Stop the disk size tests failing at random on ZFS (closes #150)

One ZFS commit can take a file through several sizes, and unix.Sync can
return before the blocks are counted. A test that expected the size on
disk to be settled therefore failed at random. The test that needs the
size to change now calls unix.Sync in a loop until it does, for at most
30 seconds. It then rescans until the size reads the same before and
after a rescan, and compares disk_size exactly, within the same 30
seconds. The other two tests fail only on a disk_size outside their two
reads. They call unix.Sync once first, so a wrong 512 usually fails them.

Model: opus-5-5

TODO.md

@@ -30,10 +30,12 @@ Newest first. An entry ends with its date and its issue or branch, where those
 are known.
 
 - The three disk size tests in `scan_test.go` no longer fail at random on ZFS.
-  `unix.Sync` can return before ZFS has counted a file's blocks. The test that
-  needs the size to change waits for it, for at most 30 seconds. Each test reads
-  the size before and after its scan and accepts either value (2026-11-02,
-  https://git.eeqj.de/sneak/sfdupes/issues/150)
+  `unix.Sync` can return before ZFS has counted a file's blocks, and one ZFS
+  commit can take a file through several sizes. The test that needs the size to
+  change waits for it, for at most 30 seconds. Each test reads the size before
+  and after its scan. The rewrite test rescans until the two reads match, then
+  compares exactly. The other two fail only on a `disk_size` outside the two
+  reads (2026-11-02, https://git.eeqj.de/sneak/sfdupes/issues/150)
 
 - `TODO.md` rewritten from scratch by the same rules as `README.md`, sentence by
   sentence. Every completed step is kept, with its date and its issue or branch.

scan_test.go

@@ -44,12 +44,15 @@ func writeFile(t *testing.T, dir, name string, data []byte) string {
 
 // diskSizeOf returns the bytes the file at path takes on disk, from its
 // own lstat: st_blocks counts 512-byte units. ZFS counts a write's
-// blocks only when it commits the write, seconds later and sometimes in
-// steps, so this value can change at any moment. fsync does not hasten
-// that. unix.Sync usually does, but it can return before the blocks are
-// counted. A test that needs the value to change therefore waits for
-// that, and a test that compares it with a scan's disk_size reads it
-// before and after the scan and accepts either.
+// blocks only when it commits the write, up to seconds later, and one
+// commit can take the file through several growing sizes. So this value
+// can change at any moment. Neither fsync nor unix.Sync hastens that,
+// but a unix.Sync call often takes long enough that the blocks are
+// counted when it returns. A test that needs the value to change waits
+// for the change. A test that compares it with a scan's disk_size reads
+// it before and after the scan. The rewrite test rescans until the two
+// reads match, then compares exactly. The other two tests fail only on
+// a disk_size outside the two reads.
 func diskSizeOf(t *testing.T, path string) int64 {
 	t.Helper()
 
@@ -1449,6 +1452,8 @@ func TestScanStoresDiskSize(t *testing.T) {
 	p := sparseFile(t, t.TempDir(), "sparse", length)
 	pokeAt(t, p, 0, []byte("x"))
 
+	unix.Sync() // see diskSizeOf
+
 	size := diskSizeOf(t, p)
 	if size == 0 || size >= length {
 		t.Fatalf("the file takes %d bytes on disk, want more than none "+
@@ -1466,8 +1471,8 @@ func TestScanStoresDiskSize(t *testing.T) {
 		after := diskSizeOf(t, p)
 
 		got := recordByPath(t, dbRecords(t, db), p).diskSize
-		if got != before && got != after {
-			t.Errorf("scan of %s: disk_size = %d, want %d or %d",
+		if got < before || got > after {
+			t.Errorf("scan of %s: disk_size = %d, want %d to %d",
 				operand, got, before, after)
 		}
 	}
@@ -1510,20 +1515,42 @@ func TestSyncScanRewriteUpdatesDiskSize(t *testing.T) {
 		unix.Sync()
 	}
 
-	// ZFS may still be counting, so the size may change during the rescan.
-	before := diskSizeOf(t, p)
+	// ZFS may still be counting, so the size may change during a rescan.
+	// Only a rescan with the same size on both sides of it can be compared
+	// exactly. A rescan that keeps the old size still fails, because the
+	// wait made before differ from it.
+	for {
+		before := diskSizeOf(t, p)
 
-	st := syncTree(t, db, dir)
+		st := syncTree(t, db, dir)
 
-	after := diskSizeOf(t, p)
+		after := diskSizeOf(t, p)
 
-	if st != (scanStats{walked: 1, updated: 1}) {
-		t.Fatalf("rescan stats = %+v, want 1 updated", st)
-	}
+		if st != (scanStats{walked: 1, updated: 1}) {
+			t.Fatalf("rescan stats = %+v, want 1 updated", st)
+		}
 
-	got := recordByPath(t, dbRecords(t, db), p).diskSize
-	if got != before && got != after {
-		t.Errorf("disk_size = %d, want %d or %d", got, before, after)
+		if before == after {
+			got := recordByPath(t, dbRecords(t, db), p).diskSize
+			if got != after {
+				t.Errorf("disk_size = %d, want %d", got, after)
+			}
+
+			return
+		}
+
+		if time.Now().After(deadline) {
+			t.Fatalf("the size on disk was still changing 30 seconds after "+
+				"the write into its hole: %d, then %d", before, after)
+		}
+
+		// A later mtime makes the next rescan read the file again.
+		later = later.Add(time.Second)
+
+		err = os.Chtimes(p, later, later)
+		if err != nil {
+			t.Fatal(err)
+		}
 	}
 }
 
@@ -1547,6 +1574,8 @@ func TestSyncScanUnchangedUpdatesDiskSize(t *testing.T) {
 		t.Fatal(err)
 	}
 
+	unix.Sync() // see diskSizeOf
+
 	// ZFS may count the blocks during the rescan; see diskSizeOf.
 	before := diskSizeOf(t, p)
 
@@ -1560,8 +1589,8 @@ func TestSyncScanUnchangedUpdatesDiskSize(t *testing.T) {
 	}
 
 	got := recordByPath(t, dbRecords(t, db), p).diskSize
-	if got != before && got != after {
-		t.Errorf("disk_size = %d, want %d or %d", got, before, after)
+	if got < before || got > after {
+		t.Errorf("disk_size = %d, want %d to %d", got, before, after)
 	}
 }