[Tarantool-patches] [PATCH] replication: removing anonymous replicas from synchro quorum

[Yan Shtunder]

Transactions have to committed after they reaches quorum of "real"
cluster members. Therefore, anonymous replicas don't have to
participate in the quorum.

Closes #5418
---
Issue: https://github.com/tarantool/tarantool/issues/5418
Patch: https://github.com/tarantool/tarantool/tree/yshtunder/gh-5418-qsync-with-anon-replicas

 src/box/relay.cc                          |   3 +-
 test/replication/qsync_with_anon.result   | 187 +++-------------------
 test/replication/qsync_with_anon.test.lua |  83 ++--------
 3 files changed, 36 insertions(+), 237 deletions(-)

diff --git a/src/box/relay.cc b/src/box/relay.cc
index 115037fc3..4d5f9a625 100644
--- a/src/box/relay.cc
+++ b/src/box/relay.cc
@@ -515,6 +515,7 @@ tx_status_update(struct cmsg *msg)
 	struct replication_ack ack;
 	ack.source = status->relay->replica->id;
 	ack.vclock = &status->vclock;
+	bool anon = status->relay->replica->anon;
 	/*
 	 * Let pending synchronous transactions know, which of
 	 * them were successfully sent to the replica. Acks are
@@ -522,7 +523,7 @@ tx_status_update(struct cmsg *msg)
 	 * the single master in 100% so far). Other instances wait
 	 * for master's CONFIRM message instead.
 	 */
-	if (txn_limbo.owner_id == instance_id) {
+	if (txn_limbo.owner_id == instance_id && !anon) {
 		txn_limbo_ack(&txn_limbo, ack.source,
 			      vclock_get(ack.vclock, instance_id));
 	}
diff --git a/test/replication/qsync_with_anon.result b/test/replication/qsync_with_anon.result
index 6a2952a32..d847a77aa 100644
--- a/test/replication/qsync_with_anon.result
+++ b/test/replication/qsync_with_anon.result
@@ -1,195 +1,57 @@
 -- test-run result file version 2
-env = require('test_run')
- | ---
- | ...
-test_run = env.new()
- | ---
- | ...
-engine = test_run:get_cfg('engine')
- | ---
- | ...
-
-orig_synchro_quorum = box.cfg.replication_synchro_quorum
- | ---
- | ...
-orig_synchro_timeout = box.cfg.replication_synchro_timeout
+test_run = require('test_run').new()
  | ---
  | ...

 NUM_INSTANCES = 2
  | ---
  | ...
-BROKEN_QUORUM = NUM_INSTANCES + 1
- | ---
- | ...

 box.schema.user.grant('guest', 'replication')
  | ---
  | ...
-
--- Setup a cluster with anonymous replica.
-test_run:cmd('create server replica_anon with rpl_master=default, script="replication/anon1.lua"')
- | ---
- | - true
- | ...
-test_run:cmd('start server replica_anon')
- | ---
- | - true
- | ...
-test_run:cmd('switch replica_anon')
- | ---
- | - true
- | ...
-
--- [RFC, Asynchronous replication] successful transaction applied on async
--- replica.
--- Testcase setup.
-test_run:switch('default')
- | ---
- | - true
- | ...
-box.cfg{replication_synchro_quorum=NUM_INSTANCES, replication_synchro_timeout=1000}
- | ---
- | ...
-_ = box.schema.space.create('sync', {is_sync=true, engine=engine})
- | ---
- | ...
-_ = box.space.sync:create_index('pk')
- | ---
- | ...
--- Testcase body.
-test_run:switch('default')
- | ---
- | - true
- | ...
-box.space.sync:insert{1} -- success
- | ---
- | - [1]
- | ...
-box.space.sync:insert{2} -- success
- | ---
- | - [2]
- | ...
-box.space.sync:insert{3} -- success
- | ---
- | - [3]
- | ...
-test_run:cmd('switch replica_anon')
- | ---
- | - true
- | ...
-box.space.sync:select{} -- 1, 2, 3
- | ---
- | - - [1]
- |   - [2]
- |   - [3]
- | ...
--- Testcase cleanup.
-test_run:switch('default')
- | ---
- | - true
- | ...
-box.space.sync:drop()
- | ---
- | ...
-
--- [RFC, Asynchronous replication] failed transaction rolled back on async
--- replica.
--- Testcase setup.
-box.cfg{replication_synchro_quorum = NUM_INSTANCES, replication_synchro_timeout = 1000}
+box.cfg{replication_synchro_quorum=NUM_INSTANCES}
  | ---
  | ...
-_ = box.schema.space.create('sync', {is_sync=true, engine=engine})
+_ = box.schema.space.create('sync', {is_sync=true})
  | ---
  | ...
 _ = box.space.sync:create_index('pk')
  | ---
  | ...
--- Write something to flush the current master's state to replica.
-_ = box.space.sync:insert{1}
- | ---
- | ...
-_ = box.space.sync:delete{1}
- | ---
- | ...

-box.cfg{replication_synchro_quorum = BROKEN_QUORUM, replication_synchro_timeout = 1000}
- | ---
- | ...
-fiber = require('fiber')
- | ---
- | ...
-ok, err = nil
- | ---
- | ...
-f = fiber.create(function()                                                     \
-    ok, err = pcall(box.space.sync.insert, box.space.sync, {1})                 \
-end)
- | ---
- | ...

-test_run:cmd('switch replica_anon')
+-- Setup a cluster with anonymous replica
+test_run:cmd('create server replica_anon with rpl_master=default,\
+              script="replication/anon1.lua"')
  | ---
  | - true
  | ...
-test_run:wait_cond(function() return box.space.sync:count() == 1 end)
+test_run:cmd('start server replica_anon')
  | ---
  | - true
  | ...
-box.space.sync:select{}
- | ---
- | - - [1]
- | ...

-test_run:switch('default')
- | ---
- | - true
- | ...
-box.cfg{replication_synchro_timeout = 0.001}
- | ---
- | ...
-test_run:wait_cond(function() return f:status() == 'dead' end)
+
+-- Testcase
+box.space.sync:insert{1}    -- error
  | ---
- | - true
+ | - error: Quorum collection for a synchronous transaction is timed out
  | ...
-box.space.sync:select{}
+box.space.sync:insert{3}    -- error
  | ---
- | - []
+ | - error: Quorum collection for a synchronous transaction is timed out
  | ...
-
 test_run:cmd('switch replica_anon')
  | ---
  | - true
  | ...
-test_run:wait_cond(function() return box.space.sync:count() == 0 end)
- | ---
- | - true
- | ...
-box.space.sync:select{}
+box.space.sync:select{}     -- []
  | ---
  | - []
  | ...

-test_run:switch('default')
- | ---
- | - true
- | ...
-box.cfg{replication_synchro_quorum=NUM_INSTANCES, replication_synchro_timeout=1000}
- | ---
- | ...
-box.space.sync:insert{1} -- success
- | ---
- | - [1]
- | ...
-test_run:cmd('switch replica_anon')
- | ---
- | - true
- | ...
-box.space.sync:select{} -- 1
- | ---
- | - - [1]
- | ...
--- Testcase cleanup.
+-- Testcase cleanup
 test_run:switch('default')
  | ---
  | - true
@@ -198,12 +60,13 @@ box.space.sync:drop()
  | ---
  | ...

--- Teardown.
-test_run:switch('default')
+
+-- Teardown
+test_run:cmd('stop server replica_anon')
  | ---
  | - true
  | ...
-test_run:cmd('stop server replica_anon')
+test_run:cmd('cleanup server replica_anon')
  | ---
  | - true
  | ...
@@ -211,15 +74,3 @@ test_run:cmd('delete server replica_anon')
  | ---
  | - true
  | ...
-box.schema.user.revoke('guest', 'replication')
- | ---
- | ...
-box.cfg{                                                                        \
-    replication_synchro_quorum = orig_synchro_quorum,                           \
-    replication_synchro_timeout = orig_synchro_timeout,                         \
-}
- | ---
- | ...
-test_run:cleanup_cluster()
- | ---
- | ...
diff --git a/test/replication/qsync_with_anon.test.lua b/test/replication/qsync_with_anon.test.lua
index d7ecaa107..2d92f08aa 100644
--- a/test/replication/qsync_with_anon.test.lua
+++ b/test/replication/qsync_with_anon.test.lua
@@ -1,84 +1,31 @@
-env = require('test_run')
-test_run = env.new()
-engine = test_run:get_cfg('engine')
-
-orig_synchro_quorum = box.cfg.replication_synchro_quorum
-orig_synchro_timeout = box.cfg.replication_synchro_timeout
+test_run = require('test_run').new()

 NUM_INSTANCES = 2
-BROKEN_QUORUM = NUM_INSTANCES + 1

 box.schema.user.grant('guest', 'replication')
-
--- Setup a cluster with anonymous replica.
-test_run:cmd('create server replica_anon with rpl_master=default, script="replication/anon1.lua"')
-test_run:cmd('start server replica_anon')
-test_run:cmd('switch replica_anon')
-
--- [RFC, Asynchronous replication] successful transaction applied on async
--- replica.
--- Testcase setup.
-test_run:switch('default')
-box.cfg{replication_synchro_quorum=NUM_INSTANCES, replication_synchro_timeout=1000}
-_ = box.schema.space.create('sync', {is_sync=true, engine=engine})
+box.cfg{replication_synchro_quorum=NUM_INSTANCES}
+_ = box.schema.space.create('sync', {is_sync=true})
 _ = box.space.sync:create_index('pk')
--- Testcase body.
-test_run:switch('default')
-box.space.sync:insert{1} -- success
-box.space.sync:insert{2} -- success
-box.space.sync:insert{3} -- success
-test_run:cmd('switch replica_anon')
-box.space.sync:select{} -- 1, 2, 3
--- Testcase cleanup.
-test_run:switch('default')
-box.space.sync:drop()

--- [RFC, Asynchronous replication] failed transaction rolled back on async
--- replica.
--- Testcase setup.
-box.cfg{replication_synchro_quorum = NUM_INSTANCES, replication_synchro_timeout = 1000}
-_ = box.schema.space.create('sync', {is_sync=true, engine=engine})
-_ = box.space.sync:create_index('pk')
--- Write something to flush the current master's state to replica.
-_ = box.space.sync:insert{1}
-_ = box.space.sync:delete{1}
-
-box.cfg{replication_synchro_quorum = BROKEN_QUORUM, replication_synchro_timeout = 1000}
-fiber = require('fiber')
-ok, err = nil
-f = fiber.create(function()                                                     \
-    ok, err = pcall(box.space.sync.insert, box.space.sync, {1})                 \
-end)

-test_run:cmd('switch replica_anon')
-test_run:wait_cond(function() return box.space.sync:count() == 1 end)
-box.space.sync:select{}
+-- Setup a cluster with anonymous replica
+test_run:cmd('create server replica_anon with rpl_master=default,\
+              script="replication/anon1.lua"')
+test_run:cmd('start server replica_anon')

-test_run:switch('default')
-box.cfg{replication_synchro_timeout = 0.001}
-test_run:wait_cond(function() return f:status() == 'dead' end)
-box.space.sync:select{}

+-- Testcase
+box.space.sync:insert{1}    -- error
+box.space.sync:insert{3}    -- error
 test_run:cmd('switch replica_anon')
-test_run:wait_cond(function() return box.space.sync:count() == 0 end)
-box.space.sync:select{}
+box.space.sync:select{}     -- []

-test_run:switch('default')
-box.cfg{replication_synchro_quorum=NUM_INSTANCES, replication_synchro_timeout=1000}
-box.space.sync:insert{1} -- success
-test_run:cmd('switch replica_anon')
-box.space.sync:select{} -- 1
--- Testcase cleanup.
+-- Testcase cleanup
 test_run:switch('default')
 box.space.sync:drop()

--- Teardown.
-test_run:switch('default')
+
+-- Teardown
 test_run:cmd('stop server replica_anon')
+test_run:cmd('cleanup server replica_anon')
 test_run:cmd('delete server replica_anon')
-box.schema.user.revoke('guest', 'replication')
-box.cfg{                                                                        \
-    replication_synchro_quorum = orig_synchro_quorum,                           \
-    replication_synchro_timeout = orig_synchro_timeout,                         \
-}
-test_run:cleanup_cluster()
--
2.25.1