MDEV-38632 ALTER EVENT doesn't re-run one-time AT event after first execution by keeper · Pull Request #5054 · MariaDB/server

keeper · 2026-05-07T20:46:40Z

A one-time event (ON SCHEDULE AT ... ON COMPLETION PRESERVE) could not
be rescheduled via ALTER EVENT after its first execution. The event
would silently fail to fire again.

Root cause: After a one-time AT event executes,
compute_next_execution_time() sets status=DISABLED and persists both
the DISABLED status and last_executed to mysql.event. When the user
reschedules with ALTER EVENT ... ENABLE, the status is updated but
last_executed remains stale. On server restart, load_events_from_db()
calls compute_next_execution_time() which sees last_executed != 0 and
unconditionally disables the event again, even though execute_at was
changed to a future time.

Fix:

event_db_repository.cc (mysql_event_fill_row): When ALTER EVENT
changes execute_at to a new value, clear last_executed in mysql.event.
This ensures the event is treated as not-yet-executed for the new
schedule.
event_data_objects.cc (compute_next_execution_time): For one-time
events, only disable if last_executed >= execute_at, meaning the event
was actually executed for the current schedule. If execute_at is after
last_executed (rescheduled), treat it as pending. This serves as a
safety net for server restarts where last_executed may persist from an
older schedule.

All new code of the whole pull request, including one or several files
that are either new files or modified ones, are contributed under the
BSD-new license. I am contributing on behalf of my employer Amazon Web
Services, Inc.

gemini-code-assist

Code Review

This pull request addresses MDEV-38632, ensuring that one-time events with ON COMPLETION PRESERVE are correctly rescheduled and re-enabled when modified via ALTER EVENT. The changes update the event queue logic to check if a one-time event is pending based on its execution timestamp and modify the database repository to clear execution history and restore the ENABLED status upon schedule changes. Review feedback highlights the need for safer error handling when retrieving timestamps in sql/event_db_repository.cc to avoid potential undefined behavior from uninitialized memory if get_date fails.

CLAassistant · 2026-05-07T21:06:07Z

All committers have signed the CLA.

gkodinov

Thank you for your contribution. Please fix the tests failing on debug builds with a dbug assert as follows:

Thread 1 (Thread 0x7f696e2c1640 (LWP 281786)):
#0  0x00007f69751019fc in pthread_kill () from /lib/x86_64-linux-gnu/libc.so.6
No symbol table info available.
#1  0x0000557c6275b316 in my_write_core (sig=6) at /home/buildbot/amd64-ubuntu-2204-debug/build/mysys/stacktrace.c:424
No locals.
#2  0x0000557c61ccebdc in handle_fatal_signal (sig=6) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/signal_handler.cc:298
        curr_time = 1778188402
        tm = {tm_sec = 22, tm_min = 13, tm_hour = 21, tm_mday = 7, tm_mon = 4, tm_year = 126, tm_wday = 4, tm_yday = 126, tm_isdst = 0, tm_gmtoff = 0, tm_zone = 0x7f6975244afb "UTC"}
        thd = 0x7f6948004e68
#3  <signal handler called>
No symbol table info available.
#4  0x00007f69751019fc in pthread_kill () from /lib/x86_64-linux-gnu/libc.so.6
No symbol table info available.
#5  0x00007f69750ad476 in raise () from /lib/x86_64-linux-gnu/libc.so.6
No symbol table info available.
#6  0x00007f69750937f3 in abort () from /lib/x86_64-linux-gnu/libc.so.6
No symbol table info available.
#7  0x00007f697509371b in ?? () from /lib/x86_64-linux-gnu/libc.so.6
No symbol table info available.
#8  0x00007f69750a4e96 in __assert_fail () from /lib/x86_64-linux-gnu/libc.so.6
No symbol table info available.
#9  0x0000557c61c85ed8 in TIME_from_longlong_datetime_packed (ltime=0x7f696e2bf830, tmp=-9223372036854775808) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/compat56.cc:270
        ymd = 140090158264344
        hms = -549755813888
        ymdhms = 1848375056
        ym = 140090796668720
        __PRETTY_FUNCTION__ = "void TIME_from_longlong_datetime_packed(MYSQL_TIME*, longlong)"
#10 0x0000557c61ca2a95 in Field_datetimef::get_TIME (this=0x7f69481b7068, ltime=0x7f696e2bf830, pos=0x7f69481eb018 "", fuzzydate={m_mode = (date_mode_t::FRAC_TRUNCATE | date_mode_t::NO_ZERO_DATE)}) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/field.cc:7387
        __PRETTY_FUNCTION__ = "virtual bool Field_datetimef::get_TIME(MYSQL_TIME*, const uchar*, date_mode_t) const"
        tmp = -9223372036854775808
#11 0x0000557c61cb84ce in Field_datetimef::get_date (this=0x7f69481b7068, ltime=0x7f696e2bf830, fuzzydate={m_mode = (date_mode_t::FRAC_TRUNCATE | date_mode_t::NO_ZERO_DATE)}) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/field.h:4122
No locals.
#12 0x0000557c61f3c213 in mysql_event_fill_row (thd=0x7f6948004e68, table=0x7f69480f1a68, et=0x7f694801b1b8, sp=0x0, sql_mode=0, is_update=1 '\001') at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/event_db_repository.cc:342
        old_execute_at = {year = 0, month = 0, day = 0, hour = 0, minute = 0, second = 0, second_part = 0, neg = 0 '\000', time_type = MYSQL_TIMESTAMP_DATE}
        schedule_changed = false
        tz_name = 0x557c638c3980 <tz_SYSTEM_name>
        time = {year = 1970, month = 1, day = 2, hour = 0, minute = 0, second = 0, second_part = 0, neg = 0 '\000', time_type = MYSQL_TIMESTAMP_DATETIME}
        scs = 0x557c6388be60 <my_charset_utf8mb3_general1400_as_ci>
        f_num = ET_FIELD_NAME
        fields = 0x7f69481ebc68
        rs = 0
        __PRETTY_FUNCTION__ = "bool mysql_event_fill_row(THD*, TABLE*, Event_parse_data*, sp_head*, sql_mode_t, my_bool)"
#13 0x0000557c61f3d545 in Event_db_repository::update_event (this=0x557c6e07f4a0, thd=0x7f6948004e68, parse_data=0x7f694801b1b8, new_dbname=0x0, new_name=0x0) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/event_db_repository.cc:891
        scs = 0x557c6388be60 <my_charset_utf8mb3_general1400_as_ci>
        table = 0x7f69480f1a68
        sp = 0x0
        saved_mode = 0
        mdl_savepoint = {m_stmt_ticket = 0x7f69481418f0, m_trans_ticket = 0x7f694825f9d0}
        ret = 1
        __PRETTY_FUNCTION__ = "bool Event_db_repository::update_event(THD*, Event_parse_data*, LEX_CSTRING*, LEX_CSTRING*)"
#14 0x0000557c619f9917 in Events::update_event (thd=0x7f6948004e68, parse_data=0x7f694801b1b8, new_dbname=0x0, new_name=0x0) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/events.cc:530
        ret = 1665952136
        save_binlog_format = BINLOG_FORMAT_STMT
        new_element = 0x557c61a55989 <MDL_context::release_transactional_locks(THD*)+209>
        __PRETTY_FUNCTION__ = "static bool Events::update_event(THD*, Event_parse_data*, LEX_CSTRING*, LEX_CSTRING*)"
#15 0x0000557c6181f97f in mysql_execute_command (thd=0x7f6948004e68, is_called_from_prepared_stmt=false) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/sql_parse.cc:5191
        res = 0
        lex = 0x7f69480094a0
        select_lex = 0x7f6948009e00
        first_table = 0x0
        all_tables = 0x0
        unit = 0x7f6948009580
        __PRETTY_FUNCTION__ = "int mysql_execute_command(THD*, bool)"
        ots = {ctx = 0x7f6948009200, traceable = false}
        orig_binlog_format = BINLOG_FORMAT_MIXED
        orig_current_stmt_binlog_format = BINLOG_FORMAT_STMT
#16 0x0000557c6182821c in mysql_parse (thd=0x7f6948004e68, rawbuf=0x7f694801b030 "ALTER EVENT event_starts_test ON SCHEDULE AT '1970-01-02 00:00:00' ON COMPLETION PRESERVE DISABLE", length=97, parser_state=0x7f696e2c01d0) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/sql_parse.cc:7941
        found_semicolon = 0x0
        error = 32617
        lex = 0x7f69480094a0
        err = false
        __PRETTY_FUNCTION__ = "void mysql_parse(THD*, char*, uint, Parser_state*)"
#17 0x0000557c61814e46 in dispatch_command (command=COM_QUERY, thd=0x7f6948004e68, packet=0x7f694808f299 "ALTER EVENT event_starts_test ON SCHEDULE AT '1970-01-02 00:00:00' ON COMPLETION PRESERVE DISABLE", packet_length=97, blocking=true) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/sql_parse.cc:1898
        packet_end = 0x7f694801b091 ""
        parser_state = {m_lip = {lookahead_token = -1, lookahead_yylval = 0x0, m_thd = 0x7f6948004e68, m_ptr = 0x7f694801b092 "\v", m_tok_start = 0x7f694801b092 "\v", m_tok_end = 0x7f694801b092 "\v", m_end_of_query = 0x7f694801b091 "", m_tok_start_prev = 0x7f694801b091 "", m_buf = 0x7f694801b030 "ALTER EVENT event_starts_test ON SCHEDULE AT '1970-01-02 00:00:00' ON COMPLETION PRESERVE DISABLE", m_buf_length = 97, m_echo = true, m_echo_saved = true, m_cpp_buf = 0x7f694801b0f0 "ALTER EVENT event_starts_test ON SCHEDULE AT '1970-01-02 00:00:00' ON COMPLETION PRESERVE DISABLE", m_cpp_ptr = 0x7f694801b151 "", m_cpp_tok_start = 0x7f694801b151 "", m_cpp_tok_start_prev = 0x7f694801b151 "", m_cpp_tok_end = 0x7f694801b151 "", m_body_utf8 = 0x0, m_body_utf8_ptr = 0x7f69481096f1 '\217' <repeats 200 times>..., m_cpp_utf8_processed_ptr = 0x0, next_state = MY_LEX_END, found_semicolon = 0x0, ignore_space = false, stmt_prepare_mode = false, multi_statements = true, hint_comment = false, yylineno = 1, m_digest = 0x0, in_comment = NO_COMMENT, in_comment_saved = (DISCARD_COMMENT | unknown: 0x5a5a5a58), m_cpp_text_start = 0x7f694801b11e "1970-01-02 00:00:00' ON COMPLETION PRESERVE DISABLE", m_cpp_text_end = 0x7f694801b131 "' ON COMPLETION PRESERVE DISABLE", m_underscore_cs = 0x0}, m_yacc = {yacc_yyss = 0x0, yacc_yyvs = 0x0, m_set_signal_info = {m_item = {0x0 <repeats 13 times>}}, m_lock_type = TL_READ_DEFAULT, m_mdl_type = MDL_SHARED_READ}, m_digest_psi = 0x7f6948008f88}
        net = 0x7f6948005270
        error = false
        do_end_of_statement = true
        log_slow_done = false
        drop_more_results = false
        __PRETTY_FUNCTION__ = "dispatch_command_return dispatch_command(enum_server_command, THD*, char*, uint, bool)"
        __FUNCTION__ = "dispatch_command"
        res = <optimized out>
#18 0x0000557c6181398c in do_command (thd=0x7f6948004e68, blocking=true) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/sql_parse.cc:1432
        return_value = DISPATCH_COMMAND_SUCCESS
        packet = 0x7f694808f298 "\003ALTER EVENT event_starts_test ON SCHEDULE AT '1970-01-02 00:00:00' ON COMPLETION PRESERVE DISABLE"
        packet_length = 98
        net = 0x7f6948005270
        command = COM_QUERY
        __PRETTY_FUNCTION__ = "dispatch_command_return do_command(THD*, bool)"
        __FUNCTION__ = "do_command"
#19 0x0000557c61a3d0d1 in do_handle_one_connection (connect=0x557c6e17f6a8, put_in_cache=true) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/sql_connect.cc:1503
        create_user = true
        thr_create_utime = 18796833249641
        thd = 0x7f6948004e68
#20 0x0000557c61a3ce77 in handle_one_connection (arg=0x557c6e0aed58) at /home/buildbot/amd64-ubuntu-2204-debug/build/sql/sql_connect.cc:1415
        connect = 0x557c6e0aed58
#21 0x0000557c6205898d in pfs_spawn_thread (arg=0x557c6e0aee38) at /home/buildbot/amd64-ubuntu-2204-debug/build/storage/perfschema/pfs.cc:2198
        typed_arg = 0x557c6e0aee38
        user_arg = 0x557c6e0aed58
        user_start_routine = 0x557c61a3ce09 <handle_one_connection(void*)>
        pfs = 0x7f69746fe940
        klass = 0x557c6d898940

keeper · 2026-05-08T23:35:48Z

Hi @gkodinov , thanks for review! I've addressed the review from Gemini, by:

Check is_null() before calling get_date on ET_FIELD_EXECUTE_AT
Check get_date() return value for both ET_FIELD_EXECUTE_AT and ET_FIELD_LAST_EXECUTED to avoid using uninitialized MYSQL_TIME

and that solves the assertion failure in debug test.

gkodinov

LGTM. So ideas on improving the test are outlined below.

I do not quite subscribe to the idea of the fix (implement the logic inside the table maintenance run instead of in the runtime data run) but since this is a preliminary review I'd leave that to the final reviewer.

Please stay tuned for the final review.

gkodinov

Hmm, one thing I've forgot: this is a bug fix. Please rebase it to 10.11.

…xecution A one-time event (ON SCHEDULE AT ... ON COMPLETION PRESERVE) could not be rescheduled via ALTER EVENT after its first execution. The event would silently fail to fire again. Root cause: After a one-time AT event executes, compute_next_execution_time() sets status=DISABLED and persists both the DISABLED status and last_executed to mysql.event. When the user reschedules with ALTER EVENT ... ENABLE, the status is updated but last_executed remains stale. On server restart, load_events_from_db() calls compute_next_execution_time() which sees last_executed != 0 and unconditionally disables the event again, even though execute_at was changed to a future time. Fix: - event_db_repository.cc (mysql_event_fill_row): When ALTER EVENT changes execute_at to a new value, clear last_executed in mysql.event. This ensures the event is treated as not-yet-executed for the new schedule. - event_data_objects.cc (compute_next_execution_time): For one-time events, only disable if last_executed >= execute_at, meaning the event was actually executed for the current schedule. If execute_at is after last_executed (rescheduled), treat it as pending. This serves as a safety net for server restarts where last_executed may persist from an older schedule. All new code of the whole pull request, including one or several files that are either new files or modified ones, are contributed under the BSD-new license. I am contributing on behalf of my employer Amazon Web Services, Inc.

keeper · 2026-05-14T00:20:04Z

To summarize my latest change:

Remove auto-re-enable heuristic
Cleanup MTR tests and revise wording in the steps
Uses --source include/restart_mysqld.inc to demonstrate the actual bug (event silently not firing after server restart despite mysql.event showing ENABLED. The test times out if the fix is not applied)
Rebase to 10.11 (and sorry for messy force pushes!)

gkodinov

LGTM. Thanks for your continued work on this.

Please stand by for the final review.

Copilot

Pull request overview

Fixes MDEV-38632 where one-time ON SCHEDULE AT ... ON COMPLETION PRESERVE events can fail to fire after being rescheduled via ALTER EVENT, especially across reload/restart scenarios where last_executed persists and causes the scheduler to treat the event as already executed.

Changes:

Clear mysql.event.last_executed on ALTER EVENT when execute_at changes (to avoid stale last_executed disabling the rescheduled event on reload).
Adjust one-time event execution logic to only auto-disable when last_executed >= execute_at (so a rescheduled execute_at after last_executed remains pending).
Add an MTR regression test and expected result for the reschedule/restart scenarios.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

File	Description
`sql/event_db_repository.cc`	Clears `last_executed` when a one-time event’s `execute_at` changes during ALTER.
`sql/event_data_objects.cc`	Refines one-time event disable check to require `last_executed >= execute_at`.
`mysql-test/main/mdev38632_alter_onetime_event.test`	Adds regression test coverage for rescheduling one-time events and restart reload behavior.
`mysql-test/main/mdev38632_alter_onetime_event.result`	Adds expected output for the new MTR test.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

sanja-byelkin · 2026-06-22T15:11:55Z

Please address copilot changes otherwise it looks OK

gkodinov · 2026-06-23T10:29:29Z

Please address copilot changes otherwise it looks OK

@sanja-byelkin The copilot got fooled by the stale PR explanation that was not edited to match the extent of the actual fix proposed. I have replied to the copilot comments now and updated the PR description.
Can you please have another look?

sanja-byelkin

The idea is good but have to be fixed.

sanja-byelkin · 2026-07-03T12:37:59Z

@@ -0,0 +1,97 @@
+#
+# MDEV-38632: ALTER EVENT doesn't run a one-time (AT) event after its first


--echo missed to be in the output

sanja-byelkin · 2026-07-03T12:38:28Z

+# MDEV-38632: ALTER EVENT doesn't run a one-time (AT) event after its first
+# execution when ON COMPLETION PRESERVE is used.
+#
+# After an AT event with ON COMPLETION PRESERVE executes, the scheduler sets


this is not needed in the test file

sanja-byelkin · 2026-07-03T12:39:52Z

+  DO INSERT INTO test.event_log(id) VALUES (NULL);
+
+--echo # Status should remain DISABLED (no schedule change)
+SELECT status FROM mysql.event WHERE db = 'test' AND name = 'mdev38632';


end version marker is missed

--echo # End of 10.11 tests

sanja-byelkin · 2026-07-03T13:46:00Z

+--source include/running_event_scheduler.inc
+
+--echo # The event should fire after server restart.
+--let $wait_timeout = 10


Why 10 sec? what is wrong with standard 30 sec?

gemini-code-assist Bot reviewed May 7, 2026

View reviewed changes

Comment thread sql/event_db_repository.cc Outdated

Comment thread sql/event_db_repository.cc Outdated

gkodinov added the External Contribution All PRs from entities outside of MariaDB Foundation, Corporation, Codership agreements. label May 8, 2026

gkodinov requested changes May 8, 2026

View reviewed changes

gkodinov self-assigned this May 8, 2026

keeper force-pushed the mdev-38632-alter-event-rerun branch from e91440e to cb709ba Compare May 8, 2026 21:55

keeper requested a review from gkodinov May 8, 2026 23:33

gkodinov approved these changes May 11, 2026

View reviewed changes

gkodinov requested changes May 11, 2026

View reviewed changes

keeper force-pushed the mdev-38632-alter-event-rerun branch from cb709ba to 556915e Compare May 14, 2026 00:07

keeper changed the base branch from main to 10.11 May 14, 2026 00:11

keeper force-pushed the mdev-38632-alter-event-rerun branch from b145e93 to 556915e Compare May 14, 2026 00:13

keeper force-pushed the mdev-38632-alter-event-rerun branch from 556915e to f441b87 Compare May 14, 2026 00:14

keeper requested a review from gkodinov May 14, 2026 00:20

gkodinov approved these changes May 14, 2026

View reviewed changes

gkodinov assigned sanja-byelkin and unassigned gkodinov May 14, 2026

sanja-byelkin requested a review from Copilot June 9, 2026 09:54

Copilot started reviewing on behalf of sanja-byelkin June 9, 2026 09:54 View session

Copilot AI reviewed Jun 9, 2026

View reviewed changes

Comment thread sql/event_db_repository.cc

Comment thread mysql-test/main/mdev38632_alter_onetime_event.test

gkodinov requested a review from sanja-byelkin June 23, 2026 10:34

sanja-byelkin requested changes Jul 7, 2026

View reviewed changes

		@@ -0,0 +1,97 @@
		#
		# MDEV-38632: ALTER EVENT doesn't run a one-time (AT) event after its first

Uh oh!

Uh oh!

Conversation

keeper commented May 7, 2026 • edited by gkodinov Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

Uh oh!

CLAassistant commented May 7, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

gkodinov left a comment

Choose a reason for hiding this comment

Uh oh!

keeper commented May 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

gkodinov left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

gkodinov left a comment

Choose a reason for hiding this comment

Uh oh!

keeper commented May 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

gkodinov left a comment

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

sanja-byelkin commented Jun 22, 2026

Uh oh!

gkodinov commented Jun 23, 2026

Uh oh!

sanja-byelkin left a comment

Choose a reason for hiding this comment

Uh oh!

sanja-byelkin Jul 3, 2026

Choose a reason for hiding this comment

Uh oh!

sanja-byelkin Jul 3, 2026

Choose a reason for hiding this comment

Uh oh!

sanja-byelkin Jul 3, 2026

Choose a reason for hiding this comment

Uh oh!

sanja-byelkin Jul 3, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Milestone

Development

Uh oh!

5 participants

keeper commented May 7, 2026 •

edited by gkodinov

Loading

CLAassistant commented May 7, 2026 •

edited

Loading

keeper commented May 8, 2026 •

edited

Loading

keeper commented May 14, 2026 •

edited

Loading