[Tarantool-patches] [PATCH 1/2] raft: fix crash on sm restart during WAL write
Vladislav Shpilevoy
v.shpilevoy at tarantool.org
Sat Nov 7 19:45:31 MSK 2020
Raft state machine crashed if was restarted during a WAL write
being in progress. When the machine was started, it didn't assume
there still can be a not finished WAL write from the time it was
enabled earlier.
The patch makes it continue waiting for the write end.
Part of #5506
---
src/box/raft.c | 13 ++++-
.../gh-5506-election-on-off.result | 55 +++++++++++++++++++
.../gh-5506-election-on-off.test.lua | 31 +++++++++++
test/replication/suite.cfg | 1 +
test/replication/suite.ini | 2 +-
5 files changed, 98 insertions(+), 4 deletions(-)
create mode 100644 test/replication/gh-5506-election-on-off.result
create mode 100644 test/replication/gh-5506-election-on-off.test.lua
diff --git a/src/box/raft.c b/src/box/raft.c
index 914b0d68f..3a99a0f26 100644
--- a/src/box/raft.c
+++ b/src/box/raft.c
@@ -857,13 +857,20 @@ raft_sm_start(void)
{
say_info("RAFT: start state machine");
assert(!ev_is_active(&raft.timer));
- assert(!raft.is_write_in_progress);
assert(!raft.is_enabled);
assert(raft.state == RAFT_STATE_FOLLOWER);
raft.is_enabled = true;
raft.is_candidate = raft.is_cfg_candidate;
- if (!raft.is_candidate) {
- /* Nop. */;
+ if (raft.is_write_in_progress) {
+ /*
+ * Nop. If write is in progress, the state machine is frozen. It
+ * is continued when write ends.
+ */
+ } else if (!raft.is_candidate) {
+ /*
+ * Nop. When a node is not a candidate, it can't initiate
+ * elections anyway, so it does not need to monitor the leader.
+ */
} else if (raft.leader != 0) {
raft_sm_wait_leader_dead();
} else {
diff --git a/test/replication/gh-5506-election-on-off.result b/test/replication/gh-5506-election-on-off.result
new file mode 100644
index 000000000..1a718396f
--- /dev/null
+++ b/test/replication/gh-5506-election-on-off.result
@@ -0,0 +1,55 @@
+-- test-run result file version 2
+test_run = require('test_run').new()
+ | ---
+ | ...
+
+old_election_mode = box.cfg.election_mode
+ | ---
+ | ...
+old_replication_timeout = box.cfg.replication_timeout
+ | ---
+ | ...
+
+--
+-- gh-5506: Raft state machine crashed in case there was a WAL write in
+-- progress, and Raft was disabled + enabled back immediately. It didn't assume
+-- that there can be a not finished WAL write when Raft is just enabled.
+--
+
+-- Start a WAL write and wait when it starts.
+box.error.injection.set("ERRINJ_WAL_DELAY_COUNTDOWN", 0)
+ | ---
+ | - ok
+ | ...
+box.cfg{ \
+ election_mode = 'candidate', \
+ replication_timeout = 0.1, \
+}
+ | ---
+ | ...
+test_run:wait_cond(function() \
+ return box.error.injection.get("ERRINJ_WAL_DELAY") \
+end)
+ | ---
+ | - true
+ | ...
+
+-- Restart the state machine. It should notice the not finished WAL write and
+-- continue waiting.
+box.cfg{election_mode = 'off'}
+ | ---
+ | ...
+box.cfg{election_mode = 'candidate'}
+ | ---
+ | ...
+box.error.injection.set("ERRINJ_WAL_DELAY", false)
+ | ---
+ | - ok
+ | ...
+
+box.cfg{ \
+ election_mode = old_election_mode, \
+ replication_timeout = old_replication_timeout, \
+}
+ | ---
+ | ...
diff --git a/test/replication/gh-5506-election-on-off.test.lua b/test/replication/gh-5506-election-on-off.test.lua
new file mode 100644
index 000000000..290408f06
--- /dev/null
+++ b/test/replication/gh-5506-election-on-off.test.lua
@@ -0,0 +1,31 @@
+test_run = require('test_run').new()
+
+old_election_mode = box.cfg.election_mode
+old_replication_timeout = box.cfg.replication_timeout
+
+--
+-- gh-5506: Raft state machine crashed in case there was a WAL write in
+-- progress, and Raft was disabled + enabled back immediately. It didn't assume
+-- that there can be a not finished WAL write when Raft is just enabled.
+--
+
+-- Start a WAL write and wait when it starts.
+box.error.injection.set("ERRINJ_WAL_DELAY_COUNTDOWN", 0)
+box.cfg{ \
+ election_mode = 'candidate', \
+ replication_timeout = 0.1, \
+}
+test_run:wait_cond(function() \
+ return box.error.injection.get("ERRINJ_WAL_DELAY") \
+end)
+
+-- Restart the state machine. It should notice the not finished WAL write and
+-- continue waiting.
+box.cfg{election_mode = 'off'}
+box.cfg{election_mode = 'candidate'}
+box.error.injection.set("ERRINJ_WAL_DELAY", false)
+
+box.cfg{ \
+ election_mode = old_election_mode, \
+ replication_timeout = old_replication_timeout, \
+}
diff --git a/test/replication/suite.cfg b/test/replication/suite.cfg
index 8fd62fdb8..f2addebda 100644
--- a/test/replication/suite.cfg
+++ b/test/replication/suite.cfg
@@ -16,6 +16,7 @@
"gh-4424-misc-orphan-on-reconfiguration-error.test.lua": {},
"gh-5426-election-on-off.test.lua": {},
"gh-5433-election-restart-recovery.test.lua": {},
+ "gh-5506-election-on-off.test.lua": {},
"once.test.lua": {},
"on_replace.test.lua": {},
"status.test.lua": {},
diff --git a/test/replication/suite.ini b/test/replication/suite.ini
index 6136c934f..34ee32550 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
+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-5506-election-on-off.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)
More information about the Tarantool-patches
mailing list