tools/cephfs_mirror: Persist metrics to omap

Persist snapshot mirroring metrics to the cephfs_mirror object omap
for the mgr/mirroring module to support status command.

The tick thread only keeps omap up to date for in-progress syncs on
registered directories. Persist explicitly when stats change so omap
is updated before a directory unregisters:

 - snap delete/rename propagation (inc_deleted_snap / inc_renamed_snap)
 - after each successful snap sync (following set_last_synced_stat)
 - after sync_snaps failure (following _inc_failed_count)
 - after sync_perms failure (following _inc_failed_count)

Without the explicit call sites, omap can keep stale live or idle state
after sync completes or fails because directories leave m_registered
before the next tick.

Fixes: https://tracker.ceph.com/issues/76686
Signed-off-by: Kotresh HR <khiremat@redhat.com>

diff --git a/src/tools/cephfs_mirror/PeerReplayer.cc b/src/tools/cephfs_mirror/PeerReplayer.cc
index 6645374969c9ca38b54d66167c6d2adecf8719c4..06206e5c8cc5d649d939c3a8e8fdd24d7e854dee 100644 (file)
--- a/src/tools/cephfs_mirror/PeerReplayer.cc
+++ b/src/tools/cephfs_mirror/PeerReplayer.cc
@@ -1166,6 +1166,7 @@ int PeerReplayer::propagate_snap_deletes(const std::string &dir_root,
       return r;
     }
     inc_deleted_snap(dir_root);
+    persist_dir_sync_stat(dir_root);
     if (m_perf_counters) {
       m_perf_counters->inc(l_cephfs_mirror_peer_replayer_snaps_deleted);
     }
@@ -1192,6 +1193,7 @@ int PeerReplayer::propagate_snap_renames(
       return r;
     }
     inc_renamed_snap(dir_root);
+    persist_dir_sync_stat(dir_root);
     if (m_perf_counters) {
       m_perf_counters->inc(l_cephfs_mirror_peer_replayer_snaps_renamed);
     }
@@ -2849,6 +2851,7 @@ int PeerReplayer::do_sync_snaps(const std::string &dir_root) {
     }
 
     set_last_synced_stat(dir_root, it->first, it->second, duration);
+    persist_dir_sync_stat(dir_root);
     if (--snaps_per_cycle == 0) {
       break;
     }
@@ -2878,6 +2881,11 @@ int PeerReplayer::sync_snaps(const std::string &dir_root,
     update_directory_current_sync_perf_counters(dir_perf,
                                                 m_snap_sync_stats.at(dir_root));
   }
+  if (r < 0) {
+    locker.unlock();
+    persist_dir_sync_stat(dir_root);
+    locker.lock();
+  }
   return r;
 }
 
@@ -2898,6 +2906,18 @@ void PeerReplayer::run_tick() {
     for (const auto &kv : m_registered) {
       refresh_directory_current_sync_perf_counters(kv.first);
     }
+
+    // persist sync stats to omap for registered directories
+    std::vector<std::string> dirs;
+    dirs.reserve(m_registered.size());
+    for (const auto &kv : m_registered) {
+      dirs.push_back(kv.first);
+    }
+    locker.unlock();
+    for (const auto &dir_root : dirs) {
+      persist_dir_sync_stat(dir_root);
+    }
+    locker.lock();
   }
 }
 
@@ -2947,6 +2967,9 @@ void PeerReplayer::run(SnapshotReplayerThread *replayer) {
               update_directory_current_sync_perf_counters(
                 dir_perf, m_snap_sync_stats.at(*dir_root));
             }
+            locker.unlock();
+            persist_dir_sync_stat(*dir_root);
+            locker.lock();
             if (m_perf_counters) {
               m_perf_counters->inc(l_cephfs_mirror_peer_replayer_snap_sync_failures);
             }