Files
sow-tools/internal/nwsync/sink.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

213 lines
7.3 KiB
Go

package nwsync
import (
"bytes"
"context"
"crypto/sha256"
"encoding/hex"
"fmt"
"io"
"os"
"path"
"path/filepath"
"strings"
"git.westgate.pw/ShadowsOverWestgate/sow-tools/internal/depot"
)
// sink is where an emit or assemble run puts what it produces. The zone is the
// production sink; a local directory exists only as the conformance path, so
// upstream's output and ours can be diffed on a developer machine.
type sink interface {
// putBlob stores one NWCompressedBuffer blob under its sha1 name and
// returns the bytes stored, or 0 if the blob was already there. Blob names
// are content hashes, so an existing name is existing content — which is
// why body is a thunk: compression is the expensive part of emit and a
// blob that is already stored must not pay for it.
putBlob(sha1Hex string, body func() []byte) (int64, error)
// putIndex stores a NSYM manifest and its sidecar under key, which is
// either an artifact-derived object key or a local path.
putIndex(key string, manifest, sidecar []byte) error
// getIndex reads back a NSYM manifest and its sidecar.
getIndex(key string) (manifest, sidecar []byte, err error)
// describe names the sink for messages.
describe(key string) string
}
// dirSink writes a local NWSync repository tree.
type dirSink struct{ root string }
func (s dirSink) putBlob(sha1Hex string, body func() []byte) (int64, error) {
blob := blobPath(s.root, sha1Hex)
if _, err := os.Stat(blob); err == nil {
return 0, nil
}
if err := os.MkdirAll(filepath.Dir(blob), 0o755); err != nil {
return 0, fmt.Errorf("create blob directory: %w", err)
}
data := body()
if err := os.WriteFile(blob, data, 0o644); err != nil {
return 0, fmt.Errorf("write blob: %w", err)
}
return int64(len(data)), nil
}
func (s dirSink) putIndex(key string, manifest, sidecar []byte) error {
target := filepath.Join(s.root, filepath.FromSlash(key))
if err := os.MkdirAll(filepath.Dir(target), 0o755); err != nil {
return fmt.Errorf("create manifest directory: %w", err)
}
if err := os.WriteFile(target, manifest, 0o644); err != nil {
return fmt.Errorf("write manifest: %w", err)
}
if err := os.WriteFile(target+".json", sidecar, 0o644); err != nil {
return fmt.Errorf("write sidecar: %w", err)
}
return nil
}
func (s dirSink) getIndex(key string) ([]byte, []byte, error) {
target := filepath.Join(s.root, filepath.FromSlash(key))
manifest, err := os.ReadFile(target)
if err != nil {
return nil, nil, fmt.Errorf("read index: %w", err)
}
sidecar, err := os.ReadFile(target + ".json")
if err != nil {
return nil, nil, fmt.Errorf("read sidecar: %w", err)
}
return manifest, sidecar, nil
}
func (s dirSink) describe(key string) string {
return filepath.Join(s.root, filepath.FromSlash(key))
}
// zoneSink uploads straight to the NWSync storage zone. Nothing bulky is ever
// written to the runner's disk: the working set is one resource at a time.
type zoneSink struct {
store depot.KeyStore
ctx context.Context
zone string
}
func (s zoneSink) putBlob(sha1Hex string, body func() []byte) (int64, error) {
key := path.Join("data", "sha1", sha1Hex[0:2], sha1Hex[2:4], sha1Hex)
// A throttled probe must never be read as "missing, re-upload" or as
// "present, skip", so only a confirmed Present skips the upload.
state, _, err := s.store.ProbeKey(s.ctx, key)
if err != nil {
return 0, fmt.Errorf("probe blob %s: %w", sha1Hex, err)
}
if state == depot.Present {
return 0, nil
}
data := body()
if err := s.put(key, data); err != nil {
return 0, fmt.Errorf("upload blob %s: %w", sha1Hex, err)
}
return int64(len(data)), nil
}
func (s zoneSink) putIndex(key string, manifest, sidecar []byte) error {
// The manifest lands last: its presence is the publication marker, so it
// must never appear before the blobs it names.
if err := s.put(key+".json", sidecar); err != nil {
return fmt.Errorf("upload sidecar %s: %w", key, err)
}
if err := s.put(key, manifest); err != nil {
return fmt.Errorf("upload index %s: %w", key, err)
}
return nil
}
func (s zoneSink) getIndex(key string) ([]byte, []byte, error) {
manifest, err := s.store.GetKey(s.ctx, key)
if err != nil {
return nil, nil, fmt.Errorf("read index: %w", err)
}
sidecar, err := s.store.GetKey(s.ctx, key+".json")
if err != nil {
return nil, nil, fmt.Errorf("read sidecar: %w", err)
}
return manifest, sidecar, nil
}
func (s zoneSink) describe(key string) string { return s.zone + "/" + key }
func (s zoneSink) put(key string, body []byte) error {
sum := sha256.Sum256(body)
return s.store.PutReader(s.ctx, key, bytes.NewReader(body), int64(len(body)), hex.EncodeToString(sum[:]))
}
// newZoneSink builds the upload sink from the environment. NWSync data lives
// in its own zone, separate from the asset depot, so it has its own zone and
// credential; only the host is shared, and Crucible has no default host.
func newZoneSink(ctx context.Context, getenv func(string) string) (sink, error) {
cfg := depot.LoadConfig(getenv)
cfg.StorageZone = getenv("NWSYNC_STORAGE_ZONE")
cfg.WriteKey = getenv("NWSYNC_STORAGE_PASSWORD")
cfg.ReadKey = cfg.WriteKey
if cfg.StorageZone == "" {
return nil, fmt.Errorf("NWSYNC_STORAGE_ZONE is unset (or pass --out DIR to write locally)")
}
if cfg.WriteKey == "" {
return nil, fmt.Errorf("NWSYNC_STORAGE_PASSWORD is unset (or pass --out DIR to write locally)")
}
if cfg.StorageHost == "" {
return nil, fmt.Errorf("BUNNY_STORAGE_HOST is unset")
}
store, err := depot.NewKeyStore(cfg)
if err != nil {
return nil, err
}
return zoneSink{store: store, ctx: ctx, zone: cfg.StorageZone}, nil
}
// indexKey is where an artifact's NSYM lives: beside the artifact itself, with
// the final extension replaced. emit and assemble must agree on this one rule,
// so it lives here and nowhere else.
//
// artifacts/haks/sha256/30/46/3046….hak -> artifacts/haks/sha256/30/46/3046….nsym
func indexKey(artifactKey string) (string, error) {
extension := path.Ext(artifactKey)
if extension == "" {
return "", fmt.Errorf("artifact key %q has no extension", artifactKey)
}
return strings.TrimSuffix(artifactKey, extension) + ".nsym", nil
}
// resolveIndexKey is where emit writes an artifact's index and where assemble
// reads it from. On the zone that is beside the artifact; locally the indexes
// sit flat beside the data tree, so upstream's output and ours diff directly.
func resolveIndexKey(artifactKey, outDir string) (string, error) {
key, err := indexKey(artifactKey)
if err != nil {
return "", err
}
if outDir != "" {
return path.Base(key), nil
}
return key, nil
}
// checkArtifactKey fails closed when the key's embedded digest is not the
// digest of the bytes being emitted. Publishing an index under the wrong key
// silently pairs a manifest with the wrong artifact.
// artifact is hashed by streaming, so a multi-gigabyte hak is never resident.
func checkArtifactKey(artifactKey string, artifact io.Reader) error {
base := path.Base(artifactKey)
digest := strings.TrimSuffix(base, path.Ext(base))
if len(digest) != 64 {
return fmt.Errorf("artifact key %q does not name a sha256", artifactKey)
}
hash := sha256.New()
if _, err := io.Copy(hash, artifact); err != nil {
return fmt.Errorf("hash artifact: %w", err)
}
if got := hex.EncodeToString(hash.Sum(nil)); got != digest {
return fmt.Errorf("artifact key %q names digest %s but the file hashes to %s", artifactKey, digest, got)
}
return nil
}