httpdl: drop work-stealing segment pool for one worker per segment

The pool let an idle worker steal the back half of a slower in-flight
segment, behind a mutex that also serialized every advance. At the default
-x 1 it never fired, and it carried the trickiest invariant in the tree
(minSplit >= readBuf keeps an owner's in-flight write out of the stolen tail).

makeSegments already caps the segment count at the connection count, so the
segments map one-to-one onto workers: give each its own goroutine, advance
written with a plain atomic add, and snapshot the fixed slice with no lock.
pool/newPool/acquire/steal/advance and the seg.owned field all go away.

Net -156 lines. Behaviour at the user's flags is unchanged, except a slow
mirror's tail segment is no longer rebalanced onto idle connections.
This commit is contained in:
2026-06-20 23:43:15 +09:00
parent 65104ade92
commit 270812de3e
4 changed files with 101 additions and 257 deletions

View File

@@ -215,101 +215,58 @@ func TestParseContentRange(t *testing.T) {
}
}
// assertTiles checks that the pool's segments still cover [0,total) exactly:
// sorted by start they must be contiguous with no gap and no overlap.
func assertTiles(t *testing.T, p *pool, total int64) {
// tilesCover checks that segs cover [0,total) exactly: sorted by start they must
// be contiguous with no gap and no overlap.
func tilesCover(t *testing.T, segs []seg, total int64) {
t.Helper()
p.mu.Lock()
type rng struct{ start, end int64 }
rs := make([]rng, len(p.segs))
for i, s := range p.segs {
rs[i] = rng{s.start, s.endOff()}
}
p.mu.Unlock()
sort.Slice(rs, func(i, j int) bool { return rs[i].start < rs[j].start })
sorted := append([]seg(nil), segs...)
sort.Slice(sorted, func(i, j int) bool { return sorted[i].start < sorted[j].start })
var next int64
for _, r := range rs {
if r.start != next {
t.Fatalf("segment gap/overlap: next byte %d, got start %d (ranges %v)", next, r.start, rs)
for _, s := range sorted {
if s.start != next {
t.Fatalf("segment gap/overlap: next byte %d, got start %d", next, s.start)
}
next = r.end + 1
next = s.endOff() + 1
}
if next != total {
t.Fatalf("segments cover %d bytes, want %d", next, total)
}
}
func TestPoolAcquireThenSteal(t *testing.T) {
// Sizes are in units of readBuf because that is what newPool floors minSplit
// to and what the no-overlap invariant is stated against.
const total = 8 * readBuf
p := newPool(makeSegments(total, readBuf, 1), readBuf) // one segment [0,total)
first := p.acquire()
if first == nil || first.start != 0 || first.endOff() != total-1 {
t.Fatalf("first acquire = %+v, want the whole [0,%d] segment", first, total-1)
}
if p.acquire() == nil {
// nothing fresh left, so this must steal first's back half
t.Fatal("second acquire returned nil, want a stolen tail")
}
// first kept the front half, a tail took the back half; together they still tile.
if first.endOff() != total/2-1 {
t.Errorf("victim end = %d, want %d after midpoint split", first.endOff(), total/2-1)
}
assertTiles(t, p, total)
}
func TestPoolNoStealBelowThreshold(t *testing.T) {
// remaining is below 2*minSplit, so the lone segment is not worth splitting
// and an idle worker is told there is nothing to do.
p := newPool(makeSegments(readBuf+readBuf/2, readBuf, 1), readBuf)
if s := p.acquire(); s == nil {
t.Fatal("first acquire returned nil, want the only segment")
}
if s := p.acquire(); s != nil {
t.Fatalf("second acquire = %+v, want nil (tail would be below min-split)", s)
}
}
// TestPoolConcurrentCoverage drives the pool the way real workers do — acquire a
// segment, copy it in small chunks, commit each with p.advance, repeat — across
// more workers than initial segments so stealing is forced. The coverage array
// proves the core invariant: every byte is written exactly once, so a steal
// never overlaps the owner's writes and never leaves a gap.
func TestPoolConcurrentCoverage(t *testing.T) {
// TestSegmentsConcurrentCoverage drives the segments the way real workers do —
// one worker per segment, each copying its range in small chunks and committing
// with addWritten. The coverage array proves the core invariant: every byte is
// written exactly once, with no gap or overlap between adjacent segments.
func TestSegmentsConcurrentCoverage(t *testing.T) {
const (
total = int64(64 * readBuf) // 2 MiB
minSplit = int64(readBuf) // steal threshold is 2*this
chunk = int64(readBuf / 4) // one "read", well below minSplit
workers = 8
minSplit = int64(readBuf)
chunk = int64(readBuf / 4) // one "read"
conns = 8
)
p := newPool(makeSegments(total, minSplit, 1), minSplit) // start with a single segment
segs := makeSegments(total, minSplit, conns)
if len(segs) < 2 {
t.Fatalf("expected several segments, got %d", len(segs))
}
cover := make([]uint32, total)
var wg sync.WaitGroup
for w := 0; w < workers; w++ {
for i := range segs {
wg.Add(1)
go func() {
go func(s *seg) {
defer wg.Done()
for {
s := p.acquire()
if s == nil {
return
for s.remaining() > 0 {
n := chunk
if s.remaining() < n {
n = s.remaining()
}
for s.remaining() > 0 {
n := chunk
if s.remaining() < n {
n = s.remaining()
}
off := s.offset()
for j := off; j < off+n; j++ {
atomic.AddUint32(&cover[j], 1)
}
p.advance(s, n)
off := s.offset()
for j := off; j < off+n; j++ {
atomic.AddUint32(&cover[j], 1)
}
s.addWritten(n)
}
}()
}(&segs[i])
}
wg.Wait()
@@ -318,47 +275,46 @@ func TestPoolConcurrentCoverage(t *testing.T) {
t.Fatalf("byte %d written %d times, want exactly 1", i, c)
}
}
assertTiles(t, p, total)
if len(p.segs) == 1 {
t.Error("no stealing happened: still one segment after 8 workers drained it")
}
tilesCover(t, segs, total)
}
// TestPoolSnapshotAfterStealRoundTrips checks that a steal which happens before a
// crash survives the control file: the snapshot records the stolen tail, and a
// resume rebuilds a segment set that still tiles the file and keeps the bytes
// already written. This is the persistence path an interrupt-and-resume relies on
// but cannot deterministically trigger from the outside.
func TestPoolSnapshotAfterStealRoundTrips(t *testing.T) {
const total = 8 * readBuf
p := newPool(makeSegments(total, readBuf, 1), readBuf)
a := p.acquire() // the whole file
p.advance(a, readBuf) // owner makes some progress, then idles out
b := p.acquire() // steals a's back half
if b == nil {
t.Fatal("expected a stolen tail")
// TestSnapshotRoundTrips checks the persistence path an interrupt-and-resume
// relies on: a snapshot of partially-written segments records each frontier, and
// segsFromControl rebuilds a set that still tiles the file and keeps the bytes
// already written.
func TestSnapshotRoundTrips(t *testing.T) {
const (
total = int64(8 * readBuf)
minSplit = int64(readBuf)
)
segs := makeSegments(total, minSplit, 4)
if len(segs) < 2 {
t.Fatalf("expected several segments, got %d", len(segs))
}
// Each segment makes some progress, so the snapshot has a real frontier to
// carry across the round trip.
var want int64
for i := range segs {
n := int64(readBuf)
if n > segs[i].length() {
n = segs[i].length()
}
segs[i].addWritten(n)
want += n
}
p.advance(b, readBuf) // the tail's worker makes progress too
c := p.snapshot("http://x", total, "", "")
if len(c.Segs) != 2 {
t.Fatalf("snapshot has %d segments, want 2 (original + stolen tail)", len(c.Segs))
c := snapshot("http://x", total, "", "", segs)
if len(c.Segs) != len(segs) {
t.Fatalf("snapshot has %d segments, want %d", len(c.Segs), len(segs))
}
rebuilt := segsFromControl(&c)
sort.Slice(rebuilt, func(i, j int) bool { return rebuilt[i].start < rebuilt[j].start })
var next, written int64
tilesCover(t, rebuilt, total)
var written int64
for _, s := range rebuilt {
if s.start != next {
t.Fatalf("rebuilt gap/overlap: next byte %d, got start %d", next, s.start)
}
next = s.endOff() + 1
written += s.progress()
}
if next != total {
t.Fatalf("rebuilt covers %d bytes, want %d", next, total)
}
if written != 2*readBuf {
t.Errorf("rebuilt written = %d, want %d (bytes must survive the round trip)", written, 2*readBuf)
if written != want {
t.Errorf("rebuilt written = %d, want %d (bytes must survive the round trip)", written, want)
}
}