blob: f4fbee1fdc5319801424fd78d4729d5334e14870 [file]
<!DOCTYPE html>
<html lang="en" data-content_root="../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Primary Key Table &#8212; C++ Paimon</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../_static/styles/theme.css?digest=90905a2f556bf617f1a9" rel="stylesheet" />
<link href="../_static/styles/pydata-sphinx-theme.css?digest=90905a2f556bf617f1a9" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../_static/copybutton.css?v=76b2166b" />
<link rel="stylesheet" type="text/css" href="../_static/sphinx-design.min.css?v=95c83b7e" />
<link rel="stylesheet" type="text/css" href="../_static/theme_overrides.css?v=d7227091" />
<!-- So that users can add custom icons -->
<script defer src="../_static/scripts/fontawesome.js?digest=90905a2f556bf617f1a9"></script>
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../_static/scripts/bootstrap.js?digest=90905a2f556bf617f1a9" />
<link rel="preload" as="script" href="../_static/scripts/pydata-sphinx-theme.js?digest=90905a2f556bf617f1a9" />
<script src="../_static/documentation_options.js?v=5929fcd5"></script>
<script src="../_static/doctools.js?v=fd6eb6e6"></script>
<script src="../_static/sphinx_highlight.js?v=6ffebe34"></script>
<script src="../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../_static/copybutton.js?v=3bb21c8c"></script>
<script src="../_static/design-tabs.js?v=f930bc37"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'user_guide/primary_key_table';</script>
<script>DOCUMENTATION_OPTIONS.search_as_you_type = false;</script>
<link rel="index" title="Index" href="../genindex.html" />
<link rel="search" title="Search" href="../search.html" />
<link rel="next" title="Append Only Table" href="append_only_table.html" />
<link rel="prev" title="Data Types" href="data_types.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="0.2.3" />
<script src="../_static/searchtools.js"></script>
<script src="../_static/language_data.js"></script>
<script src="../searchindex.js"></script>
</head>
<body data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<dialog id="pst-search-dialog">
<form class="bd-search d-flex align-items-center"
action="../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form>
</dialog>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header id="pst-header" class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
<div class="bd-header__inner bd-page-width">
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
<span class="fa-solid fa-bars"></span>
</button>
<div class=" navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="../index.html">
<p class="title logo__title">Paimon C++</p>
</a></div>
</div>
<div class=" navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item">
<nav>
<ul class="bd-navbar-elements navbar-nav">
<li class="nav-item ">
<a class="nav-link nav-internal" href="../getting_started.html">
Getting Started
</a>
</li>
<li class="nav-item current active">
<a class="nav-link nav-internal" href="../user_guide.html">
User Guide
</a>
</li>
<li class="nav-item ">
<a class="nav-link nav-internal" href="../examples/index.html">
Examples
</a>
</li>
<li class="nav-item ">
<a class="nav-link nav-internal" href="../api.html">
API Reference
</a>
</li>
</ul>
</nav></div>
</div>
<div class="navbar-header-items__end">
<div class="navbar-item navbar-persistent--container">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<div class="navbar-item">
<div class="theme-switch-container dropdown pst-js-only" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Color mode">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button dropdown-toggle" aria-label="Color mode" data-bs-toggle="dropdown">
<i class="theme-switch fa-solid fa-sun fa-lg fa-fw" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg fa-fw" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg fa-fw" data-mode="auto" title="System Settings"></i>
</button>
<ul class="dropdown-menu dropdown-menu-end">
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="auto"><i class="fa-solid fa-circle-half-stroke fa-lg fa-fw me-1"></i>System Settings</button></li>
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="light"><i class="fa-solid fa-sun fa-lg fa-fw me-1"></i>Light</button></li>
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="dark"><i class="fa-solid fa-moon fa-lg fa-fw me-1"></i>Dark</button></li>
</ul>
</div></div>
<div class="navbar-item"><ul class="navbar-icon-links"
aria-label="Icon Links">
<li class="nav-item">
<a href="https://github.com/apache/paimon-cpp" title="GitHub" class="nav-link pst-navbar-icon" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><i class="fa-brands fa-square-github fa-lg" aria-hidden="true"></i><span class="visually-hidden">GitHub</span></a>
</li>
</ul></div>
</div>
</div>
<div class="navbar-persistent--mobile">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<button class="pst-navbar-icon sidebar-toggle secondary-toggle" aria-label="On this page">
<span class="fa-solid fa-outdent"></span>
</button>
</div>
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<dialog id="pst-primary-sidebar-modal"></dialog>
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
<div class="sidebar-header-items sidebar-primary__section">
<div class="sidebar-header-items__center">
<div class="navbar-item">
<nav>
<ul class="bd-navbar-elements navbar-nav">
<li class="nav-item ">
<a class="nav-link nav-internal" href="../getting_started.html">
Getting Started
</a>
</li>
<li class="nav-item current active">
<a class="nav-link nav-internal" href="../user_guide.html">
User Guide
</a>
</li>
<li class="nav-item ">
<a class="nav-link nav-internal" href="../examples/index.html">
Examples
</a>
</li>
<li class="nav-item ">
<a class="nav-link nav-internal" href="../api.html">
API Reference
</a>
</li>
</ul>
</nav></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<div class="theme-switch-container dropdown pst-js-only" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Color mode">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button dropdown-toggle" aria-label="Color mode" data-bs-toggle="dropdown">
<i class="theme-switch fa-solid fa-sun fa-lg fa-fw" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg fa-fw" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg fa-fw" data-mode="auto" title="System Settings"></i>
</button>
<ul class="dropdown-menu dropdown-menu-end">
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="auto"><i class="fa-solid fa-circle-half-stroke fa-lg fa-fw me-1"></i>System Settings</button></li>
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="light"><i class="fa-solid fa-sun fa-lg fa-fw me-1"></i>Light</button></li>
<li><button class="dropdown-item d-flex align-items-center theme-change-button" data-mode="dark"><i class="fa-solid fa-moon fa-lg fa-fw me-1"></i>Dark</button></li>
</ul>
</div></div>
<div class="navbar-item"><ul class="navbar-icon-links"
aria-label="Icon Links">
<li class="nav-item">
<a href="https://github.com/apache/paimon-cpp" title="GitHub" class="nav-link pst-navbar-icon" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><i class="fa-brands fa-square-github fa-lg" aria-hidden="true"></i><span class="visually-hidden">GitHub</span></a>
</li>
</ul></div>
</div>
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item pst-sidebar-collapse"><button id="pst-collapse-sidebar-button" aria-expanded="true" aria-controls="pst-primary-sidebar">
<svg class="pst-icon" role="img" aria-hidden="true" focusable="false" viewBox="0 0 16 16" xmlns="http://www.w3.org/2000/svg">
<path fill="currentColor" d="M3 15.5C2.36232 15.5 1.74874 15.2564 1.28478 14.8189C0.820828 14.3815 0.541576 13.7832 0.504167 13.1467L0.5 13L0.5 3C0.499965 2.36232 0.743605 1.74874 1.18107 1.28478C1.61854 0.820828 2.21676 0.541576 2.85333 0.504167L3 0.5L13 0.5C13.6377 0.499965 14.2513 0.743605 14.7152 1.18107C15.1792 1.61854 15.4584 2.21676 15.4958 2.85333L15.5 3L15.5 13C15.5 13.6377 15.2564 14.2513 14.8189 14.7152C14.3815 15.1792 13.7832 15.4584 13.1467 15.4958L13 15.5L3 15.5ZM3 13.8333L10.5 13.8333L10.5 2.16667L3 2.16667C2.79589 2.16669 2.59889 2.24163 2.44636 2.37726C2.29383 2.5129 2.19638 2.69979 2.1725 2.9025L2.16667 3L2.16667 13C2.16669 13.2041 2.24163 13.4011 2.37726 13.5536C2.5129 13.7062 2.69979 13.8036 2.9025 13.8275L3 13.8333ZM6.65583 10.325L6.5775 10.2558L4.91083 8.58917C4.76735 8.44567 4.68116 8.25476 4.66843 8.05223C4.65569 7.84971 4.71729 7.6495 4.84167 7.48917L4.91083 7.41083L6.5775 5.74417C6.72747 5.59471 6.9287 5.50794 7.14032 5.50148C7.35194 5.49502 7.55809 5.56935 7.7169 5.70937C7.8757 5.8494 7.97525 6.04463 7.99533 6.25539C8.01541 6.46616 7.95451 6.67667 7.825 6.84417L7.75583 6.9225L6.67917 8L7.75583 9.0775C7.89931 9.22099 7.98551 9.41191 7.99824 9.61443C8.01097 9.81695 7.94938 10.0172 7.825 10.1775L7.75583 10.2558C7.61234 10.3993 7.42142 10.4855 7.2189 10.4982C7.01638 10.511 6.81617 10.4494 6.65583 10.325Z"/>
</svg>
<span class="pst-collapse-sidebar-label">Collapse Sidebar</span>
<span class="pst-expand-sidebar-label">Expand Sidebar</span>
</button></div>
<div class="sidebar-primary-item">
<nav class="bd-docs-nav bd-links"
aria-label="Section Navigation">
<p class="bd-links__title" role="heading" aria-level="1">Section Navigation</p>
<div class="bd-toc-item navbar-nav"><ul class="current nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="catalog.html">Catalog</a></li>
<li class="toctree-l1"><a class="reference internal" href="schema.html">Schema</a></li>
<li class="toctree-l1"><a class="reference internal" href="snapshot.html">Snapshot</a></li>
<li class="toctree-l1"><a class="reference internal" href="manifest.html">Manifest</a></li>
<li class="toctree-l1"><a class="reference internal" href="data_types.html">Data Types</a></li>
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Primary Key Table</a></li>
<li class="toctree-l1"><a class="reference internal" href="append_only_table.html">Append Only Table</a></li>
<li class="toctree-l1"><a class="reference internal" href="write.html">Write</a></li>
<li class="toctree-l1"><a class="reference internal" href="commit.html">Commit</a></li>
<li class="toctree-l1"><a class="reference internal" href="compaction.html">Compaction</a></li>
<li class="toctree-l1"><a class="reference internal" href="read.html">Read</a></li>
<li class="toctree-l1"><a class="reference internal" href="clean.html">Data Cleanup</a></li>
<li class="toctree-l1"><a class="reference internal" href="prefetch.html">Prefetch</a></li>
<li class="toctree-l1"><a class="reference internal" href="arrow.html">Memory Format</a></li>
<li class="toctree-l1"><a class="reference internal" href="global_index.html">Global Index</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
<div class="sidebar-primary-item">
<div id="ethical-ad-placement"
class="flat"
data-ea-publisher="readthedocs"
data-ea-type="readthedocs-sidebar"
data-ea-manual="true">
</div></div>
</div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item">
<nav aria-label="Breadcrumb" class="d-print-none">
<ul class="bd-breadcrumbs">
<li class="breadcrumb-item breadcrumb-home">
<a href="../index.html" class="nav-link" aria-label="Home">
<i class="fa-solid fa-home"></i>
</a>
</li>
<li class="breadcrumb-item"><a href="../user_guide.html" class="nav-link">User Guide</a></li>
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">Primary Key Table</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="primary-key-table">
<h1>Primary Key Table<a class="headerlink" href="#primary-key-table" title="Link to this heading">#</a></h1>
<p>If you define a table with primary key, you can insert, update or delete records
in the table.</p>
<p>Primary keys consist of a set of columns that contain unique values for each
record. Paimon enforces data ordering by sorting the primary key within each
bucket, allowing users to achieve high performance by applying filtering
conditions on the primary key.</p>
<section id="bucket">
<h2>Bucket<a class="headerlink" href="#bucket" title="Link to this heading">#</a></h2>
<p>Unpartitioned tables, or partitions in partitioned tables, are sub-divided into
buckets, to provide extra structure to the data that may be used for more
efficient querying.</p>
<p>Each bucket directory contains an LSM tree and its changelog files.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Changelog is not supported yet for C++ Paimon primary key table write.</p>
</div>
<p>The range for a bucket is determined by the hash value of one or more columns in
the records. Users can specify bucketing columns by providing the bucket-key option.
If no bucket-key option is specified, the primary key (if defined) or the complete
record will be used as the bucket key.</p>
<p>A bucket is the smallest storage unit for reads and writes, so the number of
buckets limits the maximum processing parallelism. This number should not be too
big, though, as it will result in lots of small files and low read performance.
In general, the recommended data size in each bucket is about 200MB - 1GB.</p>
<p>Also, see rescale bucket if you want to adjust the number of buckets after a
table is created.</p>
</section>
<section id="lsm-trees">
<h2>LSM Trees<a class="headerlink" href="#lsm-trees" title="Link to this heading">#</a></h2>
<p>Paimon adopts the LSM tree (log-structured merge-tree) as the data structure for
file storage. This documentation briefly introduces the concepts about LSM trees.</p>
<section id="sorted-runs">
<h3>Sorted Runs<a class="headerlink" href="#sorted-runs" title="Link to this heading">#</a></h3>
<p>LSM tree organizes files into several sorted runs. A sorted run consists of one
or multiple data files and each data file belongs to exactly one sorted run.</p>
<p>Records within a data file are sorted by their primary keys. Within a sorted run,
ranges of primary keys of data files never overlap.</p>
<a class="reference internal image-reference" href="../_images/sorted-runs.png"><img alt="Sorted Runs" class="align-center" src="../_images/sorted-runs.png" style="width: 100%;" />
</a>
<p>As you can see, different sorted runs may have overlapped primary key ranges,
and may even contain the same primary key. When querying the LSM tree, all
sorted runs must be combined and all records with the same primary key must be
merged according to the user-specified merge engine and the timestamp of each record.</p>
<p>New records written into the LSM tree will be first buffered in memory. When the
memory buffer is full, all records in memory will be sorted and flushed to disk.
A new sorted run is now created.</p>
</section>
</section>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="data_types.html"
title="previous page">
<i class="fa-solid fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">Data Types</p>
</div>
</a>
<a class="right-next"
href="append_only_table.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Append Only Table</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</div>
</footer>
</div>
<dialog id="pst-secondary-sidebar-modal"></dialog>
<div id="pst-secondary-sidebar" class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
<div class="sidebar-secondary-item">
<div
id="pst-page-navigation-heading-2"
class="page-toc tocsection onthispage">
<i class="fa-solid fa-list"></i> On this page
</div>
<nav id="pst-page-toc-nav" class="page-toc" aria-labelledby="pst-page-navigation-heading-2">
<ul class="pst-show_toc_level nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#bucket">Bucket</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#lsm-trees">LSM Trees</a><ul class="pst-show_toc_level nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#sorted-runs">Sorted Runs</a></li>
</ul>
</li>
</ul>
</nav></div>
<div class="sidebar-secondary-item">
<div class="tocsection editthispage">
<a href="https://github.com/apache/paimon-cpp/edit/main/docs/source/user_guide/primary_key_table.rst">
<i class="fa-solid fa-pencil"></i>
Edit on GitHub
</a>
</div>
</div>
</div></div>
</div>
<footer class="bd-footer-content">
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script defer src="../_static/scripts/bootstrap.js?digest=90905a2f556bf617f1a9"></script>
<script defer src="../_static/scripts/pydata-sphinx-theme.js?digest=90905a2f556bf617f1a9"></script>
<footer class="bd-footer">
<div class="bd-footer__inner bd-page-width">
<div class="footer-items__start">
<div class="footer-item">
<p class="copyright">
© Copyright 2024-2026 Apache Software Foundation.
<br/>
</p>
</div>
<div class="footer-item">
<p class="sphinx-version">
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 9.1.0.
<br/>
</p>
</div>
</div>
<div class="footer-items__end">
<div class="footer-item">
<p class="theme-version">
<!-- # L10n: Setting the PST URL as an argument as this does not need to be localized -->
Built with the <a href="https://pydata-sphinx-theme.readthedocs.io/en/stable/index.html">PyData Sphinx Theme</a> 0.20.0.
</p></div>
</div>
</div>
</footer>
</body>
</html>