[Tarantool-patches] [PATCH] replication: fill replicaset.applier.vclock after local recovery

Yan Shtunder ya.shtunder at gmail.com
Mon Aug 9 13:09:31 MSK 2021


replicaset.applier.vclock is initialized in replication_init(),
which happens before local recovery. If some changes are come
frome some instance via applier that applier.vclock will equal 0.
This means that if some wild master send this node already applied
data, the node will apply the same data twice.

Closes #6028
---
Issue: https://github.com/tarantool/tarantool/issues/6028
Patch: https://github.com/tarantool/tarantool/tree/yshtunder/gh-6028-applier-vclock

 src/box/applier.cc                            |  5 ++
 src/box/box.cc                                |  7 +++
 src/lib/core/errinj.h                         |  1 +
 test/box/errinj.result                        |  1 +
 test/replication/gh-6028-replica.lua          | 13 ++++
 .../gh-6028-vclock-is-empty.result            | 60 +++++++++++++++++++
 .../gh-6028-vclock-is-empty.test.lua          | 24 ++++++++
 7 files changed, 111 insertions(+)
 create mode 100644 test/replication/gh-6028-replica.lua
 create mode 100644 test/replication/gh-6028-vclock-is-empty.result
 create mode 100644 test/replication/gh-6028-vclock-is-empty.test.lua

diff --git a/src/box/applier.cc b/src/box/applier.cc
index 07fe7f5c7..9855b8d37 100644
--- a/src/box/applier.cc
+++ b/src/box/applier.cc
@@ -1230,6 +1230,11 @@ applier_subscribe(struct applier *applier)
 	struct vclock vclock;
 	vclock_create(&vclock);
 	vclock_copy(&vclock, &replicaset.vclock);
+
+	ERROR_INJECT(ERRINJ_REPLICASET_VCLOCK, {
+		vclock_create(&vclock);
+	});
+
 	/*
 	 * Stop accepting local rows coming from a remote
 	 * instance as soon as local WAL starts accepting writes.
diff --git a/src/box/box.cc b/src/box/box.cc
index ab7d983c9..f5cd63c9e 100644
--- a/src/box/box.cc
+++ b/src/box/box.cc
@@ -3451,6 +3451,13 @@ box_cfg_xc(void)
 		bootstrap(&instance_uuid, &replicaset_uuid,
 			  &is_bootstrap_leader);
 	}
+
+	/*
+	 * replicaset.applier.vclock is filled with real
+	 * value where local restore has already completed
+	 */
+	vclock_copy(&replicaset.applier.vclock, &replicaset.vclock);
+
 	fiber_gc();

 	/*
diff --git a/src/lib/core/errinj.h b/src/lib/core/errinj.h
index 359174b16..fcd856fbb 100644
--- a/src/lib/core/errinj.h
+++ b/src/lib/core/errinj.h
@@ -152,6 +152,7 @@ struct errinj {
 	_(ERRINJ_STDIN_ISATTY, ERRINJ_INT, {.iparam = -1}) \
 	_(ERRINJ_SNAP_COMMIT_FAIL, ERRINJ_BOOL, {.bparam = false}) \
 	_(ERRINJ_IPROTO_SINGLE_THREAD_STAT, ERRINJ_INT, {.iparam = -1}) \
+	_(ERRINJ_REPLICASET_VCLOCK, ERRINJ_BOOL, {.bparam = false}) \

 ENUM0(errinj_id, ERRINJ_LIST);
 extern struct errinj errinjs[];
diff --git a/test/box/errinj.result b/test/box/errinj.result
index 43daf5f0f..62e37bbdd 100644
--- a/test/box/errinj.result
+++ b/test/box/errinj.result
@@ -70,6 +70,7 @@ evals
   - ERRINJ_RELAY_REPORT_INTERVAL: 0
   - ERRINJ_RELAY_SEND_DELAY: false
   - ERRINJ_RELAY_TIMEOUT: 0
+  - ERRINJ_REPLICASET_VCLOCK: false
   - ERRINJ_REPLICA_JOIN_DELAY: false
   - ERRINJ_SIO_READ_MAX: -1
   - ERRINJ_SNAP_COMMIT_DELAY: false
diff --git a/test/replication/gh-6028-replica.lua b/test/replication/gh-6028-replica.lua
new file mode 100644
index 000000000..5669cc4e9
--- /dev/null
+++ b/test/replication/gh-6028-replica.lua
@@ -0,0 +1,13 @@
+#!/usr/bin/env tarantool
+
+require('console').listen(os.getenv('ADMIN'))
+
+box.error.injection.set("ERRINJ_REPLICASET_VCLOCK", true)
+
+box.cfg({
+    listen              = os.getenv("LISTEN"),
+    replication         = {os.getenv("MASTER"), os.getenv("LISTEN")},
+    memtx_memory        = 107374182,
+})
+
+box.error.injection.set("ERRINJ_REPLICASET_VCLOCK", false)
diff --git a/test/replication/gh-6028-vclock-is-empty.result b/test/replication/gh-6028-vclock-is-empty.result
new file mode 100644
index 000000000..0b103bb6e
--- /dev/null
+++ b/test/replication/gh-6028-vclock-is-empty.result
@@ -0,0 +1,60 @@
+-- test-run result file version 2
+test_run = require('test_run').new()
+ | ---
+ | ...
+
+box.schema.user.grant('guest', 'replication')
+ | ---
+ | ...
+s = box.schema.create_space('test')
+ | ---
+ | ...
+_ = s:create_index('pk')
+ | ---
+ | ...
+
+
+-- Case 1
+test_run:cmd('create server replica with rpl_master=default,\
+              script="replication/gh-6028-replica.lua"')
+ | ---
+ | - true
+ | ...
+test_run:cmd('start server replica')
+ | ---
+ | - true
+ | ...
+
+test_run:cmd('stop server replica')
+ | ---
+ | - true
+ | ...
+s:insert{1}
+ | ---
+ | - [1]
+ | ...
+
+
+-- Case 2
+test_run:cmd('start server replica')
+ | ---
+ | - true
+ | ...
+s:insert{2}
+ | ---
+ | - [2]
+ | ...
+
+
+test_run:cmd('stop server replica')
+ | ---
+ | - true
+ | ...
+test_run:cmd('cleanup server replica')
+ | ---
+ | - true
+ | ...
+test_run:cmd('delete server replica')
+ | ---
+ | - true
+ | ...
diff --git a/test/replication/gh-6028-vclock-is-empty.test.lua b/test/replication/gh-6028-vclock-is-empty.test.lua
new file mode 100644
index 000000000..ba14eca55
--- /dev/null
+++ b/test/replication/gh-6028-vclock-is-empty.test.lua
@@ -0,0 +1,24 @@
+test_run = require('test_run').new()
+
+box.schema.user.grant('guest', 'replication')
+s = box.schema.create_space('test')
+_ = s:create_index('pk')
+
+
+-- Case 1
+test_run:cmd('create server replica with rpl_master=default,\
+              script="replication/gh-6028-replica.lua"')
+test_run:cmd('start server replica')
+
+test_run:cmd('stop server replica')
+s:insert{1}
+
+
+-- Case 2
+test_run:cmd('start server replica')
+s:insert{2}
+
+
+test_run:cmd('stop server replica')
+test_run:cmd('cleanup server replica')
+test_run:cmd('delete server replica')
--
2.25.1



More information about the Tarantool-patches mailing list