mirror of
https://github.com/datahub-project/datahub.git
synced 2025-11-10 00:11:15 +00:00
92 lines
114 KiB
HTML
92 lines
114 KiB
HTML
<!doctype html>
|
||
<html lang="en" dir="ltr" class="docs-wrapper docs-doc-page docs-version-current plugin-docs plugin-id-default docs-doc-id-docs/how/load-indices" data-has-hydrated="false">
|
||
<head>
|
||
<meta charset="UTF-8">
|
||
<meta name="generator" content="Docusaurus v2.4.3">
|
||
<title data-rh="true">Load Indices: High-Performance Bulk Index Loading | DataHub</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://docs.datahub.com/docs/how/load-indices"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="current"><meta data-rh="true" name="docusaurus_tag" content="docs-default-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-current"><meta data-rh="true" property="og:title" content="Load Indices: High-Performance Bulk Index Loading | DataHub"><meta data-rh="true" name="description" content="LoadIndices is a high-performance upgrade task designed for bulk loading metadata aspects directly from the database into Elasticsearch/OpenSearch indices. Unlike RestoreIndices which focuses on correctness and consistency, LoadIndices is optimized for speed and throughput during initial deployments or large-scale data migrations."><meta data-rh="true" property="og:description" content="LoadIndices is a high-performance upgrade task designed for bulk loading metadata aspects directly from the database into Elasticsearch/OpenSearch indices. Unlike RestoreIndices which focuses on correctness and consistency, LoadIndices is optimized for speed and throughput during initial deployments or large-scale data migrations."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.datahub.com/docs/how/load-indices"><link data-rh="true" rel="alternate" href="https://docs.datahub.com/docs/how/load-indices" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.datahub.com/docs/how/load-indices" hreflang="x-default"><link data-rh="true" rel="preconnect" href="https://RK0UG797F3-dsn.algolia.net" crossorigin="anonymous"><link rel="alternate" type="application/rss+xml" href="/learn/rss.xml" title="DataHub RSS Feed">
|
||
<link rel="alternate" type="application/atom+xml" href="/learn/atom.xml" title="DataHub Atom Feed">
|
||
|
||
<link rel="preconnect" href="https://www.google-analytics.com">
|
||
<link rel="preconnect" href="https://www.googletagmanager.com">
|
||
<script async src="https://www.googletagmanager.com/gtag/js?id=G-PKGVLETT4C"></script>
|
||
<script>function gtag(){dataLayer.push(arguments)}window.dataLayer=window.dataLayer||[],gtag("js",new Date),gtag("config","G-PKGVLETT4C",{})</script>
|
||
<link rel="preconnect" href="https://www.googletagmanager.com">
|
||
<script>window.dataLayer=window.dataLayer||[]</script>
|
||
<script>!function(e,t,a,n,g){e[n]=e[n]||[],e[n].push({"gtm.start":(new Date).getTime(),event:"gtm.js"});var m=t.getElementsByTagName(a)[0],r=t.createElement(a);r.async=!0,r.src="https://www.googletagmanager.com/gtm.js?id=GTM-5M8T9HNN",m.parentNode.insertBefore(r,m)}(window,document,"script","dataLayer")</script>
|
||
|
||
|
||
<link rel="search" type="application/opensearchdescription+xml" title="DataHub" href="/opensearch.xml">
|
||
|
||
|
||
|
||
|
||
<meta httpequiv="Content-Security-Policy" content="frame-ancestors 'self' https://*.acryl.io https://acryldata.io http://localhost:*">
|
||
<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Manrope:wght@400;500;700&display=swap">
|
||
<script src="https://tools.luckyorange.com/core/lo.js?site-id=28ea8a38" async defer="defer"></script>
|
||
<script src="/scripts/rb2b.js" async defer="defer"></script>
|
||
<script src="https://app.revenuehero.io/scheduler.min.js"></script>
|
||
<script src="https://tag.clearbitscripts.com/v1/pk_2e321cabe30432a5c44c0424781aa35f/tags.js" referrerpolicy="strict-origin-when-cross-origin"></script>
|
||
<script src="/scripts/reo.js"></script>
|
||
<script id="runllm-widget-script" type="module" src="https://widget.runllm.com" crossorigin="true" runllm-name="DataHub" runllm-assistant-id="81" runllm-position="BOTTOM_RIGHT" runllm-keyboard-shortcut="Mod+j" runllm-preset="docusaurus" runllm-theme-color="#1890FF" runllm-brand-logo="https://docs.datahub.com/img/datahub-logo-color-mark.svg" runllm-community-url="https://datahub.com/slack" runllm-community-type="slack" runllm-disable-ask-a-person="true" async></script><link rel="stylesheet" href="/assets/css/styles.1e47f27f.css">
|
||
<link rel="preload" href="/assets/js/runtime~main.76cdbaa9.js" as="script">
|
||
<link rel="preload" href="/assets/js/main.b7ce4b14.js" as="script">
|
||
</head>
|
||
<body class="navigation-with-keyboard">
|
||
<noscript><iframe src="https://www.googletagmanager.com/ns.html?id=GTM-5M8T9HNN" height="0" width="0" style="display:none;visibility:hidden"></iframe></noscript>
|
||
|
||
<script>!function(){function t(t){document.documentElement.setAttribute("data-theme",t)}var e=function(){var t=null;try{t=new URLSearchParams(window.location.search).get("docusaurus-theme")}catch(t){}return t}()||function(){var t=null;try{t=localStorage.getItem("theme")}catch(t){}return t}();t(null!==e?e:"light")}(),document.documentElement.setAttribute("data-announcement-bar-initially-dismissed",function(){try{return"true"===localStorage.getItem("docusaurus.announcement.dismiss")}catch(t){}return!1}())</script><div id="__docusaurus">
|
||
<div role="region" aria-label="Skip to main content"><a class="skipToContent_fXgn" href="#__docusaurus_skipToContent_fallback">Skip to main content</a></div><div class="announcementBar_mb4j" style="background-color:transparent;color:#ffffff" role="banner"><div class="content_knG7 announcementBarContent_xLdY"><div class="shimmer-banner"><p><strong>CONTEXT:</strong> The Future of Agentic AI is On Demand</p><a href="https://datahub.com/resources/context/?utm_source=event&utm_medium=&utm_campaign=16839686-FY25-Q4-EVENT-CONTEXT-MAIS&utm_term=docs" target="_blank" class="button"><div>Watch Now<span> →</span></div></a></div></div></div><nav aria-label="Main" class="navbar navbar--fixed-top"><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 href="https://datahub.com" target="_blank" rel="noopener noreferrer" class="navbar__brand"><div class="navbar__logo"><img src="/img/datahub-logo-color-light-horizontal.svg" alt="DataHub Logo" class="themedImage_ToTc themedImage--light_HNdA"><img src="/img/datahub-logo-color-dark-horizontal.svg" alt="DataHub Logo" class="themedImage_ToTc themedImage--dark_i4oU"></div></a><div class="navbar__item dropdown dropdown--hoverable"><a href="#" aria-haspopup="true" aria-expanded="false" role="button" class="navbar__link versionNavItem_cbn8">Next</a><ul class="dropdown__menu"><li><a aria-current="page" class="dropdown__link dropdown__link--active" href="/docs/how/load-indices">Next</a></li><li><a class="dropdown__link" href="/docs/1.1.0/features">1.1.0</a></li><li><hr class="dropdown-separator" style="margin: 0.4rem;"></li><li><div class="dropdown__link"><b>Archived versions</b></div></li><li>
|
||
<a class="dropdown__link" href="https://docs-website-t9sv4w3gr-acryldata.vercel.app/docs/features">1.0.0
|
||
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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 class="dropdown__link" href="https://docs-website-t9sv4w3gr-acryldata.vercel.app/docs/0.15.0/features">0.15.0
|
||
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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 class="dropdown__link" href="https://docs-website-8jkm4uler-acryldata.vercel.app/docs/0.14.1/features">0.14.1
|
||
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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 class="dropdown__link" href="https://docs-website-eue2qafvn-acryldata.vercel.app/docs/features">0.14.0
|
||
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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 class="dropdown__link" href="https://docs-website-psat3nzgi-acryldata.vercel.app/docs/features">0.13.1
|
||
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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 class="dropdown__link" href="https://docs-website-lzxh86531-acryldata.vercel.app/docs/features">0.13.0
|
||
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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 class="dropdown__link" href="https://docs-website-2uuxmgza2-acryldata.vercel.app/docs/features">0.12.1
|
||
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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 class="dropdown__link" href="https://docs-website-irpoe2osc-acryldata.vercel.app/docs/features">0.11.0
|
||
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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 class="dropdown__link" href="https://docs-website-1gv2yzn9d-acryldata.vercel.app/docs/features">0.10.5
|
||
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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></div><div class="navbar__items navbar__items--right"><a aria-current="page" class="navbar__item navbar__link navbar__link--active" href="/docs">Docs</a><a class="navbar__item navbar__link" href="/integrations">Integrations</a><a href="https://datahub.com/slack?utm_source=docs&utm_medium=header&utm_campaign=docs_header" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link">
|
||
<style>
|
||
.slack-logo:hover {
|
||
opacity: 0.8;
|
||
}
|
||
</style>
|
||
<img class="slack-logo" src="https://upload.wikimedia.org/wikipedia/commons/d/d5/Slack_icon_2019.svg" , alt="slack" , height="20px" style="margin: 10px 0 0 0;">
|
||
</a><a href="https://github.com/datahub-project/datahub" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link">
|
||
<style>
|
||
.github-logo:hover {
|
||
opacity: 0.8;
|
||
}
|
||
</style>
|
||
<img class="github-logo" src="https://upload.wikimedia.org/wikipedia/commons/9/91/Octicons-mark-github.svg" , alt="slack" , height="20px" style="margin: 10px 0 0 0;">
|
||
</a><div class="searchBox_ZlJk"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><svg width="20" height="20" class="DocSearch-Search-Icon" viewBox="0 0 20 20" aria-hidden="true"><path d="M14.386 14.386l4.0877 4.0877-4.0877-4.0877c-2.9418 2.9419-7.7115 2.9419-10.6533 0-2.9419-2.9418-2.9419-7.7115 0-10.6533 2.9418-2.9419 7.7115-2.9419 10.6533 0 2.9419 2.9418 2.9419 7.7115 0 10.6533z" stroke="currentColor" fill="none" fill-rule="evenodd" stroke-linecap="round" stroke-linejoin="round"></path></svg><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"></span></button></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 menuWithAnnouncementBar_GW3s"><ul class="theme-doc-sidebar-menu menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menuHtmlItem_M9Kj menu__list-item"><div>Getting Started</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" aria-expanded="false" href="/docs/features">What Is DataHub?</a><button aria-label="Toggle the collapsible sidebar category 'What Is DataHub?'" type="button" class="clean-btn menu__caret"></button></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" aria-expanded="false" href="/docs/category/features">Features</a><button aria-label="Toggle the collapsible sidebar category 'Features'" type="button" class="clean-btn menu__caret"></button></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menuHtmlItem_M9Kj menu__list-item"><div>DataHub Cloud</div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/managed-datahub/managed-datahub-overview">DataHub Cloud vs. DataHub OSS</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/managed-datahub/welcome-acryl">Getting Started with DataHub Cloud</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/managed-datahub/upgrade_core_to_cloud">Upgrading from DataHub Core to Cloud</a></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/authentication/guides/sso/initialize-oidc">Configure Single Sign-On</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/managed-datahub/remote-executor/about">Remote Executor</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/managed-datahub/datahub-api/entity-events-api">DataHub API</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/managed-datahub/slack/saas-slack-app">Slack</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/managed-datahub/teams/saas-teams-app">Teams</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/managed-datahub/operator-guide/setting-up-events-api-on-aws-eventbridge">Operator Guides</a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item saasOnly"><a class="menu__link" href="/docs/managed-datahub/change-proposals">Change Proposals</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/managed-datahub/chrome-extension">Cloud Chrome Extension</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item saasOnly"><a class="menu__link" href="/docs/managed-datahub/subscription-and-notification">Subscriptions & Notifications</a></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/managed-datahub/release-notes/v_0_3_15">DataHub Cloud Release History</a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menuHtmlItem_M9Kj menu__list-item"><div>Integrations</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" aria-expanded="false" href="/docs/metadata-ingestion">Overview</a><button aria-label="Toggle the collapsible sidebar category 'Overview'" type="button" class="clean-btn menu__caret"></button></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/metadata-ingestion/cli-ingestion">Quickstart Guides</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" aria-expanded="false" href="/docs/metadata-ingestion/source_overview">Sources</a><button aria-label="Toggle the collapsible sidebar category 'Sources'" type="button" class="clean-btn menu__caret"></button></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/metadata-ingestion/schedule_docs/intro">Advanced Guides</a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menuHtmlItem_M9Kj menu__list-item"><div>API & SDKs</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" aria-expanded="true" href="/docs/metadata-modeling/metadata-model">Open Source DataHub Metadata Standard</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/metadata-modeling/metadata-model">The Metadata Model</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/what/mxe">Core Metadata Events</a></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 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" tabindex="0" href="/docs/generated/metamodel/entities/role">Entity Docs</a></div></li></ul></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/what-is-datahub/datahub-concepts">Concepts</a></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" aria-expanded="false" href="/docs/metadata-standards">Metadata Standards</a><button aria-label="Toggle the collapsible sidebar category 'Metadata Standards'" type="button" class="clean-btn menu__caret"></button></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/api/datahub-apis">APIs and SDKs Overview</a></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/api/graphql/overview">API</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/metadata-ingestion/as-a-library">Python SDK</a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/metadata-integration/java/as-a-library">Java SDK</a></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" aria-expanded="false" href="/docs/cli">DataHub CLI</a><button aria-label="Toggle the collapsible sidebar category 'DataHub CLI'" type="button" class="clean-btn menu__caret"></button></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" aria-expanded="false" href="/docs/act-on-metadata">DataHub Actions</a><button aria-label="Toggle the collapsible sidebar category 'DataHub Actions'" type="button" class="clean-btn menu__caret"></button></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/api/tutorials/datasets">Guides</a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menuHtmlItem_M9Kj menu__list-item"><div>Admin</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/authentication">Authentication</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/authorization">Authorization</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/how/delete-metadata">Advanced Guides</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/how/delete-metadata">Removing Metadata from DataHub</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/how/configuring-authorization-with-apache-ranger">Configuring Authorization with Apache Ranger</a></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 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" tabindex="0" href="/docs/managed-datahub/configuring-identity-provisioning-with-ms-entra">SCIM Provisioning</a></div></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/how/backup-datahub">Backup & Restore</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/how/restore-indices">Search and Graph Reindexing</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/how/load-indices">Load Indices: High-Performance Bulk Index Loading</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/advanced/db-retention">Configuring Database Retention</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/advanced/monitoring">Monitoring DataHub</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/deploy/telemetry">Telemetry</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/how/kafka-config">Configuring Kafka</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/how/configure-cdc">Configuring Change Data Capture (CDC) Mode</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/how/jattach-guide">Debugging by Jattach</a></li></ul></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menuHtmlItem_M9Kj menu__list-item"><div>Deployment</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" aria-expanded="false" href="/docs/category/deployment-guides">Deployment Guides</a><button aria-label="Toggle the collapsible sidebar category 'Deployment Guides'" type="button" class="clean-btn menu__caret"></button></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/deploy/confluent-cloud">Advanced Guides</a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menuHtmlItem_M9Kj menu__list-item"><div>Developers</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/architecture/architecture">Architecture</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/developers">Developing on DataHub</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/advanced/mcp-mcl">Advanced Guides</a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menuHtmlItem_M9Kj menu__list-item"><div>Community</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" aria-expanded="false" href="/docs/category/community">Community</a><button aria-label="Toggle the collapsible sidebar category 'Community'" type="button" class="clean-btn menu__caret"></button></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/releases">Release History</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">Advanced Guides</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">Load Indices: High-Performance Bulk Index Loading</span><meta itemprop="position" content="2"></li></ul></nav><span class="theme-doc-version-badge badge badge--secondary">Version: Next</span><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"><h1>Load Indices: High-Performance Bulk Index Loading</h1><p>LoadIndices is a high-performance upgrade task designed for bulk loading metadata aspects directly from the database into Elasticsearch/OpenSearch indices. Unlike RestoreIndices which focuses on correctness and consistency, LoadIndices is optimized for speed and throughput during initial deployments or large-scale data migrations.</p><h2 class="anchor anchorWithStickyNavbar_LWe7" id="overview">Overview<a href="#overview" class="hash-link" aria-label="Direct link to Overview" title="Direct link to Overview"></a></h2><p>LoadIndices bypasses the standard event-driven processing pipeline to directly stream data from the <code>metadata_aspect_v2</code> table into search indices using optimized bulk operations. This approach provides significant performance improvements for large installations while making specific architectural trade-offs that prioritize speed over consistency.</p><p>🚨 <strong>CRITICAL WARNING</strong>: LoadIndices is designed for specific use cases only and should <strong>NEVER</strong> be used in production environments with active concurrent writes, MCL-dependent systems, or real-time consistency requirements. See <a href="#performance-trade-offs--implications">Performance Trade-offs & Implications</a> for complete details.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="key-features">Key Features<a href="#key-features" class="hash-link" aria-label="Direct link to Key Features" title="Direct link to Key Features"></a></h3><ul><li><strong>🚀 High Performance</strong>: Direct streaming from database with optimized bulk operations</li><li><strong>⚡ Fast Bulk Loading</strong>: Optimized for speed over consistency during initial loads</li><li><strong>🔧 Refresh Management</strong>: Automatically disables refresh intervals during loading for optimal performance</li><li><strong>📊 Comprehensive Monitoring</strong>: Real-time progress reporting and performance metrics</li><li><strong>⚙️ Configurable Isolation</strong>: Utilizes READ_UNCOMMITTED transactions for faster scanning</li></ul><hr><h2 class="anchor anchorWithStickyNavbar_LWe7" id="performance-trade-offs--implications">Performance Trade-offs & Implications<a href="#performance-trade-offs--implications" class="hash-link" aria-label="Direct link to Performance Trade-offs & Implications" title="Direct link to Performance Trade-offs & Implications"></a></h2><p>⚠️ <strong>Critical Understanding</strong>: LoadIndices prioritizes <strong>performance over consistency</strong> by making several architectural trade-offs. Understanding these implications is crucial before using LoadIndices in production environments.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-key-trade-offs-made">🚨 Key Trade-offs Made<a href="#-key-trade-offs-made" class="hash-link" aria-label="Direct link to 🚨 Key Trade-offs Made" title="Direct link to 🚨 Key Trade-offs Made"></a></h3><h4 class="anchor anchorWithStickyNavbar_LWe7" id="1-bypass-kafkamcl-event-pipeline"><strong>1. BYPASS Kafka/MCL Event Pipeline</strong><a href="#1-bypass-kafkamcl-event-pipeline" class="hash-link" aria-label="Direct link to 1-bypass-kafkamcl-event-pipeline" title="Direct link to 1-bypass-kafkamcl-event-pipeline"></a></h4><ul><li><strong>What</strong>: LoadIndices completely bypasses Kafka MCL (Metadata Change Log) topics that normally propagate all metadata changes</li><li><strong>Architecture</strong>: <code>Database → LoadIndices → Elasticsearch</code> <strong>vs</strong> normal flow of <code>Database → Kafka MCL → Multiple Consumers → Elasticsearch/Graph/etc</code></li><li><strong>Impact</strong>: <strong>No MCL events published</strong> - downstream systems lose visibility into metadata changes</li><li><strong>Critical Implication</strong>:<ul><li><strong>MCL-Dependent Analytics</strong>: Won't have audit trail of metadata changes</li><li><strong>Integrations</strong>: External systems won't be notified of changes</li><li><strong>Custom MCL Consumers</strong>: Any custom consumers will miss these events entirely</li><li><strong>✅ Graph Service</strong>: WILL be updated (UpdateIndicesService handles graph indices) <strong>⚠️ Only when Elasticsearch is used for graph storage</strong></li></ul></li></ul><h4 class="anchor anchorWithStickyNavbar_LWe7" id="2-broken-datahub-event-architecture"><strong>2. BROKEN DataHub Event Architecture</strong><a href="#2-broken-datahub-event-architecture" class="hash-link" aria-label="Direct link to 2-broken-datahub-event-architecture" title="Direct link to 2-broken-datahub-event-architecture"></a></h4><ul><li><strong>What</strong>: Violates DataHub's core design principle that "all metadata changes flow through Kafka MCL"</li><li><strong>Normal Flow</strong>: <code>Metadata Change → MCL Event → Kafka → Multiple Consumers → Various Stores</code></li><li><strong>LoadIndices Flow</strong>: <code>Metadata Change → LoadIndices → Direct ES Write</code> (<strong>Skips Kafka entirely</strong>)</li></ul><h4 class="anchor anchorWithStickyNavbar_LWe7" id="3-read_uncommitted-isolation"><strong>3. READ_UNCOMMITTED Isolation</strong><a href="#3-read_uncommitted-isolation" class="hash-link" aria-label="Direct link to 3-read_uncommitted-isolation" title="Direct link to 3-read_uncommitted-isolation"></a></h4><ul><li><strong>What</strong>: Uses <code>TxIsolation.READ_UNCOMMITTED</code> for faster database scanning</li><li><strong>Impact</strong>: May read <strong>uncommitted changes</strong> or <strong>dirty reads</strong> from concurrent transactions</li><li><strong>Implication</strong>: Data consistency not guaranteed during active writes to database</li></ul><h4 class="anchor anchorWithStickyNavbar_LWe7" id="4-refresh-interval-manipulation"><strong>4. Refresh Interval Manipulation</strong><a href="#4-refresh-interval-manipulation" class="hash-link" aria-label="Direct link to 4-refresh-interval-manipulation" title="Direct link to 4-refresh-interval-manipulation"></a></h4><ul><li><strong>What</strong>: Automatically disables refresh intervals during bulk operations</li><li><strong>Impact</strong>: <strong>Recent updates may not be immediately searchable</strong></li><li><strong>Implication</strong>: Users won't see real-time updates in search until refresh intervals are restored</li></ul><h4 class="anchor anchorWithStickyNavbar_LWe7" id="5-no-write-concurrency-controls"><strong>5. No Write Concurrency Controls</strong><a href="#5-no-write-concurrency-controls" class="hash-link" aria-label="Direct link to 5-no-write-concurrency-controls" title="Direct link to 5-no-write-concurrency-controls"></a></h4><ul><li><strong>What</strong>: No coordination with concurrent Elasticsearch writes from live ingestion</li><li><strong>Impact</strong>: <strong>Potential conflicts</strong> with active ingestion pipelines</li><li><strong>Implication</strong>: Concurrent writes may cause data inconsistency or operation failures</li></ul><h3 class="anchor anchorWithStickyNavbar_LWe7" id="️-when-not-to-use-loadindices">⚠️ When NOT to Use LoadIndices<a href="#️-when-not-to-use-loadindices" class="hash-link" aria-label="Direct link to ⚠️ When NOT to Use LoadIndices" title="Direct link to ⚠️ When NOT to Use LoadIndices"></a></h3><p><strong>❌ DO NOT use LoadIndices if you have:</strong></p><ul><li><strong>Active ingestion pipelines</strong> writing to Elasticsearch simultaneously</li><li><strong>MCL-dependent systems</strong> that need event notifications</li><li><strong>Neo4j-based graph storage</strong> (graph updates will be missing)</li><li><strong>Real-time search requirements</strong> during the loading process</li><li><strong>Production traffic</strong> that requires immediate search consistency</li></ul><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-when-loadindices-is-appropriate">✅ When LoadIndices is Appropriate<a href="#-when-loadindices-is-appropriate" class="hash-link" aria-label="Direct link to ✅ When LoadIndices is Appropriate" title="Direct link to ✅ When LoadIndices is Appropriate"></a></h3><p><strong>✅ Safe to use LoadIndices when:</strong></p><ul><li><strong>Fresh deployment</strong> with empty Elasticsearch cluster</li><li><strong>Offline migration</strong> with no concurrent users</li><li><strong>Standalone indexing</strong> without DataHub services running</li><li><strong>Read-only replica environments</strong> with no active writes</li><li><strong>Development/testing</strong> environments</li><li><strong>Disaster recovery</strong> scenarios where faster restoration is prioritized</li><li><strong>Independent cluster setup</strong> where you need to populate indices before services start</li><li><strong>Elasticsearch-based graph storage</strong> (graph gets updated automatically)</li></ul><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-safety-requirements">🔒 Safety Requirements<a href="#-safety-requirements" class="hash-link" aria-label="Direct link to 🔒 Safety Requirements" title="Direct link to 🔒 Safety Requirements"></a></h3><p>Before using LoadIndices in any environment:</p><ol><li><p><strong>Verify Minimal Infrastructure</strong>:</p><ul><li><strong>Database</strong>: MySQL/PostgreSQL with <code>metadata_aspect_v2</code> table accessible (via Ebean ORM)</li><li><strong>Elasticsearch</strong>: Running cluster accessible via HTTP/HTTPS</li><li><strong>DataHub Services</strong>: ✅ <strong>NOT required</strong> - LoadIndices can run independently</li><li><strong>⚠️ Check Graph Storage</strong>: Verify if using Elasticsearch-based graph storage</li><li><strong>⚠️ Check Database Type</strong>: Confirm NOT using Cassandra (not supported)</li></ul></li><li><p><strong>Stop All Ingestion</strong> (if DataHub is running):</p><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Disable all Kafka consumers</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">kubectl scale deployment --replicas</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">0</span><span class="token plain"> datahub-mae-consumer</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">kubectl scale deployment --replicas</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">0</span><span class="token plain"> datahub-mce-consumer</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">kubectl scale deployment --replicas</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">0</span><span class="token plain"> datahub-gms</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></li><li><p><strong>Check Database Configuration</strong>:</p><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Check if using Cassandra (LoadIndices NOT supported)</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token function" style="color:rgb(130, 170, 255)">grep</span><span class="token plain"> -i cassandra /path/to/datahub/docker/docker-compose.yml</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Verify MySQL/PostgreSQL database is configured</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token function" style="color:rgb(130, 170, 255)">grep</span><span class="token plain"> -E </span><span class="token string" style="color:rgb(195, 232, 141)">"mysql\|postgres"</span><span class="token plain"> /path/to/datahub/docker/docker-compose.yml</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># ⚠️ If Cassandra detected, LoadIndices is NOT available</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Must use RestoreIndices instead</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></li><li><p><strong>Check Graph Storage Configuration</strong>:</p><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Check if using Neo4j (graph updates will be MISSING)</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token function" style="color:rgb(130, 170, 255)">grep</span><span class="token plain"> -r </span><span class="token string" style="color:rgb(195, 232, 141)">"neo4j"</span><span class="token plain"> /path/to/datahub/docker/docker-compose.yml</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Check DataHub configuration for graph service selection</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token function" style="color:rgb(130, 170, 255)">grep</span><span class="token plain"> -i </span><span class="token string" style="color:rgb(195, 232, 141)">"graph.*elasticsearch\|neo4j"</span><span class="token plain"> /path/to/datahub/conf/application.yml</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># ⚠️ If Neo4j is detected, LoadIndices will NOT update graph</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></li><li><p><strong>Verify No Concurrent Writes</strong>:</p><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Check for active Elasticsearch indexing</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token function" style="color:rgb(130, 170, 255)">curl</span><span class="token plain"> -s </span><span class="token string" style="color:rgb(195, 232, 141)">"localhost:9200/_nodes/stats"</span><span class="token plain"> </span><span class="token operator" style="color:rgb(137, 221, 255)">|</span><span class="token plain"> </span><span class="token function" style="color:rgb(130, 170, 255)">grep</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"index_current"</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Should show "index_current": 0</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></li><li><p><strong>Index Clean State</strong>:</p><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Ensure clean indexing state</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token function" style="color:rgb(130, 170, 255)">curl</span><span class="token plain"> -s </span><span class="token string" style="color:rgb(195, 232, 141)">"localhost:9200/_nodes/stats"</span><span class="token plain"> </span><span class="token operator" style="color:rgb(137, 221, 255)">|</span><span class="token plain"> </span><span class="token function" style="color:rgb(130, 170, 255)">grep</span><span class="token plain"> -E </span><span class="token string" style="color:rgb(195, 232, 141)">"refresh.*active"</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></li><li><p><strong>Coordinate with Operations</strong>:</p><ul><li><strong>Maintenance window</strong> scheduling</li><li><strong>User notification</strong> of search unavailability</li><li><strong>Monitoring</strong> of downstream system dependencies</li></ul></li></ol><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-consistency-guarantees">📊 Consistency Guarantees<a href="#-consistency-guarantees" class="hash-link" aria-label="Direct link to 📊 Consistency Guarantees" title="Direct link to 📊 Consistency Guarantees"></a></h3><table><thead><tr><th>Level</th><th>LoadIndices</th><th>RestoreIndices</th></tr></thead><tbody><tr><td><strong>URN-level Ordering</strong></td><td>✅ Guaranteed</td><td>✅ Guaranteed</td></tr><tr><td><strong>Real-time Searchability</strong></td><td>❌ Delayed</td><td>✅ Immediate</td></tr><tr><td><strong>Graph Service Updates (ES-based)</strong></td><td>✅ Updated</td><td>✅ Updated</td></tr><tr><td><strong>Graph Service Updates (Neo4j-based)</strong></td><td>❌ Missing</td><td>✅ Updated</td></tr><tr><td><strong>MCL Event Propagation</strong></td><td>❌ Bypassed</td><td>✅ Full propagation</td></tr><tr><td><strong>Concurrent Write Safety</strong></td><td>❌ Not safe</td><td>✅ Safe</td></tr></tbody></table><h4 class="anchor anchorWithStickyNavbar_LWe7" id="2-restore-normal-operations"><strong>2. Restore Normal Operations</strong><a href="#2-restore-normal-operations" class="hash-link" aria-label="Direct link to 2-restore-normal-operations" title="Direct link to 2-restore-normal-operations"></a></h4><ul><li><strong>Re-enable ingestion</strong> pipelines gradually</li><li><strong>Monitor Elasticsearch</strong> for conflicts</li><li><strong>Validate downstream systems</strong> are synchronized</li></ul><h4 class="anchor anchorWithStickyNavbar_LWe7" id="3-emergency-rollback-plan"><strong>3. Emergency Rollback Plan</strong><a href="#3-emergency-rollback-plan" class="hash-link" aria-label="Direct link to 3-emergency-rollback-plan" title="Direct link to 3-emergency-rollback-plan"></a></h4><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># If issues arise, prepare rollback:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># 1. Stop LoadIndices immediately</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># 2. Restore from backup indices</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># 3. Re-run with RestoreIndices for correctness</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><hr><h2 class="anchor anchorWithStickyNavbar_LWe7" id="how-loadindices-works">How LoadIndices Works<a href="#how-loadindices-works" class="hash-link" aria-label="Direct link to How LoadIndices Works" title="Direct link to How LoadIndices Works"></a></h2><p>LoadIndices operates as an upgrade task that can run <strong>independently</strong> without requiring DataHub services to be running. It consists of two main steps:</p><ol><li><strong>BuildIndicesStep</strong>: Creates and configures Elasticsearch indices (creates indices if they don't exist)</li><li><strong>LoadIndicesStep</strong>: Streams aspects from database and bulk loads them into indices</li></ol><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-independent-operation-mode">🔧 Independent Operation Mode<a href="#-independent-operation-mode" class="hash-link" aria-label="Direct link to 🔧 Independent Operation Mode" title="Direct link to 🔧 Independent Operation Mode"></a></h3><p><strong>Key Advantage</strong>: LoadIndices only requires:</p><ul><li>✅ <strong>MySQL/PostgreSQL</strong> source database (via Ebean ORM)</li><li>✅ <strong>Elasticsearch/OpenSearch</strong> destination cluster</li><li>❌ <strong>No DataHub services</strong> (maui, frontend, etc.) required</li><li>❌ <strong>Cassandra</strong>: ⚠️ <strong>NOT supported</strong> (Ebean doesn't support Cassandra)</li></ul><p>This enables <strong>offline bulk operations</strong> during maintenance windows or initial deployments where DataHub infrastructure is being set up incrementally.</p><p><strong>Index Creation</strong>: The BuildIndicesStep automatically creates all required Elasticsearch indices based on <code>IndexConvention</code> patterns, so empty Elasticsearch clusters are fully supported.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="architecture-flow">Architecture Flow<a href="#architecture-flow" class="hash-link" aria-label="Direct link to Architecture Flow" title="Direct link to Architecture Flow"></a></h3><div class="language-mermaid codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-mermaid codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token plain">graph TD</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> A[LoadIndices Upgrade] --> B[BuildIndicesStep]</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> B --> C[Create/Configure Indices]</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> C --> D[LoadIndicesStep]</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> D --> E[Disable Refresh Intervals]</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> E --> F[Stream Aspects from DB]</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> F --> G[Batch Processing]</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> G --> H[Convert to MCL Events]</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> H --> I[Bulk Write to ES]</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> I --> J[Restore Refresh Intervals]</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><h3 class="anchor anchorWithStickyNavbar_LWe7" id="key-differences-from-restoreindices">Key Differences from RestoreIndices<a href="#key-differences-from-restoreindices" class="hash-link" aria-label="Direct link to Key Differences from RestoreIndices" title="Direct link to Key Differences from RestoreIndices"></a></h3><table><thead><tr><th>Aspect</th><th>RestoreIndices</th><th>LoadIndices</th></tr></thead><tbody><tr><td><strong>Purpose</strong></td><td>Correctness & consistency</td><td>Speed & throughput</td></tr><tr><td><strong>Processing</strong></td><td>Event-driven via MCL events</td><td>Direct bulk operations</td></tr><tr><td><strong>Isolation</strong></td><td>READ_COMMITTED</td><td>READ_UNCOMMITTED</td></tr><tr><td><strong>Refresh Management</strong></td><td>Static configuration</td><td>Dynamic disable/restore</td></tr><tr><td><strong>Performance Focus</strong></td><td>Accurate replay</td><td>Maximal speed</td></tr><tr><td><strong>Use Case</strong></td><td>Recovery from inconsistencies</td><td>Initial loads & migrations</td></tr></tbody></table><hr><h2 class="anchor anchorWithStickyNavbar_LWe7" id="deployment--execution">Deployment & Execution<a href="#deployment--execution" class="hash-link" aria-label="Direct link to Deployment & Execution" title="Direct link to Deployment & Execution"></a></h2><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-standalone-deployment-advantage">🚀 Standalone Deployment Advantage<a href="#-standalone-deployment-advantage" class="hash-link" aria-label="Direct link to 🚀 Standalone Deployment Advantage" title="Direct link to 🚀 Standalone Deployment Advantage"></a></h3><p><strong>Key Benefit</strong>: LoadIndices can run with <strong>minimal infrastructure</strong> without requiring DataHub services to be running:</p><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Minimal requirements</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">✅ MySQL/PostgreSQL database </span><span class="token punctuation" style="color:rgb(199, 146, 234)">(</span><span class="token plain">with metadata_aspect_v2 table</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">✅ Elasticsearch/OpenSearch cluster</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">❌ DataHub GMS/Maui services - NOT needed</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">❌ Kafka cluster - NOT needed</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">❌ Frontend services - NOT needed</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><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-execution-methods">🔧 Execution Methods<a href="#-execution-methods" class="hash-link" aria-label="Direct link to 🔧 Execution Methods" title="Direct link to 🔧 Execution Methods"></a></h3><p>LoadIndices can be executed via:</p><ol><li><strong>Gradle Task</strong> (Recommended)</li></ol><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># From datahub-upgrade directory</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">./gradlew runLoadIndices</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># With custom thread count</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">./gradlew runLoadIndices -PesThreadCount</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">6</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><ol start="2"><li><p><strong>IDE Execution</strong>: Run <code>UpgradeTask.main()</code> with LoadIndices arguments</p></li><li><p><strong>Standalone JAR</strong>: Build and run datahub-upgrade JAR independently</p></li></ol><hr><h2 class="anchor anchorWithStickyNavbar_LWe7" id="loadindices-configuration-options">LoadIndices Configuration Options<a href="#loadindices-configuration-options" class="hash-link" aria-label="Direct link to LoadIndices Configuration Options" title="Direct link to LoadIndices Configuration Options"></a></h2><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-performance--throttling">🔄 Performance & Throttling<a href="#-performance--throttling" class="hash-link" aria-label="Direct link to 🔄 Performance & Throttling" title="Direct link to 🔄 Performance & Throttling"></a></h3><table><thead><tr><th>Argument</th><th>Description</th><th>Default</th><th>Example</th></tr></thead><tbody><tr><td><code>batchSize</code></td><td>Number of aspects per batch for processing</td><td><code>10000</code></td><td><code>-a batchSize=5000</code></td></tr><tr><td><code>limit</code></td><td>Maximum number of aspects to process</td><td><code>Integer.MAX_VALUE</code> (no limit)</td><td><code>-a limit=50000</code></td></tr></tbody></table><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-time-filtering">📅 Time Filtering<a href="#-time-filtering" class="hash-link" aria-label="Direct link to 📅 Time Filtering" title="Direct link to 📅 Time Filtering"></a></h3><table><thead><tr><th>Argument</th><th>Description</th><th>Example</th></tr></thead><tbody><tr><td><code>gePitEpochMs</code></td><td>Only process aspects created <strong>after</strong> this timestamp (milliseconds)</td><td><code>-a gePitEpochMs=1609459200000</code></td></tr><tr><td><code>lePitEpochMs</code></td><td>Only process aspects created <strong>before</strong> this timestamp (milliseconds)</td><td><code>-a lePitEpochMs=1640995200000</code></td></tr></tbody></table><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-content-filtering">🔍 Content Filtering<a href="#-content-filtering" class="hash-link" aria-label="Direct link to 🔍 Content Filtering" title="Direct link to 🔍 Content Filtering"></a></h3><table><thead><tr><th>Argument</th><th>Description</th><th>Example</th></tr></thead><tbody><tr><td><code>urnLike</code></td><td>SQL LIKE pattern to filter URNs</td><td><code>-a urnLike=urn:li:dataset:%</code></td></tr><tr><td><code>aspectNames</code></td><td>Comma-separated list of aspect names to process</td><td><code>-a aspectNames=ownership,schemaMetadata</code></td></tr><tr><td><code>lastUrn</code></td><td>Resume processing from this URN (inclusive)</td><td><code>-a lastUrn=urn:li:dataset:my-dataset</code></td></tr></tbody></table><h3 class="anchor anchorWithStickyNavbar_LWe7" id="️-system-configuration">⚙️ System Configuration<a href="#️-system-configuration" class="hash-link" aria-label="Direct link to ⚙️ System Configuration" title="Direct link to ⚙️ System Configuration"></a></h3><table><thead><tr><th>Environment Variable</th><th>Description</th><th>Default</th><th>Example</th></tr></thead><tbody><tr><td><code>ELASTICSEARCH_THREAD_COUNT</code></td><td>Number of I/O threads for BulkProcessor</td><td><code>2</code> (app config), <code>4</code> (Gradle task)</td><td><code>ELASTICSEARCH_THREAD_COUNT=4</code></td></tr><tr><td><code>ES_BULK_ASYNC</code></td><td>Enable asynchronous bulk operations</td><td><code>true</code></td><td><code>ES_BULK_ASYNC=true</code></td></tr><tr><td><code>ES_BULK_REQUESTS_LIMIT</code></td><td>Maximum bulk requests per buffer</td><td><code>10000</code></td><td><code>ES_BULK_REQUESTS_LIMIT=15000</code></td></tr><tr><td><code>ES_BULK_FLUSH_PERIOD</code></td><td>Bulk flush interval in seconds</td><td><code>300</code> (5 minutes)</td><td><code>ES_BULK_FLUSH_PERIOD=300</code></td></tr></tbody></table><hr><h2 class="anchor anchorWithStickyNavbar_LWe7" id="running-loadindices">Running LoadIndices<a href="#running-loadindices" class="hash-link" aria-label="Direct link to Running LoadIndices" title="Direct link to Running LoadIndices"></a></h2><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-docker-compose">🐳 Docker Compose<a href="#-docker-compose" class="hash-link" aria-label="Direct link to 🐳 Docker Compose" title="Direct link to 🐳 Docker Compose"></a></h3><p>If you're using Docker Compose with the DataHub source repository:</p><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Basic LoadIndices execution</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">./docker/datahub-upgrade/datahub-upgrade.sh -u LoadIndices</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># LoadIndices with performance tuning</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">./docker/datahub-upgrade/datahub-upgrade.sh -u LoadIndices </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">batchSize</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">15000</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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">limit</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">100000</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><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-gradle-task-development">🎯 Gradle Task (Development)<a href="#-gradle-task-development" class="hash-link" aria-label="Direct link to 🎯 Gradle Task (Development)" title="Direct link to 🎯 Gradle Task (Development)"></a></h3><p>For development and testing environments:</p><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Run LoadIndices with default settings</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">./gradlew :datahub-upgrade:runLoadIndices</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Run with custom thread count and batch size</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">./gradlew :datahub-upgrade:runLoadIndices </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"> -PesThreadCount</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">4</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"> -PbatchSize</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">15000</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"> -Plimit</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">50000</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>The Gradle task supports these parameters:</p><ul><li><code>esThreadCount</code>: Set <code>ELASTICSEARCH_THREAD_COUNT</code> (default: <code>4</code>)</li><li><code>batchSize</code>: Override batch size (default: <code>10000</code>)</li><li><code>limit</code>: Set processing limit</li><li><code>urnLike</code>: Filter by URN pattern</li><li><code>aspectNames</code>: Filter by aspect names</li><li><code>lePitEpochMs</code>: Process records created before this timestamp</li><li><code>gePitEpochMs</code>: Process records created after this timestamp</li><li><code>lastUrn</code>: Resume processing from this URN (inclusive)</li></ul><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-docker-environment-variables">🐳 Docker Environment Variables<a href="#-docker-environment-variables" class="hash-link" aria-label="Direct link to 🐳 Docker Environment Variables" title="Direct link to 🐳 Docker Environment Variables"></a></h3><p>Configure LoadIndices through Docker environment:</p><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Target specific entity types</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token function" style="color:rgb(130, 170, 255)">docker</span><span class="token plain"> run --rm datahub-upgrade </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"> -u LoadIndices </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">urnLike</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token plain">urn:li:dataset:% </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">batchSize</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">20000</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Process specific aspects only</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token function" style="color:rgb(130, 170, 255)">docker</span><span class="token plain"> run --rm datahub-upgrade </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"> -u LoadIndices </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">aspectNames</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token plain">ownership,status,schemaMetadata </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">batchSize</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">15000</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Time-based filtering</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token function" style="color:rgb(130, 170, 255)">docker</span><span class="token plain"> run --rm datahub-upgrade </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"> -u LoadIndices </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">gePitEpochMs</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">1640995200000</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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">limit</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">50000</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Resume from a specific URN</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token function" style="color:rgb(130, 170, 255)">docker</span><span class="token plain"> run --rm datahub-upgrade </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"> -u LoadIndices </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">lastUrn</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token plain">urn:li:dataset:my-dataset </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">batchSize</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">10000</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><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-resume-functionality">🔄 Resume Functionality<a href="#-resume-functionality" class="hash-link" aria-label="Direct link to 🔄 Resume Functionality" title="Direct link to 🔄 Resume Functionality"></a></h3><p>LoadIndices supports resuming from a specific URN when processing is interrupted:</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="resume-from-last-processed-urn"><strong>Resume from Last Processed URN</strong><a href="#resume-from-last-processed-urn" class="hash-link" aria-label="Direct link to resume-from-last-processed-urn" title="Direct link to resume-from-last-processed-urn"></a></h4><p>When LoadIndices runs, it logs the last URN processed in each batch:</p><div class="codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-text codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token plain">Batch completed - Last URN processed: urn:li:dataset:my-dataset</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">Processed 10000 aspects - 150.2 aspects/sec - Last URN: urn:li:dataset:my-dataset</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>To resume from where you left off:</p><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Resume from the last URN that was successfully processed</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">./gradlew :datahub-upgrade:runLoadIndices </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">lastUrn</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token plain">urn:li:dataset:my-dataset </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">batchSize</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">10000</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><h4 class="anchor anchorWithStickyNavbar_LWe7" id="resume-best-practices"><strong>Resume Best Practices</strong><a href="#resume-best-practices" class="hash-link" aria-label="Direct link to resume-best-practices" title="Direct link to resume-best-practices"></a></h4><ul><li><strong>Use the exact URN</strong>: Copy the URN exactly as logged (including any URL encoding)</li><li><strong>Inclusive processing</strong>: The <code>lastUrn</code> parameter processes from the specified URN onwards (inclusive)</li><li><strong>Monitor progress</strong>: Watch the logs for the "Last URN processed" messages to track progress</li><li><strong>Batch boundaries</strong>: Resume works at the URN level, not batch level - some aspects may be reprocessed</li></ul><h4 class="anchor anchorWithStickyNavbar_LWe7" id="example-resume-workflow"><strong>Example Resume Workflow</strong><a href="#example-resume-workflow" class="hash-link" aria-label="Direct link to example-resume-workflow" title="Direct link to example-resume-workflow"></a></h4><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># 1. Start initial processing</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">./gradlew :datahub-upgrade:runLoadIndices -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">batchSize</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">5000</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># 2. If interrupted, check logs for last URN:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># "Batch completed - Last URN processed: urn:li:dataset:my-dataset"</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># 3. Resume from that URN</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">./gradlew :datahub-upgrade:runLoadIndices </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">lastUrn</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token plain">urn:li:dataset:my-dataset </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"> -a </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">batchSize</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">5000</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><hr><h2 class="anchor anchorWithStickyNavbar_LWe7" id="performance-optimization">Performance Optimization<a href="#performance-optimization" class="hash-link" aria-label="Direct link to Performance Optimization" title="Direct link to Performance Optimization"></a></h2><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-elasticsearchopensearch-configuration">🚀 Elasticsearch/OpenSearch Configuration<a href="#-elasticsearchopensearch-configuration" class="hash-link" aria-label="Direct link to 🚀 Elasticsearch/OpenSearch Configuration" title="Direct link to 🚀 Elasticsearch/OpenSearch Configuration"></a></h3><h4 class="anchor anchorWithStickyNavbar_LWe7" id="bulk-processing-tuning">Bulk Processing Tuning<a href="#bulk-processing-tuning" class="hash-link" aria-label="Direct link to Bulk Processing Tuning" title="Direct link to Bulk Processing Tuning"></a></h4><div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Optimize bulk settings for LoadIndices</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token builtin class-name" style="color:rgb(255, 203, 107)">export</span><span class="token plain"> </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">ES_BULK_REQUESTS_LIMIT</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">15000</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token builtin class-name" style="color:rgb(255, 203, 107)">export</span><span class="token plain"> </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">ES_BULK_FLUSH_PERIOD</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">10</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token builtin class-name" style="color:rgb(255, 203, 107)">export</span><span class="token plain"> </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">ES_BULK_ASYNC</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token plain">true</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token builtin class-name" style="color:rgb(255, 203, 107)">export</span><span class="token plain"> </span><span class="token assign-left variable" style="color:rgb(191, 199, 213)">ELASTICSEARCH_THREAD_COUNT</span><span class="token operator" style="color:rgb(137, 221, 255)">=</span><span class="token number" style="color:rgb(247, 140, 108)">4</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><h4 class="anchor anchorWithStickyNavbar_LWe7" id="connection-pool-optimization">Connection Pool Optimization<a href="#connection-pool-optimization" class="hash-link" aria-label="Direct link to Connection Pool Optimization" title="Direct link to Connection Pool Optimization"></a></h4><p>LoadIndices automatically configures connection pooling based on thread count:</p><div class="language-yaml codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-yaml codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># datahub-upgrade/build.gradle configuration</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">environment "ELASTICSEARCH_THREAD_COUNT"</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"4"</span><span class="token plain"> </span><span class="token comment" style="color:rgb(105, 112, 152);font-style:italic"># Auto-adjusts maxConnectionsPerRoute</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><h2 class="anchor anchorWithStickyNavbar_LWe7" id="comparison-with-restoreindices">Comparison with RestoreIndices<a href="#comparison-with-restoreindices" class="hash-link" aria-label="Direct link to Comparison with RestoreIndices" title="Direct link to Comparison with RestoreIndices"></a></h2><p>Understanding when to use LoadIndices vs RestoreIndices is crucial for optimal performance and data consistency.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-purpose--design-philosophy">🎯 Purpose & Design Philosophy<a href="#-purpose--design-philosophy" class="hash-link" aria-label="Direct link to 🎯 Purpose & Design Philosophy" title="Direct link to 🎯 Purpose & Design Philosophy"></a></h3><table><thead><tr><th>Aspect</th><th>RestoreIndices</th><th>LoadIndices</th></tr></thead><tbody><tr><td><strong>Primary Purpose</strong></td><td>Data consistency & correctness</td><td>Speed & throughput</td></tr><tr><td><strong>Design Philosophy</strong></td><td>Event-driven precision</td><td>Performance optimization</td></tr><tr><td><strong>Consistency Model</strong></td><td>Full consistency guarantee</td><td>Speed-optimized trade-offs</td></tr><tr><td><strong>Use Case</strong></td><td>Production recovery</td><td>Bulk migrations & initial loads</td></tr></tbody></table><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-technical-comparison">📊 Technical Comparison<a href="#-technical-comparison" class="hash-link" aria-label="Direct link to 📊 Technical Comparison" title="Direct link to 📊 Technical Comparison"></a></h3><table><thead><tr><th>Feature</th><th>RestoreIndices</th><th>LoadIndices</th></tr></thead><tbody><tr><td><strong>Database Isolation</strong></td><td>READ_COMMITTED</td><td>READ_UNCOMMITTED</td></tr><tr><td><strong>MCL Events</strong></td><td>✅ Full MCL pipeline</td><td>❌ Bypasses MCL entirely</td></tr><tr><td><strong>Graph Updates (Elasticsearch)</strong></td><td>✅ Updated</td><td>✅ Updated</td></tr><tr><td><strong>Graph Updates (Neo4j)</strong></td><td>✅ Updated</td><td>❌ Missing</td></tr><tr><td><strong>Database Support</strong></td><td>MySQL, PostgreSQL, Cassandra</td><td>MySQL, PostgreSQL only</td></tr><tr><td><strong>Performance</strong></td><td>Slower, safer</td><td>Faster, optimized</td></tr><tr><td><strong>Real-time Consistency</strong></td><td>✅ Immediate</td><td>❌ Delayed until refresh</td></tr><tr><td><strong>Concurrency Safety</strong></td><td>✅ Safe</td><td>❌ Not safe</td></tr></tbody></table><h3 class="anchor anchorWithStickyNavbar_LWe7" id="-when-to-use-each-tool">🚀 When to Use Each Tool<a href="#-when-to-use-each-tool" class="hash-link" aria-label="Direct link to 🚀 When to Use Each Tool" title="Direct link to 🚀 When to Use Each Tool"></a></h3><h4 class="anchor anchorWithStickyNavbar_LWe7" id="-use-restoreindices-for">✅ <strong>Use RestoreIndices For:</strong><a href="#-use-restoreindices-for" class="hash-link" aria-label="Direct link to -use-restoreindices-for" title="Direct link to -use-restoreindices-for"></a></h4><ul><li><strong>Production recovery</strong> from inconsistencies</li><li><strong>Neo4j-based graph storage</strong> deployments</li><li><strong>Cassandra-based</strong> metadata storage</li><li><strong>Active ingestion</strong> pipelines running</li><li><strong>MCL-dependent systems</strong> requiring event notifications</li><li><strong>Precise event replay</strong> scenarios</li></ul><h4 class="anchor anchorWithStickyNavbar_LWe7" id="-use-loadindices-for">✅ <strong>Use LoadIndices For:</strong><a href="#-use-loadindices-for" class="hash-link" aria-label="Direct link to -use-loadindices-for" title="Direct link to -use-loadindices-for"></a></h4><ul><li><strong>Fresh deployments</strong> with empty clusters</li><li><strong>Bulk migrations</strong> during maintenance windows</li><li><strong>MySQL/PostgreSQL + Elasticsearch</strong> configurations</li><li><strong>Offline scenarios</strong> with no concurrent writes</li><li><strong>Development/testing</strong> environments</li><li><strong>Performance-critical</strong> initial data loads</li></ul></div><footer class="theme-doc-footer docusaurus-mt-lg"><div class="slackUtm_uoBr"><div class="slackUtm_uoBr"><hr>Need more help? Join the conversation in <a href="https://datahub.com/slack?utm_source=docs&utm_medium=footer&utm_campaign=docs_footer&utm_content=docs/how/load-indices">Slack!</a></div></div><div class="theme-doc-footer-edit-meta-row row"><div class="col"><a href="https://github.com/datahub-project/datahub/blob/master/docs/how/load-indices.md" target="_blank" rel="noreferrer noopener" class="theme-edit-this-page"><svg fill="currentColor" height="20" width="20" viewBox="0 0 40 40" class="iconEdit_Z9Sw" aria-hidden="true"><g><path d="m34.5 11.7l-3 3.1-6.3-6.3 3.1-3q0.5-0.5 1.2-0.5t1.1 0.5l3.9 3.9q0.5 0.4 0.5 1.1t-0.5 1.2z m-29.5 17.1l18.4-18.5 6.3 6.3-18.4 18.4h-6.3v-6.2z"></path></g></svg>Edit this page</a></div><div class="col lastUpdated_VsjB"></div></div></footer><div class="feedbackWrapper_mUHF"><div class="feedbackWidget_PX4d"><div class="feedbackButtons_wn3V"><strong>Is this page helpful?</strong><div><button class="feedbackButton_UgQs"><span role="img" aria-label="like" class="anticon anticon-like"><svg viewBox="64 64 896 896" focusable="false" data-icon="like" width="1em" height="1em" fill="currentColor" aria-hidden="true"><path d="M885.9 533.7c16.8-22.2 26.1-49.4 26.1-77.7 0-44.9-25.1-87.4-65.5-111.1a67.67 67.67 0 00-34.3-9.3H572.4l6-122.9c1.4-29.7-9.1-57.9-29.5-79.4A106.62 106.62 0 00471 99.9c-52 0-98 35-111.8 85.1l-85.9 311H144c-17.7 0-32 14.3-32 32v364c0 17.7 14.3 32 32 32h601.3c9.2 0 18.2-1.8 26.5-5.4 47.6-20.3 78.3-66.8 78.3-118.4 0-12.6-1.8-25-5.4-37 16.8-22.2 26.1-49.4 26.1-77.7 0-12.6-1.8-25-5.4-37 16.8-22.2 26.1-49.4 26.1-77.7-.2-12.6-2-25.1-5.6-37.1zM184 852V568h81v284h-81zm636.4-353l-21.9 19 13.9 25.4a56.2 56.2 0 016.9 27.3c0 16.5-7.2 32.2-19.6 43l-21.9 19 13.9 25.4a56.2 56.2 0 016.9 27.3c0 16.5-7.2 32.2-19.6 43l-21.9 19 13.9 25.4a56.2 56.2 0 016.9 27.3c0 22.4-13.2 42.6-33.6 51.8H329V564.8l99.5-360.5a44.1 44.1 0 0142.2-32.3c7.6 0 15.1 2.2 21.1 6.7 9.9 7.4 15.2 18.6 14.6 30.5l-9.6 198.4h314.4C829 418.5 840 436.9 840 456c0 16.5-7.2 32.1-19.6 43z"></path></svg></span></button><button class="feedbackButton_UgQs"><span role="img" aria-label="dislike" class="anticon anticon-dislike"><svg viewBox="64 64 896 896" focusable="false" data-icon="dislike" width="1em" height="1em" fill="currentColor" aria-hidden="true"><path d="M885.9 490.3c3.6-12 5.4-24.4 5.4-37 0-28.3-9.3-55.5-26.1-77.7 3.6-12 5.4-24.4 5.4-37 0-28.3-9.3-55.5-26.1-77.7 3.6-12 5.4-24.4 5.4-37 0-51.6-30.7-98.1-78.3-118.4a66.1 66.1 0 00-26.5-5.4H144c-17.7 0-32 14.3-32 32v364c0 17.7 14.3 32 32 32h129.3l85.8 310.8C372.9 889 418.9 924 470.9 924c29.7 0 57.4-11.8 77.9-33.4 20.5-21.5 31-49.7 29.5-79.4l-6-122.9h239.9c12.1 0 23.9-3.2 34.3-9.3 40.4-23.5 65.5-66.1 65.5-111 0-28.3-9.3-55.5-26.1-77.7zM184 456V172h81v284h-81zm627.2 160.4H496.8l9.6 198.4c.6 11.9-4.7 23.1-14.6 30.5-6.1 4.5-13.6 6.8-21.1 6.7a44.28 44.28 0 01-42.2-32.3L329 459.2V172h415.4a56.85 56.85 0 0133.6 51.8c0 9.7-2.3 18.9-6.9 27.3l-13.9 25.4 21.9 19a56.76 56.76 0 0119.6 43c0 9.7-2.3 18.9-6.9 27.3l-13.9 25.4 21.9 19a56.76 56.76 0 0119.6 43c0 9.7-2.3 18.9-6.9 27.3l-14 25.5 21.9 19a56.76 56.76 0 0119.6 43c0 19.1-11 37.5-28.8 48.4z"></path></svg></span></button></div></div></div></div></article><nav class="pagination-nav docusaurus-mt-lg" aria-label="Docs pages"><a class="pagination-nav__link pagination-nav__link--prev" href="/docs/how/restore-indices"><div class="pagination-nav__sublabel">Previous</div><div class="pagination-nav__label">Search and Graph Reindexing</div></a><a class="pagination-nav__link pagination-nav__link--next" href="/docs/advanced/db-retention"><div class="pagination-nav__sublabel">Next</div><div class="pagination-nav__label">Configuring Database Retention</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="#overview" class="table-of-contents__link toc-highlight">Overview</a><ul><li><a href="#key-features" class="table-of-contents__link toc-highlight">Key Features</a></li></ul></li><li><a href="#performance-trade-offs--implications" class="table-of-contents__link toc-highlight">Performance Trade-offs & Implications</a><ul><li><a href="#-key-trade-offs-made" class="table-of-contents__link toc-highlight">🚨 Key Trade-offs Made</a></li><li><a href="#️-when-not-to-use-loadindices" class="table-of-contents__link toc-highlight">⚠️ When NOT to Use LoadIndices</a></li><li><a href="#-when-loadindices-is-appropriate" class="table-of-contents__link toc-highlight">✅ When LoadIndices is Appropriate</a></li><li><a href="#-safety-requirements" class="table-of-contents__link toc-highlight">🔒 Safety Requirements</a></li><li><a href="#-consistency-guarantees" class="table-of-contents__link toc-highlight">📊 Consistency Guarantees</a></li></ul></li><li><a href="#how-loadindices-works" class="table-of-contents__link toc-highlight">How LoadIndices Works</a><ul><li><a href="#-independent-operation-mode" class="table-of-contents__link toc-highlight">🔧 Independent Operation Mode</a></li><li><a href="#architecture-flow" class="table-of-contents__link toc-highlight">Architecture Flow</a></li><li><a href="#key-differences-from-restoreindices" class="table-of-contents__link toc-highlight">Key Differences from RestoreIndices</a></li></ul></li><li><a href="#deployment--execution" class="table-of-contents__link toc-highlight">Deployment & Execution</a><ul><li><a href="#-standalone-deployment-advantage" class="table-of-contents__link toc-highlight">🚀 Standalone Deployment Advantage</a></li><li><a href="#-execution-methods" class="table-of-contents__link toc-highlight">🔧 Execution Methods</a></li></ul></li><li><a href="#loadindices-configuration-options" class="table-of-contents__link toc-highlight">LoadIndices Configuration Options</a><ul><li><a href="#-performance--throttling" class="table-of-contents__link toc-highlight">🔄 Performance & Throttling</a></li><li><a href="#-time-filtering" class="table-of-contents__link toc-highlight">📅 Time Filtering</a></li><li><a href="#-content-filtering" class="table-of-contents__link toc-highlight">🔍 Content Filtering</a></li><li><a href="#️-system-configuration" class="table-of-contents__link toc-highlight">⚙️ System Configuration</a></li></ul></li><li><a href="#running-loadindices" class="table-of-contents__link toc-highlight">Running LoadIndices</a><ul><li><a href="#-docker-compose" class="table-of-contents__link toc-highlight">🐳 Docker Compose</a></li><li><a href="#-gradle-task-development" class="table-of-contents__link toc-highlight">🎯 Gradle Task (Development)</a></li><li><a href="#-docker-environment-variables" class="table-of-contents__link toc-highlight">🐳 Docker Environment Variables</a></li><li><a href="#-resume-functionality" class="table-of-contents__link toc-highlight">🔄 Resume Functionality</a></li></ul></li><li><a href="#performance-optimization" class="table-of-contents__link toc-highlight">Performance Optimization</a><ul><li><a href="#-elasticsearchopensearch-configuration" class="table-of-contents__link toc-highlight">🚀 Elasticsearch/OpenSearch Configuration</a></li></ul></li><li><a href="#comparison-with-restoreindices" class="table-of-contents__link toc-highlight">Comparison with RestoreIndices</a><ul><li><a href="#-purpose--design-philosophy" class="table-of-contents__link toc-highlight">🎯 Purpose & Design Philosophy</a></li><li><a href="#-technical-comparison" class="table-of-contents__link toc-highlight">📊 Technical Comparison</a></li><li><a href="#-when-to-use-each-tool" class="table-of-contents__link toc-highlight">🚀 When to Use Each Tool</a></li></ul></li></ul></div></div></div></div></main></div></div><footer class="footer footer--dark"><div class="container container-fluid"><div class="row footer__links"><div class="col footer__col"><div class="footer__title">Docs</div><ul class="footer__items clean-list"><li class="footer__item"><a class="footer__link-item" href="/docs/">Introduction</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/quickstart">Quickstart</a></li></ul></div><div class="col footer__col"><div class="footer__title">Community</div><ul class="footer__items clean-list"><li class="footer__item"><a href="https://datahub.com/slack" target="_blank" rel="noopener noreferrer" class="footer__link-item">Slack<svg width="13.5" height="13.5" 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 class="footer__item"><a href="https://www.youtube.com/channel/UC3qFQC5IiwR5fvWEqi_tJ5w" target="_blank" rel="noopener noreferrer" class="footer__link-item">YouTube<svg width="13.5" height="13.5" 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 class="footer__item"><a href="https://medium.com/datahub-project" target="_blank" rel="noopener noreferrer" class="footer__link-item">Blog<svg width="13.5" height="13.5" 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 class="footer__item"><a class="footer__link-item" href="/docs/townhalls">Town Halls</a></li><li class="footer__item"><a href="https://datahub.com/resources/?2004611554=dh-stories" target="_blank" rel="noopener noreferrer" class="footer__link-item">Customer Stories<svg width="13.5" height="13.5" 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><div class="col footer__col"><div class="footer__title">More</div><ul class="footer__items clean-list"><li class="footer__item"><a href="https://demo.datahub.com/" target="_blank" rel="noopener noreferrer" class="footer__link-item">Demo</a></li><li class="footer__item"><a href="https://feature-requests.datahubproject.io/roadmap" target="_blank" rel="noopener noreferrer" class="footer__link-item">Roadmap<svg width="13.5" height="13.5" 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 class="footer__item"><a class="footer__link-item" href="/docs/contributing">Contributing</a></li><li class="footer__item"><a href="https://github.com/datahub-project/datahub" target="_blank" rel="noopener noreferrer" class="footer__link-item">GitHub<svg width="13.5" height="13.5" 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 class="footer__item"><a href="https://feature-requests.datahubproject.io/" target="_blank" rel="noopener noreferrer" class="footer__link-item">Feature Requests<svg width="13.5" height="13.5" 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></div><div class="footer__bottom text--center"><div class="footer__copyright">Copyright © 2015-2025 DataHub Project Authors.</div></div></div></footer></div>
|
||
<script src="/assets/js/runtime~main.76cdbaa9.js"></script>
|
||
<script src="/assets/js/main.b7ce4b14.js"></script>
|
||
</body>
|
||
</html> |