| <div role="region" aria-label="Skip to main content"><a class="skipToContent_fXgn" href="#__docusaurus_skipToContent_fallback">Skip to main content</a></div><nav aria-label="Main" class="navbar navbar--fixed-top navbar--dark"><div class="navbar__inner"><div class="navbar__items"><button aria-label="Toggle navigation bar" aria-expanded="false" class="navbar__toggle clean-btn" type="button"><svg width="30" height="30" viewBox="0 0 30 30" aria-hidden="true"><path stroke="currentColor" stroke-linecap="round" stroke-miterlimit="10" stroke-width="2" d="M4 7h22M4 15h22M4 23h22"></path></svg></button><a class="navbar__brand" href="/"><div class="navbar__logo"><img src="/img/druid_nav.png" alt="Apache® Druid" class="themedImage_ToTc themedImage--light_HNdA"><img src="/img/druid_nav.png" alt="Apache® Druid" class="themedImage_ToTc themedImage--dark_i4oU"></div></a></div><div class="navbar__items navbar__items--right"><a class="navbar__item navbar__link" href="/technology">Technology</a><a class="navbar__item navbar__link" href="/use-cases">Use Cases</a><a class="navbar__item navbar__link" href="/druid-powered">Powered By</a><a class="navbar__item navbar__link" href="/docs/latest/design/">Docs</a><a class="navbar__item navbar__link" href="/community/">Community</a><div class="navbar__item dropdown dropdown--hoverable dropdown--right"><a href="#" aria-haspopup="true" aria-expanded="false" role="button" class="navbar__link">Apache®</a><ul class="dropdown__menu"><li><a href="https://www.apache.org/" target="_blank" rel="noopener noreferrer" class="dropdown__link">Foundation<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li><li><a href="https://apachecon.com/?ref=druid.apache.org" target="_blank" rel="noopener noreferrer" class="dropdown__link">Events<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li><li><a href="https://www.apache.org/licenses/" target="_blank" rel="noopener noreferrer" class="dropdown__link">License<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li><li><a href="https://www.apache.org/foundation/thanks.html" target="_blank" rel="noopener noreferrer" class="dropdown__link">Thanks<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li><li><a href="https://www.apache.org/security/" target="_blank" rel="noopener noreferrer" class="dropdown__link">Security<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li><li><a href="https://www.apache.org/foundation/sponsorship.html" target="_blank" rel="noopener noreferrer" class="dropdown__link">Sponsorship<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li></ul></div><a class="navbar__item navbar__link" href="/downloads/">Download</a><div class="searchBox_ZlJk"><div class="navbar__search"><span aria-label="expand searchbar" role="button" class="search-icon" tabindex="0"></span><input type="search" id="search_input_react" placeholder="Loading..." aria-label="Search" class="navbar__search-input search-bar" disabled=""></div></div></div></div><div role="presentation" class="navbar-sidebar__backdrop"></div></nav><div id="__docusaurus_skipToContent_fallback" class="main-wrapper mainWrapper_z2l0 docsWrapper_BCFX"><button aria-label="Scroll back to top" class="clean-btn theme-back-to-top-button backToTopButton_sjWU" type="button"></button><div class="docPage__5DB"><aside class="theme-doc-sidebar-container docSidebarContainer_b6E3"><div class="sidebarViewport_Xe31"><div class="sidebar_njMd"><nav aria-label="Docs sidebar" class="menu thin-scrollbar menu_SIkG"><ul class="theme-doc-sidebar-menu menu__list"><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" href="/docs/latest/design/">Getting started</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" href="/docs/latest/tutorials/tutorial-msq-extern">Tutorials</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" href="/docs/latest/design/architecture">Design</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" href="/docs/latest/ingestion/">Ingestion</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret menu__link--active" aria-expanded="true" href="/docs/latest/data-management/">Data management</a></div><ul style="display:block;overflow:visible;height:auto" class="menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/docs/latest/data-management/">Overview</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/docs/latest/data-management/update">Data updates</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/docs/latest/data-management/delete">Data deletion</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/docs/latest/data-management/schema-changes">Schema changes</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link menu__link--active" aria-current="page" tabindex="0" href="/docs/latest/data-management/compaction">Compaction</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/docs/latest/data-management/automatic-compaction">Automatic compaction</a></li></ul></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" href="/docs/latest/querying/sql">Querying</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" href="/docs/latest/api-reference/">API reference</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" href="/docs/latest/configuration/">Configuration</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" href="/docs/latest/operations/web-console">Operations</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" href="/docs/latest/development/overview">Development</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" href="/docs/latest/misc/papers-and-talks">Misc</a></div></li></ul></nav></div></div></aside><main class="docMainContainer_gTbr"><div class="container padding-top--md padding-bottom--lg"><div class="row"><div class="col docItemCol_VOVn"><div class="docItemContainer_Djhp"><article><nav class="theme-doc-breadcrumbs breadcrumbsContainer_Z_bl" aria-label="Breadcrumbs"><ul class="breadcrumbs" itemscope="" itemtype="https://schema.org/BreadcrumbList"><li class="breadcrumbs__item"><a aria-label="Home page" class="breadcrumbs__link" href="/"><svg viewBox="0 0 24 24" class="breadcrumbHomeIcon_YNFT"><path d="M10 19v-5h4v5c0 .55.45 1 1 1h3c.55 0 1-.45 1-1v-7h1.7c.46 0 .68-.57.33-.87L12.67 3.6c-.38-.34-.96-.34-1.34 0l-8.36 7.53c-.34.3-.13.87.33.87H5v7c0 .55.45 1 1 1h3c.55 0 1-.45 1-1z" fill="currentColor"></path></svg></a></li><li class="breadcrumbs__item"><span class="breadcrumbs__link">Data management</span><meta itemprop="position" content="1"></li><li itemscope="" itemprop="itemListElement" itemtype="https://schema.org/ListItem" class="breadcrumbs__item breadcrumbs__item--active"><span class="breadcrumbs__link" itemprop="name">Compaction</span><meta itemprop="position" content="2"></li></ul></nav><div class="tocCollapsible_ETCw theme-doc-toc-mobile tocMobile_ITEo"><button type="button" class="clean-btn tocCollapsibleButton_TO0P">On this page</button></div><div class="theme-doc-markdown markdown"><header><h1>Compaction</h1></header><p>Query performance in Apache Druid depends on optimally sized segments. Compaction is one strategy you can use to optimize segment size for your Druid database. Compaction tasks read an existing set of segments for a given time interval and combine the data into a new "compacted" set of segments. In some cases the compacted segments are larger, but there are fewer of them. In other cases the compacted segments may be smaller. Compaction tends to increase performance because optimized segments require less per-segment processing and less memory overhead for ingestion and for querying paths.</p><h2 class="anchor anchorWithStickyNavbar_LWe7" id="compaction-strategies">Compaction strategies<a href="#compaction-strategies" class="hash-link" aria-label="Direct link to Compaction strategies" title="Direct link to Compaction strategies"></a></h2><p>There are several cases to consider compaction for segment optimization:</p><ul><li>With streaming ingestion, data can arrive out of chronological order creating many small segments.</li><li>If you append data using <code>appendToExisting</code> for <a href="/docs/latest/ingestion/native-batch">native batch</a> ingestion creating suboptimal segments.</li><li>When you use <code>index_parallel</code> for parallel batch indexing and the parallel ingestion tasks create many small segments.</li><li>When a misconfigured ingestion task creates oversized segments.</li></ul><p>By default, compaction does not modify the underlying data of the segments. However, there are cases when you may want to modify data during compaction to improve query performance:</p><ul><li>If, after ingestion, you realize that data for the time interval is sparse, you can use compaction to increase the segment granularity.</li><li>If you don't need fine-grained granularity for older data, you can use compaction to change older segments to a coarser query granularity. For example, from <code>minute</code> to <code>hour</code> or <code>hour</code> to <code>day</code>. This reduces the storage space required for older data.</li><li>You can change the dimension order to improve sorting and reduce segment size.</li><li>You can remove unused columns in compaction or implement an aggregation metric for older data.</li><li>You can change segment rollup from dynamic partitioning with best-effort rollup to hash or range partitioning with perfect rollup. For more information on rollup, see <a href="/docs/latest/ingestion/rollup#perfect-rollup-vs-best-effort-rollup">perfect vs best-effort rollup</a>.</li></ul><p>Compaction does not improve performance in all situations. For example, if you rewrite your data with each ingestion task, you don't need to use compaction. See <a href="/docs/latest/operations/segment-optimization">Segment optimization</a> for additional guidance to determine if compaction will help in your environment.</p><h2 class="anchor anchorWithStickyNavbar_LWe7" id="types-of-compaction">Types of compaction<a href="#types-of-compaction" class="hash-link" aria-label="Direct link to Types of compaction" title="Direct link to Types of compaction"></a></h2><p>You can configure the Druid Coordinator to perform automatic compaction, also called auto-compaction, for a datasource. Using its <a href="/docs/latest/design/coordinator#segment-search-policy-in-automatic-compaction">segment search policy</a>, the Coordinator periodically identifies segments for compaction starting from newest to oldest. When the Coordinator discovers segments that have not been compacted or segments that were compacted with a different or changed spec, it submits compaction tasks for the time interval covering those segments.</p><p>Automatic compaction works in most use cases and should be your first option. To learn more, see <a href="/docs/latest/data-management/automatic-compaction">Automatic compaction</a>.</p><p>In cases where you require more control over compaction, you can manually submit compaction tasks. For example:</p><ul><li>Automatic compaction is running into the limit of task slots available to it, so tasks are waiting for previous automatic compaction tasks to complete. Manual compaction can use all available task slots, therefore you can complete compaction more quickly by submitting more concurrent tasks for more intervals.</li><li>You want to force compaction for a specific time range or you want to compact data out of chronological order.</li></ul><p>See <a href="#setting-up-manual-compaction">Setting up a manual compaction task</a> for more about manual compaction tasks.</p><h2 class="anchor anchorWithStickyNavbar_LWe7" id="data-handling-with-compaction">Data handling with compaction<a href="#data-handling-with-compaction" class="hash-link" aria-label="Direct link to Data handling with compaction" title="Direct link to Data handling with compaction"></a></h2><p>During compaction, Druid overwrites the original set of segments with the compacted set. Druid also locks the segments for the time interval being compacted to ensure data consistency. By default, compaction tasks do not modify the underlying data. You can configure the compaction task to change the query granularity or add or remove dimensions in the compaction task. This means that the only changes to query results should be the result of intentional, not automatic, changes.</p><p>You can set <code>dropExisting</code> in <code>ioConfig</code> to "true" in the compaction task to configure Druid to replace all existing segments fully contained by the interval. See the suggestion for reindexing with finer granularity under <a href="/docs/latest/ingestion/native-batch#implementation-considerations">Implementation considerations</a> for an example.</p><div class="theme-admonition theme-admonition-info alert alert--info admonition_LlT9"><div class="admonitionHeading_tbUL"><span class="admonitionIcon_kALy"><svg viewBox="0 0 14 16"><path fill-rule="evenodd" d="M7 2.3c3.14 0 5.7 2.56 5.7 5.7s-2.56 5.7-5.7 5.7A5.71 5.71 0 0 1 1.3 8c0-3.14 2.56-5.7 5.7-5.7zM7 1C3.14 1 0 4.14 0 8s3.14 7 7 7 7-3.14 7-7-3.14-7-7-7zm1 3H6v5h2V4zm0 6H6v2h2v-2z"></path></svg></span>info</div><div class="admonitionContent_S0QG"><p> WARNING: <code>dropExisting</code> in <code>ioConfig</code> is a beta feature.</p></div></div><p>If an ingestion task needs to write data to a segment for a time interval locked for compaction, by default the ingestion task supersedes the compaction task and the compaction task fails without finishing. For manual compaction tasks, you can adjust the input spec interval to avoid conflicts between ingestion and compaction. For automatic compaction, you can set the <code>skipOffsetFromLatest</code> key to adjust the auto-compaction starting point from the current time to reduce the chance of conflicts between ingestion and compaction. |
| For more information, see <a href="/docs/latest/data-management/automatic-compaction#avoid-conflicts-with-ingestion">Avoid conflicts with ingestion</a>.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="segment-granularity-handling">Segment granularity handling<a href="#segment-granularity-handling" class="hash-link" aria-label="Direct link to Segment granularity handling" title="Direct link to Segment granularity handling"></a></h3><p>Unless you modify the segment granularity in <a href="#compaction-granularity-spec"><code>granularitySpec</code></a>, Druid attempts to retain the granularity for the compacted segments. When segments have different segment granularities with no overlap in interval Druid creates a separate compaction task for each to retain the segment granularity in the compacted segment.</p><p>If segments have different segment granularities before compaction but there is some overlap in interval, Druid attempts find start and end of the overlapping interval and uses the closest segment granularity level for the compacted segment.</p><p>For example consider two overlapping segments: segment "A" for the interval 01/01/2021-01/02/2021 with day granularity and segment "B" for the interval 01/01/2021-02/01/2021. Druid attempts to combine and compact the overlapped segments. In this example, the earliest start time for the two segments is 01/01/2020 and the latest end time of the two segments is 02/01/2020. Druid compacts the segments together even though they have different segment granularity. Druid uses month segment granularity for the newly compacted segment even though segment A's original segment granularity was DAY.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="query-granularity-handling">Query granularity handling<a href="#query-granularity-handling" class="hash-link" aria-label="Direct link to Query granularity handling" title="Direct link to Query granularity handling"></a></h3><p>Unless you modify the query granularity in the <a href="#compaction-granularity-spec"><code>granularitySpec</code></a>, Druid retains the query granularity for the compacted segments. If segments have different query granularities before compaction, Druid chooses the finest level of granularity for the resulting compacted segment. For example if a compaction task combines two segments, one with day query granularity and one with minute query granularity, the resulting segment uses minute query granularity.</p><div class="theme-admonition theme-admonition-info alert alert--info admonition_LlT9"><div class="admonitionHeading_tbUL"><span class="admonitionIcon_kALy"><svg viewBox="0 0 14 16"><path fill-rule="evenodd" d="M7 2.3c3.14 0 5.7 2.56 5.7 5.7s-2.56 5.7-5.7 5.7A5.71 5.71 0 0 1 1.3 8c0-3.14 2.56-5.7 5.7-5.7zM7 1C3.14 1 0 4.14 0 8s3.14 7 7 7 7-3.14 7-7-3.14-7-7-7zm1 3H6v5h2V4zm0 6H6v2h2v-2z"></path></svg></span>info</div><div class="admonitionContent_S0QG"><p> In Apache Druid 0.21.0 and prior, Druid sets the granularity for compacted segments to the default granularity of <code>NONE</code> regardless of the query granularity of the original segments.</p></div></div><p>If you configure query granularity in compaction to go from a finer granularity like month to a coarser query granularity like year, then Druid overshadows the original segment with coarser granularity. Because the new segments have a coarser granularity, running a kill task to remove the overshadowed segments for those intervals will cause you to permanently lose the finer granularity data.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="dimension-handling">Dimension handling<a href="#dimension-handling" class="hash-link" aria-label="Direct link to Dimension handling" title="Direct link to Dimension handling"></a></h3><p>Apache Druid supports schema changes. Therefore, dimensions can be different across segments even if they are a part of the same datasource. See <a href="/docs/latest/design/segments#segments-with-different-schemas">Segments with different schemas</a>. If the input segments have different dimensions, the resulting compacted segment includes all dimensions of the input segments.</p><p>Even when the input segments have the same set of dimensions, the dimension order or the data type of dimensions can be different. The dimensions of recent segments precede that of old segments in terms of data types and the ordering because more recent segments are more likely to have the preferred order and data types.</p><p>If you want to control dimension ordering or ensure specific values for dimension types, you can configure a custom <code>dimensionsSpec</code> in the compaction task spec.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="rollup">Rollup<a href="#rollup" class="hash-link" aria-label="Direct link to Rollup" title="Direct link to Rollup"></a></h3><p>Druid only rolls up the output segment when <code>rollup</code> is set for all input segments. |
| You can check that your segments are rolled up or not by using <a href="/docs/latest/querying/segmentmetadataquery#analysistypes">Segment Metadata Queries</a>.</p><h2 class="anchor anchorWithStickyNavbar_LWe7" id="setting-up-manual-compaction">Setting up manual compaction<a href="#setting-up-manual-compaction" class="hash-link" aria-label="Direct link to Setting up manual compaction" title="Direct link to Setting up manual compaction"></a></h2><p>To perform a manual compaction, you submit a compaction task. Compaction tasks merge all segments for the defined interval according to the following syntax:</p><div class="language-json codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-json codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token punctuation" style="color:rgb(199, 146, 234)">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"type"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"compact"</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"id"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> <task_id></span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"dataSource"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> <task_datasource></span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"ioConfig"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> <IO config></span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"dimensionsSpec"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> <custom dimensionsSpec></span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"transformSpec"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> <custom transformSpec></span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"metricsSpec"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> <custom metricsSpec></span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"tuningConfig"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> <parallel indexing task tuningConfig></span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"granularitySpec"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> <compaction task granularitySpec></span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"context"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> <task context></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token punctuation" style="color:rgb(199, 146, 234)">}</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg viewBox="0 0 24 24" class="copyButtonSuccessIcon_LjdS"><path fill="currentColor" d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div><table><thead><tr><th>Field</th><th>Description</th><th>Required</th></tr></thead><tbody><tr><td><code>type</code></td><td>Task type. Set the value to <code>compact</code>.</td><td>Yes</td></tr><tr><td><code>id</code></td><td>Task ID</td><td>No</td></tr><tr><td><code>dataSource</code></td><td>Data source name to compact</td><td>Yes</td></tr><tr><td><code>ioConfig</code></td><td>I/O configuration for compaction task. See <a href="#compaction-io-configuration">Compaction I/O configuration</a> for details.</td><td>Yes</td></tr><tr><td><code>dimensionsSpec</code></td><td>When set, the compaction task uses the specified <code>dimensionsSpec</code> rather than generating one from existing segments. See <a href="#compaction-dimensions-spec">Compaction dimensionsSpec</a> for details.</td><td>No</td></tr><tr><td><code>transformSpec</code></td><td>When set, the compaction task uses the specified <code>transformSpec</code> rather than using <code>null</code>. See <a href="#compaction-transform-spec">Compaction transformSpec</a> for details.</td><td>No</td></tr><tr><td><code>metricsSpec</code></td><td>When set, the compaction task uses the specified <code>metricsSpec</code> rather than generating one from existing segments.</td><td>No</td></tr><tr><td><code>segmentGranularity</code></td><td>Deprecated. Use <code>granularitySpec</code>.</td><td>No</td></tr><tr><td><code>tuningConfig</code></td><td><a href="/docs/latest/ingestion/native-batch#tuningconfig">Tuning configuration</a> for parallel indexing. <code>awaitSegmentAvailabilityTimeoutMillis</code> value is not supported for compaction tasks. Leave this parameter at the default value, 0.</td><td>No</td></tr><tr><td><code>granularitySpec</code></td><td>When set, the compaction task uses the specified <code>granularitySpec</code> rather than generating one from existing segments. See <a href="#compaction-granularity-spec">Compaction <code>granularitySpec</code></a> for details.</td><td>No</td></tr><tr><td><code>context</code></td><td><a href="/docs/latest/ingestion/tasks#context">Task context</a></td><td>No</td></tr></tbody></table><div class="theme-admonition theme-admonition-info alert alert--info admonition_LlT9"><div class="admonitionHeading_tbUL"><span class="admonitionIcon_kALy"><svg viewBox="0 0 14 16"><path fill-rule="evenodd" d="M7 2.3c3.14 0 5.7 2.56 5.7 5.7s-2.56 5.7-5.7 5.7A5.71 5.71 0 0 1 1.3 8c0-3.14 2.56-5.7 5.7-5.7zM7 1C3.14 1 0 4.14 0 8s3.14 7 7 7 7-3.14 7-7-3.14-7-7-7zm1 3H6v5h2V4zm0 6H6v2h2v-2z"></path></svg></span>info</div><div class="admonitionContent_S0QG"><p> Note: Use <code>granularitySpec</code> over <code>segmentGranularity</code> and only set one of these values. If you specify different values for these in the same compaction spec, the task fails.</p></div></div><p>To control the number of result segments per time chunk, you can set <a href="/docs/latest/ingestion/native-batch#partitionsspec"><code>maxRowsPerSegment</code></a> or <a href="/docs/latest/ingestion/native-batch#tuningconfig"><code>numShards</code></a>.</p><div class="theme-admonition theme-admonition-info alert alert--info admonition_LlT9"><div class="admonitionHeading_tbUL"><span class="admonitionIcon_kALy"><svg viewBox="0 0 14 16"><path fill-rule="evenodd" d="M7 2.3c3.14 0 5.7 2.56 5.7 5.7s-2.56 5.7-5.7 5.7A5.71 5.71 0 0 1 1.3 8c0-3.14 2.56-5.7 5.7-5.7zM7 1C3.14 1 0 4.14 0 8s3.14 7 7 7 7-3.14 7-7-3.14-7-7-7zm1 3H6v5h2V4zm0 6H6v2h2v-2z"></path></svg></span>info</div><div class="admonitionContent_S0QG"><p> You can run multiple compaction tasks in parallel. For example, if you want to compact the data for a year, you are not limited to running a single task for the entire year. You can run 12 compaction tasks with month-long intervals.</p></div></div><p>A compaction task internally generates an <code>index</code> or <code>index_parallel</code> task spec for performing compaction work with some fixed parameters. For example, its <code>inputSource</code> is always the <a href="/docs/latest/ingestion/input-sources"><code>druid</code> input source</a>, and <code>dimensionsSpec</code> and <code>metricsSpec</code> include all dimensions and metrics of the input segments by default.</p><p>Compaction tasks typically fetch all <a href="#compaction-io-configuration">relevant segments</a> prior to launching any subtasks, <em>unless</em> the following properties are all set to non-null values. It is strongly recommended to set them to non-null values to maximize performance and minimize disk usage of the <code>compact</code> task:</p><ul><li><a href="#compaction-granularity-spec"><code>granularitySpec</code></a>, with non-null values for each of <code>segmentGranularity</code>, <code>queryGranularity</code>, and <code>rollup</code></li><li><a href="#compaction-dimensions-spec"><code>dimensionsSpec</code></a></li><li><code>metricsSpec</code></li></ul><p>Compaction tasks exit without doing anything and issue a failure status code in either of the following cases:</p><ul><li>If the interval you specify has no data segments loaded.</li><li>If the interval you specify is empty.</li></ul><p>Note that the metadata between input segments and the resulting compacted segments may differ if the metadata among the input segments differs as well. If all input segments have the same metadata, however, the resulting output segment will have the same metadata as all input segments.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="example-compaction-task">Example compaction task<a href="#example-compaction-task" class="hash-link" aria-label="Direct link to Example compaction task" title="Direct link to Example compaction task"></a></h3><p>The following JSON illustrates a compaction task to compact <em>all segments</em> within the interval <code>2020-01-01/2021-01-01</code> and create new segments:</p><div class="language-json codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-json codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token punctuation" style="color:rgb(199, 146, 234)">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"type"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"compact"</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"dataSource"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"wikipedia"</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"ioConfig"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"type"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"compact"</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"inputSpec"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"type"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"interval"</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"interval"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"2020-01-01/2021-01-01"</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">}</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">}</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"granularitySpec"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"segmentGranularity"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"day"</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token property">"queryGranularity"</span><span class="token operator" style="color:rgb(137, 221, 255)">:</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"hour"</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">}</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token punctuation" style="color:rgb(199, 146, 234)">}</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg viewBox="0 0 24 24" class="copyButtonSuccessIcon_LjdS"><path fill="currentColor" d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div><p><code>granularitySpec</code> is an optional field. |
| If you don't specify <code>granularitySpec</code>, Druid retains the original segment and query granularities when compaction is complete.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="compaction-io-configuration">Compaction I/O configuration<a href="#compaction-io-configuration" class="hash-link" aria-label="Direct link to Compaction I/O configuration" title="Direct link to Compaction I/O configuration"></a></h3><p>The compaction <code>ioConfig</code> requires specifying <code>inputSpec</code> as follows:</p><table><thead><tr><th>Field</th><th>Description</th><th>Default</th><th>Required</th></tr></thead><tbody><tr><td><code>type</code></td><td>Task type. Set the value to <code>compact</code>.</td><td>none</td><td>Yes</td></tr><tr><td><code>inputSpec</code></td><td>Specification of the target <a href="#interval-inputspec">interval</a> or <a href="#segments-inputspec">segments</a>.</td><td>none</td><td>Yes</td></tr><tr><td><code>dropExisting</code></td><td>If <code>true</code>, the task replaces all existing segments fully contained by either of the following:<br>- the <code>interval</code> in the <code>interval</code> type <code>inputSpec</code>.<br>- the umbrella interval of the <code>segments</code> in the <code>segment</code> type <code>inputSpec</code>.<br>If compaction fails, Druid does not change any of the existing segments.<br><strong>WARNING</strong>: <code>dropExisting</code> in <code>ioConfig</code> is a beta feature.</td><td>false</td><td>No</td></tr><tr><td><code>allowNonAlignedInterval</code></td><td>If <code>true</code>, the task allows an explicit <a href="#compaction-granularity-spec"><code>segmentGranularity</code></a> that is not aligned with the provided <a href="#interval-inputspec">interval</a> or <a href="#segments-inputspec">segments</a>. This parameter is only used if <a href="#compaction-granularity-spec"><code>segmentGranularity</code></a> is explicitly provided.<br><br>This parameter is provided for backwards compatibility. In most scenarios it should not be set, as it can lead to data being accidentally overshadowed. This parameter may be removed in a future release.</td><td>false</td><td>No</td></tr></tbody></table><p>The compaction task has two kinds of <code>inputSpec</code>:</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="interval-inputspec">Interval <code>inputSpec</code><a href="#interval-inputspec" class="hash-link" aria-label="Direct link to interval-inputspec" title="Direct link to interval-inputspec"></a></h4><table><thead><tr><th>Field</th><th>Description</th><th>Required</th></tr></thead><tbody><tr><td><code>type</code></td><td>Task type. Set the value to <code>interval</code>.</td><td>Yes</td></tr><tr><td><code>interval</code></td><td>Interval to compact.</td><td>Yes</td></tr></tbody></table><h4 class="anchor anchorWithStickyNavbar_LWe7" id="segments-inputspec">Segments <code>inputSpec</code><a href="#segments-inputspec" class="hash-link" aria-label="Direct link to segments-inputspec" title="Direct link to segments-inputspec"></a></h4><table><thead><tr><th>Field</th><th>Description</th><th>Required</th></tr></thead><tbody><tr><td><code>type</code></td><td>Task type. Set the value to <code>segments</code>.</td><td>Yes</td></tr><tr><td><code>segments</code></td><td>A list of segment IDs.</td><td>Yes</td></tr></tbody></table><h3 class="anchor anchorWithStickyNavbar_LWe7" id="compaction-dimensions-spec">Compaction dimensions spec<a href="#compaction-dimensions-spec" class="hash-link" aria-label="Direct link to Compaction dimensions spec" title="Direct link to Compaction dimensions spec"></a></h3><table><thead><tr><th>Field</th><th>Description</th><th>Required</th></tr></thead><tbody><tr><td><code>dimensions</code></td><td>A list of dimension names or objects. Cannot have the same column in both <code>dimensions</code> and <code>dimensionExclusions</code>. Defaults to <code>null</code>, which preserves the original dimensions.</td><td>No</td></tr><tr><td><code>dimensionExclusions</code></td><td>The names of dimensions to exclude from compaction. Only names are supported here, not objects. This list is only used if the dimensions list is null or empty; otherwise it is ignored. Defaults to <code>[]</code>.</td><td>No</td></tr></tbody></table><h3 class="anchor anchorWithStickyNavbar_LWe7" id="compaction-transform-spec">Compaction transform spec<a href="#compaction-transform-spec" class="hash-link" aria-label="Direct link to Compaction transform spec" title="Direct link to Compaction transform spec"></a></h3><table><thead><tr><th>Field</th><th>Description</th><th>Required</th></tr></thead><tbody><tr><td><code>filter</code></td><td>The <code>filter</code> conditionally filters input rows during compaction. Only rows that pass the filter will be included in the compacted segments. Any of Druid's standard <a href="/docs/latest/querying/filters">query filters</a> can be used. Defaults to 'null', which will not filter any row.</td><td>No</td></tr></tbody></table><h3 class="anchor anchorWithStickyNavbar_LWe7" id="compaction-granularity-spec">Compaction granularity spec<a href="#compaction-granularity-spec" class="hash-link" aria-label="Direct link to Compaction granularity spec" title="Direct link to Compaction granularity spec"></a></h3><table><thead><tr><th>Field</th><th>Description</th><th>Required</th></tr></thead><tbody><tr><td><code>segmentGranularity</code></td><td>Time chunking period for the segment granularity. Defaults to 'null', which preserves the original segment granularity. Accepts all <a href="/docs/latest/querying/granularities">Query granularity</a> values.</td><td>No</td></tr><tr><td><code>queryGranularity</code></td><td>The resolution of timestamp storage within each segment. Defaults to 'null', which preserves the original query granularity. Accepts all <a href="/docs/latest/querying/granularities">Query granularity</a> values.</td><td>No</td></tr><tr><td><code>rollup</code></td><td>Enables compaction-time rollup. To preserve the original setting, keep the default value. To enable compaction-time rollup, set the value to <code>true</code>. Once the data is rolled up, you can no longer recover individual records.</td><td>No</td></tr></tbody></table><h2 class="anchor anchorWithStickyNavbar_LWe7" id="learn-more">Learn more<a href="#learn-more" class="hash-link" aria-label="Direct link to Learn more" title="Direct link to Learn more"></a></h2><p>See the following topics for more information:</p><ul><li><a href="/docs/latest/operations/segment-optimization">Segment optimization</a> for guidance to determine if compaction will help in your case.</li><li><a href="/docs/latest/data-management/automatic-compaction">Automatic compaction</a> for how to enable and configure automatic compaction.</li></ul></div></article><nav class="pagination-nav docusaurus-mt-lg" aria-label="Docs pages"><a class="pagination-nav__link pagination-nav__link--prev" href="/docs/latest/data-management/schema-changes"><div class="pagination-nav__sublabel">Previous</div><div class="pagination-nav__label">Schema changes</div></a><a class="pagination-nav__link pagination-nav__link--next" href="/docs/latest/data-management/automatic-compaction"><div class="pagination-nav__sublabel">Next</div><div class="pagination-nav__label">Automatic compaction</div></a></nav></div></div><div class="col col--3"><div class="tableOfContents_bqdL thin-scrollbar theme-doc-toc-desktop"><ul class="table-of-contents table-of-contents__left-border"><li><a href="#compaction-strategies" class="table-of-contents__link toc-highlight">Compaction strategies</a></li><li><a href="#types-of-compaction" class="table-of-contents__link toc-highlight">Types of compaction</a></li><li><a href="#data-handling-with-compaction" class="table-of-contents__link toc-highlight">Data handling with compaction</a><ul><li><a href="#segment-granularity-handling" class="table-of-contents__link toc-highlight">Segment granularity handling</a></li><li><a href="#query-granularity-handling" class="table-of-contents__link toc-highlight">Query granularity handling</a></li><li><a href="#dimension-handling" class="table-of-contents__link toc-highlight">Dimension handling</a></li><li><a href="#rollup" class="table-of-contents__link toc-highlight">Rollup</a></li></ul></li><li><a href="#setting-up-manual-compaction" class="table-of-contents__link toc-highlight">Setting up manual compaction</a><ul><li><a href="#example-compaction-task" class="table-of-contents__link toc-highlight">Example compaction task</a></li><li><a href="#compaction-io-configuration" class="table-of-contents__link toc-highlight">Compaction I/O configuration</a></li><li><a href="#compaction-dimensions-spec" class="table-of-contents__link toc-highlight">Compaction dimensions spec</a></li><li><a href="#compaction-transform-spec" class="table-of-contents__link toc-highlight">Compaction transform spec</a></li><li><a href="#compaction-granularity-spec" class="table-of-contents__link toc-highlight">Compaction granularity spec</a></li></ul></li><li><a href="#learn-more" class="table-of-contents__link toc-highlight">Learn more</a></li></ul></div></div></div></div></main></div></div><footer class="footer"><div class="container container-fluid"><div class="footer__bottom text--center"><div class="margin-bottom--sm"><img src="/img/favicon.png" class="themedImage_ToTc themedImage--light_HNdA footer__logo"><img src="/img/favicon.png" class="themedImage_ToTc themedImage--dark_i4oU footer__logo"></div><div class="footer__copyright">Copyright © 2023 Apache Software Foundation. Except where otherwise noted, licensed under CC BY-SA 4.0. Apache Druid, Druid, and the Druid logo are either registered trademarks or trademarks of The Apache Software Foundation in the United States and other countries.</div></div></div></footer></div> |
