#At file:///home/acorreia/workspace.sun/playground.mysql/mysql-5.0.68-custom_build/
2704 Alfranio Correia 2008-10-27
Merged patch that was proposed by Sinisa and modified by He Zhenxing to fix bugs: BUG#35542 and BUG#31665. This is an update to BUG#40337.
And introduced a new recovery process that disregards old relay-log.bin(s) and starts
re-fetching from the master based on the information in relay-log.info which may be flushed and synced after each transaction commit.
modified:
mysql-test/r/rpl_flush_log_loop.result
sql/log.cc
sql/mysql_priv.h
sql/mysqld.cc
sql/set_var.cc
sql/set_var.h
sql/slave.cc
sql/sql_class.h
per-file messages:
mysql-test/r/rpl_flush_log_loop.result
Changed result file for a test case affected by fix proposed for BUG#40337
sql/log.cc
Added support to the checkpoint interval through the parameter --sync-relay-log.
sql/mysql_priv.h
Created parameter --relay_log_throw, default = 0 thus keeping the original behavior. And added support to the checkpoint interval through the parameter --sync-relay-log, default = 0 thus keeping the original behavior.
sql/mysqld.cc
Created parameter --relay_log_throw, default = 0 thus keeping the original behavior. And added support to the checkpoint interval through the parameter --sync-relay-log, default = 0 thus keeping the original behavior.
sql/set_var.cc
Created parameter --relay_log_throw, default = 0 thus keeping the original behavior. And added support to the checkpoint interval through the parameter --sync-relay-log, default = 0 thus keeping the original behavior.
sql/set_var.h
Added support to the checkpoint interval through the parameter --sync-relay-log.
sql/slave.cc
Introduced the function init_recovery that is fired right after the startup and
updates the master.info according to the relay-log.info and throws away (i.e. ignores)the old relay-log.bin. And also added support to the checkpoint interval through the parameter --sync-relay-log.
Note that the when --sync-relay-log is on the relay-info is flushed and synced per transaction commit:
if (sync_relaylog_period &&
!error)
{
if (my_sync(rli->info_fd, MYF(MY_WME)))
error=1;
}
This is a bit different from the patch proposed for BUG#35542 and BUG#31665.
sql/sql_class.h
Created sync_period that determines how often the master.info and relay-log.bin are flushed and synch. This parameter should be seen as a checkpoint based on number of events.
=== modified file 'mysql-test/r/rpl_flush_log_loop.result'
--- a/mysql-test/r/rpl_flush_log_loop.result 2007-10-10 07:21:11 +0000
+++ b/mysql-test/r/rpl_flush_log_loop.result 2008-10-27 15:09:43 +0000
@@ -10,6 +10,7 @@ relay_log MYSQLTEST_VARDIR/master-data/r
relay_log_index
relay_log_info_file relay-log.info
relay_log_purge ON
+relay_log_throw OFF
relay_log_space_limit 0
stop slave;
change master to master_host='127.0.0.1',master_user='root',
=== modified file 'sql/log.cc'
--- a/sql/log.cc 2008-07-24 12:28:21 +0000
+++ b/sql/log.cc 2008-10-27 15:09:43 +0000
@@ -32,8 +32,7 @@
#include "message.h"
#endif
-MYSQL_LOG mysql_log, mysql_slow_log, mysql_bin_log;
-ulong sync_binlog_counter= 0;
+MYSQL_LOG mysql_log, mysql_slow_log, mysql_bin_log(&sync_binlog_period);
static Muted_query_log_event invisible_commit;
@@ -402,10 +401,11 @@ static int find_uniq_filename(char *name
}
-MYSQL_LOG::MYSQL_LOG()
+MYSQL_LOG::MYSQL_LOG(uint *sync_period)
:bytes_written(0), last_time(0), query_start(0), name(0),
prepared_xids(0), log_type(LOG_CLOSED), file_id(1), open_count(1),
write_error(FALSE), inited(FALSE), need_start_event(TRUE),
+ sync_period_ptr(sync_period),
description_event_for_exec(0), description_event_for_queue(0)
{
/*
@@ -1622,6 +1622,8 @@ bool MYSQL_LOG::append(Log_event* ev)
}
bytes_written+= ev->data_written;
DBUG_PRINT("info",("max_size: %lu",max_size));
+ if (flush_and_sync())
+ goto err;
if ((uint) my_b_append_tell(&log_file) > max_size)
new_file(0);
@@ -1652,6 +1654,8 @@ bool MYSQL_LOG::appendv(const char* buf,
bytes_written += len;
} while ((buf=va_arg(args,const char*)) && (len=va_arg(args,uint)));
DBUG_PRINT("info",("max_size: %lu",max_size));
+ if (flush_and_sync())
+ goto err;
if ((uint) my_b_append_tell(&log_file) > max_size)
new_file(0);
@@ -1758,9 +1762,10 @@ bool MYSQL_LOG::flush_and_sync()
safe_mutex_assert_owner(&LOCK_log);
if (flush_io_cache(&log_file))
return 1;
- if (++sync_binlog_counter >= sync_binlog_period && sync_binlog_period)
+ uint sync_period= get_sync_period();
+ if (sync_period && ++sync_counter >= sync_period)
{
- sync_binlog_counter= 0;
+ sync_counter= 0;
err=my_sync(fd, MYF(MY_WME));
}
return err;
=== modified file 'sql/mysql_priv.h'
--- a/sql/mysql_priv.h 2008-10-02 11:57:52 +0000
+++ b/sql/mysql_priv.h 2008-10-27 15:09:43 +0000
@@ -1310,10 +1310,11 @@ extern ulong max_binlog_size, max_relay_
extern ulong rpl_recovery_rank, thread_cache_size;
extern ulong back_log;
extern ulong specialflag, current_pid;
-extern ulong expire_logs_days, sync_binlog_period, sync_binlog_counter;
+extern ulong expire_logs_days;
+extern uint sync_binlog_period, sync_relaylog_period;
extern ulong opt_tc_log_size, tc_log_max_pages_used, tc_log_page_size;
extern ulong tc_log_page_waits;
-extern my_bool relay_log_purge, opt_innodb_safe_binlog, opt_innodb;
+extern my_bool relay_log_purge, relay_log_throw, opt_innodb_safe_binlog, opt_innodb;
extern uint test_flags,select_errors,ha_open_options;
extern uint protocol_version, mysqld_port, dropping_tables;
extern uint delay_key_write_options, lower_case_table_names;
=== modified file 'sql/mysqld.cc'
--- a/sql/mysqld.cc 2008-08-26 08:32:43 +0000
+++ b/sql/mysqld.cc 2008-10-27 15:09:43 +0000
@@ -404,7 +404,7 @@ ulong opt_ndb_cache_check_time;
const char *opt_ndb_mgmd;
ulong opt_ndb_nodeid;
#endif
-my_bool opt_readonly, use_temp_pool, relay_log_purge;
+my_bool opt_readonly, use_temp_pool, relay_log_purge, relay_log_throw;
my_bool opt_sync_frm, opt_allow_suspicious_udfs;
my_bool opt_secure_auth= 0;
char* opt_secure_file_priv= 0;
@@ -466,7 +466,8 @@ ulong max_prepared_stmt_count;
*/
ulong prepared_stmt_count=0;
ulong thread_id=1L,current_pid;
-ulong slow_launch_threads = 0, sync_binlog_period;
+ulong slow_launch_threads = 0;
+uint sync_binlog_period= 0, sync_relaylog_period= 0;
ulong expire_logs_days = 0;
ulong rpl_recovery_rank=0;
@@ -4918,6 +4919,7 @@ enum options_mysqld
OPT_QUERY_CACHE_TYPE, OPT_QUERY_CACHE_WLOCK_INVALIDATE, OPT_RECORD_BUFFER,
OPT_RECORD_RND_BUFFER, OPT_DIV_PRECINCREMENT, OPT_RELAY_LOG_SPACE_LIMIT,
OPT_RELAY_LOG_PURGE,
+ OPT_RELAY_LOG_THROW,
OPT_SLAVE_NET_TIMEOUT, OPT_SLAVE_COMPRESSED_PROTOCOL, OPT_SLOW_LAUNCH_TIME,
OPT_SLAVE_TRANS_RETRIES, OPT_READONLY, OPT_DEBUGGING,
OPT_SORT_BUFFER, OPT_TABLE_CACHE,
@@ -4995,7 +4997,8 @@ enum options_mysqld
OPT_SECURE_FILE_PRIV,
OPT_KEEP_FILES_ON_CREATE,
OPT_INNODB_ADAPTIVE_HASH_INDEX,
- OPT_FEDERATED
+ OPT_FEDERATED,
+ OPT_SYNC_RELAY_LOG
};
@@ -6302,6 +6305,11 @@ The minimum value for this variable is 4
(gptr*) &relay_log_purge,
(gptr*) &relay_log_purge, 0, GET_BOOL, NO_ARG,
1, 0, 1, 0, 1, 0},
+ {"relay_log_throw", OPT_RELAY_LOG_THROW,
+ "0 = do not ignore retrieved relay logs. 1 = ignore retrieved relay logs.",
+ (gptr*) &relay_log_throw,
+ (gptr*) &relay_log_throw, 0, GET_BOOL, NO_ARG,
+ 0, 0, 1, 0, 1, 0},
{"relay_log_space_limit", OPT_RELAY_LOG_SPACE_LIMIT,
"Maximum space to use for all relay logs.",
(gptr*) &relay_log_space_limit,
@@ -6342,8 +6350,13 @@ The minimum value for this variable is 4
{"sync-binlog", OPT_SYNC_BINLOG,
"Synchronously flush binary log to disk after every #th event. "
"Use 0 (default) to disable synchronous flushing.",
- (gptr*) &sync_binlog_period, (gptr*) &sync_binlog_period, 0, GET_ULONG,
- REQUIRED_ARG, 0, 0, ULONG_MAX, 0, 1, 0},
+ (gptr*) &sync_binlog_period, (gptr*) &sync_binlog_period, 0, GET_UINT,
+ REQUIRED_ARG, 0, 0, UINT_MAX, 0, 1, 0},
+ {"sync-relay-log", OPT_SYNC_RELAY_LOG,
+ "Synchronously flush relay log to disk after every #th event. "
+ "Use 0 (default) to disable synchronous flushing.",
+ (gptr *) &sync_relaylog_period, (gptr *) &sync_relaylog_period, 0, GET_UINT,
+ REQUIRED_ARG, 0, 0, UINT_MAX, 0, 1, 0},
{"sync-frm", OPT_SYNC_FRM, "Sync .frm to disk on create. Enabled by default.",
(gptr*) &opt_sync_frm, (gptr*) &opt_sync_frm, 0, GET_BOOL, NO_ARG, 1, 0,
0, 0, 0, 0},
=== modified file 'sql/set_var.cc'
--- a/sql/set_var.cc 2008-08-25 12:11:59 +0000
+++ b/sql/set_var.cc 2008-10-27 15:09:43 +0000
@@ -323,6 +323,8 @@ sys_var_thd_ulong sys_div_precincrement(
#ifdef HAVE_REPLICATION
sys_var_bool_ptr sys_relay_log_purge("relay_log_purge",
&relay_log_purge);
+sys_var_bool_ptr sys_relay_log_throw("relay_log_throw",
+ &relay_log_throw);
#endif
sys_var_long_ptr sys_rpl_recovery_rank("rpl_recovery_rank",
&rpl_recovery_rank);
@@ -402,7 +404,8 @@ sys_var_thd_table_type sys_table_type("
sys_var_thd_storage_engine sys_storage_engine("storage_engine",
&SV::table_type);
#ifdef HAVE_REPLICATION
-sys_var_sync_binlog_period sys_sync_binlog_period("sync_binlog", &sync_binlog_period);
+sys_var_int_ptr sys_sync_binlog_period("sync_binlog", &sync_binlog_period);
+sys_var_int_ptr sys_sync_relaylog_period("sync_relay_log", &sync_relaylog_period);
#endif
sys_var_bool_ptr sys_sync_frm("sync_frm", &opt_sync_frm);
sys_var_const_str sys_system_time_zone("system_time_zone",
@@ -733,6 +736,7 @@ sys_var *sys_variables[]=
&sys_read_rnd_buff_size,
#ifdef HAVE_REPLICATION
&sys_relay_log_purge,
+ &sys_relay_log_throw,
#endif
&sys_rpl_recovery_rank,
&sys_safe_updates,
@@ -762,6 +766,7 @@ sys_var *sys_variables[]=
&sys_storage_engine,
#ifdef HAVE_REPLICATION
&sys_sync_binlog_period,
+ &sys_sync_relaylog_period,
#endif
&sys_sync_frm,
&sys_system_time_zone,
@@ -1052,6 +1057,7 @@ struct show_var_st init_vars[]= {
{"relay_log_index", (char*) &opt_relaylog_index_name, SHOW_CHAR_PTR},
{"relay_log_info_file", (char*) &relay_log_info_file, SHOW_CHAR_PTR},
{sys_relay_log_purge.name, (char*) &sys_relay_log_purge, SHOW_SYS},
+ {sys_relay_log_throw.name, (char*) &sys_relay_log_throw, SHOW_SYS},
{"relay_log_space_limit", (char*) &relay_log_space_limit, SHOW_LONGLONG},
#endif
{sys_rpl_recovery_rank.name,(char*) &sys_rpl_recovery_rank, SHOW_SYS},
@@ -1090,6 +1096,7 @@ struct show_var_st init_vars[]= {
{sys_storage_engine.name, (char*) &sys_storage_engine, SHOW_SYS},
#ifdef HAVE_REPLICATION
{sys_sync_binlog_period.name,(char*) &sys_sync_binlog_period, SHOW_SYS},
+ {sys_sync_relaylog_period.name,(char*) &sys_sync_relaylog_period, SHOW_SYS},
#endif
{sys_sync_frm.name, (char*) &sys_sync_frm, SHOW_SYS},
#ifdef HAVE_TZNAME
@@ -1486,6 +1493,23 @@ static bool get_unsigned(THD *thd, set_v
}
+bool sys_var_int_ptr::check(THD *thd, set_var *var)
+{
+ var->save_result.ulong_value= (ulong) var->value->val_int();
+ return 0;
+}
+
+bool sys_var_int_ptr::update(THD *thd, set_var *var)
+{
+ *value= (uint) var->save_result.ulong_value;
+ return 0;
+}
+
+void sys_var_int_ptr::set_default(THD *thd, enum_var_type type)
+{
+ *value= (uint) option_limits->def_value;
+}
+
sys_var_long_ptr::
sys_var_long_ptr(const char *name_arg, ulong *value_ptr_arg,
sys_after_update_func after_update_arg)
@@ -2759,13 +2783,6 @@ bool sys_var_slave_skip_counter::update(
pthread_mutex_unlock(&LOCK_active_mi);
return 0;
}
-
-
-bool sys_var_sync_binlog_period::update(THD *thd, set_var *var)
-{
- sync_binlog_period= (ulong) var->save_result.ulonglong_value;
- return 0;
-}
#endif /* HAVE_REPLICATION */
bool sys_var_rand_seed1::update(THD *thd, set_var *var)
=== modified file 'sql/set_var.h'
--- a/sql/set_var.h 2008-01-23 15:03:58 +0000
+++ b/sql/set_var.h 2008-10-27 15:09:43 +0000
@@ -110,6 +110,26 @@ public:
{ return (byte*) value; }
};
+/**
+ Unsigned int system variable class
+ */
+class sys_var_int_ptr :public sys_var
+{
+public:
+ sys_var_int_ptr(const char *name_arg, uint *value_ptr_arg,
+ sys_after_update_func after_update_arg= NULL)
+ :sys_var(name_arg, after_update_arg),
+ value(value_ptr_arg)
+ {}
+ bool check(THD *thd, set_var *var);
+ bool update(THD *thd, set_var *var);
+ void set_default(THD *thd, enum_var_type type);
+ SHOW_TYPE show_type() { return SHOW_INT; }
+ byte *value_ptr(THD *thd, enum_var_type type, LEX_STRING *base)
+ { return (byte*) value; }
+private:
+ uint *value;
+};
/*
A global ulong variable that is protected by LOCK_global_system_variables
@@ -550,11 +570,11 @@ public:
*/
};
-class sys_var_sync_binlog_period :public sys_var_long_ptr
+class sys_var_sync_binlog_period :public sys_var_int_ptr
{
public:
- sys_var_sync_binlog_period(const char *name_arg, ulong *value_ptr_arg)
- :sys_var_long_ptr(name_arg,value_ptr_arg) {}
+ sys_var_sync_binlog_period(const char *name_arg, uint *value_ptr_arg)
+ :sys_var_int_ptr(name_arg,value_ptr_arg) {}
bool update(THD *thd, set_var *var);
};
#endif
=== modified file 'sql/slave.cc'
--- a/sql/slave.cc 2008-03-28 20:01:05 +0000
+++ b/sql/slave.cc 2008-10-27 15:09:43 +0000
@@ -66,6 +66,7 @@ static bool wait_for_relay_log_space(REL
static inline bool io_slave_killed(THD* thd,MASTER_INFO* mi);
static inline bool sql_slave_killed(THD* thd,RELAY_LOG_INFO* rli);
static int count_relay_log_space(RELAY_LOG_INFO* rli);
+static int init_recovery(MASTER_INFO* mi);
static int init_slave_thread(THD* thd, SLAVE_THD_TYPE thd_type);
static int safe_connect(THD* thd, MYSQL* mysql, MASTER_INFO* mi);
static int safe_reconnect(THD* thd, MYSQL* mysql, MASTER_INFO* mi,
@@ -174,6 +175,9 @@ int init_slave()
if (server_id && !master_host && active_mi->host[0])
master_host= active_mi->host;
+ if (init_recovery(active_mi))
+ goto err;
+
/* If server id is not set, start_slave_thread() will say it */
if (master_host && !opt_skip_slave_start)
@@ -197,6 +201,48 @@ err:
DBUG_RETURN(1);
}
+static int init_recovery(MASTER_INFO* mi)
+{
+ const char* errmsg=0;
+ DBUG_ENTER("recovery_init");
+
+ RELAY_LOG_INFO* rli = &mi->rli;
+ if (relay_log_throw && rli->group_master_log_name[0])
+ {
+ mi->master_log_pos = max(BIN_LOG_HEADER_SIZE,
+ rli->group_master_log_pos);
+ strmake(mi->master_log_name, rli->group_master_log_name,
+ sizeof(mi->master_log_name)-1);
+
+ strmake(rli->group_relay_log_name, rli->relay_log.get_log_fname(),
+ sizeof(rli->group_relay_log_name)-1);
+ strmake(rli->event_relay_log_name, rli->relay_log.get_log_fname(),
+ sizeof(mi->rli.event_relay_log_name)-1);
+
+ rli->group_relay_log_pos = rli->group_relay_log_pos = BIN_LOG_HEADER_SIZE;
+
+ if (init_relay_log_pos(rli,
+ rli->group_relay_log_name,
+ rli->group_relay_log_pos,
+ 0 /*no data lock*/,
+ &errmsg, 0))
+ DBUG_RETURN(1);
+
+ if (flush_master_info(mi, 0))
+ {
+ sql_print_error("Failed to flush master info file");
+ DBUG_RETURN(1);
+ }
+ if (flush_relay_log_info(rli))
+ {
+ sql_print_error("Failed to flush master info file");
+ DBUG_RETURN(1);
+ }
+ }
+
+ DBUG_RETURN(0);
+}
+
static void free_table_ent(TABLE_RULE_ENT* e)
{
@@ -2582,6 +2628,7 @@ int flush_master_info(MASTER_INFO* mi, b
{
IO_CACHE* file = &mi->file;
char lbuf[22];
+ int err= 0;
DBUG_ENTER("flush_master_info");
DBUG_PRINT("enter",("master_pos: %ld", (long) mi->master_log_pos));
@@ -2597,9 +2644,12 @@ int flush_master_info(MASTER_INFO* mi, b
When we come to this place in code, relay log may or not be initialized;
the caller is responsible for setting 'flush_relay_log_cache' accordingly.
*/
- if (flush_relay_log_cache &&
- flush_io_cache(mi->rli.relay_log.get_log_file()))
- DBUG_RETURN(2);
+ if (flush_relay_log_cache)
+ {
+ IO_CACHE *log_file= mi->rli.relay_log.get_log_file();
+ if (flush_io_cache(log_file))
+ DBUG_RETURN(2);
+ }
/*
We flushed the relay log BEFORE the master.info file, because if we crash
@@ -2626,12 +2676,21 @@ int flush_master_info(MASTER_INFO* mi, b
mi->password, mi->port, mi->connect_retry,
(int)(mi->ssl), mi->ssl_ca, mi->ssl_capath, mi->ssl_cert,
mi->ssl_cipher, mi->ssl_key);
- DBUG_RETURN(-flush_io_cache(file));
+ err= flush_io_cache(file);
+ static unsigned int count=1;
+ if (sync_relaylog_period && !err && count > sync_relaylog_period)
+ {
+ err= my_sync(mi->fd, MYF(MY_WME));
+ count= 1;
+ }
+ count++;
+ DBUG_RETURN(-err);
}
st_relay_log_info::st_relay_log_info()
- :info_fd(-1), cur_log_fd(-1), save_temporary_tables(0),
+ :info_fd(-1), cur_log_fd(-1), relay_log(&sync_relaylog_period),
+ save_temporary_tables(0),
cur_log_old_open_count(0), group_master_log_pos(0), log_space_total(0),
ignore_log_space_limit(0), last_master_timestamp(0), slave_skip_counter(0),
abort_pos_wait(0), slave_run_id(0), sql_thd(0), last_slave_errno(0),
@@ -4872,6 +4931,14 @@ bool flush_relay_log_info(RELAY_LOG_INFO
error=1;
if (flush_io_cache(file))
error=1;
+ static unsigned int count= 1;
+ if (sync_relaylog_period &&
+ !error)
+ {
+ if (my_sync(rli->info_fd, MYF(MY_WME)))
+ error=1;
+ }
+ count++;
/* Flushing the relay log is done by the slave I/O thread */
return error;
}
=== modified file 'sql/sql_class.h'
--- a/sql/sql_class.h 2008-09-17 06:34:00 +0000
+++ b/sql/sql_class.h 2008-10-27 15:09:43 +0000
@@ -238,6 +238,18 @@ class MYSQL_LOG: public TC_LOG
bool no_auto_events;
friend class Log_event;
+ /* pointer to the sync period variable, for binlog this will be
+ sync_binlog_period, for relay log this will be
+ sync_relay_log_period
+ */
+ uint *sync_period_ptr;
+ uint sync_counter;
+
+ inline uint get_sync_period()
+ {
+ return *sync_period_ptr;
+ }
+
public:
/*
These describe the log's format. This is used only for relay logs.
@@ -250,7 +262,7 @@ public:
Format_description_log_event *description_event_for_exec,
*description_event_for_queue;
- MYSQL_LOG();
+ MYSQL_LOG(uint *sync_period=0);
/*
note that there's no destructor ~MYSQL_LOG() !
The reason is that we don't want it to be automatically called
