testcluster: retry force repl scan on startup

There have been recent flakes on tests which use a `TestCluster`. These
failures have occurred at startup, before much test specific logic. This
patch mitigates the symptom by retrying on an error, rather than
erroring out. The error looks like:

```
testcluster.go:485: unable to retrieve conf reader: span configs not available
```

It is caused by span configs not being available, which is checked via
grabbing the `ConfReader` before forcing the replica queues to process.

The root cause of this behavior change should still be determined and
this should be considered temporary, although the root cause may be
benign.

informs: #137712
informs: #137762
Release note: None

pkg/testutils/testcluster/testcluster.go

@@ -1479,7 +1479,9 @@ func (tc *TestCluster) WaitForFullReplication() error {
 				// Force upreplication. Otherwise, if we rely on the scanner to do it,
 				// it'll take a while.
 				if err := s.ForceReplicationScanAndProcess(); err != nil {
-					return err
+					log.Infof(context.TODO(), "%v", err)
+					notReplicated = true
+					return nil
 				}
 				if err := s.ComputeMetrics(context.TODO()); err != nil {
 					// This can sometimes fail since ComputeMetrics calls