Comment 70 for bug 1833281

Just an idea, try reproducing with kernel patch `le9g.patch`:

```
diff --git a/mm/vmscan.c b/mm/vmscan.c
index dbdc46a84f63..7a0b7e32ff45 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2445,6 +2445,13 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
    BUG();
   }

+ if (NR_ACTIVE_FILE == lru) {
+ long long kib_active_file_now=global_node_page_state(NR_ACTIVE_FILE) * MAX_NR_ZONES;
+ if (kib_active_file_now <= 256*1024) {
+ nr[lru] = 0; //don't reclaim any Active(file) (see /proc/meminfo) if they are under 256MiB
+ continue;
+ }
+ }
   *lru_pages += size;
   nr[lru] = scan;
  }
```

see: https://gist.github.com/constantoverride/84eba764f487049ed642eb2111a20830#gistcomment-2997481
(^ scroll a bit up for some details of what the patch does)