Add parallel_fetch toggle for virtual member index files (#165)

Virtual members already merge concurrently, but each rpm member fetches primary/filelists/other one after another, and each deb member its Packages files the same way. On large virtuals the slowest member's serial chain pushes the merge past dnf's 30s timeout.

- add `parallel_fetch` (default false) to virtuals: model, v2 API, migration 0007
- fetch a member's index files concurrently (up to 4) when set; first error still fails the member
- thread the flag through rpm and deb member fetches

Reviewed-on: #165
Co-authored-by: unkin-agent <unkin-agent@unkin.net>
Co-committed-by: unkin-agent <unkin-agent@unkin.net>
This commit was merged in pull request #165.
This commit is contained in:
2026-10-25 15:13:57 +11:00
committed by BenVincent
parent 9294686ea6
commit cfb1f93d48
7 changed files with 395 additions and 51 deletions
+76 -28
View File
@@ -19,6 +19,7 @@ import (
"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/errgroup"
"golang.org/x/sync/singleflight"
)
@@ -26,10 +27,11 @@ 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)
rpmMember func(ctx context.Context, name string, parallel bool) (*RPMMember, error)
debMember func(ctx context.Context, name, base string, parallel bool) (*DebMember, error)
apkMember func(ctx context.Context, name, dir string) (*AlpineMember, error)
npmMember func(ctx context.Context, name, pkg string) (*NPMMember, error)
memberPath func(ctx context.Context, remote models.Remote, path string) ([]byte, error)
// NPMLocal returns a local npm repo's packument with tarball paths relative
// to the repo, or ErrNotFound.
@@ -91,6 +93,7 @@ func NewEngine(db *database.DB, proxyEngine *proxy.Engine) *Engine {
e.ansibleDoc = e.ansibleMemberDoc
e.goMember = e.fetchGoMember
e.puppetDoc = e.fetchMemberPath
e.memberPath = e.fetchMemberPath
return e
}
@@ -353,7 +356,7 @@ func (e *Engine) merged(ctx context.Context, key string, merge func(context.Cont
}
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) })
members, err := fetchMembers(virt, func(name string) (*RPMMember, error) { return e.rpmMember(ctx, name, virt.ParallelFetch) })
if err != nil {
return nil, err
}
@@ -402,7 +405,7 @@ func (e *Engine) fetchDeb(ctx context.Context, virt models.Virtual, reqPath stri
}
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) })
members, err := fetchMembers(virt, func(name string) (*DebMember, error) { return e.debMember(ctx, name, base, virt.ParallelFetch) })
if err != nil {
return nil, err
}
@@ -430,26 +433,22 @@ func debContentType(name string) string {
// 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) {
func (e *Engine) fetchDebMember(ctx context.Context, name, base string, parallel bool) (*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")
rel, err := e.memberPath(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)
}
pkgs, err := fetchFiles(ctx, parallel, debIndexFiles(parseDebRelease(rel)), func(ctx context.Context, file string) ([]byte, error) {
return e.fetchDecompressed(ctx, *remote, base, file)
})
if err != nil {
return nil, err
}
return m, nil
return &DebMember{RemoteName: name, Release: rel, Packages: pkgs}, nil
}
func (e *Engine) mergedAlpine(ctx context.Context, virt models.Virtual, dir string) (mergedRepo, error) {
@@ -559,12 +558,12 @@ func (e *Engine) cachedFile(key, path string) ([]byte, bool) {
return nil, false
}
func (e *Engine) fetchRPMMember(ctx context.Context, name string) (*RPMMember, error) {
func (e *Engine) fetchRPMMember(ctx context.Context, name string, parallel bool) (*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")
repomd, err := e.memberPath(ctx, *remote, "repodata/repomd.xml")
if err != nil {
return nil, err
}
@@ -572,17 +571,66 @@ func (e *Engine) fetchRPMMember(ctx context.Context, name string) (*RPMMember, e
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)
}
data, err := fetchFiles(ctx, parallel, locs, func(ctx context.Context, href string) ([]byte, error) {
return e.fetchDecompressed(ctx, *remote, "", href)
})
if err != nil {
return nil, err
}
return m, nil
return &RPMMember{RemoteName: name, Bases: remote.UpstreamPool(), Timestamp: ts, Data: data}, nil
}
func (e *Engine) fetchDecompressed(ctx context.Context, remote models.Remote, base, file string) ([]byte, error) {
raw, err := e.memberPath(ctx, remote, base+file)
if err != nil {
return nil, err
}
body, err := decompress(file, raw)
if err != nil {
return nil, fmt.Errorf("decompress %s: %w", file, err)
}
return body, nil
}
// maxFileFetches bounds the concurrent index file fetches per member.
const maxFileFetches = 4
// fetchFiles fetches each key's file, one at a time or up to maxFileFetches at
// once, failing on the first error and cancelling the rest.
func fetchFiles(ctx context.Context, parallel bool, files map[string]string, fetch func(ctx context.Context, file string) ([]byte, error)) (map[string][]byte, error) {
out := make(map[string][]byte, len(files))
if !parallel {
for k, f := range files {
body, err := fetch(ctx, f)
if err != nil {
return nil, err
}
out[k] = body
}
return out, nil
}
var mu sync.Mutex
g, gctx := errgroup.WithContext(ctx)
g.SetLimit(maxFileFetches)
for k, f := range files {
g.Go(func() error {
if err := gctx.Err(); err != nil {
return err
}
body, err := fetch(gctx, f)
if err != nil {
return err
}
mu.Lock()
out[k] = body
mu.Unlock()
return nil
})
}
if err := g.Wait(); err != nil {
return nil, err
}
return out, nil
}
// fetchMemberPath reads one path from a member the same way its own route