Tarantool development patches archive
 help / color / mirror / Atom feed
From: Vladislav Shpilevoy <v.shpilevoy@tarantool.org>
To: tarantool-patches@dev.tarantool.org, sergepetrenko@tarantool.org
Subject: [Tarantool-patches] [PATCH v2 20/19] replication: add test for quorum 1
Date: Wed, 1 Jul 2020 01:00:40 +0200	[thread overview]
Message-ID: <9418f015-311b-8d25-0b44-96a3b8443683@tarantool.org> (raw)
In-Reply-To: <cover.1593472477.git.v.shpilevoy@tarantool.org>

When synchro quorum is 1, the final commit and confirmation write
are done by the fiber created the transaction, right after WAL
write. This case got special handling in the previous patches,
and this commits adds a test for that.

Closes #5123
---
 test/replication/qsync_basic.result    |  33 +++++++
 test/replication/qsync_basic.test.lua  |  12 +++
 test/replication/qsync_errinj.result   | 114 +++++++++++++++++++++++++
 test/replication/qsync_errinj.test.lua |  45 ++++++++++
 test/replication/suite.ini             |   2 +-
 5 files changed, 205 insertions(+), 1 deletion(-)
 create mode 100644 test/replication/qsync_errinj.result
 create mode 100644 test/replication/qsync_errinj.test.lua

diff --git a/test/replication/qsync_basic.result b/test/replication/qsync_basic.result
index f713d4b08..cdecf00e8 100644
--- a/test/replication/qsync_basic.result
+++ b/test/replication/qsync_basic.result
@@ -299,6 +299,39 @@ box.space.sync:select{6}
  | - []
  | ...
 
+--
+-- gh-5123: quorum 1 still should write CONFIRM.
+--
+test_run:switch('default')
+ | ---
+ | - true
+ | ...
+box.cfg{replication_synchro_quorum = 1, replication_synchro_timeout = 5}
+ | ---
+ | ...
+oldlsn = box.info.lsn
+ | ---
+ | ...
+box.space.sync:replace{7}
+ | ---
+ | - [7]
+ | ...
+newlsn = box.info.lsn
+ | ---
+ | ...
+assert(newlsn >= oldlsn + 2)
+ | ---
+ | - true
+ | ...
+test_run:switch('replica')
+ | ---
+ | - true
+ | ...
+box.space.sync:select{7}
+ | ---
+ | - - [7]
+ | ...
+
 -- Cleanup.
 test_run:cmd('switch default')
  | ---
diff --git a/test/replication/qsync_basic.test.lua b/test/replication/qsync_basic.test.lua
index f84b6ee19..361f22bc3 100644
--- a/test/replication/qsync_basic.test.lua
+++ b/test/replication/qsync_basic.test.lua
@@ -118,6 +118,18 @@ test_run:switch('replica')
 box.space.test:select{6}
 box.space.sync:select{6}
 
+--
+-- gh-5123: quorum 1 still should write CONFIRM.
+--
+test_run:switch('default')
+box.cfg{replication_synchro_quorum = 1, replication_synchro_timeout = 5}
+oldlsn = box.info.lsn
+box.space.sync:replace{7}
+newlsn = box.info.lsn
+assert(newlsn >= oldlsn + 2)
+test_run:switch('replica')
+box.space.sync:select{7}
+
 -- Cleanup.
 test_run:cmd('switch default')
 
diff --git a/test/replication/qsync_errinj.result b/test/replication/qsync_errinj.result
new file mode 100644
index 000000000..1d2945761
--- /dev/null
+++ b/test/replication/qsync_errinj.result
@@ -0,0 +1,114 @@
+-- test-run result file version 2
+test_run = require('test_run').new()
+ | ---
+ | ...
+engine = test_run:get_cfg('engine')
+ | ---
+ | ...
+
+old_synchro_quorum = box.cfg.replication_synchro_quorum
+ | ---
+ | ...
+old_synchro_timeout = box.cfg.replication_synchro_timeout
+ | ---
+ | ...
+box.schema.user.grant('guest', 'super')
+ | ---
+ | ...
+
+test_run:cmd('create server replica with rpl_master=default,\
+             script="replication/replica.lua"')
+ | ---
+ | - true
+ | ...
+test_run:cmd('start server replica with wait=True, wait_load=True')
+ | ---
+ | - true
+ | ...
+
+_ = box.schema.space.create('sync', {is_sync = true, engine = engine})
+ | ---
+ | ...
+_ = box.space.sync:create_index('pk')
+ | ---
+ | ...
+
+--
+-- gh-5123: replica WAL fail shouldn't crash with quorum 1.
+--
+test_run:switch('default')
+ | ---
+ | - true
+ | ...
+box.cfg{replication_synchro_quorum = 1, replication_synchro_timeout = 5}
+ | ---
+ | ...
+box.space.sync:insert{1}
+ | ---
+ | - [1]
+ | ...
+
+test_run:switch('replica')
+ | ---
+ | - true
+ | ...
+box.error.injection.set('ERRINJ_WAL_IO', true)
+ | ---
+ | - ok
+ | ...
+
+test_run:switch('default')
+ | ---
+ | - true
+ | ...
+box.space.sync:insert{2}
+ | ---
+ | - [2]
+ | ...
+
+test_run:switch('replica')
+ | ---
+ | - true
+ | ...
+test_run:wait_upstream(1, {status='stopped'})
+ | ---
+ | - true
+ | ...
+box.error.injection.set('ERRINJ_WAL_IO', false)
+ | ---
+ | - ok
+ | ...
+
+test_run:cmd('restart server replica')
+ | 
+box.space.sync:select{2}
+ | ---
+ | - - [2]
+ | ...
+
+test_run:cmd('switch default')
+ | ---
+ | - true
+ | ...
+
+box.cfg{                                                                        \
+    replication_synchro_quorum = old_synchro_quorum,                            \
+    replication_synchro_timeout = old_synchro_timeout,                          \
+}
+ | ---
+ | ...
+test_run:cmd('stop server replica')
+ | ---
+ | - true
+ | ...
+test_run:cmd('delete server replica')
+ | ---
+ | - true
+ | ...
+
+box.space.sync:drop()
+ | ---
+ | ...
+box.schema.user.revoke('guest', 'super')
+ | ---
+ | ...
diff --git a/test/replication/qsync_errinj.test.lua b/test/replication/qsync_errinj.test.lua
new file mode 100644
index 000000000..96495ae6c
--- /dev/null
+++ b/test/replication/qsync_errinj.test.lua
@@ -0,0 +1,45 @@
+test_run = require('test_run').new()
+engine = test_run:get_cfg('engine')
+
+old_synchro_quorum = box.cfg.replication_synchro_quorum
+old_synchro_timeout = box.cfg.replication_synchro_timeout
+box.schema.user.grant('guest', 'super')
+
+test_run:cmd('create server replica with rpl_master=default,\
+             script="replication/replica.lua"')
+test_run:cmd('start server replica with wait=True, wait_load=True')
+
+_ = box.schema.space.create('sync', {is_sync = true, engine = engine})
+_ = box.space.sync:create_index('pk')
+
+--
+-- gh-5123: replica WAL fail shouldn't crash with quorum 1.
+--
+test_run:switch('default')
+box.cfg{replication_synchro_quorum = 1, replication_synchro_timeout = 5}
+box.space.sync:insert{1}
+
+test_run:switch('replica')
+box.error.injection.set('ERRINJ_WAL_IO', true)
+
+test_run:switch('default')
+box.space.sync:insert{2}
+
+test_run:switch('replica')
+test_run:wait_upstream(1, {status='stopped'})
+box.error.injection.set('ERRINJ_WAL_IO', false)
+
+test_run:cmd('restart server replica')
+box.space.sync:select{2}
+
+test_run:cmd('switch default')
+
+box.cfg{                                                                        \
+    replication_synchro_quorum = old_synchro_quorum,                            \
+    replication_synchro_timeout = old_synchro_timeout,                          \
+}
+test_run:cmd('stop server replica')
+test_run:cmd('delete server replica')
+
+box.space.sync:drop()
+box.schema.user.revoke('guest', 'super')
diff --git a/test/replication/suite.ini b/test/replication/suite.ini
index 6119a264b..11f8d4e20 100644
--- a/test/replication/suite.ini
+++ b/test/replication/suite.ini
@@ -3,7 +3,7 @@ core = tarantool
 script =  master.lua
 description = tarantool/box, replication
 disabled = consistent.test.lua
-release_disabled = catch.test.lua errinj.test.lua gc.test.lua gc_no_space.test.lua before_replace.test.lua quorum.test.lua recover_missing_xlog.test.lua sync.test.lua long_row_timeout.test.lua gh-4739-vclock-assert.test.lua gh-4730-applier-rollback.test.lua
+release_disabled = catch.test.lua errinj.test.lua gc.test.lua gc_no_space.test.lua before_replace.test.lua qsync_errinj.test.lua quorum.test.lua recover_missing_xlog.test.lua sync.test.lua long_row_timeout.test.lua gh-4739-vclock-assert.test.lua gh-4730-applier-rollback.test.lua
 config = suite.cfg
 lua_libs = lua/fast_replica.lua lua/rlimit.lua
 use_unix_sockets = True
-- 
2.21.1 (Apple Git-122.3)

  parent reply	other threads:[~2020-06-30 23:00 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <cover.1593723973.git.sergeyb@tarantool.org>
2020-06-29 23:15 ` [Tarantool-patches] [PATCH v2 00/19] Sync replication Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 01/19] replication: introduce space.is_sync option Vladislav Shpilevoy
2020-06-30 23:00     ` Vladislav Shpilevoy
2020-07-01 15:55       ` Sergey Ostanevich
2020-07-01 23:46         ` Vladislav Shpilevoy
2020-07-02  8:25       ` Serge Petrenko
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 10/19] txn_limbo: add ROLLBACK processing Vladislav Shpilevoy
2020-07-05 15:29     ` Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 11/19] box: rework local_recovery to use async txn_commit Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 12/19] replication: support ROLLBACK and CONFIRM during recovery Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 13/19] replication: add test for synchro CONFIRM/ROLLBACK Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 14/19] applier: remove writer_cond Vladislav Shpilevoy
2020-07-02  9:13     ` Serge Petrenko
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 15/19] applier: send heartbeat not only on commit, but on any write Vladislav Shpilevoy
2020-07-01 23:55     ` Vladislav Shpilevoy
2020-07-03 12:23     ` Serge Petrenko
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 16/19] txn_limbo: add diag_set in txn_limbo_wait_confirm Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 17/19] replication: delay initial join until confirmation Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 18/19] replication: only send confirmed data during final join Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 19/19] replication: block async transactions when not empty limbo Vladislav Shpilevoy
2020-07-01 17:12     ` Sergey Ostanevich
2020-07-01 23:47       ` Vladislav Shpilevoy
2020-07-03 12:28     ` Serge Petrenko
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 02/19] replication: introduce replication_synchro_* cfg options Vladislav Shpilevoy
2020-07-01 16:05     ` Sergey Ostanevich
2020-07-01 23:46       ` Vladislav Shpilevoy
2020-07-02  8:29     ` Serge Petrenko
2020-07-02 23:36       ` Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 03/19] txn: add TXN_WAIT_ACK flag Vladislav Shpilevoy
2020-07-01 17:14     ` Sergey Ostanevich
2020-07-01 23:46     ` Vladislav Shpilevoy
2020-07-02  8:30     ` Serge Petrenko
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 04/19] replication: make sync transactions wait quorum Vladislav Shpilevoy
2020-06-30 23:00     ` Vladislav Shpilevoy
2020-07-02  8:48     ` Serge Petrenko
2020-07-03 21:16       ` Vladislav Shpilevoy
2020-07-05 16:05     ` Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 05/19] xrow: introduce CONFIRM and ROLLBACK entries Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 06/19] txn: introduce various reasons for txn rollback Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 07/19] replication: write and read CONFIRM entries Vladislav Shpilevoy
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 08/19] replication: add support of qsync to the snapshot machinery Vladislav Shpilevoy
2020-07-02  8:52     ` Serge Petrenko
2020-07-08 11:43     ` Leonid Vasiliev
2020-06-29 23:15   ` [Tarantool-patches] [PATCH v2 09/19] txn_limbo: add timeout when waiting for acks Vladislav Shpilevoy
2020-06-29 23:22   ` [Tarantool-patches] [PATCH v2 00/19] Sync replication Vladislav Shpilevoy
2020-06-30 23:00   ` Vladislav Shpilevoy [this message]
2020-07-03 12:32     ` [Tarantool-patches] [PATCH v2 20/19] replication: add test for quorum 1 Serge Petrenko
2020-07-02 21:13   ` [Tarantool-patches] [PATCH 1/4] replication: regression test on gh-5119 [not fixed] sergeyb
2020-07-02 21:13   ` [Tarantool-patches] [PATCH 2/4] replication: add advanced tests for sync replication sergeyb
2020-07-02 22:46     ` Sergey Bronnikov
2020-07-02 23:20     ` Vladislav Shpilevoy
2020-07-06 12:30       ` Sergey Bronnikov
2020-07-06 23:31     ` Vladislav Shpilevoy
2020-07-07 12:12       ` Sergey Bronnikov
2020-07-07 20:57         ` Vladislav Shpilevoy
2020-07-08 12:07           ` Sergey Bronnikov
2020-07-08 22:13             ` Vladislav Shpilevoy
2020-07-09  9:39               ` Sergey Bronnikov
2020-07-02 21:13   ` [Tarantool-patches] [PATCH 3/4] replication: add tests for sync replication with anon replica sergeyb
2020-07-06 23:31     ` Vladislav Shpilevoy
2020-07-02 21:13   ` [Tarantool-patches] [PATCH 4/4] replication: add tests for sync replication with snapshots sergeyb
2020-07-02 22:46     ` Sergey Bronnikov
2020-07-02 23:20     ` Vladislav Shpilevoy
2020-07-06 23:31     ` Vladislav Shpilevoy
2020-07-07 16:00       ` Sergey Bronnikov
2020-07-06 23:31   ` [Tarantool-patches] [PATCH] Add new error injection constant ERRINJ_SYNC_TIMEOUT Vladislav Shpilevoy
2020-07-10  0:50   ` [Tarantool-patches] [PATCH v2 00/19] Sync replication Vladislav Shpilevoy
2020-07-10  7:40   ` Kirill Yukhin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=9418f015-311b-8d25-0b44-96a3b8443683@tarantool.org \
    --to=v.shpilevoy@tarantool.org \
    --cc=sergepetrenko@tarantool.org \
    --cc=tarantool-patches@dev.tarantool.org \
    --subject='Re: [Tarantool-patches] [PATCH v2 20/19] replication: add test for quorum 1' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox