') + ')', 'gi'); if (regex.test(text)) { found = true; var frag = document.createDocumentFragment(); var parts = text.split(regex); parts.forEach(function(part, i) { if (i % 2 === 0) { frag.appendChild(document.createTextNode(part)); } else { var span = document.createElement('span'); span.className = 'userscript-highlight'; span.textContent = part; frag.appendChild(span); } }); node.parentNode.replaceChild(frag, node); } }); } else if (node.nodeType === 1 && node.childNodes) { // element var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT']; if (!skipTags.includes(node.tagName)) { Array.from(node.childNodes).forEach(highlight); } } } highlight(document.body); // Re-highlight on dynamic content var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1 || node.nodeType === 3) highlight(node); }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Strip utm_, fbclid, gclid, etc. from all links on page (function() { var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content', 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid', 'ref', 'ref_src', 'source', 'medium', 'campaign']; function cleanUrl(url) { try { var u = new URL(url, window.location.origin); var changed = false; trackingParams.forEach(function(p) { if (u.searchParams.has(p)) { u.searchParams.delete(p); changed = true; } }); return changed ? u.toString() : url; } catch (e) { return url; } } function cleanLinks() { document.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } cleanLinks(); var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1) { if (node.tagName === 'A') cleanLinks(); node.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Auto-enable theater mode on YouTube (function() { function tryTheater() { var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]'); if (btn && !btn.classList.contains('activated')) { btn.click(); } } // Try immediately tryTheater(); // Try after navigation (SPA) var lastUrl = location.href; setInterval(function() { if (location.href !== lastUrl) { lastUrl = location.href; setTimeout(tryTheater, 500); } }, 1000); // Also try on player load var observer = new MutationObserver(tryTheater); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ', 'i'); if (__m === '*' || __re.test(location.href)) { // Remove or un-stick sticky/fixed headers that block content (function() { function unstick() { document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) { if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') { el.style.position = 'static'; el.style.top = 'auto'; el.style.zIndex = 'auto'; } }); } unstick(); var observer = new MutationObserver(unstick); observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] }); })(); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); })(); Fix: build-context archiving correctness and performance by mazdak · Pull Request #1341 · apple/container · GitHub
Skip to content

Fix: build-context archiving correctness and performance - #1341

Closed
mazdak wants to merge 6 commits into
apple:mainfrom
mazdak:pr2/container-archiver
Closed

Fix: build-context archiving correctness and performance#1341
mazdak wants to merge 6 commits into
apple:mainfrom
mazdak:pr2/container-archiver

Conversation

@mazdak

@mazdakmazdak commented Mar 22, 2026•
edited
Loading

Copy link
Copy Markdown
Contributor

Type of Change

  • Bug fix

Motivation and Context

While building out a Docker Compose-style plugin and validating it against our own real development stack, we ran into two classes of problems in the build-context path:

  1. correctness issues in archive generation, especially around symlinks
  2. very high client-side overhead while preparing and streaming build contexts

This PR keeps the earlier archive/symlink correctness fixes and adds a follow-up performance pass in the same codepath.

Problems addressed

Archive correctness

The previous implementation had several issues around symlink handling and archive identity:

  • symlink targets were not fully reflected in the advertised archive digest
  • absolute symlinks pointing back into the archived source tree could remain client-absolute after unpack
  • symlink targets that traversed a symlinked ancestor could fail to rewrite to the archived target

These issues could break staged/remote builds or make archive digests unstable for cache/integrity purposes.

Build-context performance

The build-context sync path was also doing unnecessary work on large repositories:

  • BuildFSSync computed the included file set, then Archiver.compress re-enumerated the source tree again
  • archive creation used relatively expensive Foundation metadata and stream APIs per file
  • path normalization work in BuildFSSync added avoidable overhead during context preparation

In practice, this showed up as very slow [internal] load build context times while testing against a real repo.

What changed

Correctness

  • preserve symlink semantics during archive/unarchive
  • include effective symlink target information in the archive digest
  • rewrite archived absolute symlinks to archive-relative paths when their targets are also present in the archive
  • canonicalize absolute symlink targets through symlinked ancestors before archive lookup

Performance

  • let BuildFSSync hand Archiver the already-computed entry list instead of forcing a second full-tree archive walk
  • replace heavier per-file Foundation metadata/stream access with lighter POSIX-based file status and reads
  • reduce unnecessary URL/path normalization in the build-context path

Testing

  • Tested locally
  • Added/updated tests

@mazdakmazdak mentioned this pull request Mar 22, 2026
Closed
@mazdak
mazdakforce-pushed the pr2/container-archiver branch from 275885b to f120d30CompareMarch 23, 2026 18:48
@mazdakmazdak changed the title Fix: Preserve symlinks when archiving build contextsFix: build-context archiving correctness and performanceMar 23, 2026
@jglogan

jglogan commented Mar 31, 2026

Copy link
Copy Markdown
Contributor

@mazdak Are these fixes and optimizations generally useful? If so, why can't they be applied to the archiver implementation in the containerization library, as opposed creating a separate implementation just for container?

@mazdak

mazdak commented Apr 5, 2026

Copy link
Copy Markdown
ContributorAuthor

Are these fixes and optimizations generally useful? If so, why can't they be applied to the archiver implementation in the containerization library, as opposed creating a separate implementation just for container?

Yes, they are indeed generally useful. Let me see about adding them to the Containerization lib and I'll circle back

@jglogan

jglogan commented Apr 5, 2026

Copy link
Copy Markdown
Contributor

Thanks for looking into this. Another thing that would be helpful would be to provide concrete examples of what was wrong for each of the "archive correctness" points and what the fix will do instead. For anything that fails in container today due to these issues, does the same failure exist in Docker, Podman, or colima?

@mazdak

mazdak commented Apr 5, 2026

Copy link
Copy Markdown
ContributorAuthor

Thanks for looking into this. Another thing that would be helpful would be to provide concrete examples of what was wrong for each of the "archive correctness" points and what the fix will do instead. For anything that fails in container today due to these issues, does the same failure exist in Docker, Podman, or colima?

It's a been a coupe of weeks, so I am going to dig and find out what the issue was. But no, this problem does not exist in docker.

I have now made two PRs and can probably close this one:

#1391
apple/containerization#652

@mazdak

mazdak commented Apr 5, 2026

Copy link
Copy Markdown
ContributorAuthor

Thanks for looking into this. Another thing that would be helpful would be to provide concrete examples of what was wrong for each of the "archive correctness" points and what the fix will do instead. For anything that fails in container today due to these issues, does the same failure exist in Docker, Podman, or colima?

I also just added more context on the original issue in #1391

@mazdakmazdak closed this Apr 6, 2026
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@vxnkjyffmq-codevxnkjyffmq-codeAwaiting requested review from vxnkjyffmq-code

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@mazdak@jglogan@vxnkjyffmq-code@katiewasnothere