Files
sow-tools/internal/nwsync/emit.go
T
archvillainette fa32dd411f
build-binaries / build-binaries (push) Successful in 2m13s
fix(nwsync): stream emit so peak memory tracks the largest resource (#76) (#78)
Closes #76. Part of #54.

`nwsync emit` held roughly 5× the artifact size in RAM, so ovh-main (7 GB, no swap) OOM-killed it on any hak over ~1.4 GB. That blocked the backfill in sow-assets-manifest and would have killed the next release rebuilding a large hak.

## What it does

- `erf.ReadIndex` / `erf.ReadPayload` — parse the header and resource table only, read one payload on demand. `erf.Read` keeps its shape but returns payloads as subslices of the buffer instead of fresh copies, which removes one full copy for the `pipeline` callers too. Callers must not mutate `Resource.Data`; the doc comment says so and no caller does.
- `nwsync.Emit` opens the artifact, hashes it by streaming for the key check (through a section reader, so the file offset stays put), then hashes, compresses and stores one resource at a time. The archive is never resident. Shadowed duplicate resrefs are now never read at all.
- Bounds checks in `ReadIndex` moved to `int64`, so key/resource-list offsets can no longer overflow.

## Not in the issue, but memory-motivated

The zstd blob encoder ran at the default concurrency, which is one encoder per CPU, each holding a window-sized history — about 200 MB of live heap doing nothing on a 24-core runner. `EncodeAll` is single-threaded per call, so concurrency 1 costs nothing. `TestSingleThreadedEncoderMatchesDefault` pins the claim that blobs come out byte-identical.

## Measured

Peak heap during emit, sampled 1 ms:

| hak | before | after |
|-----|--------|-------|
| 8 MB | 155 MB | 21 MB |
| 64 MB | 289 MB | 22 MB |

Flat, as the acceptance asks. `TestEmitPeakMemoryDoesNotScaleWithArtifactSize` fails if the 64 MB fixture costs more than the 8 MB one plus 24 MB of slack.

## Gaps

- The regression check measures Go heap, not RSS, and its largest fixture is 64 MB — a multi-GB run was not done here. A 2.15 GB hak now needs about the same ~22 MB the 64 MB one does, so the 5 GB budget is not close, but that is inference from the flat curve, not a measurement.
- mmap was suggested in the issue and skipped. Payload buffers are still anonymous, but they are one resource each (≤15 MiB), so making them file-backed buys nothing now.

🤖 Generated with [Claude Code](https://claude.com/claude-code)Reviewed-on: #78
Reviewed-by: xtul <mpiasecki720@protonmail.com>
Co-authored-by: vickydotbat <vickydotbat@tutamail.com>
2026-07-31 11:16:23 +00:00

279 lines
9.5 KiB
Go

package nwsync
import (
"context"
"crypto/sha1"
"fmt"
"io"
"os"
"path"
"path/filepath"
"slices"
"sort"
"strconv"
"strings"
"time"
"git.westgate.pw/ShadowsOverWestgate/sow-tools/internal/buildinfo"
"git.westgate.pw/ShadowsOverWestgate/sow-tools/internal/erf"
)
// fileSizeLimit matches upstream's --limit-file-size default of 15 MB. A
// resource over it is a hard failure, not a skip: upstream quit(1)s and so do
// we. Our largest resource today is 13.66 MiB, so the headroom is thin.
const fileSizeLimit = 15 * 1024 * 1024
// skippedTypes are never published, matching upstream's GobalResTypeSkipList.
var skippedTypes = resTypes("nss", "ndb", "gic")
// emitterVersion identifies the blob/manifest byte format this package
// produces. assemble refuses to merge indexes that disagree on it, because two
// producers of blobs mean a skewed emitter can otherwise write blobs the merged
// manifest quietly disagrees with. Bump it only when emitted bytes change — it
// is deliberately not the build revision, which would invalidate every
// published index on every unrelated commit.
const emitterVersion = "1"
// serverTypes are loaded only server-side; a manifest holding nothing else
// has no client contents. Mirrors upstream's GlobalResTypeServerList, whose
// trailing 0 is RESTYPE_INVALID.
var serverTypes = append(resTypes(
"are", "dlg", "fac", "gic", "git", "ifo", "itp", "jrl", "ncs", "ndb",
"nss", "ptm", "utc", "utd", "ute", "uti", "utm", "utp", "uts", "utt", "utw",
), 0)
func resTypes(extensions ...string) []uint16 {
types := make([]uint16, 0, len(extensions))
for _, extension := range extensions {
restype, ok := erf.ResourceTypeForExtension(extension)
if !ok {
panic("nwsync: unknown restype " + extension)
}
types = append(types, restype)
}
return types
}
// EmitResult reports what one emit run produced.
type EmitResult struct {
Name string // artifact name, without extension
ManifestPath string
Entries int
BlobsWritten int
}
// EmitOptions describes one emit run.
type EmitOptions struct {
ArtifactKey string // depot key of the artifact; the NSYM key is derived from it
ArtifactPath string // the file on disk
As string // name override, for a TLK whose filename is not its published name
OutDir string // write locally instead of uploading — the conformance path
Sink sink // test seam; nil means OutDir or the zone
}
// Emit explodes one artifact — a .hak/.erf or a loose file such as the TLK —
// into NWSync blobs plus a NSYM manifest describing only that artifact.
//
// Blobs go up as they are produced and the index lands last, so the presence of
// an index is the publication marker: an artifact whose emit died halfway has
// real blobs in the zone and no index, which is unambiguous. Blob names are
// content hashes, so re-running skips whatever already landed.
func Emit(options EmitOptions) (EmitResult, error) {
artifact, err := os.Open(options.ArtifactPath)
if err != nil {
return EmitResult{}, fmt.Errorf("read artifact: %w", err)
}
defer artifact.Close()
info, err := artifact.Stat()
if err != nil {
return EmitResult{}, fmt.Errorf("read artifact: %w", err)
}
// A section reader, not the file itself: hashing must not move the file
// offset out from under everything that reads the artifact afterwards.
if err := checkArtifactKey(options.ArtifactKey, io.NewSectionReader(artifact, 0, info.Size())); err != nil {
return EmitResult{}, err
}
name := options.As
if name == "" {
name = path.Base(options.ArtifactKey)
}
extension := path.Ext(name)
name = strings.TrimSuffix(name, extension)
key, err := resolveIndexKey(options.ArtifactKey, options.OutDir)
if err != nil {
return EmitResult{}, err
}
index, err := readArtifactIndex(options.ArtifactPath, artifact, info.Size(), name)
if err != nil {
return EmitResult{}, err
}
target, err := openSink(options.OutDir, options.Sink)
if err != nil {
return EmitResult{}, err
}
entries, blobs, onDiskBytes, err := emitResources(artifact, index, target)
if err != nil {
return EmitResult{}, err
}
if len(entries) == 0 {
return EmitResult{}, fmt.Errorf("%s: nothing to index (no publishable resources)", options.ArtifactPath)
}
data, err := writeManifest(entries)
if err != nil {
return EmitResult{}, err
}
if err := putManifestPair(target, key, data, entries, onDiskBytes, Sidecar{ModuleName: name}); err != nil {
return EmitResult{}, err
}
return EmitResult{Name: name, ManifestPath: target.describe(key), Entries: len(entries), BlobsWritten: blobs}, nil
}
// openSink returns the zone sink, or a local directory when outDir is set.
func openSink(outDir string, injected sink) (sink, error) {
if injected != nil {
return injected, nil
}
if outDir != "" {
return dirSink{root: outDir}, nil
}
return newZoneSink(context.Background(), os.Getenv)
}
// readArtifactIndex locates the resources of an ERF/HAK/MOD, or the single
// resource a loose file represents, without reading any payload. Upstream's
// resman does the same dispatch on the file's first three bytes. name is the
// artifact's published name, which for a loose file is also its resref.
func readArtifactIndex(path string, artifact io.ReaderAt, size int64, name string) ([]erf.IndexEntry, error) {
magic := make([]byte, 3)
if size >= 3 {
if _, err := artifact.ReadAt(magic, 0); err != nil {
return nil, fmt.Errorf("%s: %w", path, err)
}
}
switch string(magic) {
case "ERF", "HAK":
index, err := erf.ReadIndex(artifact, size)
if err != nil {
return nil, fmt.Errorf("%s: %w", path, err)
}
return index.Entries, nil
case "MOD":
// A persistent world never publishes module contents, so the .mod
// contributes no bytes to a manifest — it only says which haks and
// which TLK the manifest covers.
return nil, fmt.Errorf("%s: a module is never emitted; a manifest is haks plus the TLK", path)
}
extension := filepath.Ext(filepath.Base(path))
restype, ok := erf.ResourceTypeForExtension(extension)
if !ok {
return nil, fmt.Errorf("%s: unknown resource type %q", path, extension)
}
return []erf.IndexEntry{{Name: name, Type: restype, Offset: 0, Size: size}}, nil
}
// emitResources hashes, compresses and stores one resource at a time, reading
// each payload from the artifact only when its turn comes. Peak memory
// therefore tracks the largest single resource, not the archive: a 2 GB hak
// must emit inside a runner's few spare GB.
func emitResources(artifact io.ReaderAt, index []erf.IndexEntry, target sink) ([]Entry, int, int64, error) {
// A resref appearing twice inside one artifact resolves to the last one,
// the way resman lets the last container added win.
order := make([]Identity, 0, len(index))
latest := make(map[Identity]erf.IndexEntry, len(index))
var tooBig []string
for _, entry := range index {
if _, ok := erf.ExtensionForResourceType(entry.Type); !ok {
return nil, 0, 0, fmt.Errorf("resref %s is not resolvable (unknown restype %d)", entry.Name, entry.Type)
}
if slices.Contains(skippedTypes, entry.Type) {
continue
}
if entry.Size > fileSizeLimit {
tooBig = append(tooBig, fmt.Sprintf("%s: %d bytes > %d", entry.Name, entry.Size, fileSizeLimit))
continue
}
identity := Identity{ResRef: strings.ToLower(entry.Name), ResType: entry.Type}
if _, seen := latest[identity]; !seen {
order = append(order, identity)
}
latest[identity] = entry
}
if len(tooBig) > 0 {
sort.Strings(tooBig)
return nil, 0, 0, fmt.Errorf("resources exceed the file size limit:\n %s", strings.Join(tooBig, "\n "))
}
entries := make([]Entry, 0, len(order))
var blobs int
var onDiskBytes int64
for _, identity := range order {
payload, err := erf.ReadPayload(artifact, latest[identity])
if err != nil {
return nil, 0, 0, err
}
sum := sha1.Sum(payload)
entries = append(entries, Entry{
SHA1: sum,
Size: uint32(len(payload)),
ResRef: identity.ResRef,
ResType: identity.ResType,
})
written, err := target.putBlob(fmt.Sprintf("%x", sum), func() []byte { return compressBlob(payload) })
if err != nil {
return nil, 0, 0, err
}
if written > 0 {
blobs++
onDiskBytes += written
}
}
return entries, blobs, onDiskBytes, nil
}
// created is the sidecar timestamp. SOURCE_DATE_EPOCH pins it so a build can
// be reproduced byte for byte; the manifest itself is deterministic already.
func created() int64 {
if raw := os.Getenv("SOURCE_DATE_EPOCH"); raw != "" {
if seconds, err := strconv.ParseInt(raw, 10, 64); err == nil {
return seconds
}
}
return time.Now().Unix()
}
// putManifestPair stores a NSYM manifest and its .json sidecar at key. The
// caller supplies the sidecar fields it knows; the rest are derived from the
// entries. data must be the serialised form of entries.
func putManifestPair(target sink, key string, data []byte, entries []Entry, onDiskBytes int64, sidecar Sidecar) error {
var totalBytes int64
clientContents := false
for _, entry := range entries {
totalBytes += int64(entry.Size)
if !slices.Contains(serverTypes, entry.ResType) {
clientContents = true
}
}
sidecar.Version = manifestVersion
sidecar.SHA1 = fmt.Sprintf("%x", sha1.Sum(data))
sidecar.HashTreeDepth = hashTreeDepth
sidecar.IncludesModuleContents = false
sidecar.IncludesClientContents = clientContents
sidecar.TotalFiles = len(entries)
sidecar.TotalBytes = totalBytes
sidecar.OnDiskBytes = onDiskBytes
sidecar.Created = created()
sidecar.CreatedWith = buildinfo.String()
sidecar.EmitterVersion = emitterVersion
body, err := marshalSidecar(sidecar)
if err != nil {
return err
}
return target.putIndex(key, data, body)
}