[Tarantool-patches] [PATCH v21 3/3] test: add gh-6036-qsync-order test

[Cyrill Gorcunov via Tarantool-patches <tarantool-patches@dev.tarantool.org>]

To test that promotion requests are handled only when appropriate
write to WAL completes, because we update memory data before the
write finishes.

Note that without the patch this test fires assertion

> tarantool: src/box/txn_limbo.c:481: txn_limbo_read_rollback: Assertion `e->txn->signature >= 0' failed.

Part-of #6036

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
---
 test/replication/gh-6036-qsync-order.result   | 204 ++++++++++++++++++
 test/replication/gh-6036-qsync-order.test.lua |  97 +++++++++
 test/replication/suite.cfg                    |   1 +
 test/replication/suite.ini                    |   2 +-
 4 files changed, 303 insertions(+), 1 deletion(-)
 create mode 100644 test/replication/gh-6036-qsync-order.result
 create mode 100644 test/replication/gh-6036-qsync-order.test.lua

diff --git a/test/replication/gh-6036-qsync-order.result b/test/replication/gh-6036-qsync-order.result
new file mode 100644
index 000000000..eb3e808cb
--- /dev/null
+++ b/test/replication/gh-6036-qsync-order.result
@@ -0,0 +1,204 @@
+-- test-run result file version 2
+--
+-- gh-6036: verify that terms are locked when we're inside journal
+-- write routine, because parallel appliers may ignore the fact that
+-- the term is updated already but not yet written leading to data
+-- inconsistency.
+--
+test_run = require('test_run').new()
+ | ---
+ | ...
+
+SERVERS={"election_replica1", "election_replica2", "election_replica3"}
+ | ---
+ | ...
+test_run:create_cluster(SERVERS, "replication", {args='1 nil manual 1'})
+ | ---
+ | ...
+test_run:wait_fullmesh(SERVERS)
+ | ---
+ | ...
+
+--
+-- Create a synchro space on the master node and make
+-- sure the write processed just fine.
+test_run:switch("election_replica1")
+ | ---
+ | - true
+ | ...
+box.ctl.promote()
+ | ---
+ | ...
+s = box.schema.create_space('test', {is_sync = true})
+ | ---
+ | ...
+_ = s:create_index('pk')
+ | ---
+ | ...
+s:insert{1}
+ | ---
+ | - [1]
+ | ...
+
+test_run:switch("election_replica2")
+ | ---
+ | - true
+ | ...
+test_run:wait_lsn('election_replica2', 'election_replica1')
+ | ---
+ | ...
+
+test_run:switch("election_replica3")
+ | ---
+ | - true
+ | ...
+test_run:wait_lsn('election_replica3', 'election_replica1')
+ | ---
+ | ...
+
+--
+-- Drop connection between election_replica1 and election_replica2.
+test_run:switch("election_replica1")
+ | ---
+ | - true
+ | ...
+box.cfg({                                   \
+    replication = {                         \
+        "unix/:./election_replica1.sock",   \
+        "unix/:./election_replica3.sock",   \
+    },                                      \
+})
+ | ---
+ | ...
+--
+-- Drop connection between election_replica2 and election_replica1.
+test_run:switch("election_replica2")
+ | ---
+ | - true
+ | ...
+test_run:wait_cond(function() return box.space.test:get{1} ~= nil end)
+ | ---
+ | - true
+ | ...
+box.cfg({                                   \
+    replication = {                         \
+        "unix/:./election_replica2.sock",   \
+        "unix/:./election_replica3.sock",   \
+    },                                      \
+})
+ | ---
+ | ...
+
+--
+-- Here we have the following scheme
+--
+--              election_replica3 (will be delayed)
+--              /                \
+--    election_replica1    election_replica2
+
+--
+-- Initiate disk delay in a bit tricky way: the next write will
+-- fall into forever sleep.
+test_run:switch("election_replica3")
+ | ---
+ | - true
+ | ...
+write_cnt = box.error.injection.get("ERRINJ_WAL_WRITE_COUNT")
+ | ---
+ | ...
+--
+-- Make election_replica2 been a leader and start writting data,
+-- the PROMOTE request get queued on election_replica3 and not
+-- yet processed, same time INSERT won't complete either
+-- waiting for PROMOTE completion first. Note that we
+-- enter election_replica3 as well just to be sure the PROMOTE
+-- reached it.
+test_run:switch("election_replica2")
+ | ---
+ | - true
+ | ...
+box.ctl.promote()
+ | ---
+ | ...
+test_run:switch("election_replica3")
+ | ---
+ | - true
+ | ...
+test_run:wait_cond(function() return box.error.injection.get("ERRINJ_WAL_WRITE_COUNT") > write_cnt end)
+ | ---
+ | - true
+ | ...
+box.error.injection.set("ERRINJ_WAL_DELAY", true)
+ | ---
+ | - ok
+ | ...
+test_run:switch("election_replica2")
+ | ---
+ | - true
+ | ...
+_ = require('fiber').create(function() box.space.test:insert{2} end)
+ | ---
+ | ...
+
+--
+-- The election_replica1 node has no clue that there is a new leader
+-- and continue writing data with obsolete term. Since election_replica3
+-- is delayed now the INSERT won't proceed yet but get queued.
+test_run:switch("election_replica1")
+ | ---
+ | - true
+ | ...
+_ = require('fiber').create(function() box.space.test:insert{3} end)
+ | ---
+ | ...
+
+--
+-- Finally enable election_replica3 back. Make sure the data from new election_replica2
+-- leader get writing while old leader's data ignored.
+test_run:switch("election_replica3")
+ | ---
+ | - true
+ | ...
+box.error.injection.set('ERRINJ_WAL_DELAY', false)
+ | ---
+ | - ok
+ | ...
+test_run:wait_cond(function() return box.space.test:get{2} ~= nil end)
+ | ---
+ | - true
+ | ...
+box.space.test:select{}
+ | ---
+ | - - [1]
+ |   - [2]
+ | ...
+
+test_run:switch("default")
+ | ---
+ | - true
+ | ...
+test_run:cmd('stop server election_replica1')
+ | ---
+ | - true
+ | ...
+test_run:cmd('stop server election_replica2')
+ | ---
+ | - true
+ | ...
+test_run:cmd('stop server election_replica3')
+ | ---
+ | - true
+ | ...
+
+test_run:cmd('delete server election_replica1')
+ | ---
+ | - true
+ | ...
+test_run:cmd('delete server election_replica2')
+ | ---
+ | - true
+ | ...
+test_run:cmd('delete server election_replica3')
+ | ---
+ | - true
+ | ...
diff --git a/test/replication/gh-6036-qsync-order.test.lua b/test/replication/gh-6036-qsync-order.test.lua
new file mode 100644
index 000000000..b8df170b8
--- /dev/null
+++ b/test/replication/gh-6036-qsync-order.test.lua
@@ -0,0 +1,97 @@
+--
+-- gh-6036: verify that terms are locked when we're inside journal
+-- write routine, because parallel appliers may ignore the fact that
+-- the term is updated already but not yet written leading to data
+-- inconsistency.
+--
+test_run = require('test_run').new()
+
+SERVERS={"election_replica1", "election_replica2", "election_replica3"}
+test_run:create_cluster(SERVERS, "replication", {args='1 nil manual 1'})
+test_run:wait_fullmesh(SERVERS)
+
+--
+-- Create a synchro space on the master node and make
+-- sure the write processed just fine.
+test_run:switch("election_replica1")
+box.ctl.promote()
+s = box.schema.create_space('test', {is_sync = true})
+_ = s:create_index('pk')
+s:insert{1}
+
+test_run:switch("election_replica2")
+test_run:wait_lsn('election_replica2', 'election_replica1')
+
+test_run:switch("election_replica3")
+test_run:wait_lsn('election_replica3', 'election_replica1')
+
+--
+-- Drop connection between election_replica1 and election_replica2.
+test_run:switch("election_replica1")
+box.cfg({                                   \
+    replication = {                         \
+        "unix/:./election_replica1.sock",   \
+        "unix/:./election_replica3.sock",   \
+    },                                      \
+})
+--
+-- Drop connection between election_replica2 and election_replica1.
+test_run:switch("election_replica2")
+test_run:wait_cond(function() return box.space.test:get{1} ~= nil end)
+box.cfg({                                   \
+    replication = {                         \
+        "unix/:./election_replica2.sock",   \
+        "unix/:./election_replica3.sock",   \
+    },                                      \
+})
+
+--
+-- Here we have the following scheme
+--
+--              election_replica3 (will be delayed)
+--              /                \
+--    election_replica1    election_replica2
+
+--
+-- Initiate disk delay in a bit tricky way: the next write will
+-- fall into forever sleep.
+test_run:switch("election_replica3")
+write_cnt = box.error.injection.get("ERRINJ_WAL_WRITE_COUNT")
+--
+-- Make election_replica2 been a leader and start writting data,
+-- the PROMOTE request get queued on election_replica3 and not
+-- yet processed, same time INSERT won't complete either
+-- waiting for PROMOTE completion first. Note that we
+-- enter election_replica3 as well just to be sure the PROMOTE
+-- reached it.
+test_run:switch("election_replica2")
+box.ctl.promote()
+test_run:switch("election_replica3")
+test_run:wait_cond(function() return box.error.injection.get("ERRINJ_WAL_WRITE_COUNT") > write_cnt end)
+box.error.injection.set("ERRINJ_WAL_DELAY", true)
+test_run:switch("election_replica2")
+_ = require('fiber').create(function() box.space.test:insert{2} end)
+
+--
+-- The election_replica1 node has no clue that there is a new leader
+-- and continue writing data with obsolete term. Since election_replica3
+-- is delayed now the INSERT won't proceed yet but get queued.
+test_run:switch("election_replica1")
+_ = require('fiber').create(function() box.space.test:insert{3} end)
+
+--
+-- Finally enable election_replica3 back. Make sure the data from new election_replica2
+-- leader get writing while old leader's data ignored.
+test_run:switch("election_replica3")
+box.error.injection.set('ERRINJ_WAL_DELAY', false)
+test_run:wait_cond(function() return box.space.test:get{2} ~= nil end)
+box.space.test:select{}
+
+test_run:switch("default")
+test_run:cmd('stop server election_replica1')
+test_run:cmd('stop server election_replica2')
+test_run:cmd('stop server election_replica3')
+
+test_run:cmd('delete server election_replica1')
+test_run:cmd('delete server election_replica2')
+test_run:cmd('delete server election_replica3')
diff --git a/test/replication/suite.cfg b/test/replication/suite.cfg
index 3eee0803c..ed09b2087 100644
--- a/test/replication/suite.cfg
+++ b/test/replication/suite.cfg
@@ -59,6 +59,7 @@
     "gh-6094-rs-uuid-mismatch.test.lua": {},
     "gh-6127-election-join-new.test.lua": {},
     "gh-6035-applier-filter.test.lua": {},
+    "gh-6036-qsync-order.test.lua": {},
     "election-candidate-promote.test.lua": {},
     "*": {
         "memtx": {"engine": "memtx"},
diff --git a/test/replication/suite.ini b/test/replication/suite.ini
index 77eb95f49..080e4fbf4 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 qsync_advanced.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 gh-5140-qsync-casc-rollback.test.lua gh-5144-qsync-dup-confirm.test.lua gh-5167-qsync-rollback-snap.test.lua gh-5430-qsync-promote-crash.test.lua gh-5430-cluster-mvcc.test.lua  gh-5506-election-on-off.test.lua gh-5536-wal-limit.test.lua hang_on_synchro_fail.test.lua anon_register_gap.test.lua gh-5213-qsync-applier-order.test.lua gh-5213-qsync-applier-order-3.test.lua gh-6027-applier-error-show.test.lua gh-6032-promote-wal-write.test.lua gh-6057-qsync-confirm-async-no-wal.test.lua gh-5447-downstream-lag.test.lua gh-4040-invalid-msgpack.test.lua
+release_disabled = catch.test.lua errinj.test.lua gc.test.lua gc_no_space.test.lua before_replace.test.lua qsync_advanced.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 gh-5140-qsync-casc-rollback.test.lua gh-5144-qsync-dup-confirm.test.lua gh-5167-qsync-rollback-snap.test.lua gh-5430-qsync-promote-crash.test.lua gh-5430-cluster-mvcc.test.lua  gh-5506-election-on-off.test.lua gh-5536-wal-limit.test.lua hang_on_synchro_fail.test.lua anon_register_gap.test.lua gh-5213-qsync-applier-order.test.lua gh-5213-qsync-applier-order-3.test.lua gh-6027-applier-error-show.test.lua gh-6032-promote-wal-write.test.lua gh-6057-qsync-confirm-async-no-wal.test.lua gh-5447-downstream-lag.test.lua gh-4040-invalid-msgpack.test.lua gh-6036-qsync-order.test.lua
 config = suite.cfg
 lua_libs = lua/fast_replica.lua lua/rlimit.lua
 use_unix_sockets = True
-- 
2.31.1