Filesystem 向 asm 迁移:
第一部分：
Author: Sheng Huiping
Date Jun 07 2012
先说一下和asm 有关的dict:
select * from v$asm_operation;
select * from v$asm_disk;
select * from v$asm_diskgroup;
先看一下环境：
我们先看一下：cd $ORACLE_HOME/dbs 下没有init+ASM.ora
oracle@aoracle dbs]$ export ORACLE_SID=+ASM
[oracle@aoracle dbs]$ ls -l init+ASM.ora
ls: init+ASM.ora: No such file or directory
oracle@aoracle dbs]$ sqlplus / as sysdba
SQL*Plus: Release 10.2.0.1.0 - Production on Sat Jan 7 09:33:47 2012
Copyright (c) 1982, 2005, Oracle. All rights reserved.
Connected to an idle instance.
SQL> startup;
ORA-01078: failure in processing system parameters
LRM-00109: could not open parameter file '/u01/pp/oracle/product/10.2/db_1/dbs/init+ASM.ora'
SQL>
符合我们的预期，
好，下面我们建个init+TEST.ora
[oracle@aoracle dbs]$ vi init+TEST.ora
asm_diskstring=''
background_dump_dest=/u01/pp/oracle/admin/+TEST/bdump
user_dump_dest=/u01/pp/oracle/admin/+TEST/udump
core_dump_dest=/u01/pp/oracle/admin/+TEST/cdump
instance_type='asm'
下面开始启动一下：
[oracle@aoracle ~]$ export ORACLE_SID=+TEST
[oracle@aoracle ~]$ sqlplus / as sysdba
SQL*Plus: Release 10.2.0.1.0 - Production on Sat Jan 7 09:37:46 2012
Copyright (c) 1982, 2005, Oracle. All rights reserved.
Connected to an idle instance.
SQL> startup;
ORA-07446: sdnfy: bad value '/u01/pp/oracle/admin/+TEST/udump' for parameter user_dump_dest.
SQL> !
[oracle@aoracle ~]$ id
uid=501(oracle) gid=501(oinstall) groups=501(oinstall),502(dba),503(oper)
[oracle@aoracle ~]$ mkdir -p /u01/pp/oracle/admin/+TEST/bdump
[oracle@aoracle ~]$ mkdir -p /u01/pp/oracle/admin/+TEST/udump
[oracle@aoracle ~]$ mkdir -p /u01/pp/oracle/admin/+TEST/cdump
[oracle@aoracle ~]$ exit
exit
SQL> startup;
ORA-15150: instance lock mode 'EXCLUSIVE' conflicts with other ASM instance(s)
SQL>
看一下alert 日志：
oracle@aoracle bdump]$ more alert_+TEST.log
Sat Jan 7 09:39:09 2012
Starting ORACLE instance (normal)
Cannot determine all dependent dynamic libraries for /proc/self/exe
Unable to find dynamic library libocr10.so in search paths
RPATH = /ade/aime1_build2101/oracle/has/lib/:/ade/aime1_build2101/oracle/lib/:/ade/aime1_build2101/oracle/h
as/lib/:
LD_LIBRARY_PATH is not set!
The default library directories are /lib and /usr/lib
Unable to find dynamic library libocrb10.so in search paths
Unable to find dynamic library libocrutl10.so in search paths
Unable to find dynamic library libocrutl10.so in search paths
LICENSE_MAX_SESSION = 0
LICENSE_SESSIONS_WARNING = 0
Shared memory segment for instance monitoring created
Picked latch-free SCN scheme 2
Using LOG_ARCHIVE_DEST_1 parameter default value as /u01/pp/oracle/product/10.2/db_1/dbs/arch
Autotune of undo retention is turned off.
LICENSE_MAX_USERS = 0
SYS auditing is disabled
ksdpec: called for event 13740 prior to event group initialization
Starting up ORACLE RDBMS Version: 10.2.0.1.0.
System parameters with non-default values:
instance_type = asm
background_dump_dest = /u01/pp/oracle/admin/+TEST/bdump
user_dump_dest = /u01/pp/oracle/admin/+TEST/udump
core_dump_dest = /u01/pp/oracle/admin/+TEST/cdump
asm_diskstring =
PMON started with pid=2, OS id=5721
PSP0 started with pid=3, OS id=5723
MMAN started with pid=4, OS id=5725
DBW0 started with pid=5, OS id=5727
LGWR started with pid=6, OS id=5729
CKPT started with pid=7, OS id=5731
SMON started with pid=8, OS id=5733
RBAL started with pid=9, OS id=5735
Sat Jan 7 09:39:11 2012
sculkget: failed to lock /u01/pp/oracle/product/10.2/db_1/dbs/lk+ASM exclusive
sculkget: lock held by PID: 5038
Sat Jan 7 09:39:11 2012
USER: terminating instance due to error 15150
Instance terminated by USER, pid = 5719
---------------
分析下来，是因为，启动了其他的ASM 的实例：
[oracle@aoracle ~]$ ps -ef | grep smon | grep -v grep
oracle 5044 1 0 09:24 ? 00:00:00 asm_smon_+SHENG
我原来是装过+SHENG 的ASM 实例。
[oracle@aoracle ~]$ ps -ef | grep smon | grep -v grep
oracle 5044 1 0 09:24 ? 00:00:00 asm_smon_+SHENG
[oracle@aoracle ~]$ kill -9 5044
[oracle@aoracle ~]$ ps -ef | grep smon | grep -v grep
[oracle@aoracle ~]$ env | grep ORA
ORACLE_SID=+TEST
ORACLE_BASE=/u01/pp/oracle
ORACLE_HOME=/u01/pp/oracle/product/10.2/db_1
[oracle@aoracle ~]$ sqlplus / as sysdba
SQL*Plus: Release 10.2.0.1.0 - Production on Sat Jan 7 09:51:01 2012
Copyright (c) 1982, 2005, Oracle. All rights reserved.
Connected to an idle instance.
SQL> startup;
ASM instance started
Total System Global Area 79691776 bytes
Fixed Size 1217812 bytes
Variable Size 53308140 bytes
ASM Cache 25165824 bytes
ORA-15110: no diskgroups mounted
----------------------
好以上的测试符合我们的预期，想ASM封装 的instance 只能有一个。
如果想见很多个instance, 可以在：“ASM封装 的instance” 下面建不同的 database intance.
下面还是在原来的 +SHENG 下建不同的isntance 看看：
[oracle@aoracle ~]$ ps -ef | grep smon | grep -v grep
oracle 6161 1 0 09:51 ? 00:00:00 asm_smon_+TEST
[oracle@aoracle ~]$ kill -9 6161
[oracle@aoracle ~]$ export ORACLE_SID=+SHENG
[oracle@aoracle ~]$ sqlplus / as sysdba
SQL*Plus: Release 10.2.0.1.0 - Production on Sat Jan 7 09:55:37 2012
Copyright (c) 1982, 2005, Oracle. All rights reserved.
Connected to an idle instance.
SQL> startup;
ASM instance started
Total System Global Area 79691776 bytes
Fixed Size 1217812 bytes
Variable Size 53308140 bytes
ASM Cache 25165824 bytes
ORA-15110: no diskgroups mounted
-----------------------
看看+SHENG 下面有哪些diskgroup:
SQL> select name,state ,total_mb,usable_file_mb from v$asm_diskgroup;
NAME STATE TOTAL_MB USABLE_FILE_MB
------------------------------ ----------- ---------- --------------
SHENGASM DISMOUNTED 0 0
下面再增加两块盘，从新建个diskgroup:
下面先测试在原来的disk group 下加disk:
[root@aoracle dev]# raw -qa
/dev/raw/raw1: bound to major 8, minor 49
/dev/raw/raw2: bound to major 8, minor 65
/dev/raw/raw3: bound to major 8, minor 81
/dev/raw/raw4: bound to major 8, minor 97
[root@aoracle dev]# pwd
/dev
[root@aoracle dev]# cd raw
[root@aoracle raw]# ls
raw1 raw2 raw3 raw4
[root@aoracle raw]# ls -l
total 0
crw-rw---- 1 oracle oinstall 162, 1 Jan 7 10:45 raw1
crw-rw---- 1 oracle oinstall 162, 2 Jan 7 10:31 raw2
crw------- 1 root root 162, 3 Jan 7 10:24 raw3
crw------- 1 root root 162, 4 Jan 7 10:24 raw4
原因找到，是因为owner 是root，下面重新 vi etc/udev/rules.d/60-raw.rules
start-udev
ok,
SQL> alter diskgroup shengasm add disk '/dev/raw/raw3';
Diskgroup altered.
现在可以看到，total_mb 比原来增加了：
SQL> select name,state ,total_mb,usable_file_mb from v$asm_diskgroup;
NAME STATE TOTAL_MB USABLE_FILE_MB
------------------------------ ----------- ---------- --------------
SHENGASM MOUNTED 14322 13181
原来是：
SQL> select name,state ,total_mb,usable_file_mb from v$asm_diskgroup;
NAME STATE TOTAL_MB USABLE_FILE_MB
------------------------------ ----------- ---------- --------------
SHENGASM MOUNTED 10228 9089
下面提醒一下，和asm 有关的dict:
select * from v$asm_operation;
select * from v$asm_disk;
select * from v$asm_diskgroup;
看一disk:
SQL> select name, path from v$asm_disk;
NAME PATH
------------------------------ -------------------------------------------------
/dev/raw/raw4
/dev/raw/raw5
SHENGASM_0000 /dev/raw/raw1
SHENGASM_0002 /dev/raw/raw3
SHENGASM_0001 /dev/raw/raw2
------------------------------------
说明一下，diskgroup 和instance 没有啥关系，看一下目录就知道了：
+SHENGASM/shengasm/online_log/redo1_1.rdo
前面的+SHENGASM 是diskgroup, 后面的shengasm 就是database instance了：
SQL> create diskgroup data external redundancy disk '/dev/raw/raw4';
Diskgroup created.
SQL> alter diskgroup data add disk '/dev/raw/raw5';
Diskgroup altered.
SQL> select name, path from v$asm_disk;
NAME PATH
------------------------------ -------------------------------------------------
DATA_0000 /dev/raw/raw4
DATA_0001 /dev/raw/raw5
SHENGASM_0000 /dev/raw/raw1
SHENGASM_0002 /dev/raw/raw3
SHENGASM_0001 /dev/raw/raw2
SQL> select name,state from v$asm_diskgroup;
NAME STATE
------------------------------ -----------
SHENGASM MOUNTED
DATA MOUNTED
目标是把 ezhou 的filesystem 移到diskgroup : data 上来，
具体的操作下一个章节研究，敬请期待。
735
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
