[Tarantool-patches] [PATCH v4 10/16] box: make promote always bump the term
Serge Petrenko
sergepetrenko at tarantool.org
Wed Jul 14 21:25:38 MSK 2021
When called without elections, promote resulted in multiple
PROMOTE entries for the same term. This is not correct, because all
the promotions for the same term except the first one would be ignored
as already seen.
Part-of #6034
---
src/box/box.cc | 20 ++++++++--
src/box/raft.c | 40 +++++++++++++++++++
src/box/raft.h | 4 ++
.../gh-4114-local-space-replication.result | 7 ++--
.../gh-4114-local-space-replication.test.lua | 4 +-
.../gh-6034-election-promote-bump-term.result | 21 ++++++++++
...h-6034-election-promote-bump-term.test.lua | 9 +++++
test/replication/suite.cfg | 1 +
8 files changed, 97 insertions(+), 9 deletions(-)
create mode 100644 test/replication/gh-6034-election-promote-bump-term.result
create mode 100644 test/replication/gh-6034-election-promote-bump-term.test.lua
diff --git a/src/box/box.cc b/src/box/box.cc
index 445875f8f..ac6c487e4 100644
--- a/src/box/box.cc
+++ b/src/box/box.cc
@@ -1581,6 +1581,17 @@ box_check_promote_term_changed(uint64_t promote_term)
return 0;
}
+/** Trigger a new election round but don't wait for its result. */
+static int
+box_trigger_elections(void)
+{
+ uint64_t promote_term = txn_limbo.promote_greatest_term;
+ raft_new_term(box_raft());
+ if (box_raft_wait_term_persisted() < 0)
+ return -1;
+ return box_check_promote_term_changed(promote_term);
+}
+
/** Try waiting until limbo is emptied up to given timeout. */
static int
box_try_wait_confirm(double timeout)
@@ -1731,9 +1742,12 @@ box_promote(void)
if (run_elections && box_run_elections() < 0)
return -1;
- if (try_wait &&
- box_try_wait_confirm(2 * replication_synchro_timeout) < 0)
- return -1;
+ if (try_wait) {
+ if (box_try_wait_confirm(2 * replication_synchro_timeout) < 0)
+ return -1;
+ if (box_trigger_elections() < 0)
+ return -1;
+ }
if ((wait_lsn = box_wait_limbo_acked()) < 0)
return -1;
diff --git a/src/box/raft.c b/src/box/raft.c
index 7f787c0c5..b04932cd9 100644
--- a/src/box/raft.c
+++ b/src/box/raft.c
@@ -354,6 +354,46 @@ box_raft_wait_leader_found(void)
return 0;
}
+struct raft_wait_persisted_data {
+ struct fiber *waiter;
+ uint64_t term;
+};
+
+static int
+box_raft_wait_term_persisted_f(struct trigger *trig, void *event)
+{
+ struct raft *raft = event;
+ struct raft_wait_persisted_data *data = trig->data;
+ if (raft->term >= data->term)
+ fiber_wakeup(data->waiter);
+ return 0;
+}
+
+int
+box_raft_wait_term_persisted(void)
+{
+ if (box_raft()->term == box_raft()->volatile_term)
+ return 0;
+ struct raft_wait_persisted_data data = {
+ .waiter = fiber(),
+ .term = box_raft()->volatile_term,
+ };
+ struct trigger trig;
+ trigger_create(&trig, box_raft_wait_term_persisted_f, &data, NULL);
+ raft_on_update(box_raft(), &trig);
+
+ do {
+ fiber_yield();
+ } while (box_raft()->term < data.term && !fiber_is_cancelled());
+
+ trigger_clear(&trig);
+ if (fiber_is_cancelled()) {
+ diag_set(FiberIsCancelled);
+ return -1;
+ }
+ return 0;
+}
+
void
box_raft_init(void)
{
diff --git a/src/box/raft.h b/src/box/raft.h
index 6b6136510..4c9c7306d 100644
--- a/src/box/raft.h
+++ b/src/box/raft.h
@@ -101,6 +101,10 @@ box_raft_process(struct raft_request *req, uint32_t source);
int
box_raft_wait_leader_found();
+/** Block this fiber until the current volatile term is persisted. */
+int
+box_raft_wait_term_persisted(void);
+
void
box_raft_init(void);
diff --git a/test/replication/gh-4114-local-space-replication.result b/test/replication/gh-4114-local-space-replication.result
index 9b63a4b99..e71eb60a8 100644
--- a/test/replication/gh-4114-local-space-replication.result
+++ b/test/replication/gh-4114-local-space-replication.result
@@ -45,9 +45,8 @@ test_run:cmd('switch replica')
| ---
| - true
| ...
-box.info.vclock[0]
+a = box.info.vclock[0] or 0
| ---
- | - null
| ...
box.cfg{checkpoint_count=1}
| ---
@@ -77,9 +76,9 @@ box.space.test:insert{3}
| - [3]
| ...
-box.info.vclock[0]
+assert(box.info.vclock[0] == a + 3)
| ---
- | - 3
+ | - true
| ...
test_run:cmd('switch default')
diff --git a/test/replication/gh-4114-local-space-replication.test.lua b/test/replication/gh-4114-local-space-replication.test.lua
index c18fb3b10..65fef3bf6 100644
--- a/test/replication/gh-4114-local-space-replication.test.lua
+++ b/test/replication/gh-4114-local-space-replication.test.lua
@@ -18,7 +18,7 @@ for i = 1,10 do box.space.test:insert{i} end
box.info.vclock[0] == a + 10 or box.info.vclock[0] - a
test_run:cmd('switch replica')
-box.info.vclock[0]
+a = box.info.vclock[0] or 0
box.cfg{checkpoint_count=1}
box.space.test:select{}
box.space.test:insert{1}
@@ -27,7 +27,7 @@ box.space.test:insert{2}
box.snapshot()
box.space.test:insert{3}
-box.info.vclock[0]
+assert(box.info.vclock[0] == a + 3)
test_run:cmd('switch default')
diff --git a/test/replication/gh-6034-election-promote-bump-term.result b/test/replication/gh-6034-election-promote-bump-term.result
new file mode 100644
index 000000000..8be4e8243
--- /dev/null
+++ b/test/replication/gh-6034-election-promote-bump-term.result
@@ -0,0 +1,21 @@
+-- test-run result file version 2
+test_run = require('test_run').new()
+ | ---
+ | ...
+
+-- gh-6034: test that every box.ctl.promote() bumps
+-- the instance's term. Even when elections are disabled.
+box.cfg{election_mode='off'}
+ | ---
+ | ...
+
+term = box.info.election.term
+ | ---
+ | ...
+box.ctl.promote()
+ | ---
+ | ...
+assert(box.info.election.term == term + 1)
+ | ---
+ | - true
+ | ...
diff --git a/test/replication/gh-6034-election-promote-bump-term.test.lua b/test/replication/gh-6034-election-promote-bump-term.test.lua
new file mode 100644
index 000000000..1e814bf5d
--- /dev/null
+++ b/test/replication/gh-6034-election-promote-bump-term.test.lua
@@ -0,0 +1,9 @@
+test_run = require('test_run').new()
+
+-- gh-6034: test that every box.ctl.promote() bumps
+-- the instance's term. Even when elections are disabled.
+box.cfg{election_mode='off'}
+
+term = box.info.election.term
+box.ctl.promote()
+assert(box.info.election.term == term + 1)
diff --git a/test/replication/suite.cfg b/test/replication/suite.cfg
index ae146c366..7f9014b22 100644
--- a/test/replication/suite.cfg
+++ b/test/replication/suite.cfg
@@ -48,6 +48,7 @@
"gh-5613-bootstrap-prefer-booted.test.lua": {},
"gh-6027-applier-error-show.test.lua": {},
"gh-6032-promote-wal-write.test.lua": {},
+ "gh-6034-election-promote-bump-term.test.lua": {},
"gh-6057-qsync-confirm-async-no-wal.test.lua": {},
"gh-6094-rs-uuid-mismatch.test.lua": {},
"gh-6127-election-join-new.test.lua": {},
--
2.30.1 (Apple Git-130)
More information about the Tarantool-patches
mailing list