From 19c80df442b8afaa8ef136e50bd850b080bab1e5 Mon Sep 17 00:00:00 2001
From: Alexander Kukushkin <cyberdemn@gmail.com>
Date: Fri, 2 Sep 2016 13:44:47 +0200
Subject: [PATCH] Try to mitigate EtcdEventIndexCleared exception (#287)

This error is send by etcd when Patroni is doing "watch" on leader key
which is never updated after creation and etcd cluster receives a lot of
updates, what cleans history of events.

Instead of doing watch on modifiedIndex + 1 we will do watch on X-Etcd-Index,
which is probably still available...
---
 patroni/dcs/etcd.py | 5 +++--
 tests/test_etcd.py  | 4 +++-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/patroni/dcs/etcd.py b/patroni/dcs/etcd.py
index d81cf968..c58a2ddb 100644
--- a/patroni/dcs/etcd.py
+++ b/patroni/dcs/etcd.py
@@ -292,7 +292,8 @@ class Etcd(AbstractDCS):
             if leader:
                 member = Member(-1, leader.value, None, {})
                 member = ([m for m in members if m.name == leader.value] or [member])[0]
-                leader = Leader(leader.modifiedIndex, leader.ttl, member)
+                index = result.etcd_index if result.etcd_index > leader.modifiedIndex else leader.modifiedIndex + 1
+                leader = Leader(index, leader.ttl, member)
 
             # failover key
             failover = nodes.get(self._FAILOVER)
@@ -371,7 +372,7 @@ class Etcd(AbstractDCS):
 
             while timeout >= 1:  # when timeout is too small urllib3 doesn't have enough time to connect
                 try:
-                    self._client.watch(self.leader_path, index=cluster.leader.index + 1, timeout=timeout + 0.5)
+                    self._client.watch(self.leader_path, index=cluster.leader.index, timeout=timeout + 0.5)
                     # Synchronous work of all cluster members with etcd is less expensive
                     # than reestablishing http connection every time from every replica.
                     return True
diff --git a/tests/test_etcd.py b/tests/test_etcd.py
index f3a32a41..16035d6e 100644
--- a/tests/test_etcd.py
+++ b/tests/test_etcd.py
@@ -103,7 +103,9 @@ def etcd_read(self, key, **kwargs):
                      "expiration": "2015-05-15T09:11:09.611860899Z", "ttl": 30,
                      "modifiedIndex": 20730, "createdIndex": 20730}],
                  "modifiedIndex": 1581, "createdIndex": 1581}], "modifiedIndex": 1581, "createdIndex": 1581}}
-    return etcd.EtcdResult(**response)
+    result = etcd.EtcdResult(**response)
+    result.etcd_index = 0
+    return result
 
 
 class SleepException(Exception):