
|
|
body: { "script": { "lang": "painless", "source": "double profit = 0;for (a in params._aggs) { profit += a; } return profit" } }
|
|
- match: { acknowledged: true }
|
|
'''
|
|
|
|
// Used by analyze api
|
|
buildRestTests.setups['analyze_sample'] = '''
|
|
- do:
|
|
indices.create:
|
|
index: analyze_sample
|
|
body:
|
|
settings:
|
|
number_of_shards: 1
|
|
number_of_replicas: 0
|
|
analysis:
|
|
normalizer:
|
|
my_normalizer:
|
|
type: custom
|
|
filter: [lowercase]
|
|
mappings:
|
|
tweet:
|
|
properties:
|
|
obj1.field1:
|
|
type: text'''
|
|
|
|
// Used by percentile/percentile-rank aggregations
|
|
buildRestTests.setups['latency'] = '''
|
|
- do:
|
|
indices.create:
|
|
index: latency
|
|
body:
|
|
settings:
|
|
number_of_shards: 1
|
|
number_of_replicas: 1
|
|
mappings:
|
|
data:
|
|
properties:
|
|
load_time:
|
|
type: long
|
|
- do:
|
|
bulk:
|
|
index: latency
|
|
type: data
|
|
refresh: true
|
|
body: |'''
|
|
|
|
|
|
for (int i = 0; i < 100; i++) {
|
|
def value = i
|
|
if (i % 10) {
|
|
value = i*10
|
|
}
|
|
buildRestTests.setups['latency'] += """
|
|
{"index":{}}
|
|
{"load_time": "$value"}"""
|
|
}
|
|
|
|
// Used by iprange agg
|
|
buildRestTests.setups['iprange'] = '''
|
|
- do:
|
|
indices.create:
|
|
index: ip_addresses
|
|
body:
|
|
settings:
|
|
number_of_shards: 1
|
|
number_of_replicas: 1
|
|
mappings:
|
|
data:
|
|
properties:
|
|
ip:
|
|
type: ip
|
|
- do:
|
|
bulk:
|
|
index: ip_addresses
|
|
type: data
|
|
refresh: true
|
|
body: |'''
|
|
|
|
|
|
for (int i = 0; i < 255; i++) {
|
|
buildRestTests.setups['iprange'] += """
|
|
{"index":{}}
|
|
{"ip": "10.0.0.$i"}"""
|
|
}
|
|
for (int i = 0; i < 5; i++) {
|
|
buildRestTests.setups['iprange'] += """
|
|
{"index":{}}
|
|
{"ip": "9.0.0.$i"}"""
|
|
buildRestTests.setups['iprange'] += """
|
|
{"index":{}}
|
|
{"ip": "11.0.0.$i"}"""
|
|
buildRestTests.setups['iprange'] += """
|
|
{"index":{}}
|
|
{"ip": "12.0.0.$i"}"""
|
|
}
|