前几天遇到一客户的10205 rac,出现LMD进程IPC SEND TIMEOUT问题。准备深入研究下Oracle RAC
的LMON,LMD以及LMS进程，发现自己的VM RAC无法启动了，最后看了下，居然是有个节点的分区不见了。
++++Node2
[root@rac2 raw]# ls -ltr /dev/sdf*
brw-r----- 1 root disk 8, 84 Dec 4 2013 /dev/sdf4
brw-r----- 1 root disk 8, 83 Dec 4 2013 /dev/sdf3
brw-r----- 1 root disk 8, 82 Dec 4 2013 /dev/sdf2
brw-r----- 1 root disk 8, 81 Dec 4 2013 /dev/sdf1
brwxrwxr-x 1 oracle oinstall 8, 80 Dec 4 2013 /dev/sdf
[root@rac2 bin]# cat /etc/rc.d/rc.local
#!/bin/sh
#
# This script will be executed *after* all the other init scripts.
# You can put your own initialization stuff in here if you don't
# want to do the full Sys V style init stuff.
touch / var /lock/subsys/local
chown -R oracle:oinstall /dev/sdf
chown -R oracle:oinstall /dev/sde
chown -R oracle:oinstall /dev/sdb
chown -R oracle:oinstall /dev/sdd
chown -R oracle:oinstall /dev/sdc
chmod -R 775 /dev/sdf
chmod -R 775 /dev/sde
chmod -R 775 /dev/sdb
chmod -R 775 /dev/sdd
chmod -R 775 /dev/sdc
raw /dev/raw/raw1 /dev/sdf1
raw /dev/raw/raw2 /dev/sdf2
raw /dev/raw/raw3 /dev/sdf3
raw /dev/raw/raw4 /dev/sdf4
chown -R oracle:dba /dev/raw
++++Node1
[root@rac1 bin]# partprobe
[root@rac1 bin]# ls -ltr /dev/sdf*
brwxrwxr-x 1 oracle oinstall 8, 80 Jun 29 01:37 /dev/sdf
[root@rac1 bin]#
我这里是将其中一个共享盘进行了分区，然后绑定为raw。发现其中一个节点的分区不见了，最后把节点2
reboot之后，2个节点的分区都看不到了。无语了。
印象中Linux有一些方法可以恢复partition，尝试使用gpart来试试，如下是我尝试：
[root@rac1 repodata]# gpart /dev/sdf
Begin scan...
End scan.
Checking partitions...
Ok.
Guessed primary partition table:
Primary partition(1)
type: 000(0x00)(unused)
size: 0mb #s(0) s(0-0)
chs: (0/0/0)-(0/0/0)d (0/0/0)-(0/0/0)r
Primary partition(2)
type: 000(0x00)(unused)
size: 0mb #s(0) s(0-0)
chs: (0/0/0)-(0/0/0)d (0/0/0)-(0/0/0)r
Primary partition(3)
type: 000(0x00)(unused)
size: 0mb #s(0) s(0-0)
chs: (0/0/0)-(0/0/0)d (0/0/0)-(0/0/0)r
Primary partition(4)
type: 000(0x00)(unused)
size: 0mb #s(0) s(0-0)
chs: (0/0/0)-(0/0/0)d (0/0/0)-(0/0/0)r
[root@rac1 repodata]# gpart -W /dev/sdf /dev/sdf
Begin scan...
End scan.
Checking partitions...
Ok.
Guessed primary partition table:
Primary partition(1)
type: 000(0x00)(unused)
size: 0mb #s(0) s(0-0)
chs: (0/0/0)-(0/0/0)d (0/0/0)-(0/0/0)r
Primary partition(2)
type: 000(0x00)(unused)
size: 0mb #s(0) s(0-0)
chs: (0/0/0)-(0/0/0)d (0/0/0)-(0/0/0)r
Primary partition(3)
type: 000(0x00)(unused)
size: 0mb #s(0) s(0-0)
chs: (0/0/0)-(0/0/0)d (0/0/0)-(0/0/0)r
Primary partition(4)
type: 000(0x00)(unused)
size: 0mb #s(0) s(0-0)
chs: (0/0/0)-(0/0/0)d (0/0/0)-(0/0/0)r
Edit this table (y,n) : y
Edit which partition (1..4, q to quit) : q
Activate which partition (1..4, q to quit) : 1
Write this partition table (y,n) : y
* Warning: partition table written, you should reboot now.
[root@rac1 repodata]# ls -ltr /dev/sdf*
brwxrwxr-x 1 oracle oinstall 8, 80 Jun 29 03:57 /dev/sdf
大家可以看到，我这里gpart扫出来的，虽然能看到有4个分区，但是全是空的。不知道为什么，太怪异了。
[root@rac1 ~]# fdisk -l
Disk /dev/sda: 21.4 GB, 21474836480 bytes
255 heads, 63 sectors/track, 2610 cylinders
Units = cylinders of 16065 * 512 = 8225280 bytes
Device Boot Start End Blocks Id System
/dev/sda1 * 1 6 48163+ 83 Linux
/dev/sda2 7 515 4088542+ 83 Linux
/dev/sda3 516 776 2096482+ 82 Linux swap / Solaris
/dev/sda4 777 2610 14731605 5 Extended
/dev/sda5 777 2610 14731573+ 83 Linux
Disk /dev/sdb: 524 MB, 524288000 bytes
64 heads, 32 sectors/track, 500 cylinders
Units = cylinders of 2048 * 512 = 1048576 bytes
Disk /dev/sdb doesn't contain a valid partition table
Disk /dev/sdc: 4294 MB, 4294967296 bytes
255 heads, 63 sectors/track, 522 cylinders
Units = cylinders of 16065 * 512 = 8225280 bytes
Disk /dev/sdc doesn't contain a valid partition table
Disk /dev/sdd: 4294 MB, 4294967296 bytes
255 heads, 63 sectors/track, 522 cylinders
Units = cylinders of 16065 * 512 = 8225280 bytes
Disk /dev/sdd doesn't contain a valid partition table
Disk /dev/sde: 4294 MB, 4294967296 bytes
255 heads, 63 sectors/track, 522 cylinders
Units = cylinders of 16065 * 512 = 8225280 bytes
Disk /dev/sde doesn't contain a valid partition table
Disk /dev/sdf: 2147 MB, 2147483648 bytes
255 heads, 63 sectors/track, 261 cylinders
Units = cylinders of 16065 * 512 = 8225280 bytes
Device Boot Start End Blocks Id System
/dev/sdf1 * 1 1 0 0 Empty
Partition 1 has different physical/logical beginnings (non-Linux?):
phys=(0, 0, 0) logical=(0, 0, 1)
Partition 1 has different physical/logical endings:
phys=(0, 0, 0) logical=(267349, 89, 4)
Partition 1 does not end on cylinder boundary.
因此，最后gpart写回去也一样没用，因为数据都没了。 由于我这里也没有ocr的备份，因此只能重建了。
在10gR2 版本中，我们可以不必要重新安装，只跑root.sh脚本即可，那么怎么搞呢 ？
如果你直接运行root.sh，那么会遇到类似如下的问题：
[root@rac1 crs]# ./root.sh
WARNING: directory ‘/home/oracle/app/oracle/product/10.2.0′ is not owned by root
WARNING: directory ‘/home/oracle/app/oracle/product’ is not owned by root
WARNING: directory ‘/home/oracle/app/oracle’ is not owned by root
WARNING: directory ‘/home/oracle/app’ is not owned by root
WARNING: directory ‘/home/oracle’ is not owned by root
No value set for the CRS parameter CRS_OCR_LOCATIONS. Using Values in paramfile.crs
Checking to see if Oracle CRS stack is already configured
Oracle CRS stack is already configured and will be running under init(1M)
[root@rac1 crs]#
##### 清理部分文件，准备执行root.sh
1. 删除/etc/oracle/ocr.loc
[root@rac1 crs]# mv /etc/oracle/ocr.loc /etc/oracle/ocr.loc.bak
mv: overwrite `/etc/oracle/ocr.loc.bak'? y
2. 删除cssfatal文件
[root@rac1 crs]# cd /etc/oracle/
[root@rac1 oracle]# pwd
/etc/oracle/scls_scr/rac1/oracle
[root@rac1 oracle]# rm cssfatal
rm: remove regular file `cssfatal'? n
[root@rac1 oracle]# mv cssfatal cssfatal.bak
3. 删除/etc/inittab中的信息
最后我分开执行root.sh脚本即可，如下是过程：
节点1：
[root@rac1 rac1]# /home/oracle/app/oracle/product/10.2.0/crs/root.sh
WARNING: directory '/home/oracle/app/oracle/product/10.2.0' is not owned by root
WARNING: directory '/home/oracle/app/oracle/product' is not owned by root
WARNING: directory '/home/oracle/app/oracle' is not owned by root
WARNING: directory '/home/oracle/app' is not owned by root
WARNING: directory '/home/oracle' is not owned by root
No value set for the CRS parameter CRS_OCR_LOCATIONS. Using Values in paramfile.crs
Checking to see if Oracle CRS stack is already configured
Setting the permissions on OCR backup directory
Setting up NS directories
Oracle Cluster Registry configuration upgraded successfully
WARNING: directory '/home/oracle/app/oracle/product/10.2.0' is not owned by root
WARNING: directory '/home/oracle/app/oracle/product' is not owned by root
WARNING: directory '/home/oracle/app/oracle' is not owned by root
WARNING: directory '/home/oracle/app' is not owned by root
WARNING: directory '/home/oracle' is not owned by root
Successfully accumulated necessary OCR keys.
Using ports: CSS=49895 CRS=49896 EVMC=49898 and EVMR=49897.
node <nodenumber>: <nodename> <private interconnect name> <hostname>
node 1: rac1 rac1-priv rac1
node 2: rac2 rac2-priv rac2
Creating OCR keys for user 'root', privgrp 'root'..
Operation successful.
Now formatting voting device: /dev/raw/raw2
Format of 1 voting devices complete.
Startup will be queued to init within 30 seconds.
Adding daemons to inittab
Expecting the CRS daemons to be up within 600 seconds.
CSS is active on these nodes.
rac1
CSS is inactive on these nodes.
rac2
Local node checking complete.
Run root.sh on remaining nodes to start CRS daemons.
节点2：
[root@rac2 oracle]# /home/oracle/app/oracle/product/10.2.0/crs/root.sh
WARNING: directory '/home/oracle/app/oracle/product/10.2.0' is not owned by root
WARNING: directory '/home/oracle/app/oracle/product' is not owned by root
WARNING: directory '/home/oracle/app/oracle' is not owned by root
WARNING: directory '/home/oracle/app' is not owned by root
WARNING: directory '/home/oracle' is not owned by root
No value set for the CRS parameter CRS_OCR_LOCATIONS. Using Values in paramfile.crs
Checking to see if Oracle CRS stack is already configured
Setting the permissions on OCR backup directory
Setting up NS directories
Oracle Cluster Registry configuration upgraded successfully
WARNING: directory '/home/oracle/app/oracle/product/10.2.0' is not owned by root
WARNING: directory '/home/oracle/app/oracle/product' is not owned by root
WARNING: directory '/home/oracle/app/oracle' is not owned by root
WARNING: directory '/home/oracle/app' is not owned by root
WARNING: directory '/home/oracle' is not owned by root
clscfg: EXISTING configuration version 3 detected.
clscfg: version 3 is 10G Release 2.
Successfully accumulated necessary OCR keys.
Using ports: CSS=49895 CRS=49896 EVMC=49898 and EVMR=49897.
node <nodenumber>: <nodename> <private interconnect name> <hostname>
node 1: rac1 rac1-priv rac1
node 2: rac2 rac2-priv rac2
clscfg: Arguments check out successfully.
NO KEYS WERE WRITTEN. Supply -force parameter to override.
-force is destructive and will destroy any previous cluster
configuration.
Oracle Cluster Registry for cluster has already been initialized
Startup will be queued to init within 30 seconds.
Adding daemons to inittab
Expecting the CRS daemons to be up within 600 seconds.
CSS is active on these nodes.
rac1
rac2
CSS is active on all nodes.
Waiting for the Oracle CRSD and EVMD to start
Oracle CRS stack installed and running under init(1M)
Running vipca(silent) for configuring nodeapps
Creating VIP application resource on (2) nodes...
Creating GSD application resource on (2) nodes...
Creating ONS application resource on (2) nodes...
Starting VIP application resource on (2) nodes...
Starting GSD application resource on (2) nodes...
Starting ONS application resource on (2) nodes...
Done.
最后我们看到，crs进程都正常起来了，如下：
[root@rac1 oracle]# ps -ef|grep d.bin
oracle 12371 12370 0 04:34 ? 00:00:00 /home/oracle/app/oracle/product/10.2.0/crs/bin/evmd.bin
root 12446 11819 0 04:34 ? 00:00:00 /home/oracle/app/oracle/product/10.2.0/crs/bin/crsd.bin reboot
root 12688 12452 0 04:34 ? 00:00:00 /home/oracle/app/oracle/product/10.2.0/crs/bin/oprocd.bin run -t 1000 -m 500
oracle 12914 12520 0 04:34 ? 00:00:00 /home/oracle/app/oracle/product/10.2.0/crs/bin/ocssd.bin
root 15267 5027 0 04:41 pts/1 00:00:00 grep d.bin
[root@rac1 oracle]# cd /home/oracle/app/oracle/product/10.2.0/crs/bin
[root@rac1 bin]# ./ocrcheck
Status of Oracle Cluster Registry is as follows :
Version : 2
Total space (kbytes) : 521836
Used space (kbytes) : 4604
Available space (kbytes) : 517232
ID : 559767577
Device/File Name : /dev/raw/raw1
Device/File integrity check succeeded
Device/File not configured
Cluster registry integrity check succeeded
[root@rac1 bin]# ./crsctl query css votedisk
0. 0 /dev/raw/raw4
located 1 votedisk(s).
[root@rac1 bin]#
[root@rac2 bin]# ./crs_stat -t -v
Name Type R/RA F/FT Target State Host
----------------------------------------------------------------------
ora.rac1.gsd application 0/5 0/0 ONLINE ONLINE rac1
ora.rac1.ons application 0/3 0/0 ONLINE ONLINE rac1
ora.rac1.vip application 0/0 0/0 ONLINE ONLINE rac1
ora.rac2.gsd application 0/5 0/0 ONLINE ONLINE rac2
ora.rac2.ons application 0/3 0/0 ONLINE ONLINE rac2
ora.rac2.vip application 0/0 0/0 ONLINE ONLINE rac2
[root@rac2 bin]#
+++注册db和asm
[oracle@rac1 bdump]$ srvctl add database -d roger -o /home/oracle/app/oracle/product/10.2.0/db_1
[oracle@rac1 bdump]$ srvctl add instance -d roger -i roger1 -n rac1
[oracle@rac1 bdump]$ srvctl add instance -d roger -i roger2 -n rac2
[oracle@rac1 bdump]$ srvctl add asm -n rac1 -i +ASM1 -o /home/oracle/app/oracle/product/10.2.0/db_1
null
[PRKS-1030 : Failed to add configuration for ASM instance "+ASM1" on node "rac1" in cluster registry, [PROC-5: User does not have permission to perform a cluster registry operation on this key. Authentication error [User does not have permission to perform this operation] [0]]
[PROC-5: User does not have permission to perform a cluster registry operation on this key. Authentication error [User does not have permission to perform this operation] [0]]]
[oracle@rac1 bdump]$
[root@rac2 bin]# ./crs_getperm ora.rac1.vip
Name: ora.rac1.vip
owner:root:rwx,pgrp:oinstall:r-x,other::r--,user:oracle:r-x,
[root@rac2 bin]# ./crs_getperm ora.rac2.vip
Name: ora.rac2.vip
owner:root:rwx,pgrp:oinstall:r-x,other::r--,user:oracle:r-x,
[root@rac2 bin]#
可以看到上面执行报错了，开始以为是vip资源的问题，于是修改了owner，最后发现这是错位的步骤：
[root@rac2 bin]# ./crs_setperm ora.rac1.vip -o oracle
[root@rac2 bin]# ./crs_setperm ora.rac1.vip -g oinstall
[root@rac2 bin]# ./crs_setperm ora.rac2.vip -o oracle
[root@rac2 bin]# ./crs_setperm ora.rac2.vip -g oinstall
[root@rac2 bin]#
[oracle@rac1 bdump]$ srvctl add asm -n rac1 -i +ASM1 -o /home/oracle/app/oracle/product/10.2.0/db_1
null
[PRKS-1030 : Failed to add configuration for ASM instance "+ASM1" on node "rac1" in cluster registry, [PROC-5: User does not have permission to perform a cluster registry operation on this key. Authentication error [User does not have permission to perform this operation] [0]]
[PROC-5: User does not have permission to perform a cluster registry operation on this key. Authentication error [User does not have permission to perform this operation] [0]]]
虽然添加失败，我就改用root执行，进行添加，如下：
[root@rac1 bin]# ./srvctl add asm -n rac1 -i +ASM1 -o /home/oracle/app/oracle/product/10.2.0/db_1
[root@rac1 bin]# ./srvctl add asm -n rac2 -i +ASM2 -o /home/oracle/app/oracle/product/10.2.0/db_1
[root@rac1 bin]# ./crs_stat -p|grep asm
NAME=ora.rac1.ASM1.asm
NAME=ora.rac2.ASM2.asm
[root@rac1 bin]# ./crs_setperm ora.rac1.ASM1.asm -o oracle
[root@rac1 bin]# ./crs_setperm ora.rac1.ASM2.asm -o oracle
[root@rac1 bin]# ./crs_setperm ora.rac1.ASM1.asm -g oinstall
[root@rac1 bin]# ./crs_setperm ora.rac2.ASM2.asm -g oinstall
[oracle@rac1 bdump]$ crs_start ora.rac1.ASM1.asm
Attempting to start `ora.rac1.ASM1.asm` on member `rac1`
Start of `ora.rac1.ASM1.asm` on member `rac1` succeeded.
[oracle@rac1 bdump]$ crs_start ora.rac2.ASM2.asm
Attempting to start `ora.rac2.ASM2.asm` on member `rac2`
Start of `ora.rac2.ASM2.asm` on member `rac2` succeeded.
[oracle@rac1 bdump]$ crs_stat -t
Name Type Target State Host
------------------------------------------------------------
ora....SM1.asm application ONLINE ONLINE rac1
ora....C1.lsnr application ONLINE OFFLINE
ora.rac1.gsd application ONLINE ONLINE rac1
ora.rac1.ons application ONLINE ONLINE rac1
ora.rac1.vip application ONLINE OFFLINE
ora....SM2.asm application ONLINE ONLINE rac2
ora....C2.lsnr application ONLINE OFFLINE
ora.rac2.gsd application ONLINE ONLINE rac2
ora.rac2.ons application ONLINE ONLINE rac2
ora.rac2.vip application ONLINE OFFLINE
ora.roger.db application ONLINE ONLINE rac2
ora....r1.inst application ONLINE ONLINE rac1
ora....r2.inst application ONLINE ONLINE rac2
最后发现vip和lsnr资源死活起不来，看了下日志，才发现开始vip资源搞错了，vip资源的owner本身就应该是root才对。
通过查看crsd.log 日志，会发现如下信息:
2014-06-29 09:04:56.578: [ CRSRES][2719009680]0startRunnable: setting CLI values
2014-06-29 09:04:56.775: [ CRSRES][2708519824]0startRunnable: setting CLI values
2014-06-29 09:04:56.820: [ CRSRES][2687540112]0startRunnable: setting CLI values
2014-06-29 09:04:56.903: [ CRSRES][2719009680]0Attempting to start `ora.rac1.vip` on member `rac1`
2014-06-29 09:04:56.929: [ CRSRES][2708519824]0Attempting to start `ora.rac1.ASM1.asm` on member `rac1`
2014-06-29 09:04:56.951: [ CRSRES][2687540112]0Attempting to start `ora.roger.roger1.inst` on member `rac1`
2014-06-29 09:04:58.798: [ CRSAPP][2719009680]0StartResource error for ora.rac1.vip error code = 1
2014-06-29 09:04:59.579: [ CRSRES][2719009680]0Start of `ora.rac1.vip` on member `rac1` failed.
2014-06-29 09:05:00.007: [ COMMCRS][2644503440]clsc_send_msg: (0x98bede0) NS err (12571, 12560), transport (530, 111, 0)
2014-06-29 09:05:00.007: [ CRSCOMM][2719009680]0CLSC connect failed torac2ret = 9
2014-06-29 09:05:00.008: [ CRSEVT][2719009680]0invokepeer ret 200
2014-06-29 09:05:00.040: [ CRSRES][2719009680]0Remote start never sent to rac2: X_E2E_NotSent : Failed to connect to node: rac2
(File: caa_CmdRTI.cpp, line: 504
2014-06-29 09:05:00.040: [ CRSRES][2719009680][ALERT]0Remote start for `ora.rac1.vip` failed on member `rac2`
2014-06-29 09:05:01.047: [ CRSRES][2719009680]0startRunnable: setting CLI values
2014-06-29 09:05:01.147: [ CRSRES][2719009680]0Attempting to start `ora.rac1.vip` on member `rac1`
2014-06-29 09:05:02.400: [ CRSAPP][2719009680]0StartResource error for ora.rac1.vip error code = 1
2014-06-29 09:05:03.702: [ CRSRES][2719009680]0Start of `ora.rac1.vip` on member `rac1` failed.
2014-06-29 09:05:04.811: [ CRSRES][2613033872]0startRunnable: setting CLI values
2014-06-29 09:05:04.967: [ CRSRES][2613033872]0Attempting to start `ora.rac1.vip` on member `rac1`
2014-06-29 09:05:05.268: [ CRSAPP][2613033872]0StartResource error for ora.rac1.vip error code = 1
2014-06-29 09:05:06.769: [ CRSRES][2613033872]0Start of `ora.rac1.vip` on member `rac1` failed.
2014-06-29 09:05:11.078: [ CRSRES][2613033872]0startRunnable: setting CLI values
2014-06-29 09:05:11.342: [ CRSRES][2613033872]0Attempting to start `ora.rac1.ons` on member `rac1`
2014-06-29 09:05:13.926: [ CRSRES][2613033872]0Start of `ora.rac1.ons` on member `rac1` succeeded.
2014-06-29 09:05:13.966: [ CRSRES][2708519824]0Start of `ora.rac1.ASM1.asm` on member `rac1` succeeded.
2014-06-29 09:05:45.321: [ CRSRES][2708519824]0CRS-1002: Resource 'ora.rac1.ons' is already running on member 'rac1'
2014-06-29 09:05:46.461: [ CRSRES][2687540112]0Start of `ora.roger.roger1.inst` on member `rac1` succeeded.
2014-06-29 09:05:46.472: [ CRSRES][2698029968]0Skip online resource: ora.rac1.ons
2014-06-29 09:05:49.505: [ CRSRES][2687540112]0startRunnable: setting CLI values
2014-06-29 09:05:49.969: [ CRSRES][2613033872]0startRunnable: setting CLI values
2014-06-29 09:05:50.186: [ CRSRES][2613033872]0Attempting to start `ora.rac1.vip` on member `rac1`
2014-06-29 09:05:50.307: [ CRSRES][2687540112]0Attempting to start `ora.rac1.gsd` on member `rac1`
2014-06-29 09:05:50.788: [ CRSRES][2677050256]0Attempting to start `ora.rac2.vip` on member `rac2`
2014-06-29 09:05:50.906: [ CRSRES][2698029968]0Attempting to start `ora.rac2.gsd` on member `rac2`
2014-06-29 09:05:50.985: [ CRSRES][2719009680]0Attempting to start `ora.rac2.ons` on member `rac2`
2014-06-29 09:05:51.079: [ CRSRES][2708519824]0Attempting to start `ora.roger.db` on member `rac2`
2014-06-29 09:05:51.082: [ CRSAPP][2613033872]0StartResource error for ora.rac1.vip error code = 1
2014-06-29 09:05:51.978: [ CRSRES][2613033872]0Start of `ora.rac1.vip` on member `rac1` failed.
2014-06-29 09:05:52.059: [ CRSRES][2613033872]0rac2 : CRS-1019: Resource ora.rac1.LISTENER_RAC1.lsnr (application) cannot run on rac2
2014-06-29 09:05:53.001: [ CRSRES][2687540112]0Start of `ora.rac1.gsd` on member `rac1` succeeded.
2014-06-29 09:05:54.193: [ CRSRES][2708519824]0Start of `ora.roger.db` on member `rac2` succeeded.
2014-06-29 09:05:54.505: [ CRSRES][2698029968]0Start of `ora.rac2.gsd` on member `rac2` succeeded.
2014-06-29 09:05:54.869: [ CRSRES][2634013584]0CRS-1002: Resource 'ora.roger.db' is already running on member 'rac2'
2014-06-29 09:05:55.054: [ CRSRES][2677050256]0Start of `ora.rac2.vip` on member `rac2` failed.
2014-06-29 09:05:55.226: [ CRSRES][2677050256]0startRunnable: setting CLI values
2014-06-29 09:05:55.277: [ CRSRES][2677050256]0Attempting to start `ora.rac2.vip` on member `rac1`
2014-06-29 09:05:55.585: [ CRSAPP][2677050256]0StartResource error for ora.rac2.vip error code = 1
2014-06-29 09:05:55.714: [ CRSRES][2719009680]0Start of `ora.rac2.ons` on member `rac2` succeeded.
2014-06-29 09:05:55.910: [ CRSRES][2677050256]0Start of `ora.rac2.vip` on member `rac1` failed.
2014-06-29 09:05:56.363: [ CRSRES][2677050256]0Attempting to start `ora.rac2.vip` on member `rac2`
2014-06-29 09:05:57.180: [ CRSRES][2677050256]0Start of `ora.rac2.vip` on member `rac2` failed.
2014-06-29 09:05:57.993: [ CRSRES][2654993296]0startRunnable: setting CLI values
2014-06-29 09:05:58.611: [ CRSAPP][2654993296]0StartResource error for ora.rac1.vip error code = 1
2014-06-29 09:05:59.333: [ CRSRES][2708519824]0startRunnable: setting CLI values
2014-06-29 09:06:00.129: [ CRSAPP][2708519824]0StartResource error for ora.rac2.vip error code = 1
2014-06-29 09:06:06.328: [ CRSRES][2708519824]0startRunnable: setting CLI values
2014-06-29 09:06:06.916: [ CRSAPP][2708519824]0StartResource error for ora.rac1.vip error code = 1
最后将vip资源改回为root，一切正常：
[root@rac1 bin]# ./crs_setperm ora.rac1.vip -o root
[root@rac1 bin]# ./crs_setperm ora.rac1.vip -g root
[root@rac1 bin]# ./crs_start ora.rac1.vip
Attempting to start `ora.rac1.vip` on member `rac1`
Start of `ora.rac1.vip` on member `rac1` succeeded.
[root@rac1 bin]# ./crs_setperm ora.rac2.vip -o root
[root@rac1 bin]# ./crs_setperm ora.rac2.vip -g root
[root@rac1 bin]# ./crs_start ora.rac2.vip
Attempting to start `ora.rac2.vip` on member `rac2`
Start of `ora.rac2.vip` on member `rac2` succeeded.
[root@rac1 bin]#
[oracle@rac1 racg]$ crs_stat -t -v
Name Type R/RA F/FT Target State Host
----------------------------------------------------------------------
ora....SM1.asm application 0/5 0/0 ONLINE ONLINE rac1
ora....C1.lsnr application 0/5 0/0 ONLINE ONLINE rac1
ora.rac1.gsd application 0/5 0/0 ONLINE ONLINE rac1
ora.rac1.ons application 0/3 0/0 ONLINE ONLINE rac1
ora.rac1.vip application 0/0 0/0 ONLINE ONLINE rac1
ora....SM2.asm application 0/5 0/0 ONLINE ONLINE rac2
ora....C2.lsnr application 0/5 0/0 ONLINE ONLINE rac2
ora.rac2.gsd application 0/5 0/0 ONLINE ONLINE rac2
ora.rac2.ons application 0/3 0/0 ONLINE ONLINE rac2
ora.rac2.vip application 0/0 0/0 ONLINE ONLINE rac2
ora.roger.db application 0/0 0/1 ONLINE ONLINE rac2
ora....r1.inst application 0/5 0/0 ONLINE ONLINE rac1
ora....r2.inst application 0/5 0/0 ONLINE ONLINE rac2
[oracle@rac1 racg]$
很久没有搞10gR2 rac，有点生疏了，我檫！
标签：rac2,rac,rac1,sh,重跑,ONLINE,oracle,root,ora From： https://blog.51cto.com/databasenotes/6324134