mirror/mariadb
1
0
Fork 0
mirror of https://github.com/MariaDB/server.git synced 2025-01-24 07:44:22 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions
mariadb/sql/event_queue.cc
Dmitry Lenev 6bf6272fda Patch that refactors global read lock implementation and fixes 
bug #57006 "Deadlock between HANDLER and FLUSH TABLES WITH READ
LOCK" and bug #54673 "It takes too long to get readlock for
'FLUSH TABLES WITH READ LOCK'".

The first bug manifested itself as a deadlock which occurred
when a connection, which had some table open through HANDLER
statement, tried to update some data through DML statement
while another connection tried to execute FLUSH TABLES WITH
READ LOCK concurrently.

What happened was that FTWRL in the second connection managed
to perform first step of GRL acquisition and thus blocked all
upcoming DML. After that it started to wait for table open
through HANDLER statement to be flushed. When the first connection
tried to execute DML it has started to wait for GRL/the second
connection creating deadlock.

The second bug manifested itself as starvation of FLUSH TABLES
WITH READ LOCK statements in cases when there was a constant
stream of concurrent DML statements (in two or more
connections).

This has happened because requests for protection against GRL
which were acquired by DML statements were ignoring presence of
pending GRL and thus the latter was starved.

This patch solves both these problems by re-implementing GRL
using metadata locks.

Similar to the old implementation acquisition of GRL in new
implementation is two-step. During the first step we block
all concurrent DML and DDL statements by acquiring global S
metadata lock (each DML and DDL statement acquires global IX
lock for its duration). During the second step we block commits
by acquiring global S lock in COMMIT namespace (commit code
acquires global IX lock in this namespace).

Note that unlike in old implementation acquisition of
protection against GRL in DML and DDL is semi-automatic.
We assume that any statement which should be blocked by GRL
will either open and acquires write-lock on tables or acquires
metadata locks on objects it is going to modify. For any such
statement global IX metadata lock is automatically acquired
for its duration.

The first problem is solved because waits for GRL become
visible to deadlock detector in metadata locking subsystem
and thus deadlocks like one in the first bug become impossible.

The second problem is solved because global S locks which
are used for GRL implementation are given preference over
IX locks which are acquired by concurrent DML (and we can
switch to fair scheduling in future if needed).

Important change:
FTWRL/GRL no longer blocks DML and DDL on temporary tables.
Before this patch behavior was not consistent in this respect:
in some cases DML/DDL statements on temporary tables were
blocked while in others they were not. Since the main use cases
for FTWRL are various forms of backups and temporary tables are
not preserved during backups we have opted for consistently
allowing DML/DDL on temporary tables during FTWRL/GRL.

Important change:
This patch changes thread state names which are used when
DML/DDL of FTWRL is waiting for global read lock. It is now
either "Waiting for global read lock" or "Waiting for commit
lock" depending on the stage on which FTWRL is.

Incompatible change:
To solve deadlock in events code which was exposed by this
patch we have to replace LOCK_event_metadata mutex with
metadata locks on events. As result we have to prohibit
DDL on events under LOCK TABLES.

This patch also adds extensive test coverage for interaction
of DML/DDL and FTWRL.

Performance of new and old global read lock implementations
in sysbench tests were compared. There were no significant
difference between new and old implementations.

mysql-test/include/check_ftwrl_compatible.inc:
  Added helper script which allows to check that a statement is
  compatible with FLUSH TABLES WITH READ LOCK.
mysql-test/include/check_ftwrl_incompatible.inc:
  Added helper script which allows to check that a statement is
  incompatible with FLUSH TABLES WITH READ LOCK.
mysql-test/include/handler.inc:
  Adjusted test case to the fact that now DROP TABLE closes
  open HANDLERs for the table to be dropped before checking
  if there active FTWRL in this connection.
mysql-test/include/wait_show_condition.inc:
  Fixed small error in the timeout message. The correct name
  of variable used as parameter for this script is "$condition"
  and not "$wait_condition".
mysql-test/r/delayed.result:
  Added test coverage for scenario which triggered assert in
  metadata locking subsystem.
mysql-test/r/events_2.result:
  Updated test results after prohibiting event DDL operations
  under LOCK TABLES.
mysql-test/r/flush.result:
  Added test coverage for bug #57006 "Deadlock between HANDLER
  and FLUSH TABLES WITH READ LOCK".
mysql-test/r/flush_read_lock.result:
  Added test coverage for various aspects of FLUSH TABLES WITH
  READ LOCK functionality.
mysql-test/r/flush_read_lock_kill.result:
  Adjusted test case after replacing custom global read lock
  implementation with one based on metadata locks. Use new
  debug_sync point. Do not disable concurrent inserts as now
  InnoDB we always use InnoDB table.
mysql-test/r/handler_innodb.result:
  Adjusted test case to the fact that now DROP TABLE closes
  open HANDLERs for the table to be dropped before checking
  if there active FTWRL in this connection.
mysql-test/r/handler_myisam.result:
  Adjusted test case to the fact that now DROP TABLE closes
  open HANDLERs for the table to be dropped before checking
  if there active FTWRL in this connection.
mysql-test/r/mdl_sync.result:
  Adjusted test case after replacing custom global read lock
  implementation with one based on metadata locks. Replaced
  usage of GRL-specific debug_sync's with appropriate sync
  points in MDL subsystem.
mysql-test/suite/perfschema/r/dml_setup_instruments.result:
  Updated test results after removing global
  COND_global_read_lock condition variable.
mysql-test/suite/perfschema/r/func_file_io.result:
  Ensure that this test doesn't affect subsequent tests.
  At the end of its execution enable back P_S instrumentation
  which this test disables at some point.
mysql-test/suite/perfschema/r/func_mutex.result:
  Ensure that this test doesn't affect subsequent tests.
  At the end of its execution enable back P_S instrumentation
  which this test disables at some point.
mysql-test/suite/perfschema/r/global_read_lock.result:
  Adjusted test case to take into account that new GRL
  implementation is based on MDL.
mysql-test/suite/perfschema/r/server_init.result:
  Adjusted test case after replacing custom global read
  lock implementation with one based on MDL and replacing
  LOCK_event_metadata mutex with metadata lock.
mysql-test/suite/perfschema/t/func_file_io.test:
  Ensure that this test doesn't affect subsequent tests.
  At the end of its execution enable back P_S instrumentation
  which this test disables at some point.
mysql-test/suite/perfschema/t/func_mutex.test:
  Ensure that this test doesn't affect subsequent tests.
  At the end of its execution enable back P_S instrumentation
  which this test disables at some point.
mysql-test/suite/perfschema/t/global_read_lock.test:
  Adjusted test case to take into account that new GRL
  implementation is based on MDL.
mysql-test/suite/perfschema/t/server_init.test:
  Adjusted test case after replacing custom global read
  lock implementation with one based on MDL and replacing
  LOCK_event_metadata mutex with metadata lock.
mysql-test/suite/rpl/r/rpl_tmp_table_and_DDL.result:
  Updated test results after prohibiting event DDL under
  LOCK TABLES.
mysql-test/t/delayed.test:
  Added test coverage for scenario which triggered assert in
  metadata locking subsystem.
mysql-test/t/events_2.test:
  Updated test case after prohibiting event DDL operations
  under LOCK TABLES.
mysql-test/t/flush.test:
  Added test coverage for bug #57006 "Deadlock between HANDLER
  and FLUSH TABLES WITH READ LOCK".
mysql-test/t/flush_block_commit.test:
  Adjusted test case after changing thread state name which
  is used when COMMIT waits for FLUSH TABLES WITH READ LOCK
  from "Waiting for release of readlock" to "Waiting for commit
  lock".
mysql-test/t/flush_block_commit_notembedded.test:
  Adjusted test case after changing thread state name which is
  used when DML waits for FLUSH TABLES WITH READ LOCK. Now we
  use "Waiting for global read lock" in this case.
mysql-test/t/flush_read_lock.test:
  Added test coverage for various aspects of FLUSH TABLES WITH
  READ LOCK functionality.
mysql-test/t/flush_read_lock_kill-master.opt:
  We no longer need to use make_global_read_lock_block_commit_loop
  debug tag in this test. Instead we rely on an appropriate
  debug_sync point in MDL code.
mysql-test/t/flush_read_lock_kill.test:
  Adjusted test case after replacing custom global read lock
  implementation with one based on metadata locks. Use new
  debug_sync point. Do not disable concurrent inserts as now
  InnoDB we always use InnoDB table.
mysql-test/t/lock_multi.test:
  Adjusted test case after changing thread state names which
  are used when DML or DDL waits for FLUSH TABLES WITH READ
  LOCK to "Waiting for global read lock".
mysql-test/t/mdl_sync.test:
  Adjusted test case after replacing custom global read lock
  implementation with one based on metadata locks. Replaced
  usage of GRL-specific debug_sync's with appropriate sync
  points in MDL subsystem. Updated thread state names which
  are used when DDL waits for FTWRL.
mysql-test/t/trigger_notembedded.test:
  Adjusted test case after changing thread state names which
  are used when DML or DDL waits for FLUSH TABLES WITH READ
  LOCK to "Waiting for global read lock".
sql/event_data_objects.cc:
  Removed Event_queue_element::status/last_executed_changed
  members and Event_queue_element::update_timing_fields()
  method. We no longer use this class for updating mysql.events
  once event is chosen for execution. Accesses to instances of
  this class in scheduler thread require protection by
  Event_queue::LOCK_event_queue mutex and we try to avoid
  updating table while holding this lock.
sql/event_data_objects.h:
  Removed Event_queue_element::status/last_executed_changed
  members and Event_queue_element::update_timing_fields()
  method. We no longer use this class for updating mysql.events
  once event is chosen for execution. Accesses to instances of
  this class in scheduler thread require protection by
  Event_queue::LOCK_event_queue mutex and we try to avoid
  updating table while holding this lock.
sql/event_db_repository.cc:
  - Changed Event_db_repository methods to not release all
    metadata locks once they are done updating mysql.events
    table. This allows to keep metadata lock protecting
    against GRL and lock protecting particular event around
    until corresponding DDL statement is written to the binary
    log.
  - Removed logic for conditional update of "status" and
    "last_executed" fields from update_timing_fields_for_event()
    method. In the only case when this method is called now
    "last_executed" is always modified and tracking change
    of "status" is too much hassle.
sql/event_db_repository.h:
  Removed logic for conditional update of "status" and
  "last_executed" fields from Event_db_repository::
  update_timing_fields_for_event() method.
  In the only case when this method is called now "last_executed"
  is always modified and tracking change of "status" field is
  too much hassle.
sql/event_queue.cc:
  Changed event scheduler code not to update mysql.events
  table while holding Event_queue::LOCK_event_queue mutex.
  Doing so led to a deadlock with a new GRL implementation.
  This deadlock didn't occur with old implementation due to
  fact that code acquiring protection against GRL ignored
  pending GRL requests (which lead to GRL starvation).
  One of goals of new implementation is to disallow GRL
  starvation and so we have to solve problem with this
  deadlock in a different way.
sql/events.cc:
  Changed methods of Events class to acquire protection
  against GRL while perfoming DDL statement and keep it
  until statement is written to the binary log.
  Unfortunately this step together with new GRL implementation
  exposed deadlock involving Events::LOCK_event_metadata
  and GRL. To solve it Events::LOCK_event_metadata mutex was
  replaced with a metadata lock on event. As a side-effect
  events DDL has to be prohibited under LOCK TABLES even in
  cases when mysql.events table was explicitly locked for
  write.
sql/events.h:
  Replaced Events::LOCK_event_metadata mutex with a metadata
  lock on event.
sql/ha_ndbcluster.cc:
  Updated code after replacing custom global read lock
  implementation with one based on MDL. Since MDL subsystem
  should now be able to detect deadlocks involving metadata
  locks and GRL there is no need for special handling of
  active GRL.
sql/handler.cc:
  Replaced custom implementation of global read lock with
  one based on metadata locks. Consequently when doing
  commit instead of calling method of Global_read_lock
  class to acquire protection against GRL we simply acquire
  IX in COMMIT namespace.
sql/lock.cc:
  Replaced custom implementation of global read lock with
  one based on metadata locks. This step allows to expose
  wait for GRL to deadlock detector of MDL subsystem and
  thus succesfully resolve deadlocks similar to one behind
  bug #57006 "Deadlock between HANDLER and FLUSH TABLES
  WITH READ LOCK". It also solves problem with GRL starvation
  described in bug #54673 "It takes too long to get readlock
  for 'FLUSH TABLES WITH READ LOCK'" since metadata locks used
  by GRL give preference to FTWRL statement instead of DML
  statements (if needed in future this can be changed to
  fair scheduling).
  
  Similar to old implementation of acquisition of GRL is
  two-step. During the first step we block all concurrent
  DML and DDL statements by acquiring global S metadata lock
  (each DML and DDL statement acquires global IX lock for
  its duration). During the second step we block commits by
  acquiring global S lock in COMMIT namespace (commit code
  acquires global IX lock in this namespace).
  
  Note that unlike in old implementation acquisition of
  protection against GRL in DML and DDL is semi-automatic.
  We assume that any statement which should be blocked by GRL
  will either open and acquires write-lock on tables or acquires
  metadata locks on objects it is going to modify. For any such
  statement global IX metadata lock is automatically acquired
  for its duration.
  
  To support this change:
  - Global_read_lock::lock/unlock_global_read_lock and
    make_global_read_lock_block_commit methods were changed
    accordingly.
  - Global_read_lock::wait_if_global_read_lock() and
    start_waiting_global_read_lock() methods were dropped.
    It is now responsibility of code acquiring metadata locks
    opening tables to acquire protection against GRL by
    explicitly taking global IX lock with statement duration.
  - Global variables, mutex and condition variable used by
    old implementation was removed.
  - lock_routine_name() was changed to use statement duration for
    its global IX lock. It was also renamed to lock_object_name()
    as it now also used to take metadata locks on events.
  - Global_read_lock::set_explicit_lock_duration() was added which
    allows not to release locks used for GRL when leaving prelocked
    mode.
sql/lock.h:
  - Renamed lock_routine_name() to lock_object_name() and changed
    its signature to allow its usage for events.
  - Removed broadcast_refresh() function. It is no longer needed
    with new GRL implementation.
sql/log_event.cc:
  Release metadata locks with statement duration at the end
  of processing legacy event for LOAD DATA. This ensures that
  replication thread processing such event properly releases
  its protection against global read lock.
sql/mdl.cc:
  Changed MDL subsystem to support new MDL-based implementation
  of global read lock.
  
  Added COMMIT and EVENTS namespaces for metadata locks. Changed
  thread state name for GLOBAL namespace to "Waiting for global
  read lock".
  
  Optimized MDL_map::find_or_insert() method to avoid taking
  m_mutex mutex when looking up MDL_lock objects for GLOBAL
  or COMMIT namespaces. We keep pre-created MDL_lock objects
  for these namespaces around and simply return pointers to
  these global objects when needed.
  
  Changed MDL_lock/MDL_scoped_lock to properly handle
  notification of insert delayed handler threads when FTWRL
  takes global S lock.
  
  Introduced concept of lock duration. In addition to locks with
  transaction duration which work in the way which is similar to
  how locks worked before (i.e. they are released at the end of
  transaction), locks with statement and explicit duration were
  introduced.
  Locks with statement duration are automatically released at the
  end of statement. Locks with explicit duration require explicit
  release and obsolete concept of transactional sentinel.
  
  * Changed MDL_request and MDL_ticket classes to support notion
    of duration.
  * Changed MDL_context to keep locks with different duration in
    different lists. Changed code handling ticket list to take
    this into account.
  * Changed methods responsible for releasing locks to take into
    account duration of tickets. Particularly public
    MDL_context::release_lock() method now only can release
    tickets with explicit duration (there is still internal
    method which allows to specify duration). To release locks
    with statement or transaction duration one have to use
    release_statement/transactional_locks() methods.
  * Concept of savepoint for MDL subsystem now has to take into
    account locks with statement duration. Consequently
    MDL_savepoint class was introduced and methods working with
    savepoints were updated accordingly.
  * Added methods which allow to set duration for one or all
    locks in the context.
sql/mdl.h:
  Changed MDL subsystem to support new MDL-based implementation
  of global read lock.
  
  Added COMMIT and EVENTS namespaces for metadata locks.
  
  Introduced concept of lock duration. In addition to locks with
  transaction duration which work in the way which is similar to
  how locks worked before (i.e. they are released at the end of
  transaction), locks with statement and explicit duration were
  introduced.
  Locks with statement duration are automatically released at the
  end of statement. Locks with explicit duration require explicit
  release and obsolete concept of transactional sentinel.
  
  * Changed MDL_request and MDL_ticket classes to support notion
    of duration.
  * Changed MDL_context to keep locks with different duration in
    different lists. Changed code handling ticket list to take
    this into account.
  * Changed methods responsible for releasing locks to take into
    account duration of tickets. Particularly public
    MDL_context::release_lock() method now only can release
    tickets with explicit duration (there is still internal
    method which allows to specify duration). To release locks
    with statement or transaction duration one have to use
    release_statement/transactional_locks() methods.
  * Concept of savepoint for MDL subsystem now has to take into
    account locks with statement duration. Consequently
    MDL_savepoint class was introduced and methods working with
    savepoints were updated accordingly.
  * Added methods which allow to set duration for one or all
    locks in the context.
sql/mysqld.cc:
  Removed global mutex and condition variables which were used
  by old implementation of GRL.
  Also we no longer need to initialize Events::LOCK_event_metadata
  mutex as it was replaced with metadata locks on events.
sql/mysqld.h:
  Removed global variable, mutex and condition variables which
  were used by old implementation of GRL.
sql/rpl_rli.cc:
  When slave thread closes tables which were open for handling
  of RBR events ensure that it releases global IX lock which
  was acquired as protection against GRL.
sql/sp.cc:
  Adjusted code to the new signature of lock_object/routine_name(),
  to the fact that one now needs specify duration of lock when
  initializing MDL_request and to the fact that savepoints for MDL
  subsystem are now represented by MDL_savepoint class.
sql/sp_head.cc:
  Ensure that statements in stored procedures release statement
  metadata locks and thus release their protectiong against GRL
  in proper moment in time.
  Adjusted code to the fact that one now needs specify duration
  of lock when initializing MDL_request.
sql/sql_admin.cc:
  Adjusted code to the fact that one now needs specify duration
  of lock when initializing MDL_request.
sql/sql_base.cc:
  - Implemented support for new approach to acquiring protection
    against global read lock. We no longer acquire such protection
    explicitly on the basis of statement flags. Instead we always
    rely on code which is responsible for acquiring metadata locks
    on object to be changed acquiring this protection. This is
    achieved by acquiring global IX metadata lock with statement
    duration. Code doing this also responsible for checking that
    current connection has no active GRL by calling an
    Global_read_lock::can_acquire_protection() method.
    Changed code in open_table() and lock_table_names()
    accordingly.
    Note that as result of this change DDL and DML on temporary
    tables is always compatible with GRL (before it was
    incompatible in some cases and compatible in other cases).
  - To speed-up code acquiring protection against GRL introduced
    m_has_protection_against_grl member in Open_table_context
    class. It indicates that protection was already acquired
    sometime during open_tables() execution and new attempts
    can be skipped.
  - Thanks to new GRL implementation calls to broadcast_refresh()
    became unnecessary and were removed.
  - Adjusted code to the fact that one now needs specify duration
    of lock when initializing MDL_request and to the fact that
    savepoints for MDL subsystem are now represented by
    MDL_savepoint class.
sql/sql_base.h:
  Adjusted code to the fact that savepoints for MDL subsystem are
  now represented by MDL_savepoint class.
  Also introduced Open_table_context::m_has_protection_against_grl
  member which allows to avoid acquiring protection against GRL
  while opening tables if such protection was already acquired.
sql/sql_class.cc:
  Changed THD::leave_locked_tables_mode() after transactional
  sentinel for metadata locks was obsoleted by introduction of
  locks with explicit duration.
sql/sql_class.h:
  - Adjusted code to the fact that savepoints for MDL subsystem
    are now represented by MDL_savepoint class.
  - Changed Global_read_lock class according to changes in
    global read lock implementation:
    * wait_if_global_read_lock and start_waiting_global_read_lock
      are now gone. Instead code needing protection against GRL
      has to acquire global IX metadata lock with statement
      duration itself. To help it new can_acquire_protection()
      was introduced. Also as result of the above change
      m_protection_count member is gone too.
    * Added m_mdl_blocks_commits_lock member to store metadata
      lock blocking commits.
    * Adjusted code to the fact that concept of transactional
      sentinel was obsoleted by concept of lock duration.
  - Removed CF_PROTECT_AGAINST_GRL flag as it is no longer
    necessary. New GRL implementation acquires protection
    against global read lock automagically when statement
    acquires metadata locks on tables or other objects it
    is going to change.
sql/sql_db.cc:
  Adjusted code to the fact that one now needs specify duration
  of lock when initializing MDL_request.
sql/sql_handler.cc:
  Removed call to broadcast_refresh() function. It is no longer
  needed with new GRL implementation.
  Adjusted code after introducing duration concept for metadata
  locks. Particularly to the fact transactional sentinel was
  replaced with explicit duration.
sql/sql_handler.h:
  Renamed mysql_ha_move_tickets_after_trans_sentinel() to
  mysql_ha_set_explicit_lock_duration() after transactional
  sentinel was obsoleted by locks with explicit duration.
sql/sql_insert.cc:
  Adjusted code handling delaying inserts after switching to
  new GRL implementation. Now connection thread initiating
  delayed insert has to acquire global IX lock in addition
  to metadata lock on table being inserted into. This IX lock
  protects against GRL and similarly to SW lock on table being
  inserted into has to be passed to handler thread in order to
  avoid deadlocks.
sql/sql_lex.cc:
  LEX::protect_against_global_read_lock member is no longer
  necessary since protection against GRL is automatically
  taken by code acquiring metadata locks/opening tables.
sql/sql_lex.h:
  LEX::protect_against_global_read_lock member is no longer
  necessary since protection against GRL is automatically
  taken by code acquiring metadata locks/opening tables.
sql/sql_parse.cc:
  - Implemented support for new approach to acquiring protection
    against global read lock. We no longer acquire such protection
    explicitly on the basis of statement flags. Instead we always
    rely on code which is responsible for acquiring metadata locks
    on object to be changed acquiring this protection. This is
    achieved by acquiring global IX metadata lock with statement
    duration. This lock is automatically released at the end of
    statement execution.
  - Changed implementation of CREATE/DROP PROCEDURE/FUNCTION not
    to release metadata locks and thus protection against of GRL
    in the middle of statement execution.
  - Adjusted code to the fact that one now needs specify duration
    of lock when initializing MDL_request and to the fact that
    savepoints for MDL subsystem are now represented by
    MDL_savepoint class.
sql/sql_prepare.cc:
  Adjusted code to the to the fact that savepoints for MDL
  subsystem are now represented by MDL_savepoint class.
sql/sql_rename.cc:
  With new GRL implementation there is no need to explicitly
  acquire protection against GRL before renaming tables.
  This happens automatically in code which acquires metadata
  locks on tables being renamed.
sql/sql_show.cc:
  Adjusted code to the fact that one now needs specify duration
  of lock when initializing MDL_request and to the fact that
  savepoints for MDL subsystem are now represented by
  MDL_savepoint class.
sql/sql_table.cc:
  - With new GRL implementation there is no need to explicitly
    acquire protection against GRL before dropping tables.
    This happens automatically in code which acquires metadata
    locks on tables being dropped.
  - Changed mysql_alter_table() not to release lock on new table
    name explicitly and to rely on automatic release of locks
    at the end of statement instead. This was necessary since
    now MDL_context::release_lock() is supported only for locks
    for explicit duration.
sql/sql_trigger.cc:
  With new GRL implementation there is no need to explicitly
  acquire protection against GRL before changing table triggers.
  This happens automatically in code which acquires metadata
  locks on tables which triggers are to be changed.
sql/sql_update.cc:
  Fix bug exposed by GRL testing. During prepare phase acquire
  only S metadata locks instead of SW locks to keep prepare of
  multi-UPDATE compatible with concurrent LOCK TABLES WRITE
  and global read lock.
sql/sql_view.cc:
  With new GRL implementation there is no need to explicitly
  acquire protection against GRL before creating view.
  This happens automatically in code which acquires metadata
  lock on view to be created.
sql/sql_yacc.yy:
  LEX::protect_against_global_read_lock member is no longer
  necessary since protection against GRL is automatically
  taken by code acquiring metadata locks/opening tables.
sql/table.cc:
  Adjusted code to the fact that one now needs specify duration
  of lock when initializing MDL_request.
sql/table.h:
  Adjusted code to the fact that one now needs specify duration
  of lock when initializing MDL_request.
sql/transaction.cc:
  Replaced custom implementation of global read lock with
  one based on metadata locks. Consequently when doing
  commit instead of calling method of Global_read_lock
  class to acquire protection against GRL we simply acquire
  IX in COMMIT namespace.
  Also adjusted code to the fact that MDL savepoint is now
  represented by MDL_savepoint class.
2010-11-11 20:11:05 +03:00

824 lines
22 KiB
C++
Raw Blame History

/* Copyright (C) 2004-2006 MySQL AB, 2008-2009 Sun Microsystems, Inc
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; version 2 of the License.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */
#include "sql_priv.h"
#include "unireg.h"
#include "event_queue.h"
#include "event_data_objects.h"
#include "event_db_repository.h"
#include "events.h"
#include "sql_audit.h"
#include "tztime.h" // my_tz_find, my_tz_OFFSET0, struct Time_zone
#include "log.h" // sql_print_error
#include "sql_class.h" // struct THD
/**
@addtogroup Event_Scheduler
@{
*/
#define EVENT_QUEUE_INITIAL_SIZE 30
#define EVENT_QUEUE_EXTENT 30
#ifdef __GNUC__
#if __GNUC__ >= 2
#define SCHED_FUNC __FUNCTION__
#endif
#else
#define SCHED_FUNC "<unknown>"
#endif
#define LOCK_QUEUE_DATA() lock_data(SCHED_FUNC, __LINE__)
#define UNLOCK_QUEUE_DATA() unlock_data(SCHED_FUNC, __LINE__)
/*
Compares the execute_at members of two Event_queue_element instances.
Used as callback for the prioritized queue when shifting
elements inside.
SYNOPSIS
event_queue_element_data_compare_q()
vptr Not used (set it to NULL)
a First Event_queue_element object
b Second Event_queue_element object
RETURN VALUE
-1 a->execute_at < b->execute_at
0 a->execute_at == b->execute_at
1 a->execute_at > b->execute_at
NOTES
execute_at.second_part is not considered during comparison
*/
extern "C" int event_queue_element_compare_q(void *, uchar *, uchar *);
int event_queue_element_compare_q(void *vptr, uchar* a, uchar *b)
{
Event_queue_element *left = (Event_queue_element *)a;
Event_queue_element *right = (Event_queue_element *)b;
my_time_t lhs = left->execute_at;
my_time_t rhs = right->execute_at;
if (left->status == Event_parse_data::DISABLED)
return right->status != Event_parse_data::DISABLED;
if (right->status == Event_parse_data::DISABLED)
return 1;
return (lhs < rhs ? -1 : (lhs > rhs ? 1 : 0));
}
/*
Constructor of class Event_queue.
SYNOPSIS
Event_queue::Event_queue()
*/
Event_queue::Event_queue()
:next_activation_at(0),
mutex_last_locked_at_line(0),
mutex_last_unlocked_at_line(0),
mutex_last_attempted_lock_at_line(0),
mutex_last_locked_in_func("n/a"),
mutex_last_unlocked_in_func("n/a"),
mutex_last_attempted_lock_in_func("n/a"),
mutex_queue_data_locked(FALSE),
mutex_queue_data_attempting_lock(FALSE),
waiting_on_cond(FALSE)
{
mysql_mutex_init(key_LOCK_event_queue, &LOCK_event_queue, MY_MUTEX_INIT_FAST);
mysql_cond_init(key_COND_queue_state, &COND_queue_state, NULL);
}
Event_queue::~Event_queue()
{
deinit_queue();
mysql_mutex_destroy(&LOCK_event_queue);
mysql_cond_destroy(&COND_queue_state);
}
/*
This is a queue's constructor. Until this method is called, the
queue is unusable. We don't use a C++ constructor instead in
order to be able to check the return value. The queue is
initialized once at server startup. Initialization can fail in
case of a failure reading events from the database or out of
memory.
SYNOPSIS
Event_queue::init()
RETURN VALUE
FALSE OK
TRUE Error
*/
bool
Event_queue::init_queue(THD *thd)
{
DBUG_ENTER("Event_queue::init_queue");
DBUG_PRINT("enter", ("this: 0x%lx", (long) this));
LOCK_QUEUE_DATA();
if (init_queue_ex(&queue, EVENT_QUEUE_INITIAL_SIZE , 0 /*offset*/,
0 /*max_on_top*/, event_queue_element_compare_q,
NULL, EVENT_QUEUE_EXTENT))
{
sql_print_error("Event Scheduler: Can't initialize the execution queue");
goto err;
}
UNLOCK_QUEUE_DATA();
DBUG_RETURN(FALSE);
err:
UNLOCK_QUEUE_DATA();
DBUG_RETURN(TRUE);
}
/*
Deinits the queue. Remove all elements from it and destroys them
too.
SYNOPSIS
Event_queue::deinit_queue()
*/
void
Event_queue::deinit_queue()
{
DBUG_ENTER("Event_queue::deinit_queue");
LOCK_QUEUE_DATA();
empty_queue();
delete_queue(&queue);
UNLOCK_QUEUE_DATA();
DBUG_VOID_RETURN;
}
/**
Adds an event to the queue.
Compute the next execution time for an event, and if it is still
active, add it to the queue. Otherwise delete it.
The object is left intact in case of an error. Otherwise
the queue container assumes ownership of it.
@param[in] thd thread handle
@param[in] new_element a new element to add to the queue
@param[out] created set to TRUE if no error and the element is
added to the queue, FALSE otherwise
@retval TRUE an error occured. The value of created is undefined,
the element was not deleted.
@retval FALSE success
*/
bool
Event_queue::create_event(THD *thd, Event_queue_element *new_element,
bool *created)
{
DBUG_ENTER("Event_queue::create_event");
DBUG_PRINT("enter", ("thd: 0x%lx et=%s.%s", (long) thd,
new_element->dbname.str, new_element->name.str));
/* Will do nothing if the event is disabled */
new_element->compute_next_execution_time();
if (new_element->status != Event_parse_data::ENABLED)
{
delete new_element;
*created= FALSE;
DBUG_RETURN(FALSE);
}
DBUG_PRINT("info", ("new event in the queue: 0x%lx", (long) new_element));
LOCK_QUEUE_DATA();
*created= (queue_insert_safe(&queue, (uchar *) new_element) == FALSE);
dbug_dump_queue(thd->query_start());
mysql_cond_broadcast(&COND_queue_state);
UNLOCK_QUEUE_DATA();
DBUG_RETURN(!*created);
}
/*
Updates an event from the scheduler queue
SYNOPSIS
Event_queue::update_event()
thd Thread
dbname Schema of the event
name Name of the event
new_schema New schema, in case of RENAME TO, otherwise NULL
new_name New name, in case of RENAME TO, otherwise NULL
*/
void
Event_queue::update_event(THD *thd, LEX_STRING dbname, LEX_STRING name,
Event_queue_element *new_element)
{
DBUG_ENTER("Event_queue::update_event");
DBUG_PRINT("enter", ("thd: 0x%lx et=[%s.%s]", (long) thd, dbname.str, name.str));
if ((new_element->status == Event_parse_data::DISABLED) ||
(new_element->status == Event_parse_data::SLAVESIDE_DISABLED))
{
DBUG_PRINT("info", ("The event is disabled."));
/*
Destroy the object but don't skip to end: because we may have to remove
object from the cache.
*/
delete new_element;
new_element= NULL;
}
else
new_element->compute_next_execution_time();
LOCK_QUEUE_DATA();
find_n_remove_event(dbname, name);
/* If not disabled event */
if (new_element)
{
DBUG_PRINT("info", ("new event in the queue: 0x%lx", (long) new_element));
queue_insert_safe(&queue, (uchar *) new_element);
mysql_cond_broadcast(&COND_queue_state);
}
dbug_dump_queue(thd->query_start());
UNLOCK_QUEUE_DATA();
DBUG_VOID_RETURN;
}
/*
Drops an event from the queue
SYNOPSIS
Event_queue::drop_event()
thd Thread
dbname Schema of the event to drop
name Name of the event to drop
*/
void
Event_queue::drop_event(THD *thd, LEX_STRING dbname, LEX_STRING name)
{
DBUG_ENTER("Event_queue::drop_event");
DBUG_PRINT("enter", ("thd: 0x%lx db :%s name: %s", (long) thd,
dbname.str, name.str));
LOCK_QUEUE_DATA();
find_n_remove_event(dbname, name);
dbug_dump_queue(thd->query_start());
UNLOCK_QUEUE_DATA();
/*
We don't signal here because the scheduler will catch the change
next time it wakes up.
*/
DBUG_VOID_RETURN;
}
/*
Drops all events from the in-memory queue and disk that match
certain pattern evaluated by a comparator function
SYNOPSIS
Event_queue::drop_matching_events()
thd THD
pattern A pattern string
comparator The function to use for comparing
RETURN VALUE
>=0 Number of dropped events
NOTE
Expected is the caller to acquire lock on LOCK_event_queue
*/
void
Event_queue::drop_matching_events(THD *thd, LEX_STRING pattern,
bool (*comparator)(LEX_STRING, Event_basic *))
{
uint i= 0;
DBUG_ENTER("Event_queue::drop_matching_events");
DBUG_PRINT("enter", ("pattern=%s", pattern.str));
while (i < queue.elements)
{
Event_queue_element *et= (Event_queue_element *) queue_element(&queue, i);
DBUG_PRINT("info", ("[%s.%s]?", et->dbname.str, et->name.str));
if (comparator(pattern, et))
{
/*
The queue is ordered. If we remove an element, then all elements
after it will shift one position to the left, if we imagine it as
an array from left to the right. In this case we should not
increment the counter and the (i < queue.elements) condition is ok.
*/
queue_remove(&queue, i);
delete et;
}
else
i++;
}
/*
We don't call mysql_cond_broadcast(&COND_queue_state);
If we remove the top event:
1. The queue is empty. The scheduler will wake up at some time and
realize that the queue is empty. If create_event() comes inbetween
it will signal the scheduler
2. The queue is not empty, but the next event after the previous top,
won't be executed any time sooner than the element we removed. Hence,
we may not notify the scheduler and it will realize the change when it
wakes up from timedwait.
*/
DBUG_VOID_RETURN;
}
/*
Drops all events from the in-memory queue and disk that are from
certain schema.
SYNOPSIS
Event_queue::drop_schema_events()
thd HD
schema The schema name
*/
void
Event_queue::drop_schema_events(THD *thd, LEX_STRING schema)
{
DBUG_ENTER("Event_queue::drop_schema_events");
LOCK_QUEUE_DATA();
drop_matching_events(thd, schema, event_basic_db_equal);
UNLOCK_QUEUE_DATA();
DBUG_VOID_RETURN;
}
/*
Searches for an event in the queue
SYNOPSIS
Event_queue::find_n_remove_event()
db The schema of the event to find
name The event to find
NOTE
The caller should do the locking also the caller is responsible for
actual signalling in case an event is removed from the queue.
*/
void
Event_queue::find_n_remove_event(LEX_STRING db, LEX_STRING name)
{
uint i;
DBUG_ENTER("Event_queue::find_n_remove_event");
for (i= 0; i < queue.elements; ++i)
{
Event_queue_element *et= (Event_queue_element *) queue_element(&queue, i);
DBUG_PRINT("info", ("[%s.%s]==[%s.%s]?", db.str, name.str,
et->dbname.str, et->name.str));
if (event_basic_identifier_equal(db, name, et))
{
queue_remove(&queue, i);
delete et;
break;
}
}
DBUG_VOID_RETURN;
}
/*
Recalculates activation times in the queue. There is one reason for
that. Because the values (execute_at) by which the queue is ordered are
changed by calls to compute_next_execution_time() on a request from the
scheduler thread, if it is not running then the values won't be updated.
Once the scheduler is started again the values has to be recalculated
so they are right for the current time.
SYNOPSIS
Event_queue::recalculate_activation_times()
thd Thread
*/
void
Event_queue::recalculate_activation_times(THD *thd)
{
uint i;
DBUG_ENTER("Event_queue::recalculate_activation_times");
LOCK_QUEUE_DATA();
DBUG_PRINT("info", ("%u loaded events to be recalculated", queue.elements));
for (i= 0; i < queue.elements; i++)
{
((Event_queue_element*)queue_element(&queue, i))->compute_next_execution_time();
}
queue_fix(&queue);
/*
The disabled elements are moved to the end during the `fix`.
Start from the end and remove all of the elements which are
disabled. When we find the first non-disabled one we break, as we
have removed all. The queue has been ordered in a way the disabled
events are at the end.
*/
for (i= queue.elements; i > 0; i--)
{
Event_queue_element *element = (Event_queue_element*)queue_element(&queue, i - 1);
if (element->status != Event_parse_data::DISABLED)
break;
/*
This won't cause queue re-order, because we remove
always the last element.
*/
queue_remove(&queue, i - 1);
delete element;
}
UNLOCK_QUEUE_DATA();
/*
XXX: The events are dropped only from memory and not from disk
even if `drop_list[j]->dropped` is TRUE. There will be still on the
disk till next server restart.
Please add code here to do it.
*/
DBUG_VOID_RETURN;
}
/*
Empties the queue and destroys the Event_queue_element objects in the
queue.
SYNOPSIS
Event_queue::empty_queue()
NOTE
Should be called with LOCK_event_queue locked
*/
void
Event_queue::empty_queue()
{
uint i;
DBUG_ENTER("Event_queue::empty_queue");
DBUG_PRINT("enter", ("Purging the queue. %u element(s)", queue.elements));
sql_print_information("Event Scheduler: Purging the queue. %u events",
queue.elements);
/* empty the queue */
for (i= 0; i < queue.elements; ++i)
{
Event_queue_element *et= (Event_queue_element *) queue_element(&queue, i);
delete et;
}
resize_queue(&queue, 0);
DBUG_VOID_RETURN;
}
/*
Dumps the queue to the trace log.
SYNOPSIS
Event_queue::dbug_dump_queue()
now Current timestamp
*/
void
Event_queue::dbug_dump_queue(time_t now)
{
#ifndef DBUG_OFF
Event_queue_element *et;
uint i;
DBUG_ENTER("Event_queue::dbug_dump_queue");
DBUG_PRINT("info", ("Dumping queue . Elements=%u", queue.elements));
for (i = 0; i < queue.elements; i++)
{
et= ((Event_queue_element*)queue_element(&queue, i));
DBUG_PRINT("info", ("et: 0x%lx name: %s.%s", (long) et,
et->dbname.str, et->name.str));
DBUG_PRINT("info", ("exec_at: %lu starts: %lu ends: %lu execs_so_far: %u "
"expr: %ld et.exec_at: %ld now: %ld "
"(et.exec_at - now): %d if: %d",
(long) et->execute_at, (long) et->starts,
(long) et->ends, et->execution_count,
(long) et->expression, (long) et->execute_at,
(long) now, (int) (et->execute_at - now),
et->execute_at <= now));
}
DBUG_VOID_RETURN;
#endif
}
static const char *queue_empty_msg= "Waiting on empty queue";
static const char *queue_wait_msg= "Waiting for next activation";
/*
Checks whether the top of the queue is elligible for execution and
returns an Event_job_data instance in case it should be executed.
`now` is compared against `execute_at` of the top element in the queue.
SYNOPSIS
Event_queue::get_top_for_execution_if_time()
thd [in] Thread
event_name [out] The object to execute
RETURN VALUE
FALSE No error. event_name != NULL
TRUE Serious error
*/
bool
Event_queue::get_top_for_execution_if_time(THD *thd,
Event_queue_element_for_exec **event_name)
{
bool ret= FALSE;
*event_name= NULL;
my_time_t last_executed;
int status;
DBUG_ENTER("Event_queue::get_top_for_execution_if_time");
LOCK_QUEUE_DATA();
for (;;)
{
Event_queue_element *top= NULL;
/* Break loop if thd has been killed */
if (thd->killed)
{
DBUG_PRINT("info", ("thd->killed=%d", thd->killed));
goto end;
}
if (!queue.elements)
{
/* There are no events in the queue */
next_activation_at= 0;
/* Release any held audit resources before waiting */
mysql_audit_release(thd);
/* Wait on condition until signaled. Release LOCK_queue while waiting. */
cond_wait(thd, NULL, queue_empty_msg, SCHED_FUNC, __LINE__);
continue;
}
top= ((Event_queue_element*) queue_element(&queue, 0));
thd->set_current_time(); /* Get current time */
next_activation_at= top->execute_at;
if (next_activation_at > thd->query_start())
{
/*
Not yet time for top event, wait on condition with
time or until signaled. Release LOCK_queue while waiting.
*/
struct timespec top_time;
set_timespec(top_time, next_activation_at - thd->query_start());
/* Release any held audit resources before waiting */
mysql_audit_release(thd);
cond_wait(thd, &top_time, queue_wait_msg, SCHED_FUNC, __LINE__);
continue;
}
if (!(*event_name= new Event_queue_element_for_exec()) ||
(*event_name)->init(top->dbname, top->name))
{
ret= TRUE;
break;
}
DBUG_PRINT("info", ("Ready for execution"));
top->mark_last_executed(thd);
if (top->compute_next_execution_time())
top->status= Event_parse_data::DISABLED;
DBUG_PRINT("info", ("event %s status is %d", top->name.str, top->status));
top->execution_count++;
(*event_name)->dropped= top->dropped;
/*
Save new values of last_executed timestamp and event status on stack
in order to be able to update event description in system table once
QUEUE_DATA lock is released.
*/
last_executed= top->last_executed;
status= top->status;
if (top->status == Event_parse_data::DISABLED)
{
DBUG_PRINT("info", ("removing from the queue"));
sql_print_information("Event Scheduler: Last execution of %s.%s. %s",
top->dbname.str, top->name.str,
top->dropped? "Dropping.":"");
delete top;
queue_remove(&queue, 0);
}
else
queue_replaced(&queue);
dbug_dump_queue(thd->query_start());
break;
}
end:
UNLOCK_QUEUE_DATA();
DBUG_PRINT("info", ("returning %d et_new: 0x%lx ",
ret, (long) *event_name));
if (*event_name)
{
DBUG_PRINT("info", ("db: %s name: %s",
(*event_name)->dbname.str, (*event_name)->name.str));
Event_db_repository *db_repository= Events::get_db_repository();
(void) db_repository->update_timing_fields_for_event(thd,
(*event_name)->dbname, (*event_name)->name,
last_executed, (ulonglong) status);
}
DBUG_RETURN(ret);
}
/*
Auxiliary function for locking LOCK_event_queue. Used by the
LOCK_QUEUE_DATA macro
SYNOPSIS
Event_queue::lock_data()
func Which function is requesting mutex lock
line On which line mutex lock is requested
*/
void
Event_queue::lock_data(const char *func, uint line)
{
DBUG_ENTER("Event_queue::lock_data");
DBUG_PRINT("enter", ("func=%s line=%u", func, line));
mutex_last_attempted_lock_in_func= func;
mutex_last_attempted_lock_at_line= line;
mutex_queue_data_attempting_lock= TRUE;
mysql_mutex_lock(&LOCK_event_queue);
mutex_last_attempted_lock_in_func= "";
mutex_last_attempted_lock_at_line= 0;
mutex_queue_data_attempting_lock= FALSE;
mutex_last_locked_in_func= func;
mutex_last_locked_at_line= line;
mutex_queue_data_locked= TRUE;
DBUG_VOID_RETURN;
}
/*
Auxiliary function for unlocking LOCK_event_queue. Used by the
UNLOCK_QUEUE_DATA macro
SYNOPSIS
Event_queue::unlock_data()
func Which function is requesting mutex unlock
line On which line mutex unlock is requested
*/
void
Event_queue::unlock_data(const char *func, uint line)
{
DBUG_ENTER("Event_queue::unlock_data");
DBUG_PRINT("enter", ("func=%s line=%u", func, line));
mutex_last_unlocked_at_line= line;
mutex_queue_data_locked= FALSE;
mutex_last_unlocked_in_func= func;
mysql_mutex_unlock(&LOCK_event_queue);
DBUG_VOID_RETURN;
}
/*
Wrapper for mysql_cond_wait/timedwait
SYNOPSIS
Event_queue::cond_wait()
thd Thread (Could be NULL during shutdown procedure)
msg Message for thd->proc_info
abstime If not null then call mysql_cond_timedwait()
func Which function is requesting cond_wait
line On which line cond_wait is requested
*/
void
Event_queue::cond_wait(THD *thd, struct timespec *abstime, const char* msg,
const char *func, uint line)
{
DBUG_ENTER("Event_queue::cond_wait");
waiting_on_cond= TRUE;
mutex_last_unlocked_at_line= line;
mutex_queue_data_locked= FALSE;
mutex_last_unlocked_in_func= func;
thd->enter_cond(&COND_queue_state, &LOCK_event_queue, msg);
if (!thd->killed)
{
if (!abstime)
mysql_cond_wait(&COND_queue_state, &LOCK_event_queue);
else
mysql_cond_timedwait(&COND_queue_state, &LOCK_event_queue, abstime);
}
mutex_last_locked_in_func= func;
mutex_last_locked_at_line= line;
mutex_queue_data_locked= TRUE;
waiting_on_cond= FALSE;
/*
This will free the lock so we need to relock. Not the best thing to
do but we need to obey cond_wait()
*/
thd->exit_cond("");
lock_data(func, line);
DBUG_VOID_RETURN;
}
/*
Dumps the internal status of the queue
SYNOPSIS
Event_queue::dump_internal_status()
*/
void
Event_queue::dump_internal_status()
{
DBUG_ENTER("Event_queue::dump_internal_status");
/* element count */
puts("");
puts("Event queue status:");
printf("Element count : %u\n", queue.elements);
printf("Data locked : %s\n", mutex_queue_data_locked? "YES":"NO");
printf("Attempting lock : %s\n", mutex_queue_data_attempting_lock? "YES":"NO");
printf("LLA : %s:%u\n", mutex_last_locked_in_func,
mutex_last_locked_at_line);
printf("LUA : %s:%u\n", mutex_last_unlocked_in_func,
mutex_last_unlocked_at_line);
if (mutex_last_attempted_lock_at_line)
printf("Last lock attempt at: %s:%u\n", mutex_last_attempted_lock_in_func,
mutex_last_attempted_lock_at_line);
printf("WOC : %s\n", waiting_on_cond? "YES":"NO");
MYSQL_TIME time;
my_tz_OFFSET0->gmt_sec_to_TIME(&time, next_activation_at);
if (time.year != 1970)
printf("Next activation : %04d-%02d-%02d %02d:%02d:%02d\n",
time.year, time.month, time.day, time.hour, time.minute, time.second);
else
printf("Next activation : never");
DBUG_VOID_RETURN;
}
/**
@} (End of group Event_Scheduler)
*/
Reference in a new issue View git blame Copy permalink