crs 维护模式 exclusive mode

How To Validate ASM Instances And Diskgroups On A RAC Cluster (When CRS Does Not Start). (Doc ID 1609127.1)

​编辑To Bottom

[root@rac1 ~]# ps -ef|grep grid
root      2477     1  1 20:47 ?        00:00:51 /opt/oracle.ahf/jre/bin/java -server -Xms32m -Xmx64m -Djava.awt.headless=true -Ddisable.checkForUpdate=true -XX:HeapDumpPath=/u01/app/grid/oracle.ahf/data/rac1/diag/tfa oracle.rat.tfa.TFAMain /opt/oracle.ahf/tfa
grid      3252     1  0 20:48 ?        00:00:00 /bin/sh ./OSWatcher.sh 30 48 /bin/gzip /u01/app/grid/oracle.ahf/data/repository/suptools/rac1/oswbb/grid/archive
grid      4136  3252  0 20:48 ?        00:00:00 /bin/sh ./OSWatcherFM.sh 48 /u01/app/grid/oracle.ahf/data/repository/suptools/rac1/oswbb/grid/archive
grid     21272  4136  0 21:37 ?        00:00:00 sleep 60
grid     21336  3252  0 21:37 ?        00:00:00 sleep 30
root     21559  6928  0 21:38 pts/0    00:00:00 grep --color=auto grid
[root@rac1 ~]# 
[root@rac1 ~]# 
[root@rac1 ~]# 
[root@rac1 ~]# 
[root@rac1 ~]# 
[root@rac1 ~]# crsctl start crs -excl -nocrs
CRS-4123: Oracle High Availability Services has been started.
CRS-2672: Attempting to start 'ora.evmd' on 'rac1'
CRS-2672: Attempting to start 'ora.mdnsd' on 'rac1'
CRS-2676: Start of 'ora.evmd' on 'rac1' succeeded
CRS-2676: Start of 'ora.mdnsd' on 'rac1' succeeded
CRS-2672: Attempting to start 'ora.gpnpd' on 'rac1'
CRS-2676: Start of 'ora.gpnpd' on 'rac1' succeeded
CRS-2672: Attempting to start 'ora.cssdmonitor' on 'rac1'
CRS-2672: Attempting to start 'ora.gipcd' on 'rac1'
CRS-2676: Start of 'ora.cssdmonitor' on 'rac1' succeeded
CRS-2676: Start of 'ora.gipcd' on 'rac1' succeeded
CRS-2672: Attempting to start 'ora.cssd' on 'rac1'
CRS-2672: Attempting to start 'ora.diskmon' on 'rac1'
CRS-2676: Start of 'ora.diskmon' on 'rac1' succeeded
CRS-2676: Start of 'ora.cssd' on 'rac1' succeeded
CRS-2672: Attempting to start 'ora.cluster_interconnect.haip' on 'rac1'
CRS-2672: Attempting to start 'ora.ctssd' on 'rac1'
CRS-2676: Start of 'ora.ctssd' on 'rac1' succeeded
CRS-2676: Start of 'ora.cluster_interconnect.haip' on 'rac1' succeeded
CRS-2672: Attempting to start 'ora.asm' on 'rac1'
CRS-2676: Start of 'ora.asm' on 'rac1' succeeded
[root@rac1 ~]# ps -ef|grep grid
root      2477     1  1 20:47 ?        00:00:51 /opt/oracle.ahf/jre/bin/java -server -Xms32m -Xmx64m -Djava.awt.headless=true -Ddisable.checkForUpdate=true -XX:HeapDumpPath=/u01/app/grid/oracle.ahf/data/rac1/diag/tfa oracle.rat.tfa.TFAMain /opt/oracle.ahf/tfa
grid      3252     1  0 20:48 ?        00:00:00 /bin/sh ./OSWatcher.sh 30 48 /bin/gzip /u01/app/grid/oracle.ahf/data/repository/suptools/rac1/oswbb/grid/archive
grid      4136  3252  0 20:48 ?        00:00:00 /bin/sh ./OSWatcherFM.sh 48 /u01/app/grid/oracle.ahf/data/repository/suptools/rac1/oswbb/grid/archive
root     21723     1  2 21:38 ?        00:00:01 /u01/app/19.0.0/grid/bin/ohasd.bin exclusive
root     21812     1  1 21:38 ?        00:00:00 /u01/app/19.0.0/grid/bin/orarootagent.bin
grid     21930     1  0 21:38 ?        00:00:00 /u01/app/19.0.0/grid/bin/oraagent.bin
grid     21952     1  0 21:38 ?        00:00:00 /u01/app/19.0.0/grid/bin/mdnsd.bin
grid     21954     1  0 21:38 ?        00:00:00 /u01/app/19.0.0/grid/bin/evmd.bin
grid     21998     1  0 21:38 ?        00:00:00 /u01/app/19.0.0/grid/bin/gpnpd.bin
grid     22054 21954  0 21:38 ?        00:00:00 /u01/app/19.0.0/grid/bin/evmlogger.bin -o /u01/app/19.0.0/grid/log/[HOSTNAME]/evmd/evmlogger.info -l /u01/app/19.0.0/grid/log/[HOSTNAME]/evmd/evmlogger.log
root     22069     1  0 21:38 ?        00:00:00 /u01/app/19.0.0/grid/bin/cssdmonitor
grid     22074     1  0 21:38 ?        00:00:00 /u01/app/19.0.0/grid/bin/gipcd.bin
root     22157     1  0 21:38 ?        00:00:00 /u01/app/19.0.0/grid/bin/cssdagent
grid     22182     1  2 21:38 ?        00:00:01 /u01/app/19.0.0/grid/bin/ocssd.bin -X
grid     22357  4136  0 21:38 ?        00:00:00 sleep 60
root     22496     1  0 21:38 ?        00:00:00 /u01/app/19.0.0/grid/bin/octssd.bin reboot
grid     22576     1  0 21:38 ?        00:00:00 asm_pmon_+ASM1
grid     22580     1  0 21:38 ?        00:00:00 asm_clmn_+ASM1
grid     22584     1  0 21:38 ?        00:00:00 asm_psp0_+ASM1
grid     22589     1  0 21:38 ?        00:00:00 asm_vktm_+ASM1
grid     22595     1  0 21:38 ?        00:00:00 asm_gen0_+ASM1
grid     22599     1  0 21:38 ?        00:00:00 asm_mman_+ASM1
grid     22605     1  0 21:38 ?        00:00:00 asm_gen1_+ASM1
grid     22608     1  0 21:38 ?        00:00:00 asm_diag_+ASM1
grid     22610     1  0 21:38 ?        00:00:00 asm_ping_+ASM1
grid     22612     1  0 21:38 ?        00:00:00 asm_pman_+ASM1
grid     22616     1  0 21:38 ?        00:00:00 asm_dia0_+ASM1
grid     22618     1  1 21:38 ?        00:00:00 asm_lmon_+ASM1
grid     22622     1  0 21:38 ?        00:00:00 asm_lmd0_+ASM1
grid     22624     1  0 21:38 ?        00:00:00 asm_lms0_+ASM1
grid     22629     1  0 21:38 ?        00:00:00 asm_lmhb_+ASM1
grid     22633     1  0 21:38 ?        00:00:00 asm_lck1_+ASM1
grid     22637     1  0 21:38 ?        00:00:00 asm_dbw0_+ASM1
grid     22641     1  0 21:38 ?        00:00:00 asm_lgwr_+ASM1
grid     22645     1  0 21:38 ?        00:00:00 asm_ckpt_+ASM1
grid     22649     1  0 21:38 ?        00:00:00 asm_smon_+ASM1
grid     22653     1  0 21:38 ?        00:00:00 asm_lreg_+ASM1
grid     22657     1  0 21:38 ?        00:00:00 asm_pxmn_+ASM1
grid     22659     1  0 21:38 ?        00:00:00 asm_rbal_+ASM1
grid     22663     1  0 21:38 ?        00:00:00 asm_gmon_+ASM1
grid     22667     1  0 21:38 ?        00:00:00 asm_mmon_+ASM1
grid     22669     1  0 21:38 ?        00:00:00 asm_mmnl_+ASM1
grid     22671     1  0 21:38 ?        00:00:00 asm_imr0_+ASM1
grid     22674     1  0 21:38 ?        00:00:00 asm_scm0_+ASM1
grid     22676     1  0 21:38 ?        00:00:00 asm_lck0_+ASM1
grid     22680     1  0 21:38 ?        00:00:00 asm_m000_+ASM1
grid     22685     1  0 21:38 ?        00:00:00 asm_gcr0_+ASM1
grid     22838  3252  0 21:39 ?        00:00:00 sleep 30
root     22929  6928  0 21:39 pts/0    00:00:00 grep --color=auto grid
[root@rac1 ~]# crsctl stat res -t
CRS-4535: Cannot communicate with Cluster Ready Services
CRS-4000: Command Status failed, or completed with errors.
[root@rac1 ~]# crsctl stat res -t
CRS-4535: Cannot communicate with Cluster Ready Services
CRS-4000: Command Status failed, or completed with errors.
[root@rac1 ~]# su - grid
Last login: Sat Oct 28 21:23:14 CST 2023
[grid@rac1 ~]$ sqlplus '/as sysasm'

SQL*Plus: Release 19.0.0.0.0 - Production on Sat Oct 28 21:39:53 2023
Version 19.20.0.0.0

Copyright (c) 1982, 2022, Oracle.  All rights reserved.

Connected to:
Oracle Database 19c Enterprise Edition Release 19.0.0.0.0 - Production
Version 19.20.0.0.0

SQL> select name, state from v$asm_diskgroup;

NAME                           STATE
------------------------------ -----------
DATA1                          MOUNTED
DATA                           MOUNTED

SQL> 

This document provides the steps to validate the ASM Instances and diskgroups on a RAC Cluster (when CRS does not start). SOLUTION In order to confirm & validate the ASM instances and diskgroups are in good shape (ASM instances start and diskgroups are mounted), please perform the next steps (bypassing CRS): 1) Shutdown CRS on all the nodes: # crsctl stop crs 2) Then start the clusterware in exclusive mode on node #1: # crsctl start crs -excl -nocrs Note: On release 11.2.0.1, you need to use the next command: # crsctl start crs -excl 3) Connect to the +ASM1 instance and then make sure all the diskgroups are mounted including the OCRVOTE diskgroup: SQL> select name, state from v$asm_diskgroup; 4) If not, then mount them (example): SQL. alter diskgroup OCRVOTE mount; SQL> select name, state from v$asm_diskgroup; 5) Then shutdown the clusterware on node #1: # crsctl stop crs -f 6) Now, start  the the clusterware in exclusive mode on node #2: # crsctl start crs -excl -nocrs Note: On release 11.2.0.1, you need to use the next command: # crsctl start crs -excl 7) Connect to the +ASM2 instance and then make sure all the diskgroups are mounted including the OCRVOTE diskgroup: SQL> select name, state from v$asm_diskgroup; 8) If not, then mount them: SQL. alter diskgroup OCRVOTE mount; SQL> select name, state from v$asm_diskgroup; 9) Then shutdown the clusterware on node #2: # crsctl stop crs -f 10) Please repeat the same steps on the additional nodes.