Files
runner/act/common/git/fetch_action_test.go
T
silverwind b769a9765f perf: download actions as archives once per job (#1316)
Each step refreshed its own clone of an action, so a composite using one action repository ten times fetched it ten times per job, and a single network error failed the job.

Like actions/runner, a job now downloads each action repository and ref once, as an archive extracted into a directory per commit. Each action still gets its own copy in the job container. This restores the per-job dedupe of https://gitea.com/gitea/runner/pulls/1178, which only reached a since-deleted branch.

How a download works:

1. The action URL is taken after `insteadOf` rewriting, as git would use it.
2. The archive comes from `<url>/archive/<ref>.tar.gz`, or from codeload.github.com for github.com, as for actions/runner.
3. A cached tag or branch is revalidated with its ETag, which GitHub and Gitea 28+ answer with a 304. A cached commit pin needs no request.
4. Transient failures (5xx, 408, 429 honouring `Retry-After`, dropped transfers) are retried three times with a 10 to 30 second backoff.
5. Git takes over, cloning and exporting the commit into the same directory layout, when the URL is not HTTP(S), the ref is a short commit, the host serves no usable archive, the host cannot be connected to, or the retries run out.

Median of 3 runs, git (shallow clone, then fetch) against archives, on a cold and a warm cache:

| Action | git cold | git warm | archive cold | archive warm |
|---|---|---|---|---|
| github.com actions/checkout@v4 | 937ms | 726ms | 286ms | 171ms |
| github.com actions/cache@v4 | 1006ms | 801ms | 516ms | 161ms |
| github.com actions/setup-node@v4 | 1046ms | 786ms | 463ms | 156ms |
| gitea.com actions/checkout@v4 | 2007ms | 1165ms | 667ms | 222ms |

The action cache layout changes, so existing caches download once more.

*Written by Claude.*

Fixes: https://gitea.com/gitea/runner/issues/1220
Reviewed-on: https://gitea.com/gitea/runner/pulls/1316
Reviewed-by: bircni <[email protected]>
Co-authored-by: silverwind <[email protected]>
2026-10-15 12:49:37 +00:00

226 lines
8.2 KiB
Go

// Copyright 2026 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package git
import (
"archive/tar"
"bytes"
"encoding/base64"
"fmt"
"net/http"
"net/http/cgi"
"net/http/httptest"
"os"
"os/exec"
"path/filepath"
"strings"
"sync"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestFetchAction(t *testing.T) {
original := archiveRetryDelay
archiveRetryDelay = func(_retryAfter string) time.Duration { return time.Nanosecond }
t.Cleanup(func() { archiveRetryDelay = original })
root := t.TempDir()
remote := filepath.Join(root, "org", "action")
require.NoError(t, gitCmd("init", "--initial-branch=main", remote))
require.NoError(t, os.WriteFile(filepath.Join(remote, "action.yml"), []byte("name: action\n"), 0o644))
require.NoError(t, os.WriteFile(filepath.Join(remote, "run.sh"), []byte("#!/bin/sh\n"), 0o755))
require.NoError(t, os.Symlink("action.yml", filepath.Join(remote, "link")))
require.NoError(t, gitCmd("-C", remote, "add", "."))
require.NoError(t, gitCmd("-C", remote, "commit", "-m", "initial"))
require.NoError(t, gitCmd("-C", remote, "tag", "v1"))
gitPath, err := exec.LookPath("git")
require.NoError(t, err)
backend := &cgi.Handler{Path: gitPath, Args: []string{"http-backend"}, Env: []string{"GIT_PROJECT_ROOT=" + root, "GIT_HTTP_EXPORT_ALL=1"}}
var mu sync.Mutex
var archiveRequests []http.Header
var mirror *httptest.Server
requests, archives, failures := 0, "", 0
handler := http.HandlerFunc(func(writer http.ResponseWriter, request *http.Request) {
mu.Lock()
defer mu.Unlock()
requests++
ref, ok := strings.CutPrefix(request.URL.Path, "/org/action/archive/")
if !ok {
backend.ServeHTTP(writer, request)
return
}
archiveRequests = append(archiveRequests, request.Header.Clone())
switch {
case failures > 0:
failures--
writer.WriteHeader(http.StatusServiceUnavailable)
return
case archives == "none":
http.NotFound(writer, request)
return
case archives == "unreachable":
http.Redirect(writer, request, "http://127.0.0.1:1"+request.URL.Path, http.StatusFound)
return
case archives == "redirect" && request.Host != mirror.Listener.Addr().String():
http.Redirect(writer, request, mirror.URL+request.URL.Path, http.StatusFound)
return
}
sha, _ := gitOutput(request.Context(), remote, "rev-parse", strings.TrimSuffix(ref, ".tar.gz"))
etag := fmt.Sprintf(`W/"%s-tar.gz-%t"`, sha, archives != "unprefixed")
if request.Header.Get("If-None-Match") == etag {
writer.WriteHeader(http.StatusNotModified)
return
}
args := []string{"archive", "--format=tar.gz", sha}
if archives != "unprefixed" {
args = append(args, "--prefix=action/")
}
archive, _ := runGit(request.Context(), remote, nil, args...)
writer.Header().Set("ETag", etag)
_, _ = writer.Write(archive)
})
server := httptest.NewServer(handler)
mirror = httptest.NewServer(handler)
t.Cleanup(server.Close)
t.Cleanup(mirror.Close)
serve := func(mode string, failing int) {
mu.Lock()
defer mu.Unlock()
requests, archives, failures, archiveRequests = 0, mode, failing, nil
}
served := func() (int, []http.Header) {
mu.Lock()
defer mu.Unlock()
return requests, append([]http.Header(nil), archiveRequests...)
}
newInput := func(ref string) NewGitCloneExecutorInput {
return NewGitCloneExecutorInput{URL: server.URL + "/org/action", Ref: ref, Dir: t.TempDir(), Token: "secret"}
}
t.Run("downloads, revalidates and follows a moved tag", func(t *testing.T) {
serve("prefixed", 0)
input := newInput("v1")
tree, sha, err := FetchAction(t.Context(), input)
require.NoError(t, err)
assert.Equal(t, gitRevParse(t, remote, "v1"), sha)
assert.Equal(t, filepath.Join(input.Dir, sha), tree)
assert.NoDirExists(t, filepath.Join(tree, ".git"))
info, err := os.Stat(filepath.Join(tree, "run.sh"))
require.NoError(t, err)
assert.Equal(t, os.FileMode(0o755), info.Mode().Perm())
link, err := os.Readlink(filepath.Join(tree, "link"))
require.NoError(t, err)
assert.Equal(t, "action.yml", link)
again, _, err := FetchAction(t.Context(), input)
require.NoError(t, err)
assert.Equal(t, tree, again)
require.NoError(t, gitCmd("-C", remote, "commit", "--allow-empty", "-m", "moved"))
require.NoError(t, gitCmd("-C", remote, "tag", "--force", "v1"))
moved, movedSha, err := FetchAction(t.Context(), input)
require.NoError(t, err)
assert.Equal(t, gitRevParse(t, remote, "v1"), movedSha)
assert.NotEqual(t, tree, moved)
assert.FileExists(t, filepath.Join(tree, "action.yml"))
input.OfflineMode = true
_, offlineSha, err := FetchAction(t.Context(), input)
require.NoError(t, err)
assert.Equal(t, movedSha, offlineSha)
requests, headers := served()
assert.Equal(t, 3, requests)
require.Len(t, headers, 3)
assert.Equal(t, "Basic "+base64.StdEncoding.EncodeToString([]byte("token:secret")), headers[0].Get("Authorization"))
assert.Empty(t, headers[0].Get("If-None-Match"))
assert.Equal(t, fmt.Sprintf(`W/"%s-tar.gz-true"`, sha), headers[1].Get("If-None-Match"))
assert.Equal(t, headers[1].Get("If-None-Match"), headers[2].Get("If-None-Match"))
})
t.Run("downloads a pinned commit once and rejects a short one", func(t *testing.T) {
serve("prefixed", 0)
sha := gitRevParse(t, remote, "main")
input := newInput(sha)
for range 2 {
tree, got, err := FetchAction(t.Context(), input)
require.NoError(t, err)
assert.Equal(t, sha, got)
assert.FileExists(t, filepath.Join(tree, "action.yml"))
}
_, _, err := FetchAction(t.Context(), newInput(sha[:7]))
require.ErrorIs(t, err, ErrShortRef)
_, headers := served()
assert.Len(t, headers, 1)
assert.NoDirExists(t, filepath.Join(input.Dir, "git"))
})
t.Run("retries a failing download and drops the token on a redirect to another origin", func(t *testing.T) {
serve("redirect", 2)
input := newInput("main")
_, sha, err := FetchAction(t.Context(), input)
require.NoError(t, err)
assert.Equal(t, gitRevParse(t, remote, "main"), sha)
assert.NoDirExists(t, filepath.Join(input.Dir, "git"))
_, headers := served()
require.Len(t, headers, 4)
assert.NotEmpty(t, headers[2].Get("Authorization"))
assert.Empty(t, headers[3].Get("Authorization"))
})
t.Run("keeps an unprefixed archive whole, downloads where insteadOf points and exports a clone without an archive or from an unreachable host", func(t *testing.T) {
for _, mode := range []string{"unprefixed", "none", "unreachable"} {
serve(mode, 0)
tree, sha, err := FetchAction(t.Context(), newInput("main"))
require.NoError(t, err, mode)
assert.Equal(t, gitRevParse(t, remote, "main"), sha, mode)
assert.FileExists(t, filepath.Join(tree, "action.yml"), mode)
assert.NoDirExists(t, filepath.Join(tree, ".git"), mode)
_, headers := served()
assert.Len(t, headers, 1, mode)
}
serve("prefixed", 0)
config := filepath.Join(t.TempDir(), "gitconfig")
require.NoError(t, os.WriteFile(config, []byte("[url \""+server.URL+"/org/\"]\n\tinsteadOf = https://example.invalid/org/\n"), 0o644))
t.Setenv("GIT_CONFIG_GLOBAL", config)
input := newInput("main")
input.URL = "https://example.invalid/org/action"
_, sha, err := FetchAction(t.Context(), input)
require.NoError(t, err)
assert.Equal(t, gitRevParse(t, remote, "main"), sha)
_, headers := served()
assert.Len(t, headers, 1)
assert.NoDirExists(t, filepath.Join(input.Dir, "git"))
})
}
func TestExtractTreeConfinesEntries(t *testing.T) {
outside := t.TempDir()
for name, entries := range map[string][]*tar.Header{
"parent path": {{Name: "../escape", Typeflag: tar.TypeReg}},
"through a symlink": {{Name: "out", Typeflag: tar.TypeSymlink, Linkname: outside}, {Name: "out/escape", Typeflag: tar.TypeReg}},
} {
t.Run(name, func(t *testing.T) {
var archive bytes.Buffer
writer := tar.NewWriter(&archive)
require.NoError(t, writer.WriteHeader(&tar.Header{Typeflag: tar.TypeXGlobalHeader, PAXRecords: map[string]string{"comment": strings.Repeat("a", 40)}}))
for _, entry := range entries {
require.NoError(t, writer.WriteHeader(entry))
}
require.NoError(t, writer.Close())
dir := t.TempDir()
_, err := extractTree(&archive, dir, false)
require.Error(t, err)
assert.NoFileExists(t, filepath.Join(dir, "escape"))
assert.NoFileExists(t, filepath.Join(outside, "escape"))
})
}
}