oracle 容灾库日常维护 ,健康检查脚本以及常见问题分析

select DEST_ID, APPLIED_SCN FROM v$archive_dest

select * from v$dataguard_status;

SELECT gvi.thread#, timestamp, message FROM gv$dataguard_status gvds, gv$instance gvi WHERE gvds.inst_id = gvi.inst_id AND severity in ('Error','Fatal') ORDER BY timestamp, thread#;

1.日常维护

1.停止Standby

select process, status from v$managed_standby; --查看备库是否在应用日志进行恢复

alter database recover managed standby database cancel;
shutdown immediate;

2.切换到只读模式

-----由shutdown模式切换到只读模式-------

startup nomount;
alter database mount standby database;
alter database open read only;

-----由应用日志模式切换到只读模式-------

alter database recover managed standby database cancel;-- 取消日志应用
alter database open read only;

3.切换回管理恢复模式

startup nomount;
alter database mount standby database;
alter database recover managed standby database disconnect from session;-- 启动日志应用

alter database recover managed standby database using current logfile disconnect from session;

-查看应用日志延迟时间：

select value from v$dataguard_stats where name='apply lag';

-查看接收日志延迟时间：

select value from v$dataguard_stats where name='transport lag';

-查看主库归档

Primary: SQL> select thread#, max(sequence#) "Last Primary Seq Generated"

from v$archived_log val, v$database vdb

where val.resetlogs_change# = vdb.resetlogs_change#

group by thread# order by 1;

-查看备库已接收归档

PhyStdby:SQL> select thread#, max(sequence#) "Last Standby Seq Received"

from v$archived_log val, v$database vdb

where val.resetlogs_change# = vdb.resetlogs_change#

group by thread# order by 1;

-查看备库已应用归档

PhyStdby:SQL>select thread#, max(sequence#) "Last Standby Seq Applied"

from v$archived_log val, v$database vdb

where val.resetlogs_change# = vdb.resetlogs_change#

and val.applied in ('YES','IN-MEMORY')

group by thread# order by 1;

-查看归档应用详细情况

select first_time,sequence#,applied from v$archived_log;

-查看主备库GAP

select * from v$archive_gap;

11g 备库上面停止MRP ,启动MRP

SQL> recover managed standby database cancel;
Media recovery complete.
startup mount;

SQL> recover managed standby database using current logfile disconnect;
Media recovery complete.
SQL> select open_mode,database_role,log_mode,flashback_on from v$database;

4.主库和备库之间角色切换

4.1 主库切换为备库
alter database commit to switchover to physical standby;

alter database commit to switchover to physical standby with session shutdown;-- 主库有会话连接的时候
shutdown immediate
startup nomount;
alter database mount standby database;
alter database recover managed standby database disconnect from session;

4.2 从库切换为主库

alter database commit to switchover to primary;
shutdown immediate;
startup
alter system switch logfile;

5.备库自动使用主库传过来的日志进行恢复

alter database recover automatic standby database;

6.更改保护模式

alter database set standby database to maximize protection;
alter database set standby database to maximize availability;
alter database set standby database to maximize performancen;

7.取消自动恢复模式

alter database recover managed standby database cancel;
alter database recover managed standby database finish;
alter database recover managed standby database finish force;

FAL_CLIENT和FAL_SERVER是配置dataguard用到的两个参数,FAL指获取归档日志(Fetch Archived Log)

在一定的条件下，或者因为网络失败，或者因为资源紧张，会在primary和standby之间产生裂隙，也就是有些归档日志没有及时的传输并应用到standby库。因为MRP(managed recovery process)/LSP(logical standby process)没有与primary直接通讯的能力来获取丢失的归档日志。因此这些gaps通过FAL客户和服务器来解决，由初始化参数定义FAL_CLIENT和FAL_SERVER。

FAL_SERVER指定一个Oracle Net service name,standby数据库使用这个参数连接到FAL server,这个参数适用于standby站点。

比如,FAL_SERVER = PrimaryDB,此处PrimaryDB是一个TNS name,指向primary库。

FAL_CLIENT指定一个FAL客户端的名字，以便FAL Server可以引用standby库，这也是一个TNS name，primary库必须适当配置此TNS name指向stanby库。这个参数也是在standby库端设置。比如，

FAL_CLIENT = StandbyDB,StandbyDB是standby库的TNS name。

FAL_CLIENT和FAL_SERVER应该成对设置或改变。

这两个参数只需在standby库设置，但也可以在primary库设置这两个参数，以方便switchover或failover时primary库转变为standby角色。

alter system set fal_server='db1-old,db2-old';

ALTER SYSTEM SET fal_client='db2-1-old' SID='db2';

###11g Real-Time Apply

when pysical is read-only status, can also active mrp as follows:

ALTER DATABASE RECOVER MANAGED STANDBY DATABASE USING CURRENT LOGFILE

【Oracle官方文档中对Real-Time Apply介绍】

If the real-time apply feature is enabled, apply services can apply redo data as it is received, without waiting for the current standby redo log file to be archived. This results in faster switchover and failover times because the standby redo log files have been applied already to the standby database by the time the failover or switchover begins.

Use the ALTER DATABASE statement to enable the real-time apply feature, as follows:

For physical standby databases, issue the ALTER DATABASE RECOVER MANAGED STANDBY DATABASE USING CURRENT LOGFILE statement.

转自：http://blog.csdn.net/robbie1314520/article/details/8267283

2. 检查脚本 check script:

Primary Site Script

===============================================================================

-- This script is to be run on the Primary of a Data Guard Physical Standby Site

set echo off
set feedback off
column timecol new_value tstamp
column spool_extension new_value suffix
select to_char(sysdate,'Mondd_hhmi') timecol from sys.dual;
column output new_value dbname
select value || '_' output from v$parameter where name = 'db_name';

-- Output the results to this file

spool dg_Primary_diag_&&dbname&&tstamp
set lines 132
set pagesize 500
set numformat 999999999999999
set trim on
set trims on

-- Get the current Date

alter session set nls_date_format = 'DD-MON-YYYY HH24:MI:SS';
set feedback on
select systimestamp from dual;

-- Primary Site Details
set heading off
set feedback off
select 'Primary Site Details' from dual;
select '********************' from dual;
set heading on
set feedback on

col db_unique_name format a15
col flashb_on format a10

select DB_UNIQUE_NAME,DATABASE_ROLE DB_ROLE,FORCE_LOGGING F_LOG,FLASHBACK_ON FLASHB_ON,LOG_MODE,OPEN_MODE,
GUARD_STATUS GUARD,PROTECTION_MODE PROT_MODE
from v$database;

-- Current SCN - this value on the primary and standby sites where real time apply is in place should be nearly the same

set heading off
set feedback off
select 'Primary Site last generated SCN' from dual;
select '*******************************' from dual;
set heading on
set feedback on

select DB_UNIQUE_NAME,SWITCHOVER_STATUS,CURRENT_SCN from v$database;

set heading off
set feedback off
select 'Standby Site last applied SCN' from dual;
select '*****************************' from dual;
set heading on
set feedback on

select DEST_ID, APPLIED_SCN FROM v$archive_dest WHERE TARGET='STANDBY';

-- Incarnation Information
--

set heading off
set feedback off
select 'Incarnation Destination Configuration' from dual;
select '*************************************' from dual;
set heading on
set feedback on

select INCARNATION# INC#, RESETLOGS_CHANGE# RS_CHANGE#, RESETLOGS_TIME, PRIOR_RESETLOGS_CHANGE# PRIOR_RS_CHANGE#, STATUS,FLASHBACK_DATABASE_ALLOWED FB_OK from v$database_incarnation;

-- Archivelog Destination Details
--

set heading off
set feedback off
select 'Archive Destination Configuration' from dual;
select '*********************************' from dual;
set heading on
set feedback on

-- Current Archive Locations
--

column host_name format a30 tru
column version format a10 tru
select INSTANCE_NAME,HOST_NAME,VERSION,ARCHIVER from v$instance;

column destination format a35 wrap
column process format a7
column archiver format a8
column dest_id format 99999999

select DEST_ID,DESTINATION,STATUS,TARGET,ARCHIVER,PROCESS,REGISTER,TRANSMIT_MODE
from v$archive_dest
where DESTINATION IS NOT NULL;

column name format a22
column value format a100
select NAME,VALUE from v$parameter where NAME like 'log_archive_dest%' and upper(VALUE) like 'SERVICE%';

set heading off
set feedback off
select 'Archive Destination Errors' from dual;
select '**************************' from dual;
set heading on
set feedback on

column error format a55 tru
select DEST_ID,STATUS,ERROR from v$archive_dest
where DESTINATION IS NOT NULL;

column message format a80
select MESSAGE, TIMESTAMP
from v$dataguard_status
where SEVERITY in ('Error','Fatal')
order by TIMESTAMP;

-- Redo Log configuration
-- The size of the standby redo logs must match exactly the size on the online redo logs

set heading off
set feedback off
select 'Data Guard Redo Log Configuration' from dual;
select '*********************************' from dual;
set heading on
set feedback on

select GROUP# STANDBY_GROUP#,THREAD#,SEQUENCE#,BYTES,USED,ARCHIVED,STATUS from v$standby_log order by GROUP#,THREAD#;

select GROUP# ONLINE_GROUP#,THREAD#,SEQUENCE#,BYTES,ARCHIVED,STATUS from v$log order by GROUP#,THREAD#;

-- Data Guard Parameters
--
set heading off
set feedback off
select 'Data Guard Related Parameters' from dual;
select '*****************************' from dual;
set heading on
set feedback on

column name format a30
column value format a100
select NAME,VALUE from v$parameter where NAME IN ('db_unique_name','cluster_database','dg_broker_start','dg_broker_config_file1','dg_broker_config_file2','fal_client','fal_server','log_archive_config','log_archive_trace','log_archive_max_processes','archive_lag_target','remote_login_password_file','redo_transport_user') order by name;

-- Redo Shipping Progress

set heading off
set feedback off
select 'Data Guard Redo Shipping Progress' from dual;
select '*********************************' from dual;
set heading on
set feedback on

select systimestamp from dual;

column client_pid format a10
select PROCESS,STATUS,CLIENT_PROCESS,CLIENT_PID,THREAD#,SEQUENCE#,BLOCK#,ACTIVE_AGENTS,KNOWN_AGENTS
from v$managed_standby order by CLIENT_PROCESS,THREAD#,SEQUENCE#;

host sleep 10

select systimestamp from dual;

select PROCESS,STATUS,CLIENT_PROCESS,CLIENT_PID,THREAD#,SEQUENCE#,BLOCK#,ACTIVE_AGENTS,KNOWN_AGENTS
from v$managed_standby order by CLIENT_PROCESS,THREAD#,SEQUENCE#;

host sleep 10

select systimestamp from dual;

select PROCESS,STATUS,CLIENT_PROCESS,CLIENT_PID,THREAD#,SEQUENCE#,BLOCK#,ACTIVE_AGENTS,KNOWN_AGENTS
from v$managed_standby order by CLIENT_PROCESS,THREAD#,SEQUENCE#;

set heading off
set feedback off
select 'Data Guard Errors in the Last Hour' from dual;
select '**********************************' from dual;
set heading on
set feedback on

select TIMESTAMP,SEVERITY,ERROR_CODE,MESSAGE from v$dataguard_status where timestamp > systimestamp-1/24;
spool off

================================================================================

Standby Site Script

================================================================================

-- This script is to be run on the Standby of a Data Guard Physical Standby Site

-- Output the results to this file

spool dg_Standby_diag_&&dbname&&tstamp
set lines 132
set pagesize 500
set numformat 999999999999999
set trim on
set trims on

-- Get the current Date

set feedback on
select systimestamp from dual;

-- Standby Site Details
set heading off
set feedback off
select 'Standby Site Details' from dual;
select '********************' from dual;
set heading on
set feedback on

col db_unique_name format a15
col flashb_on format a10

select DB_UNIQUE_NAME,DATABASE_ROLE DB_ROLE,FORCE_LOGGING F_LOG,FLASHBACK_ON FLASHB_ON,LOG_MODE,OPEN_MODE,
GUARD_STATUS GUARD,PROTECTION_MODE PROT_MODE
from v$database;

-- Current SCN - this value on the primary and standby sites where real time apply is in place should be nearly the same

select DB_UNIQUE_NAME,SWITCHOVER_STATUS,CURRENT_SCN from v$database;

-- Incarnation Information
--

set heading off
set feedback off
select 'Incarnation Destination Configuration' from dual;
select '*************************************' from dual;
set heading on
set feedback on

select INCARNATION# INC#, RESETLOGS_CHANGE# RS_CHANGE#, RESETLOGS_TIME, PRIOR_RESETLOGS_CHANGE# PRIOR_RS_CHANGE#, STATUS,FLASHBACK_DATABASE_ALLOWED FB_OK from v$database_incarnation;

set heading off
set feedback off
select 'Archive Destination Configuration' from dual;
select '*********************************' from dual;
set heading on
set feedback on
-- Current Archive Locations
--

column host_name format a30 tru
column version format a10 tru
select INSTANCE_NAME,HOST_NAME,VERSION,ARCHIVER from v$instance;