1671 lines
54 KiB
HTML
1671 lines
54 KiB
HTML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
|
|
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
|
|
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">
|
|
<head>
|
|
<meta http-equiv="Content-Type" content="application/xhtml+xml; charset=UTF-8" />
|
|
<meta name="generator" content="AsciiDoc 10.2.0" />
|
|
<title>gitformat-pack(5)</title>
|
|
<style type="text/css">
|
|
/* Shared CSS for AsciiDoc xhtml11 and html5 backends */
|
|
|
|
/* Default font. */
|
|
body {
|
|
font-family: Georgia,serif;
|
|
}
|
|
|
|
/* Title font. */
|
|
h1, h2, h3, h4, h5, h6,
|
|
div.title, caption.title,
|
|
thead, p.table.header,
|
|
#toctitle,
|
|
#author, #revnumber, #revdate, #revremark,
|
|
#footer {
|
|
font-family: Arial,Helvetica,sans-serif;
|
|
}
|
|
|
|
body {
|
|
margin: 1em 5% 1em 5%;
|
|
}
|
|
|
|
a {
|
|
color: blue;
|
|
text-decoration: underline;
|
|
}
|
|
a:visited {
|
|
color: fuchsia;
|
|
}
|
|
|
|
em {
|
|
font-style: italic;
|
|
color: navy;
|
|
}
|
|
|
|
strong {
|
|
font-weight: bold;
|
|
color: #083194;
|
|
}
|
|
|
|
h1, h2, h3, h4, h5, h6 {
|
|
color: #527bbd;
|
|
margin-top: 1.2em;
|
|
margin-bottom: 0.5em;
|
|
line-height: 1.3;
|
|
}
|
|
|
|
h1, h2, h3 {
|
|
border-bottom: 2px solid silver;
|
|
}
|
|
h2 {
|
|
padding-top: 0.5em;
|
|
}
|
|
h3 {
|
|
float: left;
|
|
}
|
|
h3 + * {
|
|
clear: left;
|
|
}
|
|
h5 {
|
|
font-size: 1.0em;
|
|
}
|
|
|
|
div.sectionbody {
|
|
margin-left: 0;
|
|
}
|
|
|
|
hr {
|
|
border: 1px solid silver;
|
|
}
|
|
|
|
p {
|
|
margin-top: 0.5em;
|
|
margin-bottom: 0.5em;
|
|
}
|
|
|
|
ul, ol, li > p {
|
|
margin-top: 0;
|
|
}
|
|
ul > li { color: #aaa; }
|
|
ul > li > * { color: black; }
|
|
|
|
.monospaced, code, pre {
|
|
font-family: "Courier New", Courier, monospace;
|
|
font-size: inherit;
|
|
color: navy;
|
|
padding: 0;
|
|
margin: 0;
|
|
}
|
|
pre {
|
|
white-space: pre-wrap;
|
|
}
|
|
|
|
#author {
|
|
color: #527bbd;
|
|
font-weight: bold;
|
|
font-size: 1.1em;
|
|
}
|
|
#email {
|
|
}
|
|
#revnumber, #revdate, #revremark {
|
|
}
|
|
|
|
#footer {
|
|
font-size: small;
|
|
border-top: 2px solid silver;
|
|
padding-top: 0.5em;
|
|
margin-top: 4.0em;
|
|
}
|
|
#footer-text {
|
|
float: left;
|
|
padding-bottom: 0.5em;
|
|
}
|
|
#footer-badges {
|
|
float: right;
|
|
padding-bottom: 0.5em;
|
|
}
|
|
|
|
#preamble {
|
|
margin-top: 1.5em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
div.imageblock, div.exampleblock, div.verseblock,
|
|
div.quoteblock, div.literalblock, div.listingblock, div.sidebarblock,
|
|
div.admonitionblock {
|
|
margin-top: 1.0em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
div.admonitionblock {
|
|
margin-top: 2.0em;
|
|
margin-bottom: 2.0em;
|
|
margin-right: 10%;
|
|
color: #606060;
|
|
}
|
|
|
|
div.content { /* Block element content. */
|
|
padding: 0;
|
|
}
|
|
|
|
/* Block element titles. */
|
|
div.title, caption.title {
|
|
color: #527bbd;
|
|
font-weight: bold;
|
|
text-align: left;
|
|
margin-top: 1.0em;
|
|
margin-bottom: 0.5em;
|
|
}
|
|
div.title + * {
|
|
margin-top: 0;
|
|
}
|
|
|
|
td div.title:first-child {
|
|
margin-top: 0.0em;
|
|
}
|
|
div.content div.title:first-child {
|
|
margin-top: 0.0em;
|
|
}
|
|
div.content + div.title {
|
|
margin-top: 0.0em;
|
|
}
|
|
|
|
div.sidebarblock > div.content {
|
|
background: #ffffee;
|
|
border: 1px solid #dddddd;
|
|
border-left: 4px solid #f0f0f0;
|
|
padding: 0.5em;
|
|
}
|
|
|
|
div.listingblock > div.content {
|
|
border: 1px solid #dddddd;
|
|
border-left: 5px solid #f0f0f0;
|
|
background: #f8f8f8;
|
|
padding: 0.5em;
|
|
}
|
|
|
|
div.quoteblock, div.verseblock {
|
|
padding-left: 1.0em;
|
|
margin-left: 1.0em;
|
|
margin-right: 10%;
|
|
border-left: 5px solid #f0f0f0;
|
|
color: #888;
|
|
}
|
|
|
|
div.quoteblock > div.attribution {
|
|
padding-top: 0.5em;
|
|
text-align: right;
|
|
}
|
|
|
|
div.verseblock > pre.content {
|
|
font-family: inherit;
|
|
font-size: inherit;
|
|
}
|
|
div.verseblock > div.attribution {
|
|
padding-top: 0.75em;
|
|
text-align: left;
|
|
}
|
|
/* DEPRECATED: Pre version 8.2.7 verse style literal block. */
|
|
div.verseblock + div.attribution {
|
|
text-align: left;
|
|
}
|
|
|
|
div.admonitionblock .icon {
|
|
vertical-align: top;
|
|
font-size: 1.1em;
|
|
font-weight: bold;
|
|
text-decoration: underline;
|
|
color: #527bbd;
|
|
padding-right: 0.5em;
|
|
}
|
|
div.admonitionblock td.content {
|
|
padding-left: 0.5em;
|
|
border-left: 3px solid #dddddd;
|
|
}
|
|
|
|
div.exampleblock > div.content {
|
|
border-left: 3px solid #dddddd;
|
|
padding-left: 0.5em;
|
|
}
|
|
|
|
div.imageblock div.content { padding-left: 0; }
|
|
span.image img { border-style: none; vertical-align: text-bottom; }
|
|
a.image:visited { color: white; }
|
|
|
|
dl {
|
|
margin-top: 0.8em;
|
|
margin-bottom: 0.8em;
|
|
}
|
|
dt {
|
|
margin-top: 0.5em;
|
|
margin-bottom: 0;
|
|
font-style: normal;
|
|
color: navy;
|
|
}
|
|
dd > *:first-child {
|
|
margin-top: 0.1em;
|
|
}
|
|
|
|
ul, ol {
|
|
list-style-position: outside;
|
|
}
|
|
ol.arabic {
|
|
list-style-type: decimal;
|
|
}
|
|
ol.loweralpha {
|
|
list-style-type: lower-alpha;
|
|
}
|
|
ol.upperalpha {
|
|
list-style-type: upper-alpha;
|
|
}
|
|
ol.lowerroman {
|
|
list-style-type: lower-roman;
|
|
}
|
|
ol.upperroman {
|
|
list-style-type: upper-roman;
|
|
}
|
|
|
|
div.compact ul, div.compact ol,
|
|
div.compact p, div.compact p,
|
|
div.compact div, div.compact div {
|
|
margin-top: 0.1em;
|
|
margin-bottom: 0.1em;
|
|
}
|
|
|
|
tfoot {
|
|
font-weight: bold;
|
|
}
|
|
td > div.verse {
|
|
white-space: pre;
|
|
}
|
|
|
|
div.hdlist {
|
|
margin-top: 0.8em;
|
|
margin-bottom: 0.8em;
|
|
}
|
|
div.hdlist tr {
|
|
padding-bottom: 15px;
|
|
}
|
|
dt.hdlist1.strong, td.hdlist1.strong {
|
|
font-weight: bold;
|
|
}
|
|
td.hdlist1 {
|
|
vertical-align: top;
|
|
font-style: normal;
|
|
padding-right: 0.8em;
|
|
color: navy;
|
|
}
|
|
td.hdlist2 {
|
|
vertical-align: top;
|
|
}
|
|
div.hdlist.compact tr {
|
|
margin: 0;
|
|
padding-bottom: 0;
|
|
}
|
|
|
|
.comment {
|
|
background: yellow;
|
|
}
|
|
|
|
.footnote, .footnoteref {
|
|
font-size: 0.8em;
|
|
}
|
|
|
|
span.footnote, span.footnoteref {
|
|
vertical-align: super;
|
|
}
|
|
|
|
#footnotes {
|
|
margin: 20px 0 20px 0;
|
|
padding: 7px 0 0 0;
|
|
}
|
|
|
|
#footnotes div.footnote {
|
|
margin: 0 0 5px 0;
|
|
}
|
|
|
|
#footnotes hr {
|
|
border: none;
|
|
border-top: 1px solid silver;
|
|
height: 1px;
|
|
text-align: left;
|
|
margin-left: 0;
|
|
width: 20%;
|
|
min-width: 100px;
|
|
}
|
|
|
|
div.colist td {
|
|
padding-right: 0.5em;
|
|
padding-bottom: 0.3em;
|
|
vertical-align: top;
|
|
}
|
|
div.colist td img {
|
|
margin-top: 0.3em;
|
|
}
|
|
|
|
@media print {
|
|
#footer-badges { display: none; }
|
|
}
|
|
|
|
#toc {
|
|
margin-bottom: 2.5em;
|
|
}
|
|
|
|
#toctitle {
|
|
color: #527bbd;
|
|
font-size: 1.1em;
|
|
font-weight: bold;
|
|
margin-top: 1.0em;
|
|
margin-bottom: 0.1em;
|
|
}
|
|
|
|
div.toclevel0, div.toclevel1, div.toclevel2, div.toclevel3, div.toclevel4 {
|
|
margin-top: 0;
|
|
margin-bottom: 0;
|
|
}
|
|
div.toclevel2 {
|
|
margin-left: 2em;
|
|
font-size: 0.9em;
|
|
}
|
|
div.toclevel3 {
|
|
margin-left: 4em;
|
|
font-size: 0.9em;
|
|
}
|
|
div.toclevel4 {
|
|
margin-left: 6em;
|
|
font-size: 0.9em;
|
|
}
|
|
|
|
span.aqua { color: aqua; }
|
|
span.black { color: black; }
|
|
span.blue { color: blue; }
|
|
span.fuchsia { color: fuchsia; }
|
|
span.gray { color: gray; }
|
|
span.green { color: green; }
|
|
span.lime { color: lime; }
|
|
span.maroon { color: maroon; }
|
|
span.navy { color: navy; }
|
|
span.olive { color: olive; }
|
|
span.purple { color: purple; }
|
|
span.red { color: red; }
|
|
span.silver { color: silver; }
|
|
span.teal { color: teal; }
|
|
span.white { color: white; }
|
|
span.yellow { color: yellow; }
|
|
|
|
span.aqua-background { background: aqua; }
|
|
span.black-background { background: black; }
|
|
span.blue-background { background: blue; }
|
|
span.fuchsia-background { background: fuchsia; }
|
|
span.gray-background { background: gray; }
|
|
span.green-background { background: green; }
|
|
span.lime-background { background: lime; }
|
|
span.maroon-background { background: maroon; }
|
|
span.navy-background { background: navy; }
|
|
span.olive-background { background: olive; }
|
|
span.purple-background { background: purple; }
|
|
span.red-background { background: red; }
|
|
span.silver-background { background: silver; }
|
|
span.teal-background { background: teal; }
|
|
span.white-background { background: white; }
|
|
span.yellow-background { background: yellow; }
|
|
|
|
span.big { font-size: 2em; }
|
|
span.small { font-size: 0.6em; }
|
|
|
|
span.underline { text-decoration: underline; }
|
|
span.overline { text-decoration: overline; }
|
|
span.line-through { text-decoration: line-through; }
|
|
|
|
div.unbreakable { page-break-inside: avoid; }
|
|
|
|
|
|
/*
|
|
* xhtml11 specific
|
|
*
|
|
* */
|
|
|
|
div.tableblock {
|
|
margin-top: 1.0em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
div.tableblock > table {
|
|
border: 3px solid #527bbd;
|
|
}
|
|
thead, p.table.header {
|
|
font-weight: bold;
|
|
color: #527bbd;
|
|
}
|
|
p.table {
|
|
margin-top: 0;
|
|
}
|
|
/* Because the table frame attribute is overridden by CSS in most browsers. */
|
|
div.tableblock > table[frame="void"] {
|
|
border-style: none;
|
|
}
|
|
div.tableblock > table[frame="hsides"] {
|
|
border-left-style: none;
|
|
border-right-style: none;
|
|
}
|
|
div.tableblock > table[frame="vsides"] {
|
|
border-top-style: none;
|
|
border-bottom-style: none;
|
|
}
|
|
|
|
|
|
/*
|
|
* html5 specific
|
|
*
|
|
* */
|
|
|
|
table.tableblock {
|
|
margin-top: 1.0em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
thead, p.tableblock.header {
|
|
font-weight: bold;
|
|
color: #527bbd;
|
|
}
|
|
p.tableblock {
|
|
margin-top: 0;
|
|
}
|
|
table.tableblock {
|
|
border-width: 3px;
|
|
border-spacing: 0px;
|
|
border-style: solid;
|
|
border-color: #527bbd;
|
|
border-collapse: collapse;
|
|
}
|
|
th.tableblock, td.tableblock {
|
|
border-width: 1px;
|
|
padding: 4px;
|
|
border-style: solid;
|
|
border-color: #527bbd;
|
|
}
|
|
|
|
table.tableblock.frame-topbot {
|
|
border-left-style: hidden;
|
|
border-right-style: hidden;
|
|
}
|
|
table.tableblock.frame-sides {
|
|
border-top-style: hidden;
|
|
border-bottom-style: hidden;
|
|
}
|
|
table.tableblock.frame-none {
|
|
border-style: hidden;
|
|
}
|
|
|
|
th.tableblock.halign-left, td.tableblock.halign-left {
|
|
text-align: left;
|
|
}
|
|
th.tableblock.halign-center, td.tableblock.halign-center {
|
|
text-align: center;
|
|
}
|
|
th.tableblock.halign-right, td.tableblock.halign-right {
|
|
text-align: right;
|
|
}
|
|
|
|
th.tableblock.valign-top, td.tableblock.valign-top {
|
|
vertical-align: top;
|
|
}
|
|
th.tableblock.valign-middle, td.tableblock.valign-middle {
|
|
vertical-align: middle;
|
|
}
|
|
th.tableblock.valign-bottom, td.tableblock.valign-bottom {
|
|
vertical-align: bottom;
|
|
}
|
|
|
|
|
|
/*
|
|
* manpage specific
|
|
*
|
|
* */
|
|
|
|
body.manpage h1 {
|
|
padding-top: 0.5em;
|
|
padding-bottom: 0.5em;
|
|
border-top: 2px solid silver;
|
|
border-bottom: 2px solid silver;
|
|
}
|
|
body.manpage h2 {
|
|
border-style: none;
|
|
}
|
|
body.manpage div.sectionbody {
|
|
margin-left: 3em;
|
|
}
|
|
|
|
@media print {
|
|
body.manpage div#toc { display: none; }
|
|
}
|
|
|
|
|
|
</style>
|
|
<script type="text/javascript">
|
|
/*<+'])');
|
|
// Function that scans the DOM tree for header elements (the DOM2
|
|
// nodeIterator API would be a better technique but not supported by all
|
|
// browsers).
|
|
var iterate = function (el) {
|
|
for (var i = el.firstChild; i != null; i = i.nextSibling) {
|
|
if (i.nodeType == 1 /* Node.ELEMENT_NODE */) {
|
|
var mo = re.exec(i.tagName);
|
|
if (mo && (i.getAttribute("class") || i.getAttribute("className")) != "float") {
|
|
result[result.length] = new TocEntry(i, getText(i), mo[1]-1);
|
|
}
|
|
iterate(i);
|
|
}
|
|
}
|
|
}
|
|
iterate(el);
|
|
return result;
|
|
}
|
|
|
|
var toc = document.getElementById("toc");
|
|
if (!toc) {
|
|
return;
|
|
}
|
|
|
|
// Delete existing TOC entries in case we're reloading the TOC.
|
|
var tocEntriesToRemove = [];
|
|
var i;
|
|
for (i = 0; i < toc.childNodes.length; i++) {
|
|
var entry = toc.childNodes[i];
|
|
if (entry.nodeName.toLowerCase() == 'div'
|
|
&& entry.getAttribute("class")
|
|
&& entry.getAttribute("class").match(/^toclevel/))
|
|
tocEntriesToRemove.push(entry);
|
|
}
|
|
for (i = 0; i < tocEntriesToRemove.length; i++) {
|
|
toc.removeChild(tocEntriesToRemove[i]);
|
|
}
|
|
|
|
// Rebuild TOC entries.
|
|
var entries = tocEntries(document.getElementById("content"), toclevels);
|
|
for (var i = 0; i < entries.length; ++i) {
|
|
var entry = entries[i];
|
|
if (entry.element.id == "")
|
|
entry.element.id = "_toc_" + i;
|
|
var a = document.createElement("a");
|
|
a.href = "#" + entry.element.id;
|
|
a.appendChild(document.createTextNode(entry.text));
|
|
var div = document.createElement("div");
|
|
div.appendChild(a);
|
|
div.className = "toclevel" + entry.toclevel;
|
|
toc.appendChild(div);
|
|
}
|
|
if (entries.length == 0)
|
|
toc.parentNode.removeChild(toc);
|
|
},
|
|
|
|
|
|
/////////////////////////////////////////////////////////////////////
|
|
// Footnotes generator
|
|
/////////////////////////////////////////////////////////////////////
|
|
|
|
/* Based on footnote generation code from:
|
|
* http://www.brandspankingnew.net/archive/2005/07/format_footnote.html
|
|
*/
|
|
|
|
footnotes: function () {
|
|
// Delete existing footnote entries in case we're reloading the footnodes.
|
|
var i;
|
|
var noteholder = document.getElementById("footnotes");
|
|
if (!noteholder) {
|
|
return;
|
|
}
|
|
var entriesToRemove = [];
|
|
for (i = 0; i < noteholder.childNodes.length; i++) {
|
|
var entry = noteholder.childNodes[i];
|
|
if (entry.nodeName.toLowerCase() == 'div' && entry.getAttribute("class") == "footnote")
|
|
entriesToRemove.push(entry);
|
|
}
|
|
for (i = 0; i < entriesToRemove.length; i++) {
|
|
noteholder.removeChild(entriesToRemove[i]);
|
|
}
|
|
|
|
// Rebuild footnote entries.
|
|
var cont = document.getElementById("content");
|
|
var spans = cont.getElementsByTagName("span");
|
|
var refs = {};
|
|
var n = 0;
|
|
for (i=0; i<spans.length; i++) {
|
|
if (spans[i].className == "footnote") {
|
|
n++;
|
|
var note = spans[i].getAttribute("data-note");
|
|
if (!note) {
|
|
// Use [\s\S] in place of . so multi-line matches work.
|
|
// Because JavaScript has no s (dotall) regex flag.
|
|
note = spans[i].innerHTML.match(/\s*\[([\s\S]*)]\s*/)[1];
|
|
spans[i].innerHTML =
|
|
"[<a id='_footnoteref_" + n + "' href='#_footnote_" + n +
|
|
"' title='View footnote' class='footnote'>" + n + "</a>]";
|
|
spans[i].setAttribute("data-note", note);
|
|
}
|
|
noteholder.innerHTML +=
|
|
"<div class='footnote' id='_footnote_" + n + "'>" +
|
|
"<a href='#_footnoteref_" + n + "' title='Return to text'>" +
|
|
n + "</a>. " + note + "</div>";
|
|
var id =spans[i].getAttribute("id");
|
|
if (id != null) refs["#"+id] = n;
|
|
}
|
|
}
|
|
if (n == 0)
|
|
noteholder.parentNode.removeChild(noteholder);
|
|
else {
|
|
// Process footnoterefs.
|
|
for (i=0; i<spans.length; i++) {
|
|
if (spans[i].className == "footnoteref") {
|
|
var href = spans[i].getElementsByTagName("a")[0].getAttribute("href");
|
|
href = href.match(/#.*/)[0]; // Because IE return full URL.
|
|
n = refs[href];
|
|
spans[i].innerHTML =
|
|
"[<a href='#_footnote_" + n +
|
|
"' title='View footnote' class='footnote'>" + n + "</a>]";
|
|
}
|
|
}
|
|
}
|
|
},
|
|
|
|
install: function(toclevels) {
|
|
var timerId;
|
|
|
|
function reinstall() {
|
|
asciidoc.footnotes();
|
|
if (toclevels) {
|
|
asciidoc.toc(toclevels);
|
|
}
|
|
}
|
|
|
|
function reinstallAndRemoveTimer() {
|
|
clearInterval(timerId);
|
|
reinstall();
|
|
}
|
|
|
|
timerId = setInterval(reinstall, 500);
|
|
if (document.addEventListener)
|
|
document.addEventListener("DOMContentLoaded", reinstallAndRemoveTimer, false);
|
|
else
|
|
window.onload = reinstallAndRemoveTimer;
|
|
}
|
|
|
|
}
|
|
asciidoc.install();
|
|
/*]]>*/
|
|
</script>
|
|
</head>
|
|
<body class="manpage">
|
|
<div id="header">
|
|
<h1>
|
|
gitformat-pack(5) Manual Page
|
|
</h1>
|
|
<h2>NAME</h2>
|
|
<div class="sectionbody">
|
|
<p>gitformat-pack -
|
|
Git pack format
|
|
</p>
|
|
</div>
|
|
</div>
|
|
<div id="content">
|
|
<div class="sect1">
|
|
<h2 id="_synopsis">SYNOPSIS</h2>
|
|
<div class="sectionbody">
|
|
<div class="verseblock">
|
|
<pre class="content">$GIT_DIR/objects/pack/pack-<strong>.{pack,idx}
|
|
$GIT_DIR/objects/pack/pack-</strong>.rev
|
|
$GIT_DIR/objects/pack/pack-*.mtimes
|
|
$GIT_DIR/objects/pack/multi-pack-index</pre>
|
|
<div class="attribution">
|
|
</div></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_description">DESCRIPTION</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>The Git pack format is how Git stores most of its primary repository
|
|
data. Over the lifetime of a repository, loose objects (if any) and
|
|
smaller packs are consolidated into larger pack(s). See
|
|
<a href="git-gc.html">git-gc(1)</a> and <a href="git-pack-objects.html">git-pack-objects(1)</a>.</p></div>
|
|
<div class="paragraph"><p>The pack format is also used over-the-wire, see
|
|
e.g. <a href="gitprotocol-v2.html">gitprotocol-v2(5)</a>, as well as being a part of
|
|
other container formats in the case of <a href="gitformat-bundle.html">gitformat-bundle(5)</a>.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_checksums_and_object_ids">Checksums and object IDs</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>In a repository using the traditional SHA-1, pack checksums, index checksums,
|
|
and object IDs (object names) mentioned below are all computed using SHA-1.
|
|
Similarly, in SHA-256 repositories, these values are computed using SHA-256.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_pack_pack_files_have_the_following_format">pack-*.pack files have the following format:</h2>
|
|
<div class="sectionbody">
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
A header appears at the beginning and consists of the following:
|
|
</p>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>4-byte signature:
|
|
The signature is: {'P', 'A', 'C', 'K'}</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>4-byte version number (network byte order):
|
|
Git currently accepts version number 2 or 3 but
|
|
generates version 2 only.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>4-byte number of objects contained in the pack (network byte order)</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>Observation: we cannot have more than 4G versions ;-) and
|
|
more than 4G objects in a pack.</code></pre>
|
|
</div></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
The header is followed by a number of object entries, each of
|
|
which looks like this:
|
|
</p>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>(undeltified representation)
|
|
n-byte type and length (3-bit type, (n-1)*7+4-bit length)
|
|
compressed data</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>(deltified representation)
|
|
n-byte type and length (3-bit type, (n-1)*7+4-bit length)
|
|
base object name if OBJ_REF_DELTA or a negative relative
|
|
offset from the delta object's position in the pack if this
|
|
is an OBJ_OFS_DELTA object
|
|
compressed delta data</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>Observation: the length of each object is encoded in a variable
|
|
length format and is not constrained to 32-bit or anything.</code></pre>
|
|
</div></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
The trailer records a pack checksum of all of the above.
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
<div class="sect2">
|
|
<h3 id="_object_types">Object types</h3>
|
|
<div class="paragraph"><p>Valid object types are:</p></div>
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
OBJ_COMMIT (1)
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
OBJ_TREE (2)
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
OBJ_BLOB (3)
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
OBJ_TAG (4)
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
OBJ_OFS_DELTA (6)
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
OBJ_REF_DELTA (7)
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
<div class="paragraph"><p>Type 5 is reserved for future expansion. Type 0 is invalid.</p></div>
|
|
</div>
|
|
<div class="sect2">
|
|
<h3 id="_size_encoding">Size encoding</h3>
|
|
<div class="paragraph"><p>This document uses the following "size encoding" of non-negative
|
|
integers: From each byte, the seven least significant bits are
|
|
used to form the resulting integer. As long as the most significant
|
|
bit is 1, this process continues; the byte with MSB 0 provides the
|
|
last seven bits. The seven-bit chunks are concatenated. Later
|
|
values are more significant.</p></div>
|
|
<div class="paragraph"><p>This size encoding should not be confused with the "offset encoding",
|
|
which is also used in this document.</p></div>
|
|
</div>
|
|
<div class="sect2">
|
|
<h3 id="_deltified_representation">Deltified representation</h3>
|
|
<div class="paragraph"><p>Conceptually there are only four object types: commit, tree, tag and
|
|
blob. However to save space, an object could be stored as a "delta" of
|
|
another "base" object. These representations are assigned new types
|
|
ofs-delta and ref-delta, which is only valid in a pack file.</p></div>
|
|
<div class="paragraph"><p>Both ofs-delta and ref-delta store the "delta" to be applied to
|
|
another object (called <em>base object</em>) to reconstruct the object. The
|
|
difference between them is, ref-delta directly encodes base object
|
|
name. If the base object is in the same pack, ofs-delta encodes
|
|
the offset of the base object in the pack instead.</p></div>
|
|
<div class="paragraph"><p>The base object could also be deltified if it’s in the same pack.
|
|
Ref-delta can also refer to an object outside the pack (i.e. the
|
|
so-called "thin pack"). When stored on disk however, the pack should
|
|
be self contained to avoid cyclic dependency.</p></div>
|
|
<div class="paragraph"><p>The delta data starts with the size of the base object and the
|
|
size of the object to be reconstructed. These sizes are
|
|
encoded using the size encoding from above. The remainder of
|
|
the delta data is a sequence of instructions to reconstruct the object
|
|
from the base object. If the base object is deltified, it must be
|
|
converted to canonical form first. Each instruction appends more and
|
|
more data to the target object until it’s complete. There are two
|
|
supported instructions so far: one for copying a byte range from the
|
|
source object and one for inserting new data embedded in the
|
|
instruction itself.</p></div>
|
|
<div class="paragraph"><p>Each instruction has variable length. Instruction type is determined
|
|
by the seventh bit of the first octet. The following diagrams follow
|
|
the convention in RFC 1951 (Deflate compressed data format).</p></div>
|
|
<div class="sect3">
|
|
<h4 id="_instruction_to_copy_from_base_object">Instruction to copy from base object</h4>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>+----------+---------+---------+---------+---------+-------+-------+-------+
|
|
| 1xxxxxxx | offset1 | offset2 | offset3 | offset4 | size1 | size2 | size3 |
|
|
+----------+---------+---------+---------+---------+-------+-------+-------+</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>This is the instruction format to copy a byte range from the source
|
|
object. It encodes the offset to copy from and the number of bytes to
|
|
copy. Offset and size are in little-endian order.</p></div>
|
|
<div class="paragraph"><p>All offset and size bytes are optional. This is to reduce the
|
|
instruction size when encoding small offsets or sizes. The first seven
|
|
bits in the first octet determine which of the next seven octets is
|
|
present. If bit zero is set, offset1 is present. If bit one is set
|
|
offset2 is present and so on.</p></div>
|
|
<div class="paragraph"><p>Note that a more compact instruction does not change offset and size
|
|
encoding. For example, if only offset2 is omitted like below, offset3
|
|
still contains bits 16-23. It does not become offset2 and contains
|
|
bits 8-15 even if it’s right next to offset1.</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>+----------+---------+---------+
|
|
| 10000101 | offset1 | offset3 |
|
|
+----------+---------+---------+</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>In its most compact form, this instruction only takes up one byte
|
|
(0x80) with both offset and size omitted, which will have default
|
|
values zero. There is another exception: size zero is automatically
|
|
converted to 0x10000.</p></div>
|
|
</div>
|
|
<div class="sect3">
|
|
<h4 id="_instruction_to_add_new_data">Instruction to add new data</h4>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>+----------+============+
|
|
| 0xxxxxxx | data |
|
|
+----------+============+</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>This is the instruction to construct the target object without the base
|
|
object. The following data is appended to the target object. The first
|
|
seven bits of the first octet determine the size of data in
|
|
bytes. The size must be non-zero.</p></div>
|
|
</div>
|
|
<div class="sect3">
|
|
<h4 id="_reserved_instruction">Reserved instruction</h4>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>+----------+============
|
|
| 00000000 |
|
|
+----------+============</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>This is the instruction reserved for future expansion.</p></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_original_version_1_pack_idx_files_have_the_following_format">Original (version 1) pack-*.idx files have the following format:</h2>
|
|
<div class="sectionbody">
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
The header consists of 256 4-byte network byte order
|
|
integers. N-th entry of this table records the number of
|
|
objects in the corresponding pack, the first byte of whose
|
|
object name is less than or equal to N. This is called the
|
|
<em>first-level fan-out</em> table.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
The header is followed by sorted 24-byte entries, one entry
|
|
per object in the pack. Each entry is:
|
|
</p>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>4-byte network byte order integer, recording where the
|
|
object is stored in the packfile as the offset from the
|
|
beginning.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>one object name of the appropriate size.</code></pre>
|
|
</div></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
The file is concluded with a trailer:
|
|
</p>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>A copy of the pack checksum at the end of the corresponding
|
|
packfile.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>Index checksum of all of the above.</code></pre>
|
|
</div></div>
|
|
</li>
|
|
</ul></div>
|
|
<div class="paragraph"><p>Pack Idx file:</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code> -- +--------------------------------+
|
|
fanout | fanout[0] = 2 (for example) |-.
|
|
table +--------------------------------+ |
|
|
| fanout[1] | |
|
|
+--------------------------------+ |
|
|
| fanout[2] | |
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
|
|
| fanout[255] = total objects |---.
|
|
-- +--------------------------------+ | |
|
|
main | offset | | |
|
|
index | object name 00XXXXXXXXXXXXXXXX | | |
|
|
table +--------------------------------+ | |
|
|
| offset | | |
|
|
| object name 00XXXXXXXXXXXXXXXX | | |
|
|
+--------------------------------+<+ |
|
|
.-| offset | |
|
|
| | object name 01XXXXXXXXXXXXXXXX | |
|
|
| +--------------------------------+ |
|
|
| | offset | |
|
|
| | object name 01XXXXXXXXXXXXXXXX | |
|
|
| ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
|
|
| | offset | |
|
|
| | object name FFXXXXXXXXXXXXXXXX | |
|
|
--| +--------------------------------+<--+
|
|
trailer | | packfile checksum |
|
|
| +--------------------------------+
|
|
| | idxfile checksum |
|
|
| +--------------------------------+
|
|
.-------.
|
|
|
|
|
Pack file entry: <+</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>packed object header:
|
|
1-byte size extension bit (MSB)
|
|
type (next 3 bit)
|
|
size0 (lower 4-bit)
|
|
n-byte sizeN (as long as MSB is set, each 7-bit)
|
|
size0..sizeN form 4+7+7+..+7 bit integer, size0
|
|
is the least significant part, and sizeN is the
|
|
most significant part.
|
|
packed object data:
|
|
If it is not DELTA, then deflated bytes (the size above
|
|
is the size before compression).
|
|
If it is REF_DELTA, then
|
|
base object name (the size above is the
|
|
size of the delta data that follows).
|
|
delta data, deflated.
|
|
If it is OFS_DELTA, then
|
|
n-byte offset (see below) interpreted as a negative
|
|
offset from the type-byte of the header of the
|
|
ofs-delta entry (the size above is the size of
|
|
the delta data that follows).
|
|
delta data, deflated.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>offset encoding:
|
|
n bytes with MSB set in all but the last one.
|
|
The offset is then the number constructed by
|
|
concatenating the lower 7 bit of each byte, and
|
|
for n >= 2 adding 2^7 + 2^14 + ... + 2^(7*(n-1))
|
|
to the result.</code></pre>
|
|
</div></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_version_2_pack_idx_files_support_packs_larger_than_4_gib_and">Version 2 pack-*.idx files support packs larger than 4 GiB, and</h2>
|
|
<div class="sectionbody">
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>have some other reorganizations. They have the format:</code></pre>
|
|
</div></div>
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
A 4-byte magic number <em>\377tOc</em> which is an unreasonable
|
|
fanout[0] value.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A 4-byte version number (= 2)
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A 256-entry fan-out table just like v1.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A table of sorted object names. These are packed together
|
|
without offset values to reduce the cache footprint of the
|
|
binary search for a specific object name.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A table of 4-byte CRC32 values of the packed object data.
|
|
This is new in v2 so compressed data can be copied directly
|
|
from pack to pack during repacking without undetected
|
|
data corruption.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A table of 4-byte offset values (in network byte order).
|
|
These are usually 31-bit pack file offsets, but large
|
|
offsets are encoded as an index into the next table with
|
|
the msbit set.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A table of 8-byte offset entries (empty for pack files less
|
|
than 2 GiB). Pack files are organized with heavily used
|
|
objects toward the front, so most object references should
|
|
not need to refer to this table.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
The same trailer as a v1 pack file:
|
|
</p>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>A copy of the pack checksum at the end of the
|
|
corresponding packfile.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>Index checksum of all of the above.</code></pre>
|
|
</div></div>
|
|
</li>
|
|
</ul></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_pack_rev_files_have_the_format">pack-*.rev files have the format:</h2>
|
|
<div class="sectionbody">
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
A 4-byte magic number <em>0x52494458</em> (<em>RIDX</em>).
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A 4-byte version identifier (= 1).
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A 4-byte hash function identifier (= 1 for SHA-1, 2 for SHA-256).
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A table of index positions (one per packed object, num_objects in
|
|
total, each a 4-byte unsigned integer in network order), sorted by
|
|
their corresponding offsets in the packfile.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A trailer, containing a:
|
|
</p>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>checksum of the corresponding packfile, and</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>a checksum of all of the above.</code></pre>
|
|
</div></div>
|
|
</li>
|
|
</ul></div>
|
|
<div class="paragraph"><p>All 4-byte numbers are in network order.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_pack_mtimes_files_have_the_format">pack-*.mtimes files have the format:</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>All 4-byte numbers are in network byte order.</p></div>
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
A 4-byte magic number <em>0x4d544d45</em> (<em>MTME</em>).
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A 4-byte version identifier (= 1).
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A 4-byte hash function identifier (= 1 for SHA-1, 2 for SHA-256).
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A table of 4-byte unsigned integers. The ith value is the
|
|
modification time (mtime) of the ith object in the corresponding
|
|
pack by lexicographic (index) order. The mtimes count standard
|
|
epoch seconds.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A trailer, containing a checksum of the corresponding packfile,
|
|
and a checksum of all of the above (each having length according
|
|
to the specified hash function).
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_multi_pack_index_midx_files_have_the_following_format">multi-pack-index (MIDX) files have the following format:</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>The multi-pack-index files refer to multiple pack-files and loose objects.</p></div>
|
|
<div class="paragraph"><p>In order to allow extensions that add extra data to the MIDX, we organize
|
|
the body into "chunks" and provide a lookup table at the beginning of the
|
|
body. The header includes certain length values, such as the number of packs,
|
|
the number of base MIDX files, hash lengths and types.</p></div>
|
|
<div class="paragraph"><p>All 4-byte numbers are in network order.</p></div>
|
|
<div class="paragraph"><p>HEADER:</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>4-byte signature:
|
|
The signature is: {'M', 'I', 'D', 'X'}</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>1-byte version number:
|
|
Git only writes or recognizes version 1.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>1-byte Object Id Version
|
|
We infer the length of object IDs (OIDs) from this value:
|
|
1 => SHA-1
|
|
2 => SHA-256
|
|
If the hash type does not match the repository's hash algorithm,
|
|
the multi-pack-index file should be ignored with a warning
|
|
presented to the user.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>1-byte number of "chunks"</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>1-byte number of base multi-pack-index files:
|
|
This value is currently always zero.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>4-byte number of pack files</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>CHUNK LOOKUP:</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>(C + 1) * 12 bytes providing the chunk offsets:
|
|
First 4 bytes describe chunk id. Value 0 is a terminating label.
|
|
Other 8 bytes provide offset in current file for chunk to start.
|
|
(Chunks are provided in file-order, so you can infer the length
|
|
using the next chunk position if necessary.)</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>The CHUNK LOOKUP matches the table of contents from
|
|
the chunk-based file format, see linkgit:gitformat-chunk[5].</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>The remaining data in the body is described one chunk at a time, and
|
|
these chunks may be given in any order. Chunks are required unless
|
|
otherwise specified.</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>CHUNK DATA:</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>Packfile Names (ID: {'P', 'N', 'A', 'M'})
|
|
Store the names of packfiles as a sequence of NUL-terminated
|
|
strings. There is no extra padding between the filenames,
|
|
and they are listed in lexicographic order. The chunk itself
|
|
is padded at the end with between 0 and 3 NUL bytes to make the
|
|
chunk size a multiple of 4 bytes.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>Bitmapped Packfiles (ID: {'B', 'T', 'M', 'P'})
|
|
Stores a table of two 4-byte unsigned integers in network order.
|
|
Each table entry corresponds to a single pack (in the order that
|
|
they appear above in the `PNAM` chunk). The values for each table
|
|
entry are as follows:
|
|
- The first bit position (in pseudo-pack order, see below) to
|
|
contain an object from that pack.
|
|
- The number of bits whose objects are selected from that pack.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>OID Fanout (ID: {'O', 'I', 'D', 'F'})
|
|
The ith entry, F[i], stores the number of OIDs with first
|
|
byte at most i. Thus F[255] stores the total
|
|
number of objects.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>OID Lookup (ID: {'O', 'I', 'D', 'L'})
|
|
The OIDs for all objects in the MIDX are stored in lexicographic
|
|
order in this chunk.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>Object Offsets (ID: {'O', 'O', 'F', 'F'})
|
|
Stores two 4-byte values for every object.
|
|
1: The pack-int-id for the pack storing this object.
|
|
2: The offset within the pack.
|
|
If all offsets are less than 2^32, then the large offset chunk
|
|
will not exist and offsets are stored as in IDX v1.
|
|
If there is at least one offset value larger than 2^32-1, then
|
|
the large offset chunk must exist, and offsets larger than
|
|
2^31-1 must be stored in it instead. If the large offset chunk
|
|
exists and the 31st bit is on, then removing that bit reveals
|
|
the row in the large offsets containing the 8-byte offset of
|
|
this object.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>[Optional] Object Large Offsets (ID: {'L', 'O', 'F', 'F'})
|
|
8-byte offsets into large packfiles.</code></pre>
|
|
</div></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>[Optional] Bitmap pack order (ID: {'R', 'I', 'D', 'X'})
|
|
A list of MIDX positions (one per object in the MIDX, num_objects in
|
|
total, each a 4-byte unsigned integer in network byte order), sorted
|
|
according to their relative bitmap/pseudo-pack positions.</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>TRAILER:</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>Index checksum of the above contents.</code></pre>
|
|
</div></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_multi_pack_index_reverse_indexes">multi-pack-index reverse indexes</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>Similar to the pack-based reverse index, the multi-pack index can also
|
|
be used to generate a reverse index.</p></div>
|
|
<div class="paragraph"><p>Instead of mapping between offset, pack-, and index position, this
|
|
reverse index maps between an object’s position within the MIDX, and
|
|
that object’s position within a pseudo-pack that the MIDX describes
|
|
(i.e., the ith entry of the multi-pack reverse index holds the MIDX
|
|
position of ith object in pseudo-pack order).</p></div>
|
|
<div class="paragraph"><p>To clarify the difference between these orderings, consider a multi-pack
|
|
reachability bitmap (which does not yet exist, but is what we are
|
|
building towards here). Each bit needs to correspond to an object in the
|
|
MIDX, and so we need an efficient mapping from bit position to MIDX
|
|
position.</p></div>
|
|
<div class="paragraph"><p>One solution is to let bits occupy the same position in the oid-sorted
|
|
index stored by the MIDX. But because oids are effectively random, their
|
|
resulting reachability bitmaps would have no locality, and thus compress
|
|
poorly. (This is the reason that single-pack bitmaps use the pack
|
|
ordering, and not the .idx ordering, for the same purpose.)</p></div>
|
|
<div class="paragraph"><p>So we’d like to define an ordering for the whole MIDX based around
|
|
pack ordering, which has far better locality (and thus compresses more
|
|
efficiently). We can think of a pseudo-pack created by the concatenation
|
|
of all of the packs in the MIDX. E.g., if we had a MIDX with three packs
|
|
(a, b, c), with 10, 15, and 20 objects respectively, we can imagine an
|
|
ordering of the objects like:</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>|a,0|a,1|...|a,9|b,0|b,1|...|b,14|c,0|c,1|...|c,19|</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>where the ordering of the packs is defined by the MIDX’s pack list,
|
|
and then the ordering of objects within each pack is the same as the
|
|
order in the actual packfile.</p></div>
|
|
<div class="paragraph"><p>Given the list of packs and their counts of objects, you can
|
|
naïvely reconstruct that pseudo-pack ordering (e.g., the object at
|
|
position 27 must be (c,1) because packs "a" and "b" consumed 25 of the
|
|
slots). But there’s a catch. Objects may be duplicated between packs, in
|
|
which case the MIDX only stores one pointer to the object (and thus we’d
|
|
want only one slot in the bitmap).</p></div>
|
|
<div class="paragraph"><p>Callers could handle duplicates themselves by reading objects in order
|
|
of their bit-position, but that’s linear in the number of objects, and
|
|
much too expensive for ordinary bitmap lookups. Building a reverse index
|
|
solves this, since it is the logical inverse of the index, and that
|
|
index has already removed duplicates. But, building a reverse index on
|
|
the fly can be expensive. Since we already have an on-disk format for
|
|
pack-based reverse indexes, let’s reuse it for the MIDX’s pseudo-pack,
|
|
too.</p></div>
|
|
<div class="paragraph"><p>Objects from the MIDX are ordered as follows to string together the
|
|
pseudo-pack. Let <code>pack</code>(<code>o</code>) return the pack from which <code>o</code> was selected
|
|
by the MIDX, and define an ordering of packs based on their numeric ID
|
|
(as stored by the MIDX). Let <code>offset</code>(<code>o</code>) return the object offset of <code>o</code>
|
|
within <code>pack</code>(<code>o</code>). Then, compare <code>o1</code> and <code>o2</code> as follows:</p></div>
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
If one of <code>pack</code>(<code>o1</code>) and <code>pack</code>(<code>o2</code>) is preferred and the other
|
|
is not, then the preferred one sorts first.
|
|
</p>
|
|
<div class="paragraph"><p>(This is a detail that allows the MIDX bitmap to determine which
|
|
pack should be used by the pack-reuse mechanism, since it can ask
|
|
the MIDX for the pack containing the object at bit position 0).</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
If <code>pack</code>(<code>o1</code>) ≠ <code>pack</code>(<code>o2</code>), then sort the two objects in descending
|
|
order based on the pack ID.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Otherwise, <code>pack</code>(<code>o1</code>) <code>=</code> <code>pack</code>(<code>o2</code>), and the objects are sorted in
|
|
pack-order (i.e., <code>o1</code> sorts ahead of <code>o2</code> exactly when <code>offset</code>(<code>o1</code>)
|
|
< <code>offset</code>(<code>o2</code>)).
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
<div class="paragraph"><p>In short, a MIDX’s pseudo-pack is the de-duplicated concatenation of
|
|
objects in packs stored by the MIDX, laid out in pack order, and the
|
|
packs arranged in MIDX order (with the preferred pack coming first).</p></div>
|
|
<div class="paragraph"><p>The MIDX’s reverse index is stored in the optional <em>RIDX</em> chunk within
|
|
the MIDX itself.</p></div>
|
|
<div class="sect2">
|
|
<h3 id="_code_btmp_code_chunk"><code>BTMP</code> chunk</h3>
|
|
<div class="paragraph"><p>The Bitmapped Packfiles (<code>BTMP</code>) chunk encodes additional information
|
|
about the objects in the multi-pack index’s reachability bitmap. Recall
|
|
that objects from the MIDX are arranged in "pseudo-pack" order (see
|
|
above) for reachability bitmaps.</p></div>
|
|
<div class="paragraph"><p>From the example above, suppose we have packs "a", "b", and "c", with
|
|
10, 15, and 20 objects, respectively. In pseudo-pack order, those would
|
|
be arranged as follows:</p></div>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>|a,0|a,1|...|a,9|b,0|b,1|...|b,14|c,0|c,1|...|c,19|</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>When working with single-pack bitmaps (or, equivalently, multi-pack
|
|
reachability bitmaps with a preferred pack), <a href="git-pack-objects.html">git-pack-objects(1)</a>
|
|
performs “verbatim” reuse, attempting to reuse chunks of the bitmapped
|
|
or preferred packfile instead of adding objects to the packing list.</p></div>
|
|
<div class="paragraph"><p>When a chunk of bytes is reused from an existing pack, any objects
|
|
contained therein do not need to be added to the packing list, saving
|
|
memory and CPU time. But a chunk from an existing packfile can only be
|
|
reused when the following conditions are met:</p></div>
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
The chunk contains only objects which were requested by the caller
|
|
(i.e. does not contain any objects which the caller didn’t ask for
|
|
explicitly or implicitly).
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
All objects stored in non-thin packs as offset- or reference-deltas
|
|
also include their base object in the resulting pack.
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
<div class="paragraph"><p>The <code>BTMP</code> chunk encodes the necessary information in order to implement
|
|
multi-pack reuse over a set of packfiles as described above.
|
|
Specifically, the <code>BTMP</code> chunk encodes three pieces of information (all
|
|
32-bit unsigned integers in network byte-order) for each packfile <code>p</code>
|
|
that is stored in the MIDX, as follows:</p></div>
|
|
<div class="dlist"><dl>
|
|
<dt class="hdlist1">
|
|
<code>bitmap_pos</code>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
The first bit position (in pseudo-pack order) in the
|
|
multi-pack index’s reachability bitmap occupied by an object from <code>p</code>.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<code>bitmap_nr</code>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
The number of bit positions (including the one at
|
|
<code>bitmap_pos</code>) that encode objects from that pack <code>p</code>.
|
|
</p>
|
|
</dd>
|
|
</dl></div>
|
|
<div class="paragraph"><p>For example, the <code>BTMP</code> chunk corresponding to the above example (with
|
|
packs “a”, “b”, and “c”) would look like:</p></div>
|
|
<div class="tableblock">
|
|
<table rules="all"
|
|
width="100%"
|
|
frame="border"
|
|
cellspacing="0" cellpadding="4">
|
|
<col width="20%" />
|
|
<col width="40%" />
|
|
<col width="40%" />
|
|
<tbody>
|
|
<tr>
|
|
<td align="left" valign="top"><p class="table"></p></td>
|
|
<td align="left" valign="top"><p class="table"><code>bitmap_pos</code></p></td>
|
|
<td align="left" valign="top"><p class="table"><code>bitmap_nr</code></p></td>
|
|
</tr>
|
|
<tr>
|
|
<td align="left" valign="top"><p class="table">packfile “a”</p></td>
|
|
<td align="left" valign="top"><p class="table"><code>0</code></p></td>
|
|
<td align="left" valign="top"><p class="table"><code>10</code></p></td>
|
|
</tr>
|
|
<tr>
|
|
<td align="left" valign="top"><p class="table">packfile “b”</p></td>
|
|
<td align="left" valign="top"><p class="table"><code>10</code></p></td>
|
|
<td align="left" valign="top"><p class="table"><code>15</code></p></td>
|
|
</tr>
|
|
<tr>
|
|
<td align="left" valign="top"><p class="table">packfile “c”</p></td>
|
|
<td align="left" valign="top"><p class="table"><code>25</code></p></td>
|
|
<td align="left" valign="top"><p class="table"><code>20</code></p></td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
</div>
|
|
<div class="paragraph"><p>With this information in place, we can treat each packfile as
|
|
individually reusable in the same fashion as verbatim pack reuse is
|
|
performed on individual packs prior to the implementation of the <code>BTMP</code>
|
|
chunk.</p></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_cruft_packs">cruft packs</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>The cruft packs feature offer an alternative to Git’s traditional mechanism of
|
|
removing unreachable objects. This document provides an overview of Git’s
|
|
pruning mechanism, and how a cruft pack can be used instead to accomplish the
|
|
same.</p></div>
|
|
<div class="sect2">
|
|
<h3 id="_background">Background</h3>
|
|
<div class="paragraph"><p>To remove unreachable objects from your repository, Git offers <code>git</code> <code>repack</code> <code>-Ad</code>
|
|
(see <a href="git-repack.html">git-repack(1)</a>). Quoting from the documentation:</p></div>
|
|
<div class="listingblock">
|
|
<div class="content">
|
|
<pre><code>[...] unreachable objects in a previous pack become loose, unpacked objects,
|
|
instead of being left in the old pack. [...] loose unreachable objects will be
|
|
pruned according to normal expiry rules with the next 'git gc' invocation.</code></pre>
|
|
</div></div>
|
|
<div class="paragraph"><p>Unreachable objects aren’t removed immediately, since doing so could race with
|
|
an incoming push which may reference an object which is about to be deleted.
|
|
Instead, those unreachable objects are stored as loose objects and stay that way
|
|
until they are older than the expiration window, at which point they are removed
|
|
by <a href="git-prune.html">git-prune(1)</a>.</p></div>
|
|
<div class="paragraph"><p>Git must store these unreachable objects loose in order to keep track of their
|
|
per-object mtimes. If these unreachable objects were written into one big pack,
|
|
then either freshening that pack (because an object contained within it was
|
|
re-written) or creating a new pack of unreachable objects would cause the pack’s
|
|
mtime to get updated, and the objects within it would never leave the expiration
|
|
window. Instead, objects are stored loose in order to keep track of the
|
|
individual object mtimes and avoid a situation where all cruft objects are
|
|
freshened at once.</p></div>
|
|
<div class="paragraph"><p>This can lead to undesirable situations when a repository contains many
|
|
unreachable objects which have not yet left the grace period. Having large
|
|
directories in the shards of <code>.git/objects</code> can lead to decreased performance in
|
|
the repository. But given enough unreachable objects, this can lead to inode
|
|
starvation and degrade the performance of the whole system. Since we
|
|
can never pack those objects, these repositories often take up a large amount of
|
|
disk space, since we can only zlib compress them, but not store them in delta
|
|
chains.</p></div>
|
|
</div>
|
|
<div class="sect2">
|
|
<h3 id="_cruft_packs_2">Cruft packs</h3>
|
|
<div class="paragraph"><p>A cruft pack eliminates the need for storing unreachable objects in a loose
|
|
state by including the per-object mtimes in a separate file alongside a single
|
|
pack containing all loose objects.</p></div>
|
|
<div class="paragraph"><p>A cruft pack is written by <code>git</code> <code>repack</code> <code>--cruft</code> when generating a new pack.
|
|
<a href="git-pack-objects.html">git-pack-objects(1)</a>'s <code>--cruft</code> option. Note that <code>git</code> <code>repack</code> <code>--cruft</code>
|
|
is a classic all-into-one repack, meaning that everything in the resulting pack is
|
|
reachable, and everything else is unreachable. Once written, the <code>--cruft</code>
|
|
option instructs <code>git</code> <code>repack</code> to generate another pack containing only objects
|
|
not packed in the previous step (which equates to packing all unreachable
|
|
objects together). This progresses as follows:</p></div>
|
|
<div class="olist arabic"><ol class="arabic">
|
|
<li>
|
|
<p>
|
|
Enumerate every object, marking any object which is (a) not contained in a
|
|
kept-pack, and (b) whose mtime is within the grace period as a traversal
|
|
tip.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Perform a reachability traversal based on the tips gathered in the previous
|
|
step, adding every object along the way to the pack.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Write the pack out, along with a <code>.mtimes</code> file that records the per-object
|
|
timestamps.
|
|
</p>
|
|
</li>
|
|
</ol></div>
|
|
<div class="paragraph"><p>This mode is invoked internally by <a href="git-repack.html">git-repack(1)</a> when instructed to
|
|
write a cruft pack. Crucially, the set of in-core kept packs is exactly the set
|
|
of packs which will not be deleted by the repack; in other words, they contain
|
|
all of the repository’s reachable objects.</p></div>
|
|
<div class="paragraph"><p>When a repository already has a cruft pack, <code>git</code> <code>repack</code> <code>--cruft</code> typically only
|
|
adds objects to it. An exception to this is when <code>git</code> <code>repack</code> is given the
|
|
<code>--cruft-expiration</code> option, which allows the generated cruft pack to omit
|
|
expired objects instead of waiting for <a href="git-gc.html">git-gc(1)</a> to expire those objects
|
|
later on.</p></div>
|
|
<div class="paragraph"><p>It is <a href="git-gc.html">git-gc(1)</a> that is typically responsible for removing expired
|
|
unreachable objects.</p></div>
|
|
</div>
|
|
<div class="sect2">
|
|
<h3 id="_alternatives">Alternatives</h3>
|
|
<div class="paragraph"><p>Notable alternatives to this design include:</p></div>
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
The location of the per-object mtime data.
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
<div class="paragraph"><p>On the location of mtime data, a new auxiliary file tied to the pack was chosen
|
|
to avoid complicating the <code>.idx</code> format. If the <code>.idx</code> format were ever to gain
|
|
support for optional chunks of data, it may make sense to consolidate the
|
|
<code>.mtimes</code> format into the <code>.idx</code> itself.</p></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_git">GIT</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>Part of the <a href="git.html">git(1)</a> suite</p></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div id="footnotes"><hr /></div>
|
|
<div id="footer">
|
|
<div id="footer-text">
|
|
Last updated
|
|
2025-08-18 02:18:23 CEST
|
|
</div>
|
|
</div>
|
|
</body>
|
|
</html>
|