1221 lines
36 KiB
HTML
1221 lines
36 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>Partial Clone Design Notes</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="article">
|
|
<div id="header">
|
|
<h1>Partial Clone Design Notes</h1>
|
|
<span id="revdate"></span>
|
|
</div>
|
|
<div id="content">
|
|
<div id="preamble">
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>The "Partial Clone" feature is a performance optimization for Git that
|
|
allows Git to function without having a complete copy of the repository.
|
|
The goal of this work is to allow Git to better handle extremely large
|
|
repositories.</p></div>
|
|
<div class="paragraph"><p>During clone and fetch operations, Git downloads the complete contents
|
|
and history of the repository. This includes all commits, trees, and
|
|
blobs for the complete life of the repository. For extremely large
|
|
repositories, clones can take hours (or days) and consume 100+GiB of disk
|
|
space.</p></div>
|
|
<div class="paragraph"><p>Often in these repositories there are many blobs and trees that the user
|
|
does not need such as:</p></div>
|
|
<div class="olist arabic"><ol class="arabic">
|
|
<li>
|
|
<p>
|
|
files outside of the user’s work area in the tree. For example, in
|
|
a repository with 500K directories and 3.5M files in every commit,
|
|
we can avoid downloading many objects if the user only needs a
|
|
narrow "cone" of the source tree.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
large binary assets. For example, in a repository where large build
|
|
artifacts are checked into the tree, we can avoid downloading all
|
|
previous versions of these non-mergeable binary assets and only
|
|
download versions that are actually referenced.
|
|
</p>
|
|
</li>
|
|
</ol></div>
|
|
<div class="paragraph"><p>Partial clone allows us to avoid downloading such unneeded objects <strong>in
|
|
advance</strong> during clone and fetch operations and thereby reduce download
|
|
times and disk usage. Missing objects can later be "demand fetched"
|
|
if/when needed.</p></div>
|
|
<div class="paragraph"><p>A remote that can later provide the missing objects is called a
|
|
promisor remote, as it promises to send the objects when
|
|
requested. Initially Git supported only one promisor remote, the origin
|
|
remote from which the user cloned and that was configured in the
|
|
"extensions.partialClone" config option. Later support for more than
|
|
one promisor remote has been implemented.</p></div>
|
|
<div class="paragraph"><p>Use of partial clone requires that the user be online and the origin
|
|
remote or other promisor remotes be available for on-demand fetching
|
|
of missing objects. This may or may not be problematic for the user.
|
|
For example, if the user can stay within the pre-selected subset of
|
|
the source tree, they may not encounter any missing objects.
|
|
Alternatively, the user could try to pre-fetch various objects if they
|
|
know that they are going offline.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_non_goals">Non-Goals</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>Partial clone is a mechanism to limit the number of blobs and trees downloaded
|
|
<strong>within</strong> a given range of commits — and is therefore independent of and not
|
|
intended to conflict with existing DAG-level mechanisms to limit the set of
|
|
requested commits (i.e. shallow clone, single branch, or fetch <em><refspec></em>).</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_design_overview">Design Overview</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>Partial clone logically consists of the following parts:</p></div>
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
A mechanism for the client to describe unneeded or unwanted objects to
|
|
the server.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A mechanism for the server to omit such unwanted objects from packfiles
|
|
sent to the client.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A mechanism for the client to gracefully handle missing objects (that
|
|
were previously omitted by the server).
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
A mechanism for the client to backfill missing objects as needed.
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_design_details">Design Details</h2>
|
|
<div class="sectionbody">
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
A new pack-protocol capability "filter" is added to the fetch-pack and
|
|
upload-pack negotiation.
|
|
</p>
|
|
<div class="paragraph"><p>This uses the existing capability discovery mechanism.
|
|
See "filter" in <a href="../gitprotocol-pack.html">gitprotocol-pack(5)</a>.</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Clients pass a "filter-spec" to clone and fetch which is passed to the
|
|
server to request filtering during packfile construction.
|
|
</p>
|
|
<div class="paragraph"><p>There are various filters available to accommodate different situations.
|
|
See "--filter=<filter-spec>" in Documentation/rev-list-options.adoc.</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
On the server pack-objects applies the requested filter-spec as it
|
|
creates "filtered" packfiles for the client.
|
|
</p>
|
|
<div class="paragraph"><p>These filtered packfiles are <strong>incomplete</strong> in the traditional sense because
|
|
they may contain objects that reference objects not contained in the
|
|
packfile and that the client doesn’t already have. For example, the
|
|
filtered packfile may contain trees or tags that reference missing blobs
|
|
or commits that reference missing trees.</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
On the client these incomplete packfiles are marked as "promisor packfiles"
|
|
and treated differently by various commands.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
On the client a repository extension is added to the local config to
|
|
prevent older versions of git from failing mid-operation because of
|
|
missing objects that they cannot handle.
|
|
See <code>extensions.partialClone</code> in <a href="../git-config.html">git-config(1)</a>.
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_handling_missing_objects">Handling Missing Objects</h2>
|
|
<div class="sectionbody">
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
An object may be missing due to a partial clone or fetch, or missing
|
|
due to repository corruption. To differentiate these cases, the
|
|
local repository specially indicates such filtered packfiles
|
|
obtained from promisor remotes as "promisor packfiles".
|
|
</p>
|
|
<div class="paragraph"><p>These promisor packfiles consist of a "<name>.promisor" file with
|
|
arbitrary contents (like the "<name>.keep" files), in addition to
|
|
their "<name>.pack" and "<name>.idx" files.</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
The local repository considers a "promisor object" to be an object that
|
|
it knows (to the best of its ability) that promisor remotes have promised
|
|
that they have, either because the local repository has that object in one of
|
|
its promisor packfiles, or because another promisor object refers to it.
|
|
</p>
|
|
<div class="paragraph"><p>When Git encounters a missing object, Git can see if it is a promisor object
|
|
and handle it appropriately. If not, Git can report a corruption.</p></div>
|
|
<div class="paragraph"><p>This means that there is no need for the client to explicitly maintain an
|
|
expensive-to-modify list of missing objects.[a]</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Since almost all Git code currently expects any referenced object to be
|
|
present locally and because we do not want to force every command to do
|
|
a dry-run first, a fallback mechanism is added to allow Git to attempt
|
|
to dynamically fetch missing objects from promisor remotes.
|
|
</p>
|
|
<div class="paragraph"><p>When the normal object lookup fails to find an object, Git invokes
|
|
promisor_remote_get_direct() to try to get the object from a promisor
|
|
remote and then retry the object lookup. This allows objects to be
|
|
"faulted in" without complicated prediction algorithms.</p></div>
|
|
<div class="paragraph"><p>For efficiency reasons, no check as to whether the missing object is
|
|
actually a promisor object is performed.</p></div>
|
|
<div class="paragraph"><p>Dynamic object fetching tends to be slow as objects are fetched one at
|
|
a time.</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
<code>checkout</code> (and any other command using <code>unpack-trees</code>) has been taught
|
|
to bulk pre-fetch all required missing blobs in a single batch.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
<code>rev-list</code> has been taught to print missing objects.
|
|
</p>
|
|
<div class="paragraph"><p>This can be used by other commands to bulk prefetch objects.
|
|
For example, a "git log -p A..B" may internally want to first do
|
|
something like "git rev-list --objects --quiet --missing=print A..B"
|
|
and prefetch those objects in bulk.</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
<code>fsck</code> has been updated to be fully aware of promisor objects.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
<code>repack</code> in GC has been updated to not touch promisor packfiles at all,
|
|
and to only repack other objects.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
The global variable "fetch_if_missing" is used to control whether an
|
|
object lookup will attempt to dynamically fetch a missing object or
|
|
report an error.
|
|
</p>
|
|
<div class="paragraph"><p>We are not happy with this global variable and would like to remove it,
|
|
but that requires significant refactoring of the object code to pass an
|
|
additional flag.</p></div>
|
|
</li>
|
|
</ul></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_fetching_missing_objects">Fetching Missing Objects</h2>
|
|
<div class="sectionbody">
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
Fetching of objects is done by invoking a "git fetch" subprocess.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
The local repository sends a request with the hashes of all requested
|
|
objects, and does not perform any packfile negotiation.
|
|
It then receives a packfile.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Because we are reusing the existing fetch mechanism, fetching
|
|
currently fetches all objects referred to by the requested objects, even
|
|
though they are not necessary.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Fetching with <code>--refetch</code> will request a complete new filtered packfile from
|
|
the remote, which can be used to change a filter without needing to
|
|
dynamically fetch missing objects.
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_using_many_promisor_remotes">Using many promisor remotes</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>Many promisor remotes can be configured and used.</p></div>
|
|
<div class="paragraph"><p>This allows for example a user to have multiple geographically-close
|
|
cache servers for fetching missing blobs while continuing to do
|
|
filtered <code>git-fetch</code> commands from the central server.</p></div>
|
|
<div class="paragraph"><p>When fetching objects, promisor remotes are tried one after the other
|
|
until all the objects have been fetched.</p></div>
|
|
<div class="paragraph"><p>Remotes that are considered "promisor" remotes are those specified by
|
|
the following configuration variables:</p></div>
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
<code>extensions.partialClone</code> <code>=</code> <em><name></em>
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
<code>remote.</code><em><name></em><code>.promisor</code> <code>=</code> <code>true</code>
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
<code>remote.</code><em><name></em><code>.partialCloneFilter</code> <code>=</code> ...
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
<div class="paragraph"><p>Only one promisor remote can be configured using the
|
|
<code>extensions.partialClone</code> config variable. This promisor remote will
|
|
be the last one tried when fetching objects.</p></div>
|
|
<div class="paragraph"><p>We decided to make it the last one we try, because it is likely that
|
|
someone using many promisor remotes is doing so because the other
|
|
promisor remotes are better for some reason (maybe they are closer or
|
|
faster for some kind of objects) than the origin, and the origin is
|
|
likely to be the remote specified by extensions.partialClone.</p></div>
|
|
<div class="paragraph"><p>This justification is not very strong, but one choice had to be made,
|
|
and anyway the long term plan should be to make the order somehow
|
|
fully configurable.</p></div>
|
|
<div class="paragraph"><p>For now though the other promisor remotes will be tried in the order
|
|
they appear in the config file.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_current_limitations">Current Limitations</h2>
|
|
<div class="sectionbody">
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
It is not possible to specify the order in which the promisor
|
|
remotes are tried in other ways than the order in which they appear
|
|
in the config file.
|
|
</p>
|
|
<div class="paragraph"><p>It is also not possible to specify an order to be used when fetching
|
|
from one remote and a different order when fetching from another
|
|
remote.</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
It is not possible to push only specific objects to a promisor
|
|
remote.
|
|
</p>
|
|
<div class="paragraph"><p>It is not possible to push at the same time to multiple promisor
|
|
remote in a specific order.</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Dynamic object fetching will only ask promisor remotes for missing
|
|
objects. We assume that promisor remotes have a complete view of the
|
|
repository and can satisfy all such requests.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Repack essentially treats promisor and non-promisor packfiles as 2
|
|
distinct partitions and does not mix them.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Dynamic object fetching invokes fetch-pack once <strong>for each item</strong>
|
|
because most algorithms stumble upon a missing object and need to have
|
|
it resolved before continuing their work. This may incur significant
|
|
overhead — and multiple authentication requests — if many objects are
|
|
needed.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Dynamic object fetching currently uses the existing pack protocol V0
|
|
which means that each object is requested via fetch-pack. The server
|
|
will send a full set of info/refs when the connection is established.
|
|
If there are a large number of refs, this may incur significant overhead.
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_future_work">Future Work</h2>
|
|
<div class="sectionbody">
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
Improve the way to specify the order in which promisor remotes are
|
|
tried.
|
|
</p>
|
|
<div class="paragraph"><p>For example this could allow specifying explicitly something like:
|
|
"When fetching from this remote, I want to use these promisor remotes
|
|
in this order, though, when pushing or fetching to that remote, I want
|
|
to use those promisor remotes in that order."</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Allow pushing to promisor remotes.
|
|
</p>
|
|
<div class="paragraph"><p>The user might want to work in a triangular work flow with multiple
|
|
promisor remotes that each have an incomplete view of the repository.</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Allow non-pathname-based filters to make use of packfile bitmaps (when
|
|
present). This was just an omission during the initial implementation.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Investigate use of a long-running process to dynamically fetch a series
|
|
of objects, such as proposed in [5,6] to reduce process startup and
|
|
overhead costs.
|
|
</p>
|
|
<div class="paragraph"><p>It would be nice if pack protocol V2 could allow that long-running
|
|
process to make a series of requests over a single long-running
|
|
connection.</p></div>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Investigate pack protocol V2 to avoid the info/refs broadcast on
|
|
each connection with the server to dynamically fetch missing objects.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
Investigate the need to handle loose promisor objects.
|
|
</p>
|
|
<div class="paragraph"><p>Objects in promisor packfiles are allowed to reference missing objects
|
|
that can be dynamically fetched from the server. An assumption was
|
|
made that loose objects are only created locally and therefore should
|
|
not reference a missing object. We may need to revisit that assumption
|
|
if, for example, we dynamically fetch a missing tree and store it as a
|
|
loose object rather than a single object packfile.</p></div>
|
|
<div class="paragraph"><p>This does not necessarily mean we need to mark loose objects as promisor;
|
|
it may be sufficient to relax the object lookup or is-promisor functions.</p></div>
|
|
</li>
|
|
</ul></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_non_tasks">Non-Tasks</h2>
|
|
<div class="sectionbody">
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
Every time the subject of "demand loading blobs" comes up it seems
|
|
that someone suggests that the server be allowed to "guess" and send
|
|
additional objects that may be related to the requested objects.
|
|
</p>
|
|
<div class="paragraph"><p>No work has gone into actually doing that; we’re just documenting that
|
|
it is a common suggestion. We’re not sure how it would work and have
|
|
no plans to work on it.</p></div>
|
|
<div class="paragraph"><p>It is valid for the server to send more objects than requested (even
|
|
for a dynamic object fetch), but we are not building on that.</p></div>
|
|
</li>
|
|
</ul></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_footnotes">Footnotes</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>[a] expensive-to-modify list of missing objects: Earlier in the design of
|
|
partial clone we discussed the need for a single list of missing objects.
|
|
This would essentially be a sorted linear list of OIDs that were
|
|
omitted by the server during a clone or subsequent fetches.</p></div>
|
|
<div class="paragraph"><p>This file would need to be loaded into memory on every object lookup.
|
|
It would need to be read, updated, and re-written (like the .git/index)
|
|
on every explicit "git fetch" command <strong>and</strong> on any dynamic object fetch.</p></div>
|
|
<div class="paragraph"><p>The cost to read, update, and write this file could add significant
|
|
overhead to every command if there are many missing objects. For example,
|
|
if there are 100M missing blobs, this file would be at least 2GiB on disk.</p></div>
|
|
<div class="paragraph"><p>With the "promisor" concept, we <strong>infer</strong> a missing object based upon the
|
|
type of packfile that references it.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_related_links">Related Links</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>[0] <a href="https://crbug.com/git/2">https://crbug.com/git/2</a>
|
|
Bug#2: Partial Clone</p></div>
|
|
<div class="paragraph"><p>[1] <a href="https://lore.kernel.org/git/20170113155253.1644-1-benpeart@microsoft.com/">https://lore.kernel.org/git/20170113155253.1644-1-benpeart@microsoft.com/</a><br />
|
|
Subject: [RFC] Add support for downloading blobs on demand<br />
|
|
Date: Fri, 13 Jan 2017 10:52:53 -0500</p></div>
|
|
<div class="paragraph"><p>[2] <a href="https://lore.kernel.org/git/cover.1506714999.git.jonathantanmy@google.com/">https://lore.kernel.org/git/cover.1506714999.git.jonathantanmy@google.com/</a><br />
|
|
Subject: [PATCH 00/18] Partial clone (from clone to lazy fetch in 18 patches)<br />
|
|
Date: Fri, 29 Sep 2017 13:11:36 -0700</p></div>
|
|
<div class="paragraph"><p>[3] <a href="https://lore.kernel.org/git/20170426221346.25337-1-jonathantanmy@google.com/">https://lore.kernel.org/git/20170426221346.25337-1-jonathantanmy@google.com/</a><br />
|
|
Subject: Proposal for missing blob support in Git repos<br />
|
|
Date: Wed, 26 Apr 2017 15:13:46 -0700</p></div>
|
|
<div class="paragraph"><p>[4] <a href="https://lore.kernel.org/git/1488999039-37631-1-git-send-email-git@jeffhostetler.com/">https://lore.kernel.org/git/1488999039-37631-1-git-send-email-git@jeffhostetler.com/</a><br />
|
|
Subject: [PATCH 00/10] RFC Partial Clone and Fetch<br />
|
|
Date: Wed, 8 Mar 2017 18:50:29 +0000</p></div>
|
|
<div class="paragraph"><p>[5] <a href="https://lore.kernel.org/git/20170505152802.6724-1-benpeart@microsoft.com/">https://lore.kernel.org/git/20170505152802.6724-1-benpeart@microsoft.com/</a><br />
|
|
Subject: [PATCH v7 00/10] refactor the filter process code into a reusable module<br />
|
|
Date: Fri, 5 May 2017 11:27:52 -0400</p></div>
|
|
<div class="paragraph"><p>[6] <a href="https://lore.kernel.org/git/20170714132651.170708-1-benpeart@microsoft.com/">https://lore.kernel.org/git/20170714132651.170708-1-benpeart@microsoft.com/</a><br />
|
|
Subject: [RFC/PATCH v2 0/1] Add support for downloading blobs on demand<br />
|
|
Date: Fri, 14 Jul 2017 09:26:50 -0400</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>
|