Files
sow-tools/internal/nwsync/memory_test.go
T
archvillainetteandClaude Opus 5 59b233e3db fix(nwsync): stream emit so peak memory tracks the largest resource (#76)
Emit read the whole artifact into memory and erf.Read then allocated a
second full copy of every payload, so a hak cost about 5x its size in
RAM. The 7 GB runner was OOM-killed on any hak over ~1.4 GB, which
blocks the NWSync backfill and every release that rebuilds a large hak.

Emit now opens the artifact, hashes it by streaming for the key check,
parses only the header and resource table via erf.ReadIndex, and reads,
hashes, compresses and stores one payload at a time. erf.Read keeps its
old shape but returns payloads as subslices instead of fresh copies,
which removes the second copy for the other callers too.

The zstd encoder pool also held one window-sized history per CPU — about
200 MB of live heap on a 24-core runner. EncodeAll is single-threaded
per call, so concurrency 1 gives byte-identical blobs for far less
memory.

Peak heap is now flat at ~22 MB for both an 8 MB and a 64 MB hak, and a
regression test asserts it does not scale with artifact size.

Closes #76

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-31 13:06:29 +02:00

127 lines
3.6 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package nwsync
import (
"fmt"
"os"
"path/filepath"
"runtime"
"runtime/debug"
"testing"
"time"
"git.westgate.pw/ShadowsOverWestgate/sow-tools/internal/erf"
)
// resourceSize is one payload in the memory fixtures. Real haks hold a few MB
// per resource, and peak memory is meant to track that, not the archive.
const resourceSize = 1 << 20
// writeStreamedHak builds a hak of count resources without ever holding the
// archive in memory, so the fixture itself does not decide the measurement.
// Payloads are distinct, so no blob is deduplicated away.
func writeStreamedHak(t *testing.T, path string, count int) {
t.Helper()
payload := filepath.Join(t.TempDir(), "payload.bin")
body := make([]byte, resourceSize)
for index := range body {
body[index] = byte(index)
}
resources := make([]erf.Resource, 0, count)
for index := range count {
// A distinct first byte per resource is enough to give every payload
// its own sha1 while still streaming from one file per resource.
unique := filepath.Join(filepath.Dir(payload), fmt.Sprintf("p%d.bin", index))
body[0] = byte(index)
body[1] = byte(index >> 8)
if err := os.WriteFile(unique, body, 0o644); err != nil {
t.Fatal(err)
}
resources = append(resources, erf.Resource{
Name: fmt.Sprintf("res%05d", index),
Type: restype(t, "tga"),
SourcePath: unique,
Size: resourceSize,
})
}
file, err := os.Create(path)
if err != nil {
t.Fatal(err)
}
defer file.Close()
if err := erf.Write(file, erf.New("HAK", resources)); err != nil {
t.Fatalf("write hak: %v", err)
}
}
// peakHeapDuring runs work while sampling the heap, and returns the largest
// live heap it saw.
func peakHeapDuring(work func()) uint64 {
runtime.GC()
done := make(chan struct{})
peak := make(chan uint64, 1)
go func() {
var highest uint64
var stats runtime.MemStats
for {
select {
case <-done:
peak <- highest
return
default:
}
runtime.ReadMemStats(&stats)
if stats.HeapAlloc > highest {
highest = stats.HeapAlloc
}
time.Sleep(time.Millisecond)
}
}()
work()
close(done)
return <-peak
}
// TestEmitPeakMemoryDoesNotScaleWithArtifactSize is the regression check for
// the OOM kills on large haks: emit used to hold the whole archive (twice), so
// a 2 GB hak needed about 10 GB. Emitting an archive 8× bigger must not cost
// meaningfully more memory.
func TestEmitPeakMemoryDoesNotScaleWithArtifactSize(t *testing.T) {
if testing.Short() {
t.Skip("writes a 64 MB fixture")
}
// A lazy GC lets garbage pile up in proportion to the live heap, which
// hides the thing under test. Collecting eagerly makes the sampled heap
// track what emit actually holds.
defer debug.SetGCPercent(debug.SetGCPercent(10))
measure := func(count int) uint64 {
dir := t.TempDir()
hak := filepath.Join(dir, "big.hak")
writeStreamedHak(t, hak, count)
// The key is computed outside the measurement: the test helper reads
// the whole file to hash it, which emit itself no longer does.
options := EmitOptions{
ArtifactKey: artifactKey(t, hak),
ArtifactPath: hak,
As: filepath.Base(hak),
OutDir: filepath.Join(dir, "out"),
}
return peakHeapDuring(func() {
if _, err := Emit(options); err != nil {
t.Fatalf("emit %d resources: %v", count, err)
}
})
}
small := measure(8) // 8 MB
large := measure(64) // 64 MB
const slack = 24 << 20
t.Logf("peak heap: 8 MB hak %d bytes, 64 MB hak %d bytes", small, large)
if large > small+slack {
t.Fatalf("peak heap scaled with artifact size: 8 MB hak peaked at %d bytes, 64 MB hak at %d", small, large)
}
}