| <!doctype html> |
| <html lang="en" dir="ltr"> |
| <head> |
| <meta charset="UTF-8"> |
| <meta name="viewport" content="width=device-width,initial-scale=1"> |
| <meta name="generator" content="Docusaurus v2.0.0-beta.14"> |
| <link rel="alternate" type="application/rss+xml" href="/blog/rss.xml" title="Apache Hudi: User-Facing Analytics RSS Feed"> |
| <link rel="alternate" type="application/atom+xml" href="/blog/atom.xml" title="Apache Hudi: User-Facing Analytics Atom Feed"> |
| <link rel="alternate" type="application/json" href="/blog/feed.json" title="Apache Hudi: User-Facing Analytics JSON Feed"> |
| <link rel="search" type="application/opensearchdescription+xml" title="Apache Hudi" href="/opensearch.xml"> |
| <link rel="alternate" type="application/rss+xml" href="/videos/rss.xml" title="Apache Hudi RSS Feed"> |
| <link rel="alternate" type="application/atom+xml" href="/videos/atom.xml" title="Apache Hudi Atom Feed"> |
| <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Comfortaa|Ubuntu|Roboto|Source+Code+Pro"> |
| <link rel="stylesheet" href="https://at-ui.github.io/feather-font/css/iconfont.css"><title data-react-helmet="true">Optimize Data lake layout using Clustering in Apache Hudi | Apache Hudi</title><meta data-react-helmet="true" name="twitter:card" content="summary_large_image"><meta data-react-helmet="true" property="og:url" content="https://hudi.apache.org/blog/2021/01/27/hudi-clustering-intro"><meta data-react-helmet="true" name="docsearch:language" content="en"><meta data-react-helmet="true" name="docsearch:docusaurus_tag" content="default"><meta data-react-helmet="true" name="keywords" content="apache hudi, data lake, lakehouse, big data, apache spark, apache flink, presto, trino, analytics, data engineering"><meta data-react-helmet="true" property="og:title" content="Optimize Data lake layout using Clustering in Apache Hudi | Apache Hudi"><meta data-react-helmet="true" name="description" content="Background"><meta data-react-helmet="true" property="og:description" content="Background"><meta data-react-helmet="true" property="og:image" content="https://hudi.apache.org/assets/images/blog/2021-01-27-hudi-clustering-intro.png"><meta data-react-helmet="true" name="twitter:image" content="https://hudi.apache.org/assets/images/blog/2021-01-27-hudi-clustering-intro.png"><meta data-react-helmet="true" property="og:type" content="article"><meta data-react-helmet="true" property="article:published_time" content="2021-01-27T00:00:00.000Z"><meta data-react-helmet="true" property="article:tag" content="design,clustering,apache hudi"><link data-react-helmet="true" rel="icon" href="/assets/images/favicon.ico"><link data-react-helmet="true" rel="canonical" href="https://hudi.apache.org/blog/2021/01/27/hudi-clustering-intro"><link data-react-helmet="true" rel="alternate" href="https://hudi.apache.org/blog/2021/01/27/hudi-clustering-intro" hreflang="en"><link data-react-helmet="true" rel="alternate" href="https://hudi.apache.org/cn/blog/2021/01/27/hudi-clustering-intro" hreflang="cn"><link data-react-helmet="true" rel="alternate" href="https://hudi.apache.org/blog/2021/01/27/hudi-clustering-intro" hreflang="x-default"><link data-react-helmet="true" rel="preconnect" href="https://BH4D9OD16A-dsn.algolia.net" crossorigin="anonymous"><link rel="stylesheet" href="/assets/css/styles.ea681a30.css"> |
| <link rel="preload" href="/assets/js/runtime~main.2cab5691.js" as="script"> |
| <link rel="preload" href="/assets/js/main.bd020950.js" as="script"> |
| </head> |
| <body> |
| <script>!function(){function t(t){document.documentElement.setAttribute("data-theme",t)}var e=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><a href="#" class="skipToContent_OuoZ">Skip to main content</a></div><div class="announcementBar_axC9" role="banner"><div class="announcementBarPlaceholder_xYHE"></div><div class="announcementBarContent_6uhP">⭐️ If you like Apache Hudi, give it a star on <a target="_blank" rel="noopener noreferrer" href="https://github.com/apache/hudi">GitHub</a>! ⭐</div><button type="button" class="clean-btn close announcementBarClose_A3A1" aria-label="Close"><svg viewBox="0 0 15 15" width="14" height="14"><g stroke="currentColor" stroke-width="3.1"><path d="M.75.75l13.5 13.5M14.25.75L.75 14.25"></path></g></svg></button></div><nav class="navbar navbar--fixed-top navbarWrapper_UIa0"><div class="navbar__inner"><img referrerpolicy="no-referrer-when-downgrade" src="https://static.scarf.sh/a.png?x-pxid=8f594acf-9b77-44fb-9475-3e82ead1910c" width="0" height="0" alt=""><img referrerpolicy="no-referrer-when-downgrade" src="https://analytics.apache.org/matomo.php?idsite=47&rec=1" width="0" height="0" alt=""><div class="navbar__items"><button aria-label="Navigation bar toggle" class="navbar__toggle clean-btn" type="button" tabindex="0"><svg width="30" height="30" viewBox="0 0 30 30" aria-hidden="true"><path stroke="currentColor" stroke-linecap="round" stroke-miterlimit="10" stroke-width="2" d="M4 7h22M4 15h22M4 23h22"></path></svg></button><a class="navbar__brand" href="/"><div class="navbar__logo navbarLogo_Bz6n"><img src="/assets/images/hudi.png" alt="Apache Hudi" class="themedImage_TMUO themedImage--light_4Vu1"><img src="/assets/images/hudi.png" alt="Apache Hudi" class="themedImage_TMUO themedImage--dark_uzRr"></div></a><a class="navbar__item navbar__link" href="/docs/overview"><div class="labelWrapperDropdown_Mqbj">Docs</div></a><div class="navbar__item dropdown dropdown--hoverable"><a href="#" class="navbar__link downloadLinkDropdownHide_aDP3"><div class="labelWrapperDropdown_Mqbj">Learn<svg width="10" height="6" viewBox="0 0 10 6" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M8.5 1.25 5 4.75l-3.5-3.5" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path></svg></div></a><ul class="dropdown__menu"><li><a class="dropdown__link" href="/talks"><div class="labelWrapperDropdown_Mqbj">Talks</div></a></li><li><a class="dropdown__link" href="/videos"><div class="labelWrapperDropdown_Mqbj">Video Guides</div></a></li><li><a class="dropdown__link" href="/docs/faq"><div class="labelWrapperDropdown_Mqbj">FAQ</div></a></li><li><a class="dropdown__link" href="/tech-specs"><div class="labelWrapperDropdown_Mqbj">Tech Specs</div></a></li><li><a class="dropdown__link" href="/tech-specs-1point0"><div class="labelWrapperDropdown_Mqbj">Tech Specs 1.0</div></a></li><li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank" rel="noopener noreferrer" class="dropdown__link"><span class="externalLink_AE3f">Technical Wiki<svg width="20" height="20" viewBox="0 0 26 26" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M16.965 8.745 9.01 16.7M10.561 8.758l6.403-.013-.013 6.403" stroke="#0DB1F9" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path><rect x="4.5" y="4.5" width="17" height="17" rx="2.5" stroke="#0DB1F9"></rect></svg></span></a></li></ul></div><div class="navbar__item dropdown dropdown--hoverable"><a href="#" class="navbar__link downloadLinkDropdownHide_aDP3"><div class="labelWrapperDropdown_Mqbj">Contribute<svg width="10" height="6" viewBox="0 0 10 6" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M8.5 1.25 5 4.75l-3.5-3.5" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path></svg></div></a><ul class="dropdown__menu"><li><a class="dropdown__link" href="/contribute/how-to-contribute"><div class="labelWrapperDropdown_Mqbj">How to Contribute</div></a></li><li><a class="dropdown__link" href="/contribute/developer-setup"><div class="labelWrapperDropdown_Mqbj">Developer Setup</div></a></li><li><a class="dropdown__link" href="/contribute/rfc-process"><div class="labelWrapperDropdown_Mqbj">RFC Process</div></a></li><li><a class="dropdown__link" href="/contribute/report-security-issues"><div class="labelWrapperDropdown_Mqbj">Report Security Issues</div></a></li><li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank" rel="noopener noreferrer" class="dropdown__link"><span class="externalLink_AE3f">Report Issues<svg width="20" height="20" viewBox="0 0 26 26" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M16.965 8.745 9.01 16.7M10.561 8.758l6.403-.013-.013 6.403" stroke="#0DB1F9" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path><rect x="4.5" y="4.5" width="17" height="17" rx="2.5" stroke="#0DB1F9"></rect></svg></span></a></li></ul></div><div class="navbar__item dropdown dropdown--hoverable"><a href="#" class="navbar__link downloadLinkDropdownHide_aDP3"><div class="labelWrapperDropdown_Mqbj">Community<svg width="10" height="6" viewBox="0 0 10 6" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M8.5 1.25 5 4.75l-3.5-3.5" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path></svg></div></a><ul class="dropdown__menu"><li><a class="dropdown__link" href="/community/get-involved"><div class="labelWrapperDropdown_Mqbj">Get Involved</div></a></li><li><a class="dropdown__link" href="/community/syncs"><div class="labelWrapperDropdown_Mqbj">Community Syncs</div></a></li><li><a class="dropdown__link" href="/community/office_hours"><div class="labelWrapperDropdown_Mqbj">Office Hours</div></a></li><li><a class="dropdown__link" href="/community/team"><div class="labelWrapperDropdown_Mqbj">Team</div></a></li></ul></div><a aria-current="page" class="navbar__item navbar__link navbar__link--active" href="/blog"><div class="labelWrapperDropdown_Mqbj">Blog</div></a><a class="navbar__item navbar__link" href="/powered-by"><div class="labelWrapperDropdown_Mqbj">Who's Using</div></a><a class="navbar__item navbar__link" href="/roadmap"><div class="labelWrapperDropdown_Mqbj">Roadmap</div></a><a class="navbar__item navbar__link" href="/releases/download"><div class="labelWrapperDropdown_Mqbj">Download</div></a></div><div class="navbar__items navbar__items--right"><div class="navbar__item dropdown dropdown--hoverable dropdown--right"><a class="navbar__link downloadLinkDropdownHide_aDP3" href="/docs/overview"><div class="labelWrapperDropdown_Mqbj">0.14.1<svg width="10" height="6" viewBox="0 0 10 6" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M8.5 1.25 5 4.75l-3.5-3.5" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path></svg></div></a><ul class="dropdown__menu"><li><a class="dropdown__link" href="/docs/next/overview"><div class="labelWrapperDropdown_Mqbj">Current</div></a></li><li><a class="dropdown__link" href="/docs/overview"><div class="labelWrapperDropdown_Mqbj">0.14.1</div></a></li><li><a class="dropdown__link" href="/docs/0.14.0/overview"><div class="labelWrapperDropdown_Mqbj">0.14.0</div></a></li><li><a class="dropdown__link" href="/docs/0.13.1/overview"><div class="labelWrapperDropdown_Mqbj">0.13.1</div></a></li><li><a class="dropdown__link" href="/docs/0.13.0/overview"><div class="labelWrapperDropdown_Mqbj">0.13.0</div></a></li><li><a class="dropdown__link" href="/docs/0.12.3/overview"><div class="labelWrapperDropdown_Mqbj">0.12.3</div></a></li><li><a class="dropdown__link" href="/docs/0.12.2/overview"><div class="labelWrapperDropdown_Mqbj">0.12.2</div></a></li><li><a class="dropdown__link" href="/docs/0.12.1/overview"><div class="labelWrapperDropdown_Mqbj">0.12.1</div></a></li><li><a class="dropdown__link" href="/docs/0.12.0/overview"><div class="labelWrapperDropdown_Mqbj">0.12.0</div></a></li><li><a class="dropdown__link" href="/docs/0.11.1/overview"><div class="labelWrapperDropdown_Mqbj">0.11.1</div></a></li><li><a class="dropdown__link" href="/docs/0.11.0/overview"><div class="labelWrapperDropdown_Mqbj">0.11.0</div></a></li><li><a class="dropdown__link" href="/docs/0.10.1/overview"><div class="labelWrapperDropdown_Mqbj">0.10.1</div></a></li><li><a class="dropdown__link" href="/docs/0.10.0/overview"><div class="labelWrapperDropdown_Mqbj">0.10.0</div></a></li><li><a class="dropdown__link" href="/docs/0.9.0/overview"><div class="labelWrapperDropdown_Mqbj">0.9.0</div></a></li><li><a class="dropdown__link" href="/docs/0.8.0/overview"><div class="labelWrapperDropdown_Mqbj">0.8.0</div></a></li><li><a class="dropdown__link" href="/docs/0.7.0/overview"><div class="labelWrapperDropdown_Mqbj">0.7.0</div></a></li><li><a class="dropdown__link" href="/docs/0.6.0/quick-start-guide"><div class="labelWrapperDropdown_Mqbj">0.6.0</div></a></li><li><a class="dropdown__link" href="/docs/0.5.3/quick-start-guide"><div class="labelWrapperDropdown_Mqbj">0.5.3</div></a></li><li><a class="dropdown__link" href="/docs/0.5.2/quick-start-guide"><div class="labelWrapperDropdown_Mqbj">0.5.2</div></a></li><li><a class="dropdown__link" href="/docs/0.5.1/quick-start-guide"><div class="labelWrapperDropdown_Mqbj">0.5.1</div></a></li><li><a class="dropdown__link" href="/docs/0.5.0/quick-start-guide"><div class="labelWrapperDropdown_Mqbj">0.5.0</div></a></li></ul></div><div class="navbar__item dropdown dropdown--hoverable dropdown--right"><a href="#" class="navbar__link downloadLinkDropdownHide_aDP3"><div class="labelWrapperDropdown_Mqbj"><span><svg viewBox="0 0 20 20" width="20" height="20" aria-hidden="true" class="iconLanguage_zID8"><path fill="currentColor" d="M19.753 10.909c-.624-1.707-2.366-2.726-4.661-2.726-.09 0-.176.002-.262.006l-.016-2.063 3.525-.607c.115-.019.133-.119.109-.231-.023-.111-.167-.883-.188-.976-.027-.131-.102-.127-.207-.109-.104.018-3.25.461-3.25.461l-.013-2.078c-.001-.125-.069-.158-.194-.156l-1.025.016c-.105.002-.164.049-.162.148l.033 2.307s-3.061.527-3.144.543c-.084.014-.17.053-.151.143.019.09.19 1.094.208 1.172.018.08.072.129.188.107l2.924-.504.035 2.018c-1.077.281-1.801.824-2.256 1.303-.768.807-1.207 1.887-1.207 2.963 0 1.586.971 2.529 2.328 2.695 3.162.387 5.119-3.06 5.769-4.715 1.097 1.506.256 4.354-2.094 5.98-.043.029-.098.129-.033.207l.619.756c.08.096.206.059.256.023 2.51-1.73 3.661-4.515 2.869-6.683zm-7.386 3.188c-.966-.121-.944-.914-.944-1.453 0-.773.327-1.58.876-2.156a3.21 3.21 0 011.229-.799l.082 4.277a2.773 2.773 0 01-1.243.131zm2.427-.553l.046-4.109c.084-.004.166-.01.252-.01.773 0 1.494.145 1.885.361.391.217-1.023 2.713-2.183 3.758zm-8.95-7.668a.196.196 0 00-.196-.145h-1.95a.194.194 0 00-.194.144L.008 16.916c-.017.051-.011.076.062.076h1.733c.075 0 .099-.023.114-.072l1.008-3.318h3.496l1.008 3.318c.016.049.039.072.113.072h1.734c.072 0 .078-.025.062-.076-.014-.05-3.083-9.741-3.494-11.04zm-2.618 6.318l1.447-5.25 1.447 5.25H3.226z"></path></svg><span>English</span></span><svg width="14" height="14" viewBox="0 0 14 14" fill="none" xmlns="http://www.w3.org/2000/svg"><g clip-path="url(#a)"><path d="M14 6.457a6.842 6.842 0 0 0-7-6.02 6.843 6.843 0 0 0-7 6.02v1.085a6.843 6.843 0 0 0 7 6.02 6.843 6.843 0 0 0 7-6.02V6.457Zm-1.094 0h-2.625a9.92 9.92 0 0 0-.376-2.222 6.65 6.65 0 0 0 1.531-.875 5.25 5.25 0 0 1 1.444 3.097h.026Zm-8.032 0a8.479 8.479 0 0 1 .324-1.872 7.376 7.376 0 0 0 3.63 0c.175.61.284 1.239.325 1.872h-4.28Zm4.305 1.085a8.391 8.391 0 0 1-.324 1.873 7.464 7.464 0 0 0-3.658 0 8.479 8.479 0 0 1-.323-1.873h4.305Zm.35-4.375A10.342 10.342 0 0 0 8.75 1.75c.627.194 1.218.49 1.75.875a5.748 5.748 0 0 1-.998.577l.027-.035ZM7.254 1.54A8.75 8.75 0 0 1 8.46 3.552c-.48.11-.97.165-1.461.167-.492-.001-.982-.057-1.461-.167.308-.722.715-1.4 1.207-2.012h.508ZM4.498 3.202a5.748 5.748 0 0 1-.998-.577 6.029 6.029 0 0 1 1.75-.875c-.294.46-.546.947-.753 1.452Zm-1.873.15c.47.358.984.652 1.531.874A9.625 9.625 0 0 0 3.78 6.45H1.155a5.25 5.25 0 0 1 1.47-3.098ZM1.12 7.541h2.625c.038.753.164 1.5.376 2.223a6.649 6.649 0 0 0-1.531.875 5.25 5.25 0 0 1-1.47-3.098Zm3.377 3.255c.207.506.459.992.753 1.453a6.03 6.03 0 0 1-1.75-.875c.312-.226.646-.419.997-.578Zm2.25 1.663a8.594 8.594 0 0 1-1.208-2.013 6.501 6.501 0 0 1 2.922 0 8.54 8.54 0 0 1-1.207 2.013h-.508Zm2.755-1.663c.367.156.716.35 1.042.578a6.338 6.338 0 0 1-1.75.875c.275-.464.512-.95.708-1.453Zm1.873-.148a6.647 6.647 0 0 0-1.531-.875 9.45 9.45 0 0 0 .376-2.223h2.625a5.25 5.25 0 0 1-1.47 3.098Z" fill="#1C1E21"></path></g><defs><clipPath id="a"><path fill="#fff" d="M0 0h14v14H0z"></path></clipPath></defs></svg></div></a><ul class="dropdown__menu"><li><a href="/blog/2021/01/27/hudi-clustering-intro" target="_self" rel="noopener noreferrer" class="dropdown__link dropdown__link--active"><div class="labelWrapperDropdown_Mqbj">English</div></a></li><li><a href="/cn/blog/2021/01/27/hudi-clustering-intro" target="_self" rel="noopener noreferrer" class="dropdown__link"><div class="labelWrapperDropdown_Mqbj">Chinese</div></a></li></ul></div><a href="https://github.com/apache/hudi" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link header-github-link" aria-label="GitHub repository"><div class="labelWrapperDropdown_Mqbj"></div></a><a href="https://twitter.com/ApacheHudi" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link header-twitter-link" aria-label="Hudi Twitter Handle"><div class="labelWrapperDropdown_Mqbj"></div></a><a href="https://join.slack.com/t/apache-hudi/shared_invite/zt-2ggm1fub8-_yt4Reu9djwqqVRFC7X49g" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link header-slack-link" aria-label="Hudi Slack Channel"><div class="labelWrapperDropdown_Mqbj"></div></a><a href="https://www.youtube.com/channel/UCs7AhE0BWaEPZSChrBR-Muw" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link header-youtube-link" aria-label="Hudi YouTube Channel"><div class="labelWrapperDropdown_Mqbj"></div></a><a href="https://www.linkedin.com/company/apache-hudi/?viewAsMember=true" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link header-linkedin-link" aria-label="Hudi Linkedin Page"><div class="labelWrapperDropdown_Mqbj"></div></a><div class="searchBox_fBfG"><div role="button" class="searchButton_g9-U" aria-label="Search"><span class="searchText_RI6l">Search</span><svg width="14" height="14" viewBox="0 0 14 14" fill="none" xmlns="http://www.w3.org/2000/svg"><circle cx="6.864" cy="6.864" r="5.243" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></circle><path d="m10.51 10.783 2.056 2.05" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path></svg></div></div></div></div><div role="presentation" class="navbar-sidebar__backdrop"></div><div class="navbar-sidebar"><div class="navbar-sidebar__brand"><a class="navbar__brand" href="/"><div class="navbar__logo"><img src="/assets/images/hudi.png" alt="Apache Hudi" class="themedImage_TMUO themedImage--light_4Vu1"><img src="/assets/images/hudi.png" alt="Apache Hudi" class="themedImage_TMUO themedImage--dark_uzRr"></div></a><button type="button" class="clean-btn navbar-sidebar__close"><svg viewBox="0 0 15 15" width="21" height="21"><g stroke="var(--ifm-color-emphasis-600)" stroke-width="1.2"><path d="M.75.75l13.5 13.5M14.25.75L.75 14.25"></path></g></svg></button></div><div class="navbar-sidebar__items"><div class="navbar-sidebar__item menu"><ul class="menu__list"><li class="menu__list-item"><a class="menu__link" href="/docs/overview"><div class="labelWrapperDropdown_Mqbj">Docs</div></a></li><li class="menu__list-item menu__list-item--collapsed"><a role="button" class="menu__link menu__link--sublist"><div class="labelWrapperDropdown_Mqbj">Learn</div></a></li><li class="menu__list-item menu__list-item--collapsed"><a role="button" class="menu__link menu__link--sublist"><div class="labelWrapperDropdown_Mqbj">Contribute</div></a></li><li class="menu__list-item menu__list-item--collapsed"><a role="button" class="menu__link menu__link--sublist"><div class="labelWrapperDropdown_Mqbj">Community</div></a></li><li class="menu__list-item"><a aria-current="page" class="menu__link menu__link--active" href="/blog"><div class="labelWrapperDropdown_Mqbj">Blog</div></a></li><li class="menu__list-item"><a class="menu__link" href="/powered-by"><div class="labelWrapperDropdown_Mqbj">Who's Using</div></a></li><li class="menu__list-item"><a class="menu__link" href="/roadmap"><div class="labelWrapperDropdown_Mqbj">Roadmap</div></a></li><li class="menu__list-item"><a class="menu__link" href="/releases/download"><div class="labelWrapperDropdown_Mqbj">Download</div></a></li><li class="menu__list-item menu__list-item--collapsed"><a role="button" class="menu__link menu__link--sublist"><div class="labelWrapperDropdown_Mqbj">Versions</div></a></li><li class="menu__list-item menu__list-item--collapsed"><a role="button" class="menu__link menu__link--sublist"><div class="labelWrapperDropdown_Mqbj"><span><svg viewBox="0 0 20 20" width="20" height="20" aria-hidden="true" class="iconLanguage_zID8"><path fill="currentColor" d="M19.753 10.909c-.624-1.707-2.366-2.726-4.661-2.726-.09 0-.176.002-.262.006l-.016-2.063 3.525-.607c.115-.019.133-.119.109-.231-.023-.111-.167-.883-.188-.976-.027-.131-.102-.127-.207-.109-.104.018-3.25.461-3.25.461l-.013-2.078c-.001-.125-.069-.158-.194-.156l-1.025.016c-.105.002-.164.049-.162.148l.033 2.307s-3.061.527-3.144.543c-.084.014-.17.053-.151.143.019.09.19 1.094.208 1.172.018.08.072.129.188.107l2.924-.504.035 2.018c-1.077.281-1.801.824-2.256 1.303-.768.807-1.207 1.887-1.207 2.963 0 1.586.971 2.529 2.328 2.695 3.162.387 5.119-3.06 5.769-4.715 1.097 1.506.256 4.354-2.094 5.98-.043.029-.098.129-.033.207l.619.756c.08.096.206.059.256.023 2.51-1.73 3.661-4.515 2.869-6.683zm-7.386 3.188c-.966-.121-.944-.914-.944-1.453 0-.773.327-1.58.876-2.156a3.21 3.21 0 011.229-.799l.082 4.277a2.773 2.773 0 01-1.243.131zm2.427-.553l.046-4.109c.084-.004.166-.01.252-.01.773 0 1.494.145 1.885.361.391.217-1.023 2.713-2.183 3.758zm-8.95-7.668a.196.196 0 00-.196-.145h-1.95a.194.194 0 00-.194.144L.008 16.916c-.017.051-.011.076.062.076h1.733c.075 0 .099-.023.114-.072l1.008-3.318h3.496l1.008 3.318c.016.049.039.072.113.072h1.734c.072 0 .078-.025.062-.076-.014-.05-3.083-9.741-3.494-11.04zm-2.618 6.318l1.447-5.25 1.447 5.25H3.226z"></path></svg><span>Languages</span></span></div></a></li><li class="menu__list-item"><a href="https://github.com/apache/hudi" target="_blank" rel="noopener noreferrer" class="menu__link header-github-link" aria-label="GitHub repository"><div class="labelWrapperDropdown_Mqbj"></div></a></li><li class="menu__list-item"><a href="https://twitter.com/ApacheHudi" target="_blank" rel="noopener noreferrer" class="menu__link header-twitter-link" aria-label="Hudi Twitter Handle"><div class="labelWrapperDropdown_Mqbj"></div></a></li><li class="menu__list-item"><a href="https://join.slack.com/t/apache-hudi/shared_invite/zt-2ggm1fub8-_yt4Reu9djwqqVRFC7X49g" target="_blank" rel="noopener noreferrer" class="menu__link header-slack-link" aria-label="Hudi Slack Channel"><div class="labelWrapperDropdown_Mqbj"></div></a></li><li class="menu__list-item"><a href="https://www.youtube.com/channel/UCs7AhE0BWaEPZSChrBR-Muw" target="_blank" rel="noopener noreferrer" class="menu__link header-youtube-link" aria-label="Hudi YouTube Channel"><div class="labelWrapperDropdown_Mqbj"></div></a></li><li class="menu__list-item"><a href="https://www.linkedin.com/company/apache-hudi/?viewAsMember=true" target="_blank" rel="noopener noreferrer" class="menu__link header-linkedin-link" aria-label="Hudi Linkedin Page"><div class="labelWrapperDropdown_Mqbj"></div></a></li></ul></div><div class="navbar-sidebar__item menu"><button type="button" class="clean-btn navbar-sidebar__back">← Back to main menu</button></div></div></div></nav><div class="main-wrapper blog-wrapper blog-post-page"><div class="container margin-vert--lg"><div class="row"><main class="col col--9 col--offset-2" itemscope="" itemtype="http://schema.org/Blog"><article itemprop="blogPost" itemscope="" itemtype="http://schema.org/BlogPosting"><header class="postHeader_Ipb1"><div><h1 class="blogPostTitle_RC3s" itemprop="headline"><h1 class="blogPostPageTitle_bKZt" itemprop="headline">Optimize Data lake layout using Clustering in Apache Hudi</h1></h1><div class="blogInfo_1FPd margin-top--sm margin-bottom--sm"><div class="blogPostText_jBA8 row"><time datetime="2021-01-27T00:00:00.000Z" itemprop="datePublished">January 27, 2021</time><div><div><div><a itemprop="url"><span class="blogPostAuthorsList_dlEG" itemprop="name">satish.kotha</span></a></div></div></div></div><div class="blogPostData_A2Le">6 min read</div></div></div><ul class="authorTimeTags_oN88 padding--none margin-left--sm tagsWrapperPostPage_VdId"><li class="tag_MgfY tagPostPage_gnvv"><a class="tag_WK-t tagRegular_LXbV" href="/blog/tags/design">design</a></li><li class="tag_MgfY tagPostPage_gnvv"><a class="tag_WK-t tagRegular_LXbV" href="/blog/tags/clustering">clustering</a></li><li class="tag_MgfY tagPostPage_gnvv"><a class="tag_WK-t tagRegular_LXbV" href="/blog/tags/apache-hudi">apache hudi</a></li></ul></header><div class="markdown" itemprop="articleBody"><h2 class="anchor anchorWithStickyNavbar_y2LR" id="background">Background<a class="hash-link" href="#background" title="Direct link to heading"></a></h2><p>Apache Hudi brings stream processing to big data, providing fresh data while being an order of magnitude efficient over traditional batch processing. In a data lake/warehouse, one of the key trade-offs is between ingestion speed and query performance. Data ingestion typically prefers small files to improve parallelism and make data available to queries as soon as possible. However, query performance degrades poorly with a lot of small files. Also, during ingestion, data is typically co-located based on arrival time. However, the query engines perform better when the data frequently queried is co-located together. In most architectures each of these systems tend to add optimizations independently to improve performance which hits limitations due to un-optimized data layouts. This blog introduces a new kind of table service called clustering <a href="https://cwiki.apache.org/confluence/display/HUDI/RFC+-+19+Clustering+data+for+freshness+and+query+performance" target="_blank" rel="noopener noreferrer">[RFC-19]</a> to reorganize data for improved query performance without compromising on ingestion speed.</p><h2 class="anchor anchorWithStickyNavbar_y2LR" id="clustering-architecture">Clustering Architecture<a class="hash-link" href="#clustering-architecture" title="Direct link to heading"></a></h2><p>At a high level, Hudi provides different operations such as insert/upsert/bulk_insert through it’s write client API to be able to write data to a Hudi table. To be able to choose a trade-off between file size and ingestion speed, Hudi provides a knob <code>hoodie.parquet.small.file.limit</code> to be able to configure the smallest allowable file size. Users are able to configure the small file <a href="https://hudi.apache.org/docs/configurations#compactionSmallFileSize" target="_blank" rel="noopener noreferrer">soft limit</a> to <code>0</code> to force new data to go into a new set of filegroups or set it to a higher value to ensure new data gets “padded” to existing files until it meets that limit that adds to ingestion latencies.</p><p>To be able to support an architecture that allows for fast ingestion without compromising query performance, we have introduced a ‘clustering’ service to rewrite the data to optimize Hudi data lake file layout.</p><p>Clustering table service can run asynchronously or synchronously adding a new action type called “REPLACE”, that will mark the clustering action in the Hudi metadata timeline.</p><h4 class="anchor anchorWithStickyNavbar_y2LR" id="overall-there-are-2-parts-to-clustering">Overall, there are 2 parts to clustering<a class="hash-link" href="#overall-there-are-2-parts-to-clustering" title="Direct link to heading"></a></h4><ol><li>Scheduling clustering: Create a clustering plan using a pluggable clustering strategy.</li><li>Execute clustering: Process the plan using an execution strategy to create new files and replace old files.</li></ol><h4 class="anchor anchorWithStickyNavbar_y2LR" id="scheduling-clustering">Scheduling clustering<a class="hash-link" href="#scheduling-clustering" title="Direct link to heading"></a></h4><p>Following steps are followed to schedule clustering.</p><ol><li>Identify files that are eligible for clustering: Depending on the clustering strategy chosen, the scheduling logic will identify the files eligible for clustering.</li><li>Group files that are eligible for clustering based on specific criteria. Each group is expected to have data size in multiples of ‘targetFileSize’. Grouping is done as part of ‘strategy’ defined in the plan. Additionally, there is an option to put a cap on group size to improve parallelism and avoid shuffling large amounts of data.</li><li>Finally, the clustering plan is saved to the timeline in an avro <a href="https://github.com/apache/hudi/blob/master/hudi-common/src/main/avro/HoodieClusteringPlan.avsc" target="_blank" rel="noopener noreferrer">metadata format</a>.</li></ol><h4 class="anchor anchorWithStickyNavbar_y2LR" id="running-clustering">Running clustering<a class="hash-link" href="#running-clustering" title="Direct link to heading"></a></h4><ol><li>Read the clustering plan and get the ‘clusteringGroups’ that mark the file groups that need to be clustered.</li><li>For each group, we instantiate appropriate strategy class with strategyParams (example: sortColumns) and apply that strategy to rewrite the data.</li><li>Create a “REPLACE” commit and update the metadata in <a href="https://github.com/apache/hudi/blob/master/hudi-common/src/main/java/org/apache/hudi/common/model/HoodieReplaceCommitMetadata.java" target="_blank" rel="noopener noreferrer">HoodieReplaceCommitMetadata</a>.</li></ol><p>Clustering Service builds on Hudi’s MVCC based design to allow for writers to continue to insert new data while clustering action runs in the background to reformat data layout, ensuring snapshot isolation between concurrent readers and writers.</p><p>NOTE: Clustering can only be scheduled for tables / partitions not receiving any concurrent updates. In the future, concurrent updates use-case will be supported as well.</p><p><img alt="Clustering example" src="/assets/images/example_perf_improvement-acd223093d7c84fb6f0a896dcb571737.png"> |
| <em>Figure: Illustrating query performance improvements by clustering</em></p><h4 class="anchor anchorWithStickyNavbar_y2LR" id="setting-up-clustering">Setting up clustering<a class="hash-link" href="#setting-up-clustering" title="Direct link to heading"></a></h4><p>Inline clustering can be setup easily using spark dataframe options. See sample below</p><div class="codeBlockContainer_J+bg language-scala theme-code-block"><div class="codeBlockContent_csEI scala"><pre tabindex="0" class="prism-code language-scala codeBlock_rtdJ thin-scrollbar" style="color:#F8F8F2;background-color:#282A36"><code class="codeBlockLines_1zSZ"><span class="token-line" style="color:#F8F8F2"><span class="token plain">import org.apache.hudi.QuickstartUtils._</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">import scala.collection.JavaConversions._</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">import org.apache.spark.sql.SaveMode._</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">import org.apache.hudi.DataSourceReadOptions._</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">import org.apache.hudi.DataSourceWriteOptions._</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">import org.apache.hudi.config.HoodieWriteConfig._</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">val df = //generate data frame</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">df.write.format("org.apache.hudi").</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> options(getQuickstartWriteConfigs).</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> option(PRECOMBINE_FIELD_OPT_KEY, "ts").</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> option(RECORDKEY_FIELD_OPT_KEY, "uuid").</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> option(PARTITIONPATH_FIELD_OPT_KEY, "partitionpath").</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> option(TABLE_NAME, "tableName").</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> option("hoodie.parquet.small.file.limit", "0").</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> option("hoodie.clustering.inline", "true").</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> option("hoodie.clustering.inline.max.commits", "4").</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> option("hoodie.clustering.plan.strategy.target.file.max.bytes", "1073741824").</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> option("hoodie.clustering.plan.strategy.small.file.limit", "629145600").</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> option("hoodie.clustering.plan.strategy.sort.columns", "column1,column2"). //optional, if sorting is needed as part of rewriting data</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> mode(Append).</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> save("dfs://location");</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div><p>For more advanced usecases, async clustering pipeline can also be setup. See an example <a href="https://cwiki.apache.org/confluence/display/HUDI/RFC+-+19+Clustering+data+for+freshness+and+query+performance#RFC19Clusteringdataforfreshnessandqueryperformance-SetupforAsyncclusteringJob" target="_blank" rel="noopener noreferrer">here</a>.</p><h2 class="anchor anchorWithStickyNavbar_y2LR" id="table-query-performance">Table Query Performance<a class="hash-link" href="#table-query-performance" title="Direct link to heading"></a></h2><p>We created a dataset from one partition of a known production style table with ~20M records and on-disk size of ~200GB. The dataset has rows for multiple “sessions”. Users always query this data using a predicate on session. Data for a single session is spread across multiple data files because ingestion groups data based on arrival time. The below experiment shows that by clustering on session, we are able to improve the data locality and reduce query execution time by more than 50%.</p><p>Query: </p><div class="codeBlockContainer_J+bg language-scala theme-code-block"><div class="codeBlockContent_csEI scala"><pre tabindex="0" class="prism-code language-scala codeBlock_rtdJ thin-scrollbar" style="color:#F8F8F2;background-color:#282A36"><code class="codeBlockLines_1zSZ"><span class="token-line" style="color:#F8F8F2"><span class="token plain">spark.sql("select * from table where session_id=123")</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div><h3 class="anchor anchorWithStickyNavbar_y2LR" id="before-clustering">Before Clustering<a class="hash-link" href="#before-clustering" title="Direct link to heading"></a></h3><p>Query took 2.2 minutes to complete. Note that the number of output rows in the “scan parquet” part of the query plan includes all 20M rows in the table.</p><p><img alt="Query Plan Before Clustering" src="/assets/images/Query_Plan_Before_Clustering-cbf67c7e66765c7b42ad88521739d39f.png"> |
| <em>Figure: Spark SQL query details before clustering</em></p><h3 class="anchor anchorWithStickyNavbar_y2LR" id="after-clustering">After Clustering<a class="hash-link" href="#after-clustering" title="Direct link to heading"></a></h3><p>The query plan is similar to above. But, because of improved data locality and predicate push down, spark is able to prune a lot of rows. After clustering, the same query only outputs 110K rows (out of 20M rows) while scanning parquet files. This cuts query time to less than a minute from 2.2 minutes.</p><p><img alt="Query Plan Before Clustering" src="/assets/images/Query_Plan_After_Clustering-e669cd3887eaadb0f9d23cd4a773535e.png"> |
| <em>Figure: Spark SQL query details after clustering</em></p><p>The table below summarizes query performance improvements from experiments run using Spark3</p><table><thead><tr><th>Table State</th><th>Query runtime</th><th>Num Records Processed</th><th>Num files on disk</th><th>Size of each file</th></tr></thead><tbody><tr><td><strong>Unclustered</strong></td><td>130,673 ms</td><td>~20M</td><td>13642</td><td>~150 MB</td></tr><tr><td><strong>Clustered</strong></td><td>55,963 ms</td><td>~110K</td><td>294</td><td>~600 MB</td></tr></tbody></table><p>Query runtime is reduced by 60% after clustering. Similar results were observed on other sample datasets. See example query plans and more details at the <a href="https://cwiki.apache.org/confluence/display/HUDI/RFC+-+19+Clustering+data+for+freshness+and+query+performance#RFC19Clusteringdataforfreshnessandqueryperformance-PerformanceEvaluation" target="_blank" rel="noopener noreferrer">RFC-19 performance evaluation</a>.</p><p>We expect dramatic speedup for large tables, where the query runtime is almost entirely dominated by actual I/O and not query planning, unlike the example above.</p><h2 class="anchor anchorWithStickyNavbar_y2LR" id="summary">Summary<a class="hash-link" href="#summary" title="Direct link to heading"></a></h2><p>Using clustering, we can improve query performance by</p><ol><li>Leveraging concepts such as <a href="https://en.wikipedia.org/wiki/Z-order_curve" target="_blank" rel="noopener noreferrer">space filling curves</a> to adapt data lake layout and reduce the amount of data read during queries.</li><li>Stitch small files into larger ones and reduce the total number of files that need to be scanned by the query engine.</li></ol><p>Clustering also enables stream processing over big data. Ingestion can write small files to satisfy latency requirements of stream processing. Clustering can be used in the background to stitch these small files into larger files and reduce file count.</p><p>Besides this, the clustering framework also provides the flexibility to asynchronously rewrite data based on specific requirements. We foresee many other use-cases adopting clustering framework with custom pluggable strategies to satisfy on-demand data lake management activities. Some such notable use-cases that are actively being solved using clustering:</p><ol><li>Rewrite data and encrypt data at rest.</li><li>Prune unused columns from tables and reduce storage footprint.</li></ol></div><footer0 class="row docusaurus-mt-lg blogPostDetailsFull_2lop"><div class="col margin-top--sm"><a href="https://github.com/apache/hudi/edit/asf-site/website/blog/blog/2021-01-27-hudi-clustering-intro.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_mS5F" 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></footer0></article><nav class="pagination-nav docusaurus-mt-lg" aria-label="Blog post page navigation"><div class="pagination-nav__item"><a class="pagination-nav__link" href="/blog/2021/02/13/hudi-key-generators"><div class="pagination-nav__sublabel">Newer Post</div><div class="pagination-nav__label">« <!-- -->Apache Hudi Key Generators</div></a></div><div class="pagination-nav__item pagination-nav__item--next"><a class="pagination-nav__link" href="/blog/2020/12/01/high-perf-data-lake-with-hudi-and-alluxio-t3go"><div class="pagination-nav__sublabel">Older Post</div><div class="pagination-nav__label">Building High-Performance Data Lake Using Apache Hudi and Alluxio at T3Go<!-- --> »</div></a></div></nav></main><div class="col col--2"><div class="tableOfContents_vrFS thin-scrollbar"><ul class="table-of-contents table-of-contents__left-border"><li><a href="#background" class="table-of-contents__link toc-highlight">Background</a></li><li><a href="#clustering-architecture" class="table-of-contents__link toc-highlight">Clustering Architecture</a></li><li><a href="#table-query-performance" class="table-of-contents__link toc-highlight">Table Query Performance</a><ul><li><a href="#before-clustering" class="table-of-contents__link toc-highlight">Before Clustering</a></li><li><a href="#after-clustering" class="table-of-contents__link toc-highlight">After Clustering</a></li></ul></li><li><a href="#summary" class="table-of-contents__link toc-highlight">Summary</a></li></ul></div></div></div></div></div><footer class="footer"><div class="container container-fluid"><div class="row footer__links"><div class="col footer__col"><div class="footer__title">About</div><ul class="footer__items"><li class="footer__item"><a class="footer__link-item" href="/blog/2021/07/21/streaming-data-lake-platform">Our Vision</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/concepts">Concepts</a></li><li class="footer__item"><a class="footer__link-item" href="/community/team">Team</a></li><li class="footer__item"><a class="footer__link-item" href="/releases/release-0.14.1">Releases</a></li><li class="footer__item"><a class="footer__link-item" href="/releases/download">Download</a></li><li class="footer__item"><a class="footer__link-item" href="/powered-by">Who's Using</a></li></ul></div><div class="col footer__col"><div class="footer__title">Learn</div><ul class="footer__items"><li class="footer__item"><a class="footer__link-item" href="/docs/quick-start-guide">Quick Start</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/docker_demo">Docker Demo</a></li><li class="footer__item"><a class="footer__link-item" href="/blog">Blog</a></li><li class="footer__item"><a class="footer__link-item" href="/talks">Talks</a></li><li class="footer__item"><a class="footer__link-item" href="/videos">Video Guides</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/faq">FAQ</a></li><li class="footer__item"><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>Technical Wiki<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><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></span></a></li></ul></div><div class="col footer__col"><div class="footer__title">Hudi On Cloud</div><ul class="footer__items"><li class="footer__item"><a class="footer__link-item" href="/docs/s3_hoodie">AWS</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/gcs_hoodie">Google Cloud</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/oss_hoodie">Alibaba Cloud</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/azure_hoodie">Microsoft Azure</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/cos_hoodie">Tencent Cloud</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/ibm_cos_hoodie">IBM Cloud</a></li></ul></div><div class="col footer__col"><div class="footer__title">Community</div><ul class="footer__items"><li class="footer__item"><a class="footer__link-item" href="/community/get-involved">Get Involved</a></li><li class="footer__item"><a href="https://join.slack.com/t/apache-hudi/shared_invite/zt-2ggm1fub8-_yt4Reu9djwqqVRFC7X49g" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>Slack<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><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></span></a></li><li class="footer__item"><a href="https://github.com/apache/hudi" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>GitHub<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><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></span></a></li><li class="footer__item"><a href="https://twitter.com/ApacheHudi" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>Twitter<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><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></span></a></li><li class="footer__item"><a href="https://www.youtube.com/channel/UCs7AhE0BWaEPZSChrBR-Muw" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>YouTube<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><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></span></a></li><li class="footer__item"><a href="https://www.linkedin.com/company/apache-hudi/?viewAsMember=true" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>Linkedin<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><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></span></a></li><li class="footer__item"><a href="mailto:dev-subscribe@hudi.apache.org?Subject=SubscribeToHudi" target="_blank" rel="noopener noreferrer" class="footer__link-item">Mailing List</a></li></ul></div><div class="col footer__col"><div class="footer__title">Apache</div><ul class="footer__items"><li class="footer__item"><a href="https://www.apache.org/events/current-event" target="_blank" rel="noopener noreferrer" class="footer__link-item">Events</a></li><li class="footer__item"><a href="https://www.apache.org/foundation/thanks.html" target="_blank" rel="noopener noreferrer" class="footer__link-item">Thanks</a></li><li class="footer__item"><a href="https://www.apache.org/licenses" target="_blank" rel="noopener noreferrer" class="footer__link-item">License</a></li><li class="footer__item"><a href="https://www.apache.org/security" target="_blank" rel="noopener noreferrer" class="footer__link-item">Security</a></li><li class="footer__item"><a href="https://www.apache.org/foundation/sponsorship.html" target="_blank" rel="noopener noreferrer" class="footer__link-item">Sponsorship</a></li><li class="footer__item"><a href="https://www.apache.org" target="_blank" rel="noopener noreferrer" class="footer__link-item">Foundation</a></li></ul></div></div><div class="footer__bottom text--center"><div class="margin-bottom--sm"><a href="https://hudi.apache.org/" target="_blank" rel="noopener noreferrer" class="footerLogoLink_SRtH"><img src="/assets/images/logo-big.png" alt="Apache Hudi™" class="themedImage_TMUO themedImage--light_4Vu1 footer__logo"><img src="/assets/images/logo-big.png" alt="Apache Hudi™" class="themedImage_TMUO themedImage--dark_uzRr footer__logo"></a></div><div class="footer__copyright">Copyright © 2021 <a href="https://apache.org">The Apache Software Foundation</a>, Licensed under the <a href="https://www.apache.org/licenses/LICENSE-2.0"> Apache License, Version 2.0</a>. <br>Hudi, Apache and the Apache feather logo are trademarks of The Apache Software Foundation.</div></div></div></footer></div> |
| <script src="/assets/js/runtime~main.2cab5691.js"></script> |
| <script src="/assets/js/main.bd020950.js"></script> |
| </body> |
| </html> |
