From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: From: Serge Petrenko Subject: [PATCH v2.1 2/2] replication: fix a failing assert in replica_on_applier_disconnect() Date: Fri, 17 Aug 2018 10:06:51 +0300 Message-Id: In-Reply-To: References: In-Reply-To: References: To: vdavydov.dev@gmail.com Cc: kyukhin@tarantool.org, tarantool-patches@freelists.org, Serge Petrenko List-ID: One possible case when two applier errors happen one after another wasn't handled in replica_on_applier_disconnect(), which lead to occasional test failures and crashes. Handle this case and add a regression test. Part of #3510 --- src/box/replication.cc | 4 ++++ test/replication/er_load.lua | 25 +++++++++++++++++++++++++ test/replication/er_load1.lua | 1 + test/replication/er_load2.lua | 1 + test/replication/misc.result | 32 ++++++++++++++++++++++++++++++++ test/replication/misc.test.lua | 12 ++++++++++++ 6 files changed, 75 insertions(+) create mode 100644 test/replication/er_load.lua create mode 120000 test/replication/er_load1.lua create mode 120000 test/replication/er_load2.lua diff --git a/src/box/replication.cc b/src/box/replication.cc index 4270911ef..c9283bd82 100644 --- a/src/box/replication.cc +++ b/src/box/replication.cc @@ -358,6 +358,10 @@ replica_on_applier_disconnect(struct replica *replica) assert(replicaset.applier.connected > 0); replicaset.applier.connected--; break; + case APPLIER_LOADING: + assert(replicaset.applier.loading > 0); + replicaset.applier.loading--; + break; case APPLIER_DISCONNECTED: break; default: diff --git a/test/replication/er_load.lua b/test/replication/er_load.lua new file mode 100644 index 000000000..071fc7b02 --- /dev/null +++ b/test/replication/er_load.lua @@ -0,0 +1,25 @@ +#!/usr/bin/env tarantool + +-- get instance id from filename (er_load1.lua => 1) +local INSTANCE_ID = string.match(arg[0], '%d') + +local SOCKET_DIR = require('fio').cwd() +local function instance_uri(instance_id) + return SOCKET_DIR..'/er_load'..instance_id..'.sock' +end + +require('console').listen(os.getenv('ADMIN')) + +box.cfg{ + listen = instance_uri(INSTANCE_ID); + replication = { + instance_uri(INSTANCE_ID), + instance_uri(INSTANCE_ID % 2 + 1) + }, + replication_timeout = 0.01, + read_only = INSTANCE_ID == '2' +} +box.once('bootstrap', function() + box.schema.user.grant('guest', 'replication') + box.space._cluster:delete(2) +end) diff --git a/test/replication/er_load1.lua b/test/replication/er_load1.lua new file mode 120000 index 000000000..18f7ffa5a --- /dev/null +++ b/test/replication/er_load1.lua @@ -0,0 +1 @@ +er_load.lua \ No newline at end of file diff --git a/test/replication/er_load2.lua b/test/replication/er_load2.lua new file mode 120000 index 000000000..18f7ffa5a --- /dev/null +++ b/test/replication/er_load2.lua @@ -0,0 +1 @@ +er_load.lua \ No newline at end of file diff --git a/test/replication/misc.result b/test/replication/misc.result index 9df2a2c4b..16b0fc362 100644 --- a/test/replication/misc.result +++ b/test/replication/misc.result @@ -232,3 +232,35 @@ test_run:drop_cluster(SERVERS) box.schema.user.revoke('guest', 'replication') --- ... +-- gh-3510 assertion failure in replica_on_applier_disconnect() +test_run:cmd('create server er_load1 with script="replication/er_load1.lua"') +--- +- true +... +test_run:cmd('create server er_load2 with script="replication/er_load2.lua"') +--- +- true +... +test_run:cmd('start server er_load1 with wait=False, wait_load=False') +--- +- true +... +-- instance er_load2 will fail with error ER_READONLY. this is ok. +-- We only test here that er_load1 doesn't assert. +test_run:cmd('start server er_load2 with wait=True, wait_load=True, crash_expected = True') +--- +- false +... +test_run:cmd('stop server er_load1') +--- +- true +... +-- er_load2 exits automatically. +test_run:cmd('cleanup server er_load1') +--- +- true +... +test_run:cmd('cleanup server er_load2') +--- +- true +... diff --git a/test/replication/misc.test.lua b/test/replication/misc.test.lua index 979c5d58c..852d7374b 100644 --- a/test/replication/misc.test.lua +++ b/test/replication/misc.test.lua @@ -91,3 +91,15 @@ test_run:cmd("switch default") test_run:drop_cluster(SERVERS) box.schema.user.revoke('guest', 'replication') + +-- gh-3510 assertion failure in replica_on_applier_disconnect() +test_run:cmd('create server er_load1 with script="replication/er_load1.lua"') +test_run:cmd('create server er_load2 with script="replication/er_load2.lua"') +test_run:cmd('start server er_load1 with wait=False, wait_load=False') +-- instance er_load2 will fail with error ER_READONLY. this is ok. +-- We only test here that er_load1 doesn't assert. +test_run:cmd('start server er_load2 with wait=True, wait_load=True, crash_expected = True') +test_run:cmd('stop server er_load1') +-- er_load2 exits automatically. +test_run:cmd('cleanup server er_load1') +test_run:cmd('cleanup server er_load2') -- 2.15.2 (Apple Git-101.1)