Files
artifactapi/internal/virtual/engine.go
T
unkin-agent ed6216d78b
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
Serve deb virtual indexes by hash and bound cached suites
2026-10-17 12:46:14 +11:00

520 lines
15 KiB
Go

package virtual
import (
"context"
"errors"
"fmt"
"io"
"log/slog"
"net/http"
"net/http/httptest"
"net/url"
"path"
"slices"
"strings"
"sync"
"time"
"git.unkin.net/unkin/artifactapi/internal/database"
"git.unkin.net/unkin/artifactapi/internal/provider"
"git.unkin.net/unkin/artifactapi/internal/proxy"
"git.unkin.net/unkin/artifactapi/pkg/models"
"golang.org/x/sync/singleflight"
)
type Engine struct {
db *database.DB
proxyEngine *proxy.Engine
getRemote func(context.Context, string) (*models.Remote, error)
rpmMember func(context.Context, string) (*RPMMember, error)
debMember func(ctx context.Context, name, base string) (*DebMember, error)
mergeTTL time.Duration
sf singleflight.Group
mu sync.Mutex
gens map[string]*repoGen
}
// mergedRepo is a merged index document plus the files it references.
type mergedRepo interface {
index() []byte
files() map[string][]byte
}
func (r *RPMRepo) index() []byte { return r.Repomd }
func (r *RPMRepo) files() map[string][]byte { return r.Files }
func (r *DebRepo) index() []byte { return r.Release }
func (r *DebRepo) files() map[string][]byte { return r.Files }
// repoGen holds a virtual's current merge plus the previous one, so a client
// holding the previous index can still fetch the files it references.
type repoGen struct {
cur, prev mergedRepo
at, used time.Time
}
const rpmMergeTTL = 60 * time.Second
// maxDebSuites bounds the client-chosen suites cached per deb virtual.
const maxDebSuites = 32
func NewEngine(db *database.DB, proxyEngine *proxy.Engine) *Engine {
e := &Engine{db: db, proxyEngine: proxyEngine, getRemote: db.GetRemote, mergeTTL: rpmMergeTTL}
e.rpmMember = e.fetchRPMMember
e.debMember = e.fetchDebMember
return e
}
func (e *Engine) Fetch(ctx context.Context, virt models.Virtual, path string, proxyBaseURL string) ([]byte, string, error) {
switch virt.PackageType {
case models.PackageRPM:
return e.fetchRPM(ctx, virt, path)
case models.PackageDeb:
return e.fetchDeb(ctx, virt, path)
}
merger, err := GetMerger(virt.PackageType)
if err != nil {
return nil, "", fmt.Errorf("unsupported virtual type %q: %w", virt.PackageType, err)
}
members, err := e.fetchMemberIndexes(ctx, virt, path)
if err != nil {
return nil, "", err
}
if len(members) == 0 {
return nil, "", fmt.Errorf("no members reachable for virtual %q", virt.Name)
}
merged, err := merger.MergeIndexes(members, proxyBaseURL)
if err != nil {
return nil, "", fmt.Errorf("merge indexes: %w", err)
}
contentType := "application/octet-stream"
switch virt.PackageType {
case models.PackageHelm:
contentType = "text/yaml"
case models.PackagePyPI:
contentType = "text/html"
}
return merged, contentType, nil
}
func (e *Engine) fetchMemberIndexes(ctx context.Context, virt models.Virtual, path string) ([]MemberIndex, error) {
type result struct {
index MemberIndex
err error
}
results := make([]result, len(virt.Members))
var wg sync.WaitGroup
for i, memberName := range virt.Members {
wg.Add(1)
go func(idx int, name string) {
defer wg.Done()
remote, err := e.db.GetRemote(ctx, name)
if err != nil {
results[idx] = result{err: fmt.Errorf("remote %q: %w", name, err)}
return
}
if remote.RepoType == models.RepoTypeLocal {
body, err := e.fetchLocalIndex(ctx, *remote, path)
if err != nil {
results[idx] = result{err: fmt.Errorf("local index %q: %w", name, err)}
return
}
results[idx] = result{index: MemberIndex{RemoteName: name, RepoType: remote.RepoType, BaseURL: remote.BaseURL, Body: body}}
return
}
prov, err := provider.Get(remote.PackageType)
if err != nil {
results[idx] = result{err: fmt.Errorf("provider %q: %w", remote.PackageType, err)}
return
}
fetchResult, err := e.proxyEngine.Fetch(ctx, *remote, path, prov)
if err != nil {
results[idx] = result{err: fmt.Errorf("fetch %q/%s: %w", name, path, err)}
return
}
defer fetchResult.Reader.Close()
body, err := io.ReadAll(fetchResult.Reader)
if err != nil {
results[idx] = result{err: fmt.Errorf("read %q: %w", name, err)}
return
}
results[idx] = result{index: MemberIndex{RemoteName: name, RepoType: remote.RepoType, BaseURL: remote.BaseURL, Body: body}}
}(i, memberName)
}
wg.Wait()
var members []MemberIndex
for _, r := range results {
if r.err != nil {
slog.Warn("virtual member fetch failed", "error", r.err)
continue
}
members = append(members, r.index)
}
return members, nil
}
func (e *Engine) fetchLocalIndex(ctx context.Context, remote models.Remote, path string) ([]byte, error) {
prov, err := provider.Get(remote.PackageType)
if err != nil {
return nil, fmt.Errorf("no provider for %q: %w", remote.PackageType, err)
}
indexer, ok := prov.(provider.LocalIndexer)
if !ok {
return nil, fmt.Errorf("provider %q does not support local index generation", remote.PackageType)
}
return indexer.GenerateLocalIndex(ctx, e.db, remote.Name, path)
}
var (
ErrNotFound = errors.New("not found")
ErrBadPath = errors.New("invalid path")
)
// MemberRedirect maps an rpm or deb virtual package path (<member>/<href>, as
// written by MergeRPM/MergeDeb) to the owning member's route. ok is false for
// any other path; ErrBadPath means the path is absolute or escapes the member.
func (e *Engine) MemberRedirect(ctx context.Context, virt models.Virtual, path, rawQuery, proxyBaseURL string) (string, bool, error) {
switch virt.PackageType {
case models.PackageRPM:
if strings.HasPrefix(path, "repodata/") {
return "", false, nil
}
case models.PackageDeb:
// apt requests a flat repo's files under its "./" dist verbatim.
path = strings.TrimPrefix(path, "./")
if strings.HasPrefix(path, "dists/") {
return "", false, nil
}
default:
return "", false, nil
}
name, rest, found := strings.Cut(path, "/")
if !found || !slices.Contains(virt.Members, name) {
return "", false, nil
}
segs, err := memberSegments(rest)
if err != nil {
return "", false, err
}
remote, err := e.getRemote(ctx, name)
if err != nil {
return "", false, nil
}
loc := fmt.Sprintf("%s/api/v1/%s/%s/%s", strings.TrimRight(proxyBaseURL, "/"), remote.RepoType, url.PathEscape(name), strings.Join(segs, "/"))
if rawQuery != "" {
loc += "?" + rawQuery
}
return loc, true, nil
}
// memberSegments decodes rest and returns its path-escaped segments, rejecting
// absolute paths and any "." or ".." segment.
func memberSegments(rest string) ([]string, error) {
dec, err := url.PathUnescape(rest)
if err != nil || dec == "" || strings.HasPrefix(dec, "/") {
return nil, ErrBadPath
}
segs := strings.Split(dec, "/")
for i, s := range segs {
if s == "." || s == ".." || strings.Contains(s, "\\") {
return nil, ErrBadPath
}
segs[i] = url.PathEscape(s)
}
return segs, nil
}
func (e *Engine) fetchRPM(ctx context.Context, virt models.Virtual, path string) ([]byte, string, error) {
if !strings.HasPrefix(path, "repodata/") {
return nil, "", ErrNotFound
}
key := "rpm\x00" + virt.Name
if path != "repodata/repomd.xml" {
if body, ok := e.cachedFile(key, path); ok {
return body, "application/gzip", nil
}
}
repo, err := e.merged(ctx, key, func(ctx context.Context) (mergedRepo, error) {
return e.mergeRPM(ctx, virt)
})
if err != nil {
return nil, "", err
}
if path == "repodata/repomd.xml" {
return repo.index(), "application/xml", nil
}
if body, ok := repo.files()[path]; ok {
return body, "application/gzip", nil
}
return nil, "", ErrNotFound
}
// merged returns the merge cached under key, reusing it for mergeTTL and
// collapsing concurrent merges of the same key into one.
// ponytail: per-replica cache; behind a non-sticky LB a data request landing on
// another replica re-merges and 404s if a member changed in between. Move to the
// shared redis cache if that shows up.
func (e *Engine) merged(ctx context.Context, key string, merge func(context.Context) (mergedRepo, error)) (mergedRepo, error) {
e.mu.Lock()
g := e.gens[key]
if g != nil && time.Since(g.at) < e.mergeTTL {
g.used = time.Now()
e.mu.Unlock()
return g.cur, nil
}
e.mu.Unlock()
v, err, _ := e.sf.Do(key, func() (any, error) {
repo, err := merge(context.WithoutCancel(ctx))
if err != nil {
return nil, err
}
e.mu.Lock()
defer e.mu.Unlock()
if e.gens == nil {
e.gens = map[string]*repoGen{}
}
g := e.gens[key]
switch {
case g == nil:
e.gens[key] = &repoGen{cur: repo, at: time.Now(), used: time.Now()}
case string(g.cur.index()) == string(repo.index()):
g.at, g.used = time.Now(), time.Now()
repo = g.cur
default:
g.prev, g.cur, g.at, g.used = g.cur, repo, time.Now(), time.Now()
}
return repo, nil
})
if err != nil {
return nil, err
}
return v.(mergedRepo), nil
}
func (e *Engine) mergeRPM(ctx context.Context, virt models.Virtual) (*RPMRepo, error) {
members, err := fetchMembers(virt, func(name string) (*RPMMember, error) { return e.rpmMember(ctx, name) })
if err != nil {
return nil, err
}
repo, err := MergeRPM(members)
if err != nil {
return nil, fmt.Errorf("merge rpm repodata: %w", err)
}
return repo, nil
}
// fetchMembers reads every member in parallel, failing if any member fails.
func fetchMembers[T any](virt models.Virtual, fetch func(name string) (*T, error)) ([]T, error) {
members := make([]T, len(virt.Members))
errs := make([]error, len(virt.Members))
var wg sync.WaitGroup
for i, name := range virt.Members {
wg.Add(1)
go func() {
defer wg.Done()
m, err := fetch(name)
if err != nil {
errs[i] = fmt.Errorf("member %q: %w", name, err)
return
}
members[i] = *m
}()
}
wg.Wait()
// %v, not %w: a member failure is a 502 whatever its cause, never a 404.
if err := errors.Join(errs...); err != nil {
return nil, fmt.Errorf("virtual %q: %v", virt.Name, err)
}
return members, nil
}
func (e *Engine) fetchDeb(ctx context.Context, virt models.Virtual, reqPath string) ([]byte, string, error) {
base, name, ok := debIndexPath(strings.TrimPrefix(path.Clean("/"+reqPath), "/"))
if !ok {
return nil, "", ErrNotFound
}
key := "deb\x00" + virt.Name + "\x00" + base
if name != "Release" {
if body, ok := e.cachedFile(key, name); ok {
return body, debContentType(name), nil
}
}
repo, err := e.merged(ctx, key, func(ctx context.Context) (mergedRepo, error) {
members, err := fetchMembers(virt, func(name string) (*DebMember, error) { return e.debMember(ctx, name, base) })
if err != nil {
return nil, err
}
return MergeDeb(members), nil
})
if err != nil {
return nil, "", err
}
e.evictLRU("deb\x00"+virt.Name+"\x00", maxDebSuites)
if name == "Release" {
return repo.index(), "text/plain", nil
}
if body, ok := repo.files()[name]; ok {
return body, debContentType(name), nil
}
return nil, "", ErrNotFound
}
func debContentType(name string) string {
if strings.HasSuffix(name, ".gz") {
return "application/gzip"
}
return "text/plain"
}
// fetchDebMember reads a member's Release under base and each binary Packages
// index it lists.
func (e *Engine) fetchDebMember(ctx context.Context, name, base string) (*DebMember, error) {
remote, err := e.getRemote(ctx, name)
if err != nil {
return nil, fmt.Errorf("remote %q: %w", name, err)
}
rel, err := e.fetchMemberPath(ctx, *remote, base+"Release")
if err != nil {
return nil, err
}
m := &DebMember{RemoteName: name, Release: rel, Packages: map[string][]byte{}}
for dir, file := range debIndexFiles(parseDebRelease(rel)) {
raw, err := e.fetchMemberPath(ctx, *remote, base+file)
if err != nil {
return nil, err
}
if m.Packages[dir], err = decompress(file, raw); err != nil {
return nil, fmt.Errorf("decompress %s: %w", file, err)
}
}
return m, nil
}
// evictLRU drops the least recently used merges under prefix beyond keep.
func (e *Engine) evictLRU(prefix string, keep int) {
e.mu.Lock()
defer e.mu.Unlock()
var keys []string
for k := range e.gens {
if strings.HasPrefix(k, prefix) {
keys = append(keys, k)
}
}
slices.SortFunc(keys, func(a, b string) int { return e.gens[b].used.Compare(e.gens[a].used) })
for _, k := range keys[min(len(keys), keep):] {
delete(e.gens, k)
}
}
func (e *Engine) cachedFile(key, path string) ([]byte, bool) {
e.mu.Lock()
defer e.mu.Unlock()
g := e.gens[key]
if g == nil {
return nil, false
}
for _, r := range []mergedRepo{g.cur, g.prev} {
if r == nil {
continue
}
if body, ok := r.files()[path]; ok {
g.used = time.Now()
return body, true
}
}
return nil, false
}
func (e *Engine) fetchRPMMember(ctx context.Context, name string) (*RPMMember, error) {
remote, err := e.getRemote(ctx, name)
if err != nil {
return nil, fmt.Errorf("remote %q: %w", name, err)
}
repomd, err := e.fetchMemberPath(ctx, *remote, "repodata/repomd.xml")
if err != nil {
return nil, err
}
locs, ts, err := parseRepomd(repomd)
if err != nil {
return nil, err
}
m := &RPMMember{RemoteName: name, Bases: remote.UpstreamPool(), Timestamp: ts, Data: map[string][]byte{}}
for t, href := range locs {
raw, err := e.fetchMemberPath(ctx, *remote, href)
if err != nil {
return nil, err
}
if m.Data[t], err = decompress(href, raw); err != nil {
return nil, fmt.Errorf("decompress %s: %w", href, err)
}
}
return m, nil
}
// fetchMemberPath reads one path from a member the same way its own route
// would serve it: local index, synthesized remote (e.g. github_rpm), or proxy.
func (e *Engine) fetchMemberPath(ctx context.Context, remote models.Remote, path string) ([]byte, error) {
prov, err := provider.Get(remote.PackageType)
if err != nil {
return nil, fmt.Errorf("provider %q: %w", remote.PackageType, err)
}
var serve func(w http.ResponseWriter, r *http.Request) bool
if remote.RepoType == models.RepoTypeLocal {
indexer, ok := prov.(provider.LocalIndexer)
if !ok {
return nil, fmt.Errorf("provider %q does not serve a local index", remote.PackageType)
}
serve = func(w http.ResponseWriter, r *http.Request) bool {
return indexer.ServeLocalIndex(w, r, e.db, remote.Name, path)
}
} else if rs, ok := prov.(provider.RemoteServer); ok {
serve = func(w http.ResponseWriter, r *http.Request) bool {
return rs.ServeRemote(w, r, remote, path, "", e.db)
}
}
if serve != nil {
rec := httptest.NewRecorder()
if serve(rec, httptest.NewRequestWithContext(ctx, http.MethodGet, "/"+path, nil)) {
if rec.Code != http.StatusOK {
return nil, fmt.Errorf("%s/%s: status %d", remote.Name, path, rec.Code)
}
return rec.Body.Bytes(), nil
}
if remote.RepoType == models.RepoTypeLocal {
return nil, fmt.Errorf("%s/%s: %w", remote.Name, path, ErrNotFound)
}
}
res, err := e.proxyEngine.Fetch(ctx, remote, path, prov)
if err != nil {
return nil, fmt.Errorf("fetch %s/%s: %w", remote.Name, path, err)
}
defer res.Reader.Close()
return io.ReadAll(res.Reader)
}