[Tarantool-patches] [PATCH v1 09/12] test: increase timeouts in replication/misc

Alexander V. Tikhonov avtikhon at tarantool.org
Tue Nov 26 09:21:45 MSK 2019


From: Alexander Turenko <alexander.turenko at tarantool.org>

All changes are needed to eliminate sporadic fails when testing is run
with, say, 30 parallel jobs.

First, replication_connect_timeout is increased to 30 seconds. This
parameter doesn't change meaning of the test cases.

Second, increase replication_timeout from 0.01 to 0.03. We usually set
it to 0.1 in tests, but a duration of the gh-3160 test case ('Send
heartbeats if there are changes from a remote master only') is around
100 * replication_timeout seconds and we don't want to make this test
much longer. Runs of the test case (w/o other ones that are in
replication/mics.test.lua) in 30 parallel jobs show that 0.03 is enough
for the gh-3160 case to pass stably and hopefully enough for the
following test cases too.

(cherry picked from commit 697caa6b731ae89627958b1fda2aa1da49ecee5d)
---
 test/replication/misc.result   | 43 ++++++++--------------------------
 test/replication/misc.test.lua | 27 ++++++++-------------
 2 files changed, 20 insertions(+), 50 deletions(-)

diff --git a/test/replication/misc.result b/test/replication/misc.result
index b4af9e41f..6c9582035 100644
--- a/test/replication/misc.result
+++ b/test/replication/misc.result
@@ -117,32 +117,12 @@ SERVERS = { 'autobootstrap1', 'autobootstrap2', 'autobootstrap3' }
 ---
 ...
 -- Deploy a cluster.
-test_run:create_cluster(SERVERS, "replication", {args="0.1"})
+test_run:create_cluster(SERVERS, "replication", {args="0.03"})
 ---
 ...
 test_run:wait_fullmesh(SERVERS)
 ---
 ...
-test_run:cmd("switch autobootstrap1")
----
-- true
-...
-test_run = require('test_run').new()
----
-...
-box.cfg{replication_timeout = 0.01, replication_connect_timeout=0.01}
----
-...
-test_run:cmd("switch autobootstrap2")
----
-- true
-...
-test_run = require('test_run').new()
----
-...
-box.cfg{replication_timeout = 0.01, replication_connect_timeout=0.01}
----
-...
 test_run:cmd("switch autobootstrap3")
 ---
 - true
@@ -150,10 +130,7 @@ test_run:cmd("switch autobootstrap3")
 test_run = require('test_run').new()
 ---
 ...
-fiber=require('fiber')
----
-...
-box.cfg{replication_timeout = 0.01, replication_connect_timeout=0.01}
+fiber = require('fiber')
 ---
 ...
 _ = box.schema.space.create('test_timeout'):create_index('pk')
@@ -163,11 +140,11 @@ test_run:cmd("setopt delimiter ';'")
 ---
 - true
 ...
-function wait_follow(replicaA, replicaB)
+function wait_not_follow(replicaA, replicaB)
     return test_run:wait_cond(function()
         return replicaA.status ~= 'follow' or replicaB.status ~= 'follow'
-    end, 0.01)
-end ;
+    end, box.cfg.replication_timeout)
+end;
 ---
 ...
 function test_timeout()
@@ -175,16 +152,16 @@ function test_timeout()
     local replicaB = box.info.replication[3].upstream or box.info.replication[2].upstream
     local follows = test_run:wait_cond(function()
         return replicaA.status == 'follow' or replicaB.status == 'follow'
-    end, 0.1)
-    if not follows then error('replicas not in follow status') end
-    for i = 0, 99 do 
+    end)
+    if not follows then error('replicas are not in the follow status') end
+    for i = 0, 99 do
         box.space.test_timeout:replace({1})
-        if wait_follow(replicaA, replicaB) then
+        if wait_not_follow(replicaA, replicaB) then
             return error(box.info.replication)
         end
     end
     return true
-end ;
+end;
 ---
 ...
 test_run:cmd("setopt delimiter ''");
diff --git a/test/replication/misc.test.lua b/test/replication/misc.test.lua
index dd374a210..bdfeea11c 100644
--- a/test/replication/misc.test.lua
+++ b/test/replication/misc.test.lua
@@ -44,40 +44,33 @@ test_run:cleanup_cluster()
 SERVERS = { 'autobootstrap1', 'autobootstrap2', 'autobootstrap3' }
 
 -- Deploy a cluster.
-test_run:create_cluster(SERVERS, "replication", {args="0.1"})
+test_run:create_cluster(SERVERS, "replication", {args="0.03"})
 test_run:wait_fullmesh(SERVERS)
-test_run:cmd("switch autobootstrap1")
-test_run = require('test_run').new()
-box.cfg{replication_timeout = 0.01, replication_connect_timeout=0.01}
-test_run:cmd("switch autobootstrap2")
-test_run = require('test_run').new()
-box.cfg{replication_timeout = 0.01, replication_connect_timeout=0.01}
 test_run:cmd("switch autobootstrap3")
 test_run = require('test_run').new()
-fiber=require('fiber')
-box.cfg{replication_timeout = 0.01, replication_connect_timeout=0.01}
+fiber = require('fiber')
 _ = box.schema.space.create('test_timeout'):create_index('pk')
 test_run:cmd("setopt delimiter ';'")
-function wait_follow(replicaA, replicaB)
+function wait_not_follow(replicaA, replicaB)
     return test_run:wait_cond(function()
         return replicaA.status ~= 'follow' or replicaB.status ~= 'follow'
-    end, 0.01)
-end ;
+    end, box.cfg.replication_timeout)
+end;
 function test_timeout()
     local replicaA = box.info.replication[1].upstream or box.info.replication[2].upstream
     local replicaB = box.info.replication[3].upstream or box.info.replication[2].upstream
     local follows = test_run:wait_cond(function()
         return replicaA.status == 'follow' or replicaB.status == 'follow'
-    end, 0.1)
-    if not follows then error('replicas not in follow status') end
-    for i = 0, 99 do 
+    end)
+    if not follows then error('replicas are not in the follow status') end
+    for i = 0, 99 do
         box.space.test_timeout:replace({1})
-        if wait_follow(replicaA, replicaB) then
+        if wait_not_follow(replicaA, replicaB) then
             return error(box.info.replication)
         end
     end
     return true
-end ;
+end;
 test_run:cmd("setopt delimiter ''");
 test_timeout()
 
-- 
2.17.1



More information about the Tarantool-patches mailing list