mgr: relax osd ok-to-stop condition on degraded pgs

Right now, the "ok-to-stop" condition is relatively rigorous, it allows
stopping an osd only if no PG on it is non-active or degraded. But there
are situations in which an OSD is part of a degraded pg and the pg still
still have > min_size complete replicas after the OSD is stopped.

In 9750061, we changed from considering
just acting to using avail_no_missing (OSDs that have no missing objects).
When the projected pg_acting is constructed this way, we can safely compare
to min_size... even for a PG marked degraded.

Fixes: https://tracker.ceph.com/issues/49392
Signed-off-by: Xuehan Xu <xxhdx1985126@gmail.com>

src/mgr/DaemonServer.cc

@@ -1643,20 +1643,21 @@ bool DaemonServer::_handle_command(
 	    continue;
 	  }
 	  touched_pgs++;
-	  if (!(q.second.state & PG_STATE_ACTIVE) ||
-	      (q.second.state & PG_STATE_DEGRADED)) {
-	    ++dangerous_pgs;
-	    continue;
-	  }
+
 	  const pg_pool_t *pi = osdmap.get_pg_pool(q.first.pool());
 	  if (!pi) {
 	    ++dangerous_pgs; // pool is creating or deleting
-	  } else {
-	    if (pg_acting.size() < pi->min_size) {
-	      ++dangerous_pgs;
-	    }
+            continue;
 	  }
-	}
+
+	  if (!(q.second.state & PG_STATE_ACTIVE)) {
+	    ++dangerous_pgs;
+	    continue;
+	  }
+          if (pg_acting.size() < pi->min_size) {
+            ++dangerous_pgs;
+          }
+        }
       });
     if (r) {
       cmdctx->reply(r, ss);