yexinru/doc-exports
1
0
Fork 0
forked from docs/doc-exports
Code Pull Requests Activity
Files
a41a4e0331fbc0beff63bb28fa59228cc9a751df
doc-exports/docs/css/umn/css_01_0173.html
zhengxiu 93d856d5c5 css umn 25.6.0 version 
Reviewed-by: Pruthi, Vineet <vineet.pruthi@t-systems.com>
Co-authored-by: zhengxiu <zhengxiu@huawei.com>
Co-committed-by: zhengxiu <zhengxiu@huawei.com>
2025-11-25 11:34:43 +00:00

877 lines
69 KiB
HTML
Raw Blame History

<a name="EN-US_TOPIC_0000001938377556"></a><a name="EN-US_TOPIC_0000001938377556"></a>
<h1 class="topictitle1">Configuring Enhanced Aggregation for an Elasticsearch Cluster</h1>
<div id="body0000001080755515"><p id="EN-US_TOPIC_0000001938377556__p1411873495616">CSS Elasticsearch clusters enhance aggregation performance in the face of large data volumes by leveraging vectorization and optimized clustering, enabling faster analytics and decision-making in complex situations.</p>
<div class="section" id="EN-US_TOPIC_0000001938377556__section20798162114246"><h4 class="sectiontitle">How the Feature Works</h4><div class="p" id="EN-US_TOPIC_0000001938377556__p12670194615815">Enhanced aggregation works by pre-sorting and physically clustering data using carefully selected sorting and clustering keys, thereby minimizing data scanning and computational overheads during aggregation.<ul id="EN-US_TOPIC_0000001938377556__ul37581221901"><li id="EN-US_TOPIC_0000001938377556__li2075832117013">Sorting key: A field (such as timestamps) used to physically order documents on disk, ensuring that documents with identical or similar sorting key values are stored contiguously.</li><li id="EN-US_TOPIC_0000001938377556__li107581121905">Clustering key: A subset of fields from the sorting key that groups related documents into contiguous physical blocks. This way, aggregations can process contiguous data blocks, instead of scattered documents.</li></ul>
</div>
<div class="tablenoborder"><table cellpadding="4" cellspacing="0" summary="" id="EN-US_TOPIC_0000001938377556__table4445153814017" frame="border" border="1" rules="all"><caption><b>Table 1 </b>Common scenarios for enhanced aggregation</caption><thead align="left"><tr id="EN-US_TOPIC_0000001938377556__row544518387406"><th align="left" class="cellrowborder" valign="top" width="30%" id="mcps1.3.2.3.2.3.1.1"><p id="EN-US_TOPIC_0000001938377556__p1446638124017">Scenario</p>
</th>
<th align="left" class="cellrowborder" valign="top" width="70%" id="mcps1.3.2.3.2.3.1.2"><p id="EN-US_TOPIC_0000001938377556__p17446133817408">Description</p>
</th>
</tr>
</thead>
<tbody><tr id="EN-US_TOPIC_0000001938377556__row15446123804018"><td class="cellrowborder" valign="top" width="30%" headers="mcps1.3.2.3.2.3.1.1 "><p id="EN-US_TOPIC_0000001938377556__p13446133824019">Aggregation of low-cardinality fields</p>
</td>
<td class="cellrowborder" valign="top" width="70%" headers="mcps1.3.2.3.2.3.1.2 "><p id="EN-US_TOPIC_0000001938377556__p1946035511314">Aggregates fields that have a small number of unique values. In this case, grouping is used. One example is counting the number of orders per city. A clustering operation can easily achieve this purpose.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row344603804011"><td class="cellrowborder" valign="top" width="30%" headers="mcps1.3.2.3.2.3.1.1 "><p id="EN-US_TOPIC_0000001938377556__p154461338134016">Aggregation of high-cardinality fields</p>
</td>
<td class="cellrowborder" valign="top" width="70%" headers="mcps1.3.2.3.2.3.1.2 "><p id="EN-US_TOPIC_0000001938377556__p16876102720418">Aggregates fields that have a large number of unique values. Histogram aggregation is typically used. One example is counting the hourly visits. A clustering key can be used to accelerate data aggregation by a specified scope or range.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row1446183812402"><td class="cellrowborder" valign="top" width="30%" headers="mcps1.3.2.3.2.3.1.1 "><p id="EN-US_TOPIC_0000001938377556__p444619382405">Hybrid aggregation of low- and high-cardinality fields</p>
</td>
<td class="cellrowborder" valign="top" width="70%" headers="mcps1.3.2.3.2.3.1.2 "><p id="EN-US_TOPIC_0000001938377556__p161716399415">Groups and aggregates low-cardinality fields first (for example, orders per city), and then creates a histogram using high-cardinality fields (for example, timestamps). Multi-level clustering improves the efficiency of hybrid queries.</p>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="section" id="EN-US_TOPIC_0000001938377556__section1995816338248"><h4 class="sectiontitle">Constraints</h4><p id="EN-US_TOPIC_0000001938377556__p6662155817386">Only Elasticsearch 7.10.2 supports enhanced aggregation.</p>
</div>
<div class="section" id="EN-US_TOPIC_0000001938377556__section1023014371242"><h4 class="sectiontitle">Aggregation of Low-Cardinality Fields</h4><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p199262406512">Generally, low-cardinality fields use grouping as a way of aggregation. With appropriate sorting keys, grouping prepares the data for batch vectorization.</p>
<div class="p" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1837203315211">For example, to aggregate two low-cardinality fields <span class="parmvalue" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_parmvalue175541800024857"><b>city</b></span> and <span class="parmvalue" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_parmvalue77728844824857"><b>product</b></span>, perform the following steps:<ol id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_ol9347189143313"><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li134729163315">Run the following command to set the index <strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b125571245724857">testindex</strong>:<pre class="screen" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_screen15668204051911">PUT testindex
{
"mappings": {
"properties": {
"date": {
"type": "date",
"format": "yyyy-MM-dd"
},
"city": {
"type": "keyword"
},
"product": {
"type": "keyword"
},
"trade": {
"type": "double"
}
}
},
"settings": {
"index": {
"search": {
"turbo": {
"enabled": "true"
}
},
"sort": {
"field": [
"city",
"product"
]
},
"cluster": {
"field": [
"city",
"product"
]
}
}
}
}</pre>
<div class="tablenoborder"><table cellpadding="4" cellspacing="0" summary="" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_table2140181015246" frame="border" border="1" rules="all"><caption><b>Table 2 </b>Parameters for low-cardinality field aggregation</caption><thead align="left"><tr id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_row5140151052419"><th align="left" class="cellrowborder" valign="top" width="22.400000000000002%" id="mcps1.3.4.3.3.1.3.2.4.1.1"><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1114031062419">Parameter</p>
</th>
<th align="left" class="cellrowborder" valign="top" width="14.649999999999999%" id="mcps1.3.4.3.3.1.3.2.4.1.2"><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p121401410122413">Type</p>
</th>
<th align="left" class="cellrowborder" valign="top" width="62.949999999999996%" id="mcps1.3.4.3.3.1.3.2.4.1.3"><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p2014020105243">Description</p>
</th>
</tr>
</thead>
<tbody><tr id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_row17140310172413"><td class="cellrowborder" valign="top" width="22.400000000000002%" headers="mcps1.3.4.3.3.1.3.2.4.1.1 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p41401210162413">index.search.turbo.enabled</p>
</td>
<td class="cellrowborder" valign="top" width="14.649999999999999%" headers="mcps1.3.4.3.3.1.3.2.4.1.2 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p14140181012246">Boolean</p>
</td>
<td class="cellrowborder" valign="top" width="62.949999999999996%" headers="mcps1.3.4.3.3.1.3.2.4.1.3 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p171408102243">Whether to enable enhanced aggregation. Normally, enhanced aggregation must be enabled where aggregations are used.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1914071072417">The value can be:</p>
<ul id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_ul1140161011248"><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li214013104248"><strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b32806207024857">false</strong> (default): Disable enhanced aggregation.</li><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li131401010112411"><strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b37325016524857">true</strong>: Enable enhanced aggregation.</li></ul>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_row81402103247"><td class="cellrowborder" valign="top" width="22.400000000000002%" headers="mcps1.3.4.3.3.1.3.2.4.1.1 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p191401310192411">index.sort.field</p>
</td>
<td class="cellrowborder" valign="top" width="14.649999999999999%" headers="mcps1.3.4.3.3.1.3.2.4.1.2 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1614171018244">Array of strings</p>
</td>
<td class="cellrowborder" valign="top" width="62.949999999999996%" headers="mcps1.3.4.3.3.1.3.2.4.1.3 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p19990419192413">Specify sorting keys. Sorting keys are fields used to sequence or rank documents.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p141411310152420">You can specify one or multiple fields as sorting keys. When multiple fields are specified, they will apply in the sequence in which they are specified. Documents are first ranked by the first field, then the initial result set is ranked by the second field, and so on.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p16141010172413">Value range: The value must be fields contained in the index.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_row7141151052417"><td class="cellrowborder" valign="top" width="22.400000000000002%" headers="mcps1.3.4.3.3.1.3.2.4.1.1 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p614114100248">index.cluster.field</p>
</td>
<td class="cellrowborder" valign="top" width="14.649999999999999%" headers="mcps1.3.4.3.3.1.3.2.4.1.2 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1514161012417">Array of strings</p>
</td>
<td class="cellrowborder" valign="top" width="62.949999999999996%" headers="mcps1.3.4.3.3.1.3.2.4.1.3 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p899191992410">Specify clustering keys. Clustering keys determine which documents are collected into the same clusters.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p41416103248">During an aggregation operation, documents in the same cluster can be processed in batches, significantly enhancing aggregation performance.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p13141131020244">Constraint: The clustering keys must be a subset of the sorting keys.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p191411110142415">Value range: The value must be fields contained in the index.</p>
</td>
</tr>
</tbody>
</table>
</div>
</li><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li8759456133412">Run the following command to import sample data.<pre class="screen" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_screen8461112912356">PUT /_bulk
{ "index": { "_index": "testindex", "_id": "1" } }
{ "date": "2025-01-01", "city": "cityA", "product": "books", "trade": 3000.0}
{ "index": { "_index": "testindex", "_id": "2" } }
{ "date": "2025-01-02", "city": "cityA", "product": "books", "trade": 1000.0}
{ "index": { "_index": "testindex", "_id": "3" } }
{ "date": "2025-01-01", "city": "cityA", "product": "bottles", "trade": 100.0}
{ "index": { "_index": "testindex", "_id": "4" } }
{ "date": "2025-01-02", "city": "cityA", "product": "bottles", "trade": 300.0}
{ "index": { "_index": "testindex", "_id": "5" } }
{ "date": "2025-01-01", "city": "cityB", "product": "books", "trade": 7000.0}
{ "index": { "_index": "testindex", "_id": "6" } }
{ "date": "2025-01-02", "city": "cityB", "product": "books", "trade": 1000.0}</pre>
</li><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li12421247203517">Run the following query command to aggregate low-cardinality fields.<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1261816720230"><a name="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li12421247203517"></a><a name="en-us_topic_0000002385090550_li12421247203517"></a>For example, query the average <strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b17478843711">trade</strong> value for each product in different cities.</p>
<pre class="screen" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_screen12975125591812">POST testindex/_search
{
"size": 0,
"aggs": {
"groupby_city": {
"terms": {
"field": "city"
},
"aggs": {
"groupby_product": {
"terms": {
"field": "product"
},
"aggs": {
"avg_trade": {
"avg": {
"field": "trade"
}
}
}
}
}
}
}
}</pre>
</li></ol>
</div>
</div>
<div class="section" id="EN-US_TOPIC_0000001938377556__section189669435249"><h4 class="sectiontitle">Aggregation of High-Cardinality Fields</h4><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p678313515564">High-cardinality fields commonly use histogram aggregation, which facilitates data processing per range or scope.</p>
<div class="p" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1965613583310">For example, to aggregate the typical high-cardinality field <span class="parmvalue" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_parmvalue104865218524857"><b>date</b></span>, perform the following steps:<ol id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_ol10656950331"><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li96564553314">Run the following command to set the index <strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b35457407224857">testindex</strong>:<pre class="screen" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_screen88731611173312">PUT testindex
{
"mappings": {
"properties": {
"date": {
"type": "date",
"format": "yyyy-MM-dd"
},
"score": {
"type": "double"
}
}
},
"settings": {
"index": {
"search": {
"turbo": {
"enabled": "true"
}
},
"sort": {
"field": [
"date"
]
}
}
}
}</pre>
<div class="tablenoborder"><table cellpadding="4" cellspacing="0" summary="" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_table46578510331" frame="border" border="1" rules="all"><caption><b>Table 3 </b>Parameters for high-cardinality field aggregation</caption><thead align="left"><tr id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_row19657056332"><th align="left" class="cellrowborder" valign="top" width="22.400000000000002%" id="mcps1.3.5.3.2.1.3.2.4.1.1"><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p196571152333">Parameter</p>
</th>
<th align="left" class="cellrowborder" valign="top" width="14.649999999999999%" id="mcps1.3.5.3.2.1.3.2.4.1.2"><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p065705183315">Type</p>
</th>
<th align="left" class="cellrowborder" valign="top" width="62.949999999999996%" id="mcps1.3.5.3.2.1.3.2.4.1.3"><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1765817516331">Description</p>
</th>
</tr>
</thead>
<tbody><tr id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_row1265819573315"><td class="cellrowborder" valign="top" width="22.400000000000002%" headers="mcps1.3.5.3.2.1.3.2.4.1.1 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p46581658336">index.search.turbo.enabled</p>
</td>
<td class="cellrowborder" valign="top" width="14.649999999999999%" headers="mcps1.3.5.3.2.1.3.2.4.1.2 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p19658155133316">Boolean</p>
</td>
<td class="cellrowborder" valign="top" width="62.949999999999996%" headers="mcps1.3.5.3.2.1.3.2.4.1.3 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1665817563316">Whether to enable enhanced aggregation. Normally, enhanced aggregation must be enabled where aggregations are used.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p176581756333">The value can be:</p>
<ul id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_ul1465812503317"><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li565810533315"><strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b169949161824857">false</strong> (default): Disable enhanced aggregation.</li><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li865816514330"><strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b21974600424857">true</strong>: Enable enhanced aggregation.</li></ul>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_row96583512335"><td class="cellrowborder" valign="top" width="22.400000000000002%" headers="mcps1.3.5.3.2.1.3.2.4.1.1 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p565820543313">index.sort.field</p>
</td>
<td class="cellrowborder" valign="top" width="14.649999999999999%" headers="mcps1.3.5.3.2.1.3.2.4.1.2 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p265845113310">Array of strings</p>
</td>
<td class="cellrowborder" valign="top" width="62.949999999999996%" headers="mcps1.3.5.3.2.1.3.2.4.1.3 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p10658135143318">Specify sorting keys. Sorting keys are fields used to sequence or rank documents.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p265817514330">You can specify one or multiple fields as sorting keys. When multiple fields are specified, they will apply in the sequence in which they are specified. Documents are first ranked by the first field, then the initial result set is ranked by the second field, and so on.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p206581533313">Value range: The value must be fields contained in the index.</p>
</td>
</tr>
</tbody>
</table>
</div>
</li><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li15659175133314">Run the following command to import sample data.<pre class="screen" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_screen13828141618336">PUT /_bulk
{ "index": { "_index": "testindex", "_id": "1" } }
{ "date": "2025-01-01", "score": "12.0"}
{ "index": { "_index": "testindex", "_id": "2" } }
{ "date": "2025-01-02","score": "24.0"}
{ "index": { "_index": "testindex", "_id": "3" } }
{ "date": "2025-01-01","score": "53.0"}
{ "index": { "_index": "testindex", "_id": "4" } }
{ "date": "2025-01-02", "score": "22.0"}
{ "index": { "_index": "testindex", "_id": "5" } }
{ "date": "2025-01-01", "score": "99.0"}
{ "index": { "_index": "testindex", "_id": "6" } }
{ "date": "2025-01-02","score": "26.0"}</pre>
</li><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li365910514330">Run the following query command to aggregate high-cardinality fields.<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p203671926173819"><a name="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li365910514330"></a><a name="en-us_topic_0000002385090550_li365910514330"></a>This query groups the <strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b95987077024857">date</strong> field using a histogram and then calculates the average score.</p>
<pre class="screen" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_screen718102015337">POST testindex/_search?pretty
{
"size": 0,
"aggs": {
"groupbytime": {
"date_histogram": {
"field": "date",
"calendar_interval": "day"
},
"aggs": {
"avg_score": {
"avg": {
"field": "score"
}
}
}
}
}
}</pre>
</li></ol>
</div>
</div>
<div class="section" id="EN-US_TOPIC_0000001938377556__section10515934174813"><h4 class="sectiontitle">Hybrid Aggregation of Low- and High-Cardinality Fields</h4><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1348015351818">Where low-cardinality and high-cardinality fields are mixed, first groups and aggregates low-cardinality fields, and then aggregates high-cardinality fields using histograms.</p>
<div class="p" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p7476039173911">For example, to first group the low-cardinality field <strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b140667669024857">city</strong>, then group the low-cardinality field <strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b32787888524857">product</strong>, and then group the high-cardinality field <strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b70054635324857">date</strong> into a histogram, perform the following steps:<ol id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_ol1947683910394"><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li1847693913396">Run the following command to set the index <strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b18332905124857">testindex</strong>:<pre class="screen" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_screen68786453393">PUT testindex
{
"mappings": {
"properties": {
"date": {
"type": "date",
"format": "yyyy-MM-dd"
},
"city": {
"type": "keyword"
},
"product": {
"type": "keyword"
},
"trade": {
"type": "double"
}
}
},
"settings": {
"index": {
"search": {
"turbo": {
"enabled": "true"
}
},
"sort": {
"field": [
"city",
"product",
"date"
]
},
"cluster": {
"field": [
"city",
"product"
]
}
}
}
}</pre>
<div class="tablenoborder"><table cellpadding="4" cellspacing="0" summary="" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_table2476153912394" frame="border" border="1" rules="all"><caption><b>Table 4 </b>Parameters for hybrid aggregation of low- and high-cardinality fields</caption><thead align="left"><tr id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_row1476123913911"><th align="left" class="cellrowborder" valign="top" width="22.400000000000002%" id="mcps1.3.6.3.4.1.3.2.4.1.1"><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p10476123943910">Parameter</p>
</th>
<th align="left" class="cellrowborder" valign="top" width="14.649999999999999%" id="mcps1.3.6.3.4.1.3.2.4.1.2"><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1847619391394">Type</p>
</th>
<th align="left" class="cellrowborder" valign="top" width="62.949999999999996%" id="mcps1.3.6.3.4.1.3.2.4.1.3"><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p947673916399">Description</p>
</th>
</tr>
</thead>
<tbody><tr id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_row4476339193910"><td class="cellrowborder" valign="top" width="22.400000000000002%" headers="mcps1.3.6.3.4.1.3.2.4.1.1 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p5476193953913">index.search.turbo.enabled</p>
</td>
<td class="cellrowborder" valign="top" width="14.649999999999999%" headers="mcps1.3.6.3.4.1.3.2.4.1.2 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p20476113914396">Boolean</p>
</td>
<td class="cellrowborder" valign="top" width="62.949999999999996%" headers="mcps1.3.6.3.4.1.3.2.4.1.3 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p17477173915395">Whether to enable enhanced aggregation. Normally, enhanced aggregation must be enabled where aggregations are used.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1047719394397">The value can be:</p>
<ul id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_ul947710396399"><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li4477939123915"><strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b304434424857">false</strong> (default): Disable enhanced aggregation.</li><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li1477133993916"><strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b212861831624857">true</strong>: Enable enhanced aggregation.</li></ul>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_row134771039183917"><td class="cellrowborder" valign="top" width="22.400000000000002%" headers="mcps1.3.6.3.4.1.3.2.4.1.1 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p7477143943913">index.sort.field</p>
</td>
<td class="cellrowborder" valign="top" width="14.649999999999999%" headers="mcps1.3.6.3.4.1.3.2.4.1.2 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p174775396392">Array of strings</p>
</td>
<td class="cellrowborder" valign="top" width="62.949999999999996%" headers="mcps1.3.6.3.4.1.3.2.4.1.3 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p6477183953914">Specify sorting keys. Sorting keys are fields used to sequence or rank documents.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p154773391399">You can specify one or multiple fields as sorting keys. When multiple fields are specified, they will apply in the sequence in which they are specified. Documents are first ranked by the first field, then the initial result set is ranked by the second field, and so on.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p14579112318424">Constraint: High-cardinality fields must be among the sorting keys, and must follow the last low-cardinality field.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p174773395398">Value range: The value must be fields contained in the index.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_row10477183918399"><td class="cellrowborder" valign="top" width="22.400000000000002%" headers="mcps1.3.6.3.4.1.3.2.4.1.1 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1547773916393">index.cluster.field</p>
</td>
<td class="cellrowborder" valign="top" width="14.649999999999999%" headers="mcps1.3.6.3.4.1.3.2.4.1.2 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1447773933910">Array of strings</p>
</td>
<td class="cellrowborder" valign="top" width="62.949999999999996%" headers="mcps1.3.6.3.4.1.3.2.4.1.3 "><p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p447783919394">Specify clustering keys. Clustering keys determine which documents are collected into the same clusters.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1047753910396">During an aggregation operation, documents in the same cluster can be processed in batches, significantly enhancing aggregation performance.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p1347793993916">Constraint: The clustering keys must be a subset of the sorting keys.</p>
<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p5477183914396">Value range: The value must be fields contained in the index.</p>
</td>
</tr>
</tbody>
</table>
</div>
</li><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li6477039153911">Run the following command to import sample data.<pre class="screen" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_screen15247205193919">PUT /_bulk
{ "index": { "_index": "testindex", "_id": "1" } }
{ "date": "2025-01-01", "city": "cityA", "product": "books", "trade": 3000.0}
{ "index": { "_index": "testindex", "_id": "2" } }
{ "date": "2025-01-02", "city": "cityA", "product": "books", "trade": 1000.0}
{ "index": { "_index": "testindex", "_id": "3" } }
{ "date": "2025-01-01", "city": "cityA", "product": "bottles", "trade": 100.0}
{ "index": { "_index": "testindex", "_id": "4" } }
{ "date": "2025-01-02", "city": "cityA", "product": "bottles", "trade": 300.0}
{ "index": { "_index": "testindex", "_id": "5" } }
{ "date": "2025-01-01", "city": "cityB", "product": "books", "trade": 7000.0}
{ "index": { "_index": "testindex", "_id": "6" } }
{ "date": "2025-01-02", "city": "cityB", "product": "books", "trade": 1000.0}</pre>
</li><li id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li447753953918">Run the following query command to perform a hybrid aggregation of low- and high-cardinality fields.<p id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_p16402195182418"><a name="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_li447753953918"></a><a name="en-us_topic_0000002385090550_li447753953918"></a>For example, query the average <strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b19397113622">trade</strong> value of each product in different cities on each day specified by the <strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_b1121419571827">date</strong> field.</p>
<pre class="screen" id="EN-US_TOPIC_0000001938377556__en-us_topic_0000002385090550_screen1565616541392">POST testindex/_search
{
"size": 0,
"aggs": {
"groupby_region": {
"terms": {
"field": "city"
},
"aggs": {
"groupby_host": {
"terms": {
"field": "product"
},
"aggs": {
"groupby_timestamp": {
"date_histogram": {
"field": "date",
"interval": "day"
},
"aggs": {
"avg_score": {
"avg": {
"field": "trade"
}
}
}
}
}
}
}
}
}
}</pre>
</li></ol>
</div>
</div>
<div class="section" id="EN-US_TOPIC_0000001938377556__section113412041516"><h4 class="sectiontitle">Performance Testing</h4><div class="p" id="EN-US_TOPIC_0000001938377556__p14991919101713"><strong id="EN-US_TOPIC_0000001938377556__b11847105125315">Test environment</strong><ul id="EN-US_TOPIC_0000001938377556__ul1982216149184"><li id="EN-US_TOPIC_0000001938377556__li19823314141810">Dataset: esrally nyc_taxis</li><li id="EN-US_TOPIC_0000001938377556__li18545125541914">Cluster specifications: 4U16G, 100 GB, high I/O x 3 nodes</li></ul>
</div>
<div class="p" id="EN-US_TOPIC_0000001938377556__p431113518242"><strong id="EN-US_TOPIC_0000001938377556__en-us_topic_0139700192_b38233575">Test Procedure</strong><ol id="EN-US_TOPIC_0000001938377556__ol151371575253"><li id="EN-US_TOPIC_0000001938377556__li91379782513">Create an index template in the cluster, specify sorting keys, and disable enhanced aggregation.<pre class="screen" id="EN-US_TOPIC_0000001938377556__screen2175057172514">PUT /_template/nyc_taxis
{
"template": "nyc_taxis*",
"settings": {
"index.search.turbo.enabled": false,
"index.sort.field": "dropoff_datetime",
"number_of_shards": 3,
"number_of_replicas": 0
}
}</pre>
</li><li id="EN-US_TOPIC_0000001938377556__li1749626112817">Use esrally to test the nyc_taxis dataset and obtain the result when enhanced aggregation is disabled.</li><li id="EN-US_TOPIC_0000001938377556__li19332174052811">Create another index template in the same cluster, specify sorting keys, and enable enhanced aggregation.<pre class="screen" id="EN-US_TOPIC_0000001938377556__screen193741915132910">PUT /_template/nyc_taxis
{
"template": "nyc_taxis*",
"settings": {
"index.search.turbo.enabled": true,
"index.sort.field": "dropoff_datetime",
"number_of_shards": 3,
"number_of_replicas": 0
}
}</pre>
</li><li id="EN-US_TOPIC_0000001938377556__li457317010290">Use esrally to test the nyc_taxis dataset and obtain the result when enhanced aggregation is enabled.</li></ol>
</div>
<p id="EN-US_TOPIC_0000001938377556__p7938152411291"><strong id="EN-US_TOPIC_0000001938377556__b6141859151519">Test Result</strong></p>
<p id="EN-US_TOPIC_0000001938377556__p1087475612294">This test focuses on the query result of <span class="parmvalue" id="EN-US_TOPIC_0000001938377556__parmvalue7824163619550"><b>dropoff_datetime</b></span> aggregation, that is, the results of tasks <span class="parmvalue" id="EN-US_TOPIC_0000001938377556__parmvalue10954195115555"><b>autohisto_agg</b></span> and <span class="parmvalue" id="EN-US_TOPIC_0000001938377556__parmvalue269165555519"><b>date_histogram_agg</b></span>. The following table compares the test results between when enhanced aggregation is disabled and when it is enabled.</p>
<div class="tablenoborder"><table cellpadding="4" cellspacing="0" summary="" id="EN-US_TOPIC_0000001938377556__table12001931426" frame="border" border="1" rules="all"><thead align="left"><tr id="EN-US_TOPIC_0000001938377556__row87950426565"><th align="left" class="cellrowborder" rowspan="2" valign="top" id="mcps1.3.7.6.1.14.1.1"><p id="EN-US_TOPIC_0000001938377556__p182311311571">Metric</p>
</th>
<th align="left" class="cellrowborder" rowspan="2" valign="top" id="mcps1.3.7.6.1.14.1.2"><p id="EN-US_TOPIC_0000001938377556__p3231431135715">Task</p>
</th>
<th align="left" class="cellrowborder" rowspan="2" valign="top" id="mcps1.3.7.6.1.14.1.3"><p id="EN-US_TOPIC_0000001938377556__p16231193125710">Unit</p>
</th>
<th align="left" class="cellrowborder" colspan="3" valign="top" id="mcps1.3.7.6.1.14.1.4"><p id="EN-US_TOPIC_0000001938377556__p8231731125719">Enhanced Aggregation Disabled</p>
</th>
<th align="left" class="cellrowborder" colspan="3" valign="top" id="mcps1.3.7.6.1.14.1.5"><p id="EN-US_TOPIC_0000001938377556__p523113111573">Enhanced Aggregation Enabled</p>
</th>
<th align="left" class="cellrowborder" valign="top" id="mcps1.3.7.6.1.14.1.6"><p id="EN-US_TOPIC_0000001938377556__p8231931195711">Enhanced Aggregation Disabled</p>
</th>
<th align="left" class="cellrowborder" valign="top" id="mcps1.3.7.6.1.14.1.7"><p id="EN-US_TOPIC_0000001938377556__p023123117575">Enhanced Aggregation Enabled</p>
</th>
<th align="left" class="cellrowborder" rowspan="2" valign="top" id="mcps1.3.7.6.1.14.1.8"><p id="EN-US_TOPIC_0000001938377556__p152311531105717">open/close</p>
</th>
<th align="left" class="cellrowborder" rowspan="2" valign="top" id="mcps1.3.7.6.1.14.1.9"><p id="EN-US_TOPIC_0000001938377556__p9231173112573">Conclusion</p>
</th>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row1536475314562"><th align="left" class="cellrowborder" valign="top" id="mcps1.3.7.6.1.14.2.1"><p id="EN-US_TOPIC_0000001938377556__p73616585815">Test Round 1</p>
</th>
<th align="left" class="cellrowborder" valign="top" id="mcps1.3.7.6.1.14.2.2"><p id="EN-US_TOPIC_0000001938377556__p836165145813">Test Round 2</p>
</th>
<th align="left" class="cellrowborder" valign="top" id="mcps1.3.7.6.1.14.2.3"><p id="EN-US_TOPIC_0000001938377556__p536255581">Test Round 3</p>
</th>
<th align="left" class="cellrowborder" valign="top" id="mcps1.3.7.6.1.14.2.4"><p id="EN-US_TOPIC_0000001938377556__p153615505812">Test Round 1</p>
</th>
<th align="left" class="cellrowborder" valign="top" id="mcps1.3.7.6.1.14.2.5"><p id="EN-US_TOPIC_0000001938377556__p1636205115819">Test Round 2</p>
</th>
<th align="left" class="cellrowborder" valign="top" id="mcps1.3.7.6.1.14.2.6"><p id="EN-US_TOPIC_0000001938377556__p20372545815">Test Round 3</p>
</th>
<th align="left" class="cellrowborder" valign="top" id="mcps1.3.7.6.1.14.2.7"><p id="EN-US_TOPIC_0000001938377556__p13651153175619">Mean Value</p>
</th>
<th align="left" class="cellrowborder" valign="top" id="mcps1.3.7.6.1.14.2.8"><p id="EN-US_TOPIC_0000001938377556__p2365195335610">Mean Value</p>
</th>
</tr>
</thead>
<tbody><tr id="EN-US_TOPIC_0000001938377556__row1630913364217"><td class="cellrowborder" valign="top" width="15.67077872012336%" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p163099314219">Min Throughput</p>
</td>
<td class="cellrowborder" valign="top" width="10.350809560524285%" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p430973154218">autohisto_agg</p>
</td>
<td class="cellrowborder" valign="top" width="6.746337702390131%" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p4309193154210">ops/s</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p73094312423">4.42</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p1630918316420">4.44</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p113091333426">4.43</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p1530953204212">11.66</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p4309631422">11.94</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p1830973134215">11.96</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p5309143104210">4.43</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p4309136429">11.85</p>
</td>
<td class="cellrowborder" valign="top" width="6.3415574402467225%" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p1931016312428">2.68</p>
</td>
<td class="cellrowborder" rowspan="4" valign="top" width="12.085582112567463%" headers="mcps1.3.7.6.1.14.1.9 "><p id="EN-US_TOPIC_0000001938377556__p7310113194216">Throughput improves more than 2.5 times.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row1631016384219"><td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p1131023164211">Mean Throughput</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p2310133422">autohisto_agg</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p173101733426">ops/s</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p63107314210">4.50</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p14310113164220">4.46</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p16310936425">4.44</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p1310236424">11.81</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p83101333428">11.99</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p1731023114212">12.00</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p031043154219">4.47</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p103102354220">11.93</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p15310432425">2.67</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row123109313423"><td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p3310238425">Median Throughput</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p143107314211">autohisto_agg</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p123107314211">ops/s</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p53104319422">4.51</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p15310133134213">4.46</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p16310133124219">4.44</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p11310331428">11.83</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p1310836420">11.98</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p193101236427">12.00</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p1310133174214">4.47</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p18310337423">11.94</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p1631020310423">2.67</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row1931063194210"><td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p1031017318427">Max Throughput</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p331023174218">autohisto_agg</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p23106334216">ops/s</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p4310183184220">4.54</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p1131083174211">4.48</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p15310153174214">4.45</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p731013324214">11.90</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p18311163144211">12.07</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p1631120311424">12.02</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p1531117314219">4.49</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p1731118354215">12.00</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p1431110374220">2.67</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row4311113184214"><td class="cellrowborder" valign="top" width="15.67077872012336%" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p4311143154212">100th percentile latency</p>
</td>
<td class="cellrowborder" valign="top" width="10.350809560524285%" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p153111433428">autohisto_agg</p>
</td>
<td class="cellrowborder" valign="top" width="6.746337702390131%" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p1331153154213">ms</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p1731113320420">216.30</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p03113384219">-</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p2311636427">-</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p1431112320423">-</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p531183134210">84.56</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p15311103194212">80.38</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p8311123164216">216.30</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p173112036429">82.47</p>
</td>
<td class="cellrowborder" valign="top" width="6.3415574402467225%" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p1131123204220">0.38</p>
</td>
<td class="cellrowborder" rowspan="2" valign="top" width="12.085582112567463%" headers="mcps1.3.7.6.1.14.1.9 "><p id="EN-US_TOPIC_0000001938377556__p10311173154219">Latency decreases by more than 60%.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row7311632420"><td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p431114334214">100th percentile service time</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p123119314425">autohisto_agg</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p4311173144213">ms</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p331143164211">216.30</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p1931123164218">-</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p163114315428">-</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p14311434426">-</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p93114314211">84.56</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p1731115354219">80.38</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p5311639421">216.30</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p831163114215">82.47</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p431113354217">0.38</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row1931110313420"><td class="cellrowborder" valign="top" width="15.67077872012336%" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p33111736425">error rate</p>
</td>
<td class="cellrowborder" valign="top" width="10.350809560524285%" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p1311103104216">autohisto_agg</p>
</td>
<td class="cellrowborder" valign="top" width="6.746337702390131%" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p113117324213">%</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p631116310428">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p43125316422">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p131243134217">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p531211374212">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p1531283124218">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p43121233427">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p18312203184214">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p631211317420">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.3415574402467225%" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p83121934422">0</p>
</td>
<td class="cellrowborder" valign="top" width="12.085582112567463%" headers="mcps1.3.7.6.1.14.1.9 "><p id="EN-US_TOPIC_0000001938377556__p11312032426">-</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row631210311427"><td class="cellrowborder" valign="top" width="15.67077872012336%" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p9312203184215">Min Throughput</p>
</td>
<td class="cellrowborder" valign="top" width="10.350809560524285%" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p8312135424">date_histogram_agg</p>
</td>
<td class="cellrowborder" valign="top" width="6.746337702390131%" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p20312103144214">ops/s</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p23124312426">4.72</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p103121332426">4.67</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p173121233425">4.65</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p123125315428">12.57</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p19312038424">12.40</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p131293134215">12.59</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p6312633425">4.68</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p43126314425">12.52</p>
</td>
<td class="cellrowborder" valign="top" width="6.3415574402467225%" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p23121835426">2.68</p>
</td>
<td class="cellrowborder" rowspan="4" valign="top" width="12.085582112567463%" headers="mcps1.3.7.6.1.14.1.9 "><p id="EN-US_TOPIC_0000001938377556__p13127313427">Throughput improves more than 2.5 times.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row931273164218"><td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p53126314216">Mean Throughput</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p2312173174212">date_histogram_agg</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p153121330428">ops/s</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p1031213318427">4.73</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p0312433426">4.67</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p133129319429">4.67</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p1931243114211">12.61</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p831223104219">12.46</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p331253154214">12.61</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p1312939424">4.69</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p13131635424">12.56</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p33131236428">2.68</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row123136311425"><td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p1331310311426">Median Throughput</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p163131138426">date_histogram_agg</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p43133311429">ops/s</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p63131384210">4.73</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p13132344211">4.67</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p15313163124217">4.67</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p19313533423">12.62</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p1031313104214">12.46</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p1313123174213">12.60</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p331312310424">4.69</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p1031315311428">12.56</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p133131384215">2.68</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row16313173114214"><td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p7313836425">Max Throughput</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p43138364212">date_histogram_agg</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p18313163184219">ops/s</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p193131037426">4.74</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p183134311423">4.67</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p73138311427">4.67</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p631383184213">12.64</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p10313163174210">12.49</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p431312354215">12.63</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p131315320429">4.69</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p23131139423">12.59</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p43132314212">2.68</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row1731353184218"><td class="cellrowborder" valign="top" width="15.67077872012336%" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p183134313423">50th percentile latency</p>
</td>
<td class="cellrowborder" valign="top" width="10.350809560524285%" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p3210214135317">date_histogram_agg</p>
</td>
<td class="cellrowborder" valign="top" width="6.746337702390131%" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p1331310315421">ms</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p9313337425">202.61</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p1313133184214">218.09</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p13313637429">213.43</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p1831323144218">77.64</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p83143364216">76.02</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p83148320426">82.63</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p15314123174214">211.38</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p331413334211">78.77</p>
</td>
<td class="cellrowborder" valign="top" width="6.3415574402467225%" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p143143364211">0.37</p>
</td>
<td class="cellrowborder" rowspan="4" valign="top" width="12.085582112567463%" headers="mcps1.3.7.6.1.14.1.9 "><p id="EN-US_TOPIC_0000001938377556__p131413124212">Latency decreases by more than 60%.</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row1531463104213"><td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p103143310424">100th percentile latency</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p031423184211">date_histogram_agg</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p8314143104217">ms</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p2031411324213">207.35</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p43141933425">223.88</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p8314173124211">246.63</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p11314113194218">77.99</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p33141231424">-</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p63148334217">-</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p1231453144216">225.95</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p63141338420">77.99</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p4314173144219">0.35</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row193141439426"><td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p123145334217">50th percentile service time</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p631417394216">date_histogram_agg</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p13141304217">ms</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p331423164217">202.61</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p163141837424">218.09</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p13314123164218">213.43</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p1931420314423">77.64</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p9314173164216">76.02</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p131416314423">82.63</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p1231493154213">211.38</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p1931412394219">78.77</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p831419314429">0.37</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row19314193114219"><td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p131417304220">100th percentile service time</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p1731410313427">date_histogram_agg</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p143151539423">ms</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p43151320426">207.35</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p1531512314211">223.88</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p18315931425">246.63</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p17315133425">77.99</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p143159310420">-</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p1231573114215">-</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p231515324214">225.95</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p1131514314422">77.99</p>
</td>
<td class="cellrowborder" valign="top" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p731516314210">0.35</p>
</td>
</tr>
<tr id="EN-US_TOPIC_0000001938377556__row153152312429"><td class="cellrowborder" valign="top" width="15.67077872012336%" headers="mcps1.3.7.6.1.14.1.1 mcps1.3.7.6.1.14.2.1 "><p id="EN-US_TOPIC_0000001938377556__p8315235426">error rate</p>
</td>
<td class="cellrowborder" valign="top" width="10.350809560524285%" headers="mcps1.3.7.6.1.14.1.2 mcps1.3.7.6.1.14.2.2 "><p id="EN-US_TOPIC_0000001938377556__p1131517312423">date_histogram_agg</p>
</td>
<td class="cellrowborder" valign="top" width="6.746337702390131%" headers="mcps1.3.7.6.1.14.1.3 mcps1.3.7.6.1.14.2.3 "><p id="EN-US_TOPIC_0000001938377556__p9315103194215">%</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.4 "><p id="EN-US_TOPIC_0000001938377556__p2315637420">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.5 "><p id="EN-US_TOPIC_0000001938377556__p331523194213">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.4 mcps1.3.7.6.1.14.2.6 "><p id="EN-US_TOPIC_0000001938377556__p1531543194212">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.7 "><p id="EN-US_TOPIC_0000001938377556__p15315183114212">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 mcps1.3.7.6.1.14.2.8 "><p id="EN-US_TOPIC_0000001938377556__p1431563164211">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.5 "><p id="EN-US_TOPIC_0000001938377556__p14315133164217">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.6 "><p id="EN-US_TOPIC_0000001938377556__p731563174212">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.100616808018503%" headers="mcps1.3.7.6.1.14.1.7 "><p id="EN-US_TOPIC_0000001938377556__p731573114211">0</p>
</td>
<td class="cellrowborder" valign="top" width="6.3415574402467225%" headers="mcps1.3.7.6.1.14.1.8 "><p id="EN-US_TOPIC_0000001938377556__p7315113104212">0</p>
</td>
<td class="cellrowborder" valign="top" width="12.085582112567463%" headers="mcps1.3.7.6.1.14.1.9 "><p id="EN-US_TOPIC_0000001938377556__p3315173124215">-</p>
</td>
</tr>
</tbody>
</table>
</div>
<p id="EN-US_TOPIC_0000001938377556__p186501028163916"><strong id="EN-US_TOPIC_0000001938377556__b11329155215810">Test Conclusion</strong></p>
<p id="EN-US_TOPIC_0000001938377556__p7866113219392">Given the same cluster configuration, aggregation performance improves significantly when enhanced aggregation is enabled. Query throughput improves by more than 2.5 times, and latency decreases by more than 60%.</p>
</div>
</div>
<div>
<div class="familylinks">
<div class="parentlink"><strong>Parent topic:</strong> <a href="css_01_0111.html">Enhancing Search Capabilities for Elasticsearch Clusters</a></div>
</div>
</div>
View Git Blame Copy Permalink