<!-- 
RSS generated by JIRA (9.7.1#970001-sha1:2222b88b221c4928ef0de3161136cc90c8356a66) at Thu Feb 08 04:10:43 UTC 2024

It is possible to restrict the fields that are returned in this document by specifying the 'field' parameter in your request.
For example, to request only the issue key and summary append 'field=key&field=summary' to the URL of your request.
-->
<rss version="0.92" >
<channel>
    <title>MongoDB Jira</title>
    <link>https://jira.mongodb.org</link>
    <description>This file is an XML representation of an issue</description>
    <language>en-us</language>    <build-info>
        <version>9.7.1</version>
        <build-number>970001</build-number>
        <build-date>13-04-2023</build-date>
    </build-info>


<item>
            <title>[SERVER-25957] Optimize $filter + $arrayElemAt to avoid scanning entire array</title>
                <link>https://jira.mongodb.org/browse/SERVER-25957</link>
                <project id="10000" key="SERVER">Core Server</project>
                    <description>&lt;p&gt;If you have a very large array, and want to extract the first element matching some predicate, you should be able to do so without scanning the entire array.&lt;/p&gt;

&lt;p&gt;We should optimize the combination of $arrayElemAt and $filter to do so.&lt;/p&gt;

&lt;h5&gt;&lt;a name=&quot;OriginalDescription&quot;&gt;&lt;/a&gt;Original Description&lt;/h5&gt;
&lt;p&gt;Why can&apos;t $elemMatch be used in the $project phase? It would allow me to easily select an element out of an array.&lt;/p&gt;

&lt;p&gt;Example:&lt;/p&gt;
&lt;p/&gt;
&lt;div id=&quot;syntaxplugin&quot; class=&quot;syntaxplugin&quot; style=&quot;border: 1px dashed #bbb; border-radius: 5px !important; overflow: auto; max-height: 30em;&quot;&gt;
&lt;table cellspacing=&quot;0&quot; cellpadding=&quot;0&quot; border=&quot;0&quot; width=&quot;100%&quot; style=&quot;font-size: 1em; line-height: 1.4em !important; font-weight: normal; font-style: normal; color: black;&quot;&gt;
		&lt;tbody &gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;  margin-top: 10px;   width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;db.person.aggregate([&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;   width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;  { &quot;$project&quot;: {&apos;main_event&apos; :&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;   width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;    {&apos;$events_array&apos;: {&apos;$elemMatch&apos; : {&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;   width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;      &apos;event_status&apos; : &apos;main&apos;&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;   width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;    }}}&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;   width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;  }}&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;   margin-bottom: 10px;  width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;]);&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
			&lt;/tbody&gt;
&lt;/table&gt;
&lt;/div&gt;
&lt;p/&gt;

&lt;p&gt;Basically what I&apos;m looking for is an easier way to convert an array into a scalar without having to $unwind and then re-$group, which is taxing for proc time.&lt;/p&gt;
</description>
                <environment></environment>
        <key id="313966">SERVER-25957</key>
            <summary>Optimize $filter + $arrayElemAt to avoid scanning entire array</summary>
                <type id="4" iconUrl="https://jira.mongodb.org/secure/viewavatar?size=xsmall&amp;avatarId=14710&amp;avatarType=issuetype">Improvement</type>
                                            <priority id="3" iconUrl="https://jira.mongodb.org/images/icons/priorities/major.svg">Major - P3</priority>
                        <status id="10038" iconUrl="https://jira.mongodb.org/images/icons/subtask.gif" description="">Backlog</status>
                    <statusCategory id="2" key="new" colorName="default"/>
                                    <resolution id="-1">Unresolved</resolution>
                                        <assignee username="backlog-query-optimization">Backlog - Query Optimization</assignee>
                                    <reporter username="xdc">Xavier Del Castillo</reporter>
                        <labels>
                            <label>neweng</label>
                            <label>optimization</label>
                            <label>qopt-team</label>
                    </labels>
                <created>Sun, 4 Sep 2016 03:26:06 +0000</created>
                <updated>Tue, 6 Dec 2022 04:17:29 +0000</updated>
                                            <version>2.6.4</version>
                                                    <component>Aggregation Framework</component>
                                        <votes>1</votes>
                                    <watches>8</watches>
                                                                                                                <comments>
                            <comment id="2607415" author="charlie.swanson" created="Fri, 13 Dec 2019 18:57:17 +0000"  >&lt;p&gt;The above commit message mentioned the wrong SERVER ticket so this was mistakenly closed.  There is a work in progress pull request &lt;a href=&quot;https://github.com/mongodb/mongo/pull/1236&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;here&lt;/a&gt;.&lt;/p&gt;</comment>
                            <comment id="2607409" author="craig.homa" created="Fri, 13 Dec 2019 18:54:17 +0000"  >&lt;p&gt;Re-opening this as it was closed in error.&lt;/p&gt;</comment>
                            <comment id="1879516" author="xgen-internal-githook" created="Tue, 1 May 2018 19:21:18 +0000"  >&lt;p&gt;Author:&lt;/p&gt;
{&apos;email&apos;: &apos;KevinCybura@gmail.com&apos;, &apos;name&apos;: &apos;KevinCybura&apos;}
&lt;p&gt;Message: &lt;a href=&quot;https://jira.mongodb.org/browse/SERVER-25957&quot; title=&quot;Optimize $filter + $arrayElemAt to avoid scanning entire array&quot; class=&quot;issue-link&quot; data-issue-key=&quot;SERVER-25957&quot;&gt;SERVER-25957&lt;/a&gt; Optimize $indexOfArray when array argument is constant.&lt;/p&gt;

&lt;p&gt;Signed-off-by: Charlie Swanson &amp;lt;charlie.swanson@mongodb.com&amp;gt;&lt;/p&gt;

&lt;p&gt;Closes #1229&lt;br/&gt;
Branch: master&lt;br/&gt;
&lt;a href=&quot;https://github.com/mongodb/mongo/commit/ae01d46b2d70ce2491cc01ef131dd101089c6d21&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://github.com/mongodb/mongo/commit/ae01d46b2d70ce2491cc01ef131dd101089c6d21&lt;/a&gt;&lt;/p&gt;</comment>
                            <comment id="1849691" author="asya" created="Thu, 29 Mar 2018 20:37:23 +0000"  >&lt;p&gt;Please note that:&lt;/p&gt;

&lt;blockquote&gt;&lt;p&gt;For answering the question &quot;Is there an element in this array that matches this?&quot; &lt;/p&gt;&lt;/blockquote&gt;

&lt;p&gt;This should not be done with &lt;tt&gt;$filter&lt;/tt&gt; in aggregation expressions, but with &lt;a href=&quot;https://docs.mongodb.com/manual/reference/operator/aggregation/in/&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;&lt;tt&gt;$in&lt;/tt&gt;&lt;/a&gt;.&lt;/p&gt;</comment>
                            <comment id="1609940" author="asya" created="Wed, 28 Jun 2017 22:00:14 +0000"  >&lt;p&gt;This may be useful as a general optimization not just for $arrayElemAt but for any sort of $slice of the result array.   In other words, it would be useful to be able to short circuit out of $filter early if the full result array will not be used.&lt;/p&gt;

&lt;p/&gt;
&lt;div id=&quot;syntaxplugin&quot; class=&quot;syntaxplugin&quot; style=&quot;border: 1px dashed #bbb; border-radius: 5px !important; overflow: auto; max-height: 30em;&quot;&gt;
&lt;table cellspacing=&quot;0&quot; cellpadding=&quot;0&quot; border=&quot;0&quot; width=&quot;100%&quot; style=&quot;font-size: 1em; line-height: 1.4em !important; font-weight: normal; font-style: normal; color: black;&quot;&gt;
		&lt;tbody &gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;  margin-top: 10px;   width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;{$project:{newarr:{$slice:[&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;   width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;          {$filter:{input:&quot;$bigArray&quot;, cond: { ... } } },&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;   width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;          0,&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;   width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;          5&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
				&lt;tr id=&quot;syntaxplugin_code_and_gutter&quot;&gt;
						&lt;td  style=&quot; line-height: 1.4em !important; padding: 0em; vertical-align: top;&quot;&gt;
					&lt;pre style=&quot;font-size: 1em; margin: 0 10px;   margin-bottom: 10px;  width: auto; padding: 0;&quot;&gt;&lt;span style=&quot;color: black; font-family: &apos;Consolas&apos;, &apos;Bitstream Vera Sans Mono&apos;, &apos;Courier New&apos;, Courier, monospace !important;&quot;&gt;]}}}&lt;/span&gt;&lt;/pre&gt;
			&lt;/td&gt;
		&lt;/tr&gt;
			&lt;/tbody&gt;
&lt;/table&gt;
&lt;/div&gt;
&lt;p/&gt;
&lt;p&gt;The above should be able to stop processing &quot;$bigArray&quot; in $filter as soon as 5 elements have been generated from $filter expression.&lt;/p&gt;</comment>
                            <comment id="1395777" author="xdc" created="Wed, 28 Sep 2016 16:48:56 +0000"  >&lt;p&gt;Thanks for considering this request.&lt;/p&gt;</comment>
                            <comment id="1380491" author="charlie.swanson" created="Fri, 9 Sep 2016 14:46:34 +0000"  >&lt;p&gt;&lt;a href=&quot;https://jira.mongodb.org/secure/ViewProfile.jspa?name=xdc&quot; class=&quot;user-hover&quot; rel=&quot;xdc&quot;&gt;xdc&lt;/a&gt;, This seems like a legitimate request, at least as a performance improvement. As you noticed above, you can use $filter to do most of the work, so if you combine that with an {&lt;tt&gt;$arrayElemAt: [{$filter: ...}, 0]&lt;/tt&gt;} it should do what you want.&lt;/p&gt;

&lt;p&gt;I&apos;ll convert this ticket into a request for the above expression to be optimized not to scan the entire array, instead stopping at the first matching element.&lt;/p&gt;</comment>
                            <comment id="1376343" author="xdc" created="Sun, 4 Sep 2016 03:31:20 +0000"  >&lt;p&gt;This is a clone task of: &lt;a href=&quot;https://jira.mongodb.org/browse/SERVER-14876&quot; title=&quot;support $elemMatch in aggregation $project operator&quot; class=&quot;issue-link&quot; data-issue-key=&quot;SERVER-14876&quot;&gt;&lt;del&gt;SERVER-14876&lt;/del&gt;&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;The resolution was that:&lt;br/&gt;
&amp;gt; This use case is handled by the new $filter expression.&lt;/p&gt;

&lt;p&gt;$filter was implemented on: &lt;a href=&quot;https://jira.mongodb.org/browse/SERVER-17943&quot; class=&quot;external-link&quot; rel=&quot;nofollow&quot;&gt;https://jira.mongodb.org/browse/SERVER-17943&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;However, I do not think `$filter` and `$elemMatch` are equal - according to the docs `$elemMatch` stops looking when it matches &lt;em&gt;at least&lt;/em&gt; one, potentially stopping scanning early - however `$filter` will scan the whole array, even if the first element in the array matches the condition, returning the subset of elements passing the condition. For answering the question &quot;Is there an element in this array that matches this?&quot; `$elemMatch` is the correct choice, `$filter` can answer that question but does unnecessary work.&lt;/p&gt;

&lt;p&gt;Thoughts on the above use case?&lt;/p&gt;</comment>
                    </comments>
                <issuelinks>
                            <issuelinktype id="10012">
                    <name>Related</name>
                                            <outwardlinks description="related to">
                                        <issuelink>
            <issuekey id="484109">SERVER-32739</issuekey>
        </issuelink>
                            </outwardlinks>
                                                        </issuelinktype>
                    </issuelinks>
                <attachments>
                    </attachments>
                <subtasks>
                    </subtasks>
                <customfields>
                                                <customfield id="customfield_10050" key="com.atlassian.jira.toolkit:comments">
                        <customfieldname># Replies</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>8.0</customfieldvalue>
                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                                                                                                                                <customfield id="customfield_12751" key="com.atlassian.jira.plugin.system.customfieldtypes:multiselect">
                        <customfieldname>Assigned Teams</customfieldname>
                        <customfieldvalues>
                                <customfieldvalue key="25126"><![CDATA[Query Optimization]]></customfieldvalue>
    
                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    <customfield id="customfield_10055" key="com.atlassian.jira.ext.charting:firstresponsedate">
                        <customfieldname>Date of 1st Reply</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>Fri, 9 Sep 2016 14:46:34 +0000</customfieldvalue>

                        </customfieldvalues>
                    </customfield>
                                                                <customfield id="customfield_10052" key="com.atlassian.jira.toolkit:dayslastcommented">
                        <customfieldname>Days since reply</customfieldname>
                        <customfieldvalues>
                                        4 years, 8 weeks, 5 days ago
    
                        </customfieldvalues>
                    </customfield>
                                                                <customfield id="customfield_18254" key="com.onresolve.jira.groovy.groovyrunner:scripted-field">
                        <customfieldname>Dependencies</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue><![CDATA[]]></customfieldvalue>


                        </customfieldvalues>
                    </customfield>
                                                                <customfield id="customfield_15850" key="com.atlassian.jira.plugins.jira-development-integration-plugin:devsummary">
                        <customfieldname>Development</customfieldname>
                        <customfieldvalues>
                            
                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        <customfield id="customfield_10057" key="com.atlassian.jira.toolkit:lastusercommented">
                        <customfieldname>Last comment by Customer</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>true</customfieldvalue>
                        </customfieldvalues>
                    </customfield>
                                                                                            <customfield id="customfield_10056" key="com.atlassian.jira.toolkit:lastupdaterorcommenter">
                        <customfieldname>Last commenter</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>alexander.golin@mongodb.com</customfieldvalue>

                        </customfieldvalues>
                    </customfield>
                                                                <customfield id="customfield_11151" key="com.atlassian.jira.toolkit:LastCommentDate">
                        <customfieldname>Last public comment date</customfieldname>
                        <customfieldvalues>
                            4 years, 8 weeks, 5 days ago
                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                                                                                                    <customfield id="customfield_10051" key="com.atlassian.jira.toolkit:participants">
                        <customfieldname>Participants</customfieldname>
                        <customfieldvalues>
                                        <customfieldvalue>asya.kamsky@mongodb.com</customfieldvalue>
            <customfieldvalue>backlog-query-optimization</customfieldvalue>
            <customfieldvalue>charlie.swanson@mongodb.com</customfieldvalue>
            <customfieldvalue>craig.homa@mongodb.com</customfieldvalue>
            <customfieldvalue>xgen-internal-githook</customfieldvalue>
            <customfieldvalue>xdc</customfieldvalue>
    
                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                                                                        <customfield id="customfield_14254" key="com.pyxis.greenhopper.jira:gh-lexo-rank">
                        <customfieldname>Product Rank</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>1|hrjx0v:</customfieldvalue>

                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                <customfield id="customfield_12550" key="com.pyxis.greenhopper.jira:gh-lexo-rank">
                        <customfieldname>Rank</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>2|hr2ha7:</customfieldvalue>

                        </customfieldvalues>
                    </customfield>
                                                                <customfield id="customfield_10558" key="com.pyxis.greenhopper.jira:gh-global-rank">
                        <customfieldname>Rank (Obsolete)</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>9223372036854775807</customfieldvalue>
                        </customfieldvalues>
                    </customfield>
                                                                                            <customfield id="customfield_23361" key="com.onresolve.jira.groovy.groovyrunner:scripted-field">
                        <customfieldname>Requested By</customfieldname>
                        <customfieldvalues>
                                

                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    <customfield id="customfield_22870" key="com.onresolve.jira.groovy.groovyrunner:scripted-field">
                        <customfieldname>Triagers</customfieldname>
                        <customfieldvalues>
                                

                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                                                                                                                                                                                                                    <customfield id="customfield_14350" key="com.pyxis.greenhopper.jira:gh-lexo-rank">
                        <customfieldname>serverRank</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>1|hrxttj:</customfieldvalue>

                        </customfieldvalues>
                    </customfield>
                                    </customfields>
    </item>
</channel>
</rss>