转至:https://blog.51cto.com/sf1314/2123068
select inst_id,status,count(*) from gv$session group by inst_id,status order by status;
$ORACLE_HOME dbmsadminspreport.sql
Oracle数据库巡检
一、操作系统检查
1.操作系统资源使用情况top/topas/iostat/vmstat 重点关注CPU/内存/交换的使用情况
2.操作系统空间使用情况df -h/-g 重点关注数据库目录空间(du -sh *)(du -sm *)
3.操作系统告警日志
HP: cat /var/adm/syslog/syslog.log
AIX:errpt | more
LINUX: cat /var/log/messages
SUN:cat /var/log/messages
Windows:事件查看器,查看事件内容
4.uptime查看操作系统是否有重启过特别是rac如有重启重点检查grid的alert日志查明原因
二、集群检查
1.检查集群状态crs_stat -t
2.检查集群中数据库的状态crsctl status res -t
3.检查service状态(grid:lsnrctl status),如都飘在一个检点上需要reload到对应节点(srvctl -h)
srvctl relocate service -d <db_unique_name> -s <service_name> {-i <old_inst_name> -t <new_inst_name> | -c <current_node> -n <target_node>} [-f]
4.检查集群alert日志 10g:$CRS_HOME/log/{hostname}/alert{hostname}.log11g:$ORACLE_HOME/log/{hostname}/alert{hostname}.log
5.ASM磁盘空间是否正常
select name,total_mb,free_mb from v$asm_diskgroup;
6.检查磁盘状态
select name,path,STATE,MODE_STATUS from v$asm_disk;
三、数据库检查
1.重点表空间使用情况确保使用率在85%以内
2.资源使用情况select * from v$resource_limit;(set linesize 300;set pagesize 300;)
3.闪回使用情况
select flashback_on from v$database;
查询视图v$recovery_file_dest视图来了解其位置和最大的大小
select * from v$recovery_file_dest;
使用v$flash_recovery_area_usage确定闪回恢复区中的文件使用明细
select * from v$flash_recovery_area_usage;
4.11g的新客户检查新特性是否关闭
是否开启审计show parameter audit_trail (db 开 none 关)
如开启询问是否有特许需求可以关闭
alter system set audit_trail=none scope=spfile sid='*';
truncate table sys.aud$;
select OWNER,SEGMENT_NAME,SEGMENT_TYPE,TABLESPACE_NAME,BYTES/1024/1024 MB from dba_segments where SEGMENT_TYPE='TABLE' and SEGMENT_NAME='AUD$';
5.清理监听日志 (win: > listener.log server 2008 R2 : echo " " > log.xml)
10g及10g以前:$ORACLE_HOME/network/log
11g以后:$ORACLE_BASE/diag/tnslsnr/{hostname}/listener/trace
lsnrctl status查看监听日志目录
10g: $ORACLE_HOME/network/admin/log/ 11g:/oracle/gridbase/diag/tnslsnr/s1-11g/listener/alert/log.xml
LSNRCTL> set
LSNRCTL> set current_listener LISTENER
Current Listener is LISTENER
LSNRCTL> set log_status off
LSNRCTL> set log_status on
LSNRCTL> exit
11g LISTENER_SCAN1
LSNRCTL> set current_listener LISTENER_SCAN1
6.检查数据库告警日志
10g以前:$ORACLE_BASE/admin/{SID}/bdump
D:ORACLEPRODUCT10.2.0ADMIN{SID}BDUMP
11g:$ORACLE_BASE/diag/rdbms/{DB_NAME}/{SID}/trace
7.查看数据库等待事件
--查看整体数据库的等待事件情况
select event,count(*) from gv$session_wait where wait_class<>'Idle' group by event;
8.收集awr报告
(1)获取AWR报告
SQL>@ /rdbms/admin/awrrpt.sql (退出sqlplus即可看到AWR报告)
询问客户高峰期时间点,截取1-2小时的报告
四、备份检查
1.确定是否存在逻辑或物理备份并查看备份情况(需检查备份日志)
2.如存在dbra或dg需检查同步情况
切日志,查看备库是否应用正常
select THREAD#,max(sequence#) from v$archived_log group by thread#; 主机
select THREAD#,max(sequence#) from v$archived_log where applied='YES' group by thread#; 备库
select THREAD#,max(sequence#) from v$archived_log group by thread#; 备库
备机空间检查
3.ogg同步情况检查
[oracle@localhost odc12]$ ps -ef | grep mgr
oracle 8492 1 0 Mar17 00:02:29 ./mgr PARAMFILE /odc12/dirprm/mgr.prm REPORTFILE /odc12/dirrpt/MGR.rpt PROCESSID MGR USESUBDIRS
oracle 26085 1 0 Mar22 00:00:15 ./mgr PARAMFILE /odc/dirprm/mgr.prm REPORTFILE /odc/dirrpt/MGR.rpt PROCESSID MGR PORT 7809
cd /odc12
./ggsci
info all
ggserr.log
五、跑巡检脚本
六、信息收集打包
1.操作系统日志
2.集群alert日志 grid用户(/oracle/grid/crs_1($ORACLE_HOME)/log/zjrac1)
3.数据库alert日志
4.巡检脚本输出内容
mkdir
表空间检查
set feed off
set linesize 100
set pagesize 200
column "USED (MB)" format a10
column "FREE (MB)" format a10
column "TOTAL (MB)" format a10
column PER_FREE format a10
--spool tablespace.alert
SELECT F.TABLESPACE_NAME,
TO_CHAR ((T.TOTAL_SPACE - F.FREE_SPACE),'999,999') "USED (MB)",
TO_CHAR (F.FREE_SPACE, '999,999') "FREE (MB)",
TO_CHAR (T.TOTAL_SPACE, '999,999') "TOTAL (MB)",
TO_CHAR ((ROUND ((F.FREE_SPACE/T.TOTAL_SPACE)*100)),'999')||' %' PER_FREE,
TO_CHAR (T.MAX_SPACE,'999,999') "MAXEXTEND (MB)"
FROM (
SELECT TABLESPACE_NAME,
ROUND (SUM (BLOCKS*(SELECT VALUE/1024
FROM V$PARAMETER
WHERE NAME = 'db_block_size')/1024)
) FREE_SPACE
FROM DBA_FREE_SPACE
GROUP BY TABLESPACE_NAME
) F,
(
SELECT TABLESPACE_NAME,
ROUND (SUM (BYTES/1048576)) TOTAL_SPACE,
ROUND (SUM (MAXBYTES/1048576)) MAX_SPACE
FROM DBA_DATA_FILES
GROUP BY TABLESPACE_NAME
) T
WHERE F.TABLESPACE_NAME = T.TABLESPACE_NAME
order by PER_FREE asc;
表空间:
select tpsname,status,mgr,maxsize,c_userd,max_used from (
SELECT d.tablespace_name tpsname,d.status status,
d.segment_space_management mgr, d.contents type,
TO_CHAR(NVL(trunc(A.maxbytes / 1024 / 1024), 0),'99G999G990') maxsize,
TO_CHAR(NVL((a.bytes - NVL(f.bytes, 0)) / a.bytes * 100, 0),'990D00') c_userd,
TO_CHAR(NVL((a.bytes - NVL(f.bytes, 0)) / a.maxbytes * 100, 0),'990D00') max_used
FROM sys.dba_tablespaces d,
(SELECT tablespace_name,sum(bytes) bytes,SUM(case autoextensible when 'NO' then BYTES when 'YES' then MAXBYTES else null end ) maxbytes FROM dba_data_files GROUP BY tablespace_name) a,
(SELECT tablespace_name,SUM(bytes) bytes, MAX(bytes) largest_free FROM dba_free_space GROUP BY tablespace_name) f
WHERE d.tablespace_name = a.tablespace_name AND d.tablespace_name = f.tablespace_name(+)
)
where max_used>80
order by max_used desc;
其它:
SQL> select file_name,bytes/1024/1024,maxbytes/1024/1024,AUTOEXTENSIBLE from dba_data_files;