cephfs,mon: require confirmation to fail unhealthy FS

Confirmation flag must be passed when running the command "ceph fs fail"
when the MDS for this FS has either of the two health warnings: MDS_TRIM
or MDS_CACHE_OVERSIZED. Else, the command will fail and print an
appropriate error message.

Restarting an MDS with these health warnings is not recommened since it
will have a slow recovery during restart which will create new problems.

Fixes: https://tracker.ceph.com/issues/61866
Signed-off-by: Rishabh Dave <ridave@redhat.com>

diff --git a/src/mon/FSCommands.cc b/src/mon/FSCommands.cc
index 357d1a2a1698cef67e54ab11bb2df795f00a49fd..2660d1bda96243d2a57c0f680c2ca638ab29a2fe 100644 (file)
--- a/src/mon/FSCommands.cc
+++ b/src/mon/FSCommands.cc
@@ -108,6 +108,15 @@ class FailHandler : public FileSystemCommandHandler
       return -ENOENT;
     }
 
+  bool confirm = false;
+  cmd_getval(cmdmap, "yes_i_really_mean_it", confirm);
+  if (!confirm &&
+      mon->mdsmon()->has_health_warnings({
+       MDS_HEALTH_TRIM, MDS_HEALTH_CACHE_OVERSIZED})) {
+    ss << errmsg_for_unhealthy_mds;
+    return -EPERM;
+  }
+
     auto f = [](auto&& fs) {
       fs.get_mds_map().set_flag(CEPH_MDSMAP_NOT_JOINABLE);
     };

diff --git a/src/mon/MonCommands.h b/src/mon/MonCommands.h
index 793b164c7b3540f3ea7fff4604f55c42d37b659f..b2a678dff53c53bf3b07f9d8597403a14fb46ec4 100644 (file)
--- a/src/mon/MonCommands.h
+++ b/src/mon/MonCommands.h
@@ -356,7 +356,8 @@ COMMAND("fs new "
        "make new filesystem using named pools <metadata> and <data>",
        "fs", "rw")
 COMMAND("fs fail "
-       "name=fs_name,type=CephString ",
+       "name=fs_name,type=CephString "
+        "name=yes_i_really_mean_it,type=CephBool,req=false",
        "bring the file system down and all of its ranks",
        "fs", "rw")
 COMMAND("fs rm "