From f81e6dc8abe3535a54cbf683992c95c4eaf4e186 Mon Sep 17 00:00:00 2001
From: John Spray <john.spray@redhat.com>
Date: Thu, 12 Oct 2017 11:57:50 +0100
Subject: [PATCH] mon: handle monitor lag when killing mgrs

Fixes: http://tracker.ceph.com/issues/20629
Signed-off-by: John Spray <john.spray@redhat.com>
(cherry picked from commit 3c3776b30a2da3f5d2ece15c57713c0ce191c778)
---
 src/mon/MgrMonitor.cc | 25 ++++++++++++++++++++++++-
 src/mon/MgrMonitor.h  |  5 +++++
 2 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/src/mon/MgrMonitor.cc b/src/mon/MgrMonitor.cc
index 86895671583..a307dd4df5c 100644
--- a/src/mon/MgrMonitor.cc
+++ b/src/mon/MgrMonitor.cc
@@ -538,7 +538,28 @@ void MgrMonitor::tick()
     return;
 
   const auto now = ceph::coarse_mono_clock::now();
-  const auto cutoff = now - std::chrono::seconds(g_conf->get_val<int64_t>("mon_mgr_beacon_grace"));
+
+  const auto mgr_beacon_grace = std::chrono::seconds(
+      g_conf->get_val<int64_t>("mon_mgr_beacon_grace"));
+
+  // Note that this is the mgr daemon's tick period, not ours (the
+  // beacon is sent with this period).
+  const auto mgr_tick_period = std::chrono::seconds(
+      g_conf->get_val<int64_t>("mgr_tick_period"));
+
+  if (last_tick != ceph::coarse_mono_clock::time_point::min()
+      && (now - last_tick > (mgr_beacon_grace - mgr_tick_period))) {
+    // This case handles either local slowness (calls being delayed
+    // for whatever reason) or cluster election slowness (a long gap
+    // between calls while an election happened)
+    dout(4) << __func__ << ": resetting beacon timeouts due to mon delay "
+            "(slow election?) of " << now - last_tick << " seconds" << dendl;
+    for (auto &i : last_beacon) {
+      i.second = now;
+    }
+  }
+
+  last_tick = now;
 
   // Populate any missing beacons (i.e. no beacon since MgrMonitor
   // instantiation) with the current time, so that they will
@@ -556,6 +577,7 @@ void MgrMonitor::tick()
   // Cull standbys first so that any remaining standbys
   // will be eligible to take over from the active if we cull him.
   std::list<uint64_t> dead_standbys;
+  const auto cutoff = now - mgr_beacon_grace;
   for (const auto &i : pending_map.standbys) {
     auto last_beacon_time = last_beacon.at(i.first);
     if (last_beacon_time < cutoff) {
@@ -614,6 +636,7 @@ void MgrMonitor::on_restart()
 {
   // Clear out the leader-specific state.
   last_beacon.clear();
+  last_tick = ceph::coarse_mono_clock::now();
 }
 
 
diff --git a/src/mon/MgrMonitor.h b/src/mon/MgrMonitor.h
index f7fb506cd1b..82315d3550d 100644
--- a/src/mon/MgrMonitor.h
+++ b/src/mon/MgrMonitor.h
@@ -118,6 +118,11 @@ public:
   void count_metadata(const string& field, std::map<string,int> *out);
 
   friend class C_Updated;
+
+  // When did the mon last call into our tick() method?  Used for detecting
+  // when the mon was not updating us for some period (e.g. during slow
+  // election) to reset last_beacon timeouts
+  ceph::coarse_mono_clock::time_point last_tick;
 };
 
 #endif
-- 
2.47.3