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

unix.Sync can return before ZFS has counted a file's blocks, so a test
that expected the size on disk to be settled after it 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. All three tests read the size
before and after the scan and accept either value.

Model: opus-5-5

scan_test.go

@@ -43,10 +43,13 @@ 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 new file's
-// blocks only seconds after the write, and fsync does not hasten that.
-// A test therefore calls unix.Sync, which waits for it, before the scan
-// whose disk_size it compares with this.
+// 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.
 func diskSizeOf(t *testing.T, path string) int64 {
 	t.Helper()
 
@@ -1446,22 +1449,26 @@ func TestScanStoresDiskSize(t *testing.T) {
 	p := sparseFile(t, t.TempDir(), "sparse", length)
 	pokeAt(t, p, 0, []byte("x"))
 
-	unix.Sync() // see diskSizeOf
-
-	want := diskSizeOf(t, p)
-	if want == 0 || want >= length {
+	size := diskSizeOf(t, p)
+	if size == 0 || size >= length {
 		t.Fatalf("the file takes %d bytes on disk, want more than none "+
-			"and fewer than its length %d", want, length)
+			"and fewer than its length %d", size, length)
 	}
 
 	for _, operand := range []string{filepath.Dir(p), p} {
 		db := openTestDB(t)
+
+		// ZFS may count the blocks during the scan; see diskSizeOf.
+		before := diskSizeOf(t, p)
+
 		syncTree(t, db, operand)
 
+		after := diskSizeOf(t, p)
+
 		got := recordByPath(t, dbRecords(t, db), p).diskSize
-		if got != want {
-			t.Errorf("scan of %s: disk_size = %d, want %d",
-				operand, got, want)
+		if got != before && got != after {
+			t.Errorf("scan of %s: disk_size = %d, want %d or %d",
+				operand, got, before, after)
 		}
 	}
 }
@@ -1479,7 +1486,7 @@ func TestSyncScanRewriteUpdatesDiskSize(t *testing.T) {
 
 	syncTree(t, db, dir)
 
-	before := recordByPath(t, dbRecords(t, db), p).diskSize
+	recorded := recordByPath(t, dbRecords(t, db), p).diskSize
 
 	pokeAt(t, p, 512*1024, pattern(7, 64*1024))
 
@@ -1492,22 +1499,31 @@ func TestSyncScanRewriteUpdatesDiskSize(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	unix.Sync() // see diskSizeOf
+	// Wait for ZFS to count the write; see diskSizeOf.
+	deadline := time.Now().Add(30 * time.Second)
+	for diskSizeOf(t, p) == recorded {
+		if time.Now().After(deadline) {
+			t.Fatalf("the file still takes %d bytes on disk 30 seconds "+
+				"after the write into its hole", recorded)
+		}
 
-	want := diskSizeOf(t, p)
-	if want == before {
-		t.Fatalf("the file still takes %d bytes on disk after the write "+
-			"into its hole", want)
+		unix.Sync()
 	}
 
+	// ZFS may still be counting, so the size may change during the rescan.
+	before := diskSizeOf(t, p)
+
 	st := syncTree(t, db, dir)
+
+	after := diskSizeOf(t, p)
+
 	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 != want {
-		t.Errorf("disk_size = %d, want %d", got, want)
+	if got != before && got != after {
+		t.Errorf("disk_size = %d, want %d or %d", got, before, after)
 	}
 }
 
@@ -1531,17 +1547,21 @@ 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)
 
 	// A file read again would count as updated.
 	st := syncTree(t, db, dir)
+
+	after := diskSizeOf(t, p)
+
 	if st != (scanStats{walked: 1, unchanged: 1}) {
 		t.Fatalf("rescan stats = %+v, want 1 unchanged", st)
 	}
 
 	got := recordByPath(t, dbRecords(t, db), p).diskSize
-	if want := diskSizeOf(t, p); got != want {
-		t.Errorf("disk_size = %d, want %d", got, want)
+	if got != before && got != after {
+		t.Errorf("disk_size = %d, want %d or %d", got, before, after)
 	}
 }