如何在线关闭ora.crf服务，删除CHM文件-由于bdb文件过大导致软件目录告警

2020-08-24 00:00:00 集群删除文件生产在线

ora.crf服务的功能是Cluster Health Monitor（简称CHM）,是Oracle提供监控检测工具，可以自动收集操作系统的资源（CPU、内存、SWAP、进程、I/O以及网络等）信息。CHM会每秒收集一次数据。这些系统资源数据对于诊断集群系统的节点重启、Hang、实例驱逐(Eviction)、性能问题等。但是由于生成的bdb文件很多，对软件目录是个很大的冲击。本文测试如何在线停止ora.crf服务，并删除其记录的文件（太占用软件目录）。这个测试用例来自银行生产环境的实施前的测试文档。

在线停止ora.crf服务，删除CHM文件

1 查询当前资源ora.crf状态

[grid@rac1 ~]$ crsctl status res ora.crf -init

NAME=ora.crf

TYPE=ora.crf.type

TARGET=ONLINE

STATE=ONLINE on rac1

[grid@rac1 ~]$ crsctl stat res -t -init

--------------------------------------------------------------------------------

NAME TARGET STATE SERVER STATE_DETAILS

--------------------------------------------------------------------------------

Cluster Resources

--------------------------------------------------------------------------------

ora.asm

1 ONLINE ONLINE rac1 Started

ora.cluster_interconnect.haip

1 ONLINE ONLINE rac1

ora.crf

1 ONLINE ONLINE rac1

2 停止ora.crf资源服务

[grid@rac1 ~]$ /oracle/asm/bin/crsctl stop res ora.crf -init

CRS-2673: Attempting to stop 'ora.crf' on 'rac1'

CRS-2677: Stop of 'ora.crf' on 'rac1' succeeded

[grid@rac1 ~]$ /oracle/asm/bin/crsctl status res ora.crf -init

NAME=ora.crf

TYPE=ora.crf.type

TARGET=OFFLINE

STATE=OFFLINE

3 删除CHM的bdb文件。(root用户）

cd /oracle/asm/crf/db/rac1/

[root@rac1 rac1]# ls -lrt *.bdb

-rw-r----- 1 root root 8192 Apr 15 22:26 crfconn.bdb

-rw-r----- 1 root root 8192 Sep 17 10:08 repdhosts.bdb

-rw-r----- 1 root root 442368 Sep 17 10:08 crfts.bdb

-rw-r----- 1 root root 487424 Sep 17 10:08 crfloclts.bdb

-rw-r----- 1 root root 565248 Sep 17 10:08 crfhosts.bdb

-rw-r----- 1 root root 729088 Sep 17 10:08 crfcpu.bdb

-rw-r----- 1 root root 26214400 Sep 17 10:08 crfclust.bdb

-rw-r----- 1 root root 536576 Sep 17 10:08 crfalert.bdb

[root@rac1 rac1]# rm -rf *.bdb

验证删除

[root@rac1 rac1]# ls -lrt *.bdb

ls: cannot access *.bdb: No such file or directory

4 禁止ora.crf随机自启动（root用户）

/[root@rac1 rac1]# /oracle/asm/bin/crsctl modify res ora.crf -attr ENABLED=0 -init

验证修改效果

[root@rac1 rac1]# /oracle/asm/bin/crsctl status res ora.crf -init -f <<<<<<<< DISABLED = 0

NAME=ora.crf

TYPE=ora.crf.type

STATE=OFFLINE

TARGET=OFFLINE

ACL=owner:root:rw-,pgrp:dba:rw-,other::r--,user:grid:r-x

ACTION_FAILURE_TEMPLATE=

ACTION_SCRIPT=

ACTIVE_PLACEMENT=0

AGENT_FILENAME=%CRS_HOME%/bin/orarootagent%CRS_EXE_SUFFIX%

AUTO_START=always

CARDINALITY=1

CARDINALITY_ID=0

CHECK_ARGS=

CHECK_COMMAND=

CHECK_INTERVAL=30

CLEAN_ARGS=

CLEAN_COMMAND=

CREATION_SEED=16

DAEMON_LOGGING_LEVELS=CRFMOND=0,CRFLDREP=0,CRFLOGD=0,CRFPROXY=0,OCLUMON=0,OCRAPI=0,OCRCLI=0,OCRMSG=0,CSSCLNT=0,CRFM=0

DAEMON_TRACING_LEVELS=CRFMOND=0,CRFLDREP=0,CRFLOGD=0,CRFPROXY=0,OCLUMON=0,OCRAPI=0,OCRCLI=0,OCRMSG=0,CSSCLNT=0,CRFM=0

DEFAULT_TEMPLATE=

DEGREE=1

DESCRIPTION="Resource type for Crf Agents"

DETACHED=true

ENABLED=0

FAILOVER_DELAY=0

FAILURE_INTERVAL=3

FAILURE_THRESHOLD=5

HOSTING_MEMBERS=

ID=ora.crf

LOAD=1

LOGGING_LEVEL=1

NOT_RESTARTING_TEMPLATE=

OFFLINE_CHECK_INTERVAL=0

ORA_VERSION=11.2.0.4.0

PID_FILE=

PLACEMENT=balanced

PROCESS_TO_MONITOR=

PROFILE_CHANGE_TEMPLATE=

RESTART_ATTEMPTS=5

SCRIPT_TIMEOUT=60

SERVER_POOLS=

START_ARGS=

START_COMMAND=

START_DEPENDENCIES=hard(ora.gpnpd)

START_TIMEOUT=120

STATE_CHANGE_TEMPLATE=

STOP_ARGS=

STOP_COMMAND=

STOP_DEPENDENCIES=hard(shutdown:ora.gipcd)

STOP_TIMEOUT=120

UNRESPONSIVE_TIMEOUT=180

UPTIME_THRESHOLD=1m

USR_ORA_ENV=

[root@rac1 rac1]# /oracle/asm/bin/crsctl status res ora.crf -init

NAME=ora.crf

TYPE=ora.crf.type

TARGET=OFFLINE

STATE=OFFLINE

5 此时集群状态

[root@rac1 rac1]# /oracle/asm/bin/crsctl stat res -t -init

--------------------------------------------------------------------------------

NAME TARGET STATE SERVER STATE_DETAILS

--------------------------------------------------------------------------------

Cluster Resources

--------------------------------------------------------------------------------

ora.asm

1 ONLINE ONLINE rac1 Started

ora.cluster_interconnect.haip

1 ONLINE ONLINE rac1

ora.crf

1 OFFLINE OFFLINE

ora.crsd

1 ONLINE ONLINE rac1

ora.cssd

1 ONLINE ONLINE rac1

ora.cssdmonitor

1 ONLINE ONLINE rac1

ora.ctssd

1 ONLINE ONLINE rac1 ACTIVE:0

ora.diskmon

1 OFFLINE OFFLINE

ora.evmd

1 ONLINE ONLINE rac1

ora.gipcd

1 ONLINE ONLINE rac1

ora.gpnpd

1 ONLINE ONLINE rac1

ora.mdnsd

1 ONLINE ONLINE rac1

[root@rac1 rac1]# /oracle/asm/bin/crsctl stat res -t

--------------------------------------------------------------------------------

NAME TARGET STATE SERVER STATE_DETAILS

--------------------------------------------------------------------------------

Local Resources

--------------------------------------------------------------------------------

ora.ASMOCR.dg

ONLINE ONLINE rac1

ONLINE ONLINE rac2

ora.ASMVG1.dg

ONLINE ONLINE rac1

ONLINE ONLINE rac2

ora.LISTENER.lsnr

ONLINE ONLINE rac1

ONLINE ONLINE rac2

ora.asm

ONLINE ONLINE rac1 Started

ONLINE ONLINE rac2 Started

ora.gsd

OFFLINE OFFLINE rac1

OFFLINE OFFLINE rac2

ora.net1.network

ONLINE ONLINE rac1

ONLINE ONLINE rac2

ora.ons

ONLINE ONLINE rac1

ONLINE ONLINE rac2

--------------------------------------------------------------------------------

Cluster Resources

--------------------------------------------------------------------------------

ora.LISTENER_SCAN1.lsnr

1 ONLINE ONLINE rac2

ora.cvu

1 ONLINE ONLINE rac1

ora.oc4j

1 ONLINE ONLINE rac1

ora.orcl.db

1 ONLINE ONLINE rac1 Open

2 ONLINE ONLINE rac2 Open

ora.rac1.vip

1 ONLINE ONLINE rac1

ora.rac2.vip

1 ONLINE ONLINE rac2

ora.scan1.vip

1 ONLINE ONLINE rac2

6 另一个节点相同操作

***********************************************************简化后的操作步骤******************************************************************

在两个节点分别执行

1 停止ora.crf资源服务

/oracle/asm/bin/crsctl stop res ora.crf -init

/oracle/asm/bin/crsctl status res ora.crf -init

2 删除CHM文件

cd /oracle/asm/crf/db/rac1/

rm -rf *. bdb

rm -rf *.ldb

3 禁止ora.crf随机自启动

/oracle/asm/bin/crsctl modify res ora.crf -attr ENABLED=0 -init (/oracle/asm/bin/crsctl modify res ora.crf -attr ENABLED=0 -init -f)

验证文件修改结果

/oracle/asm/bin/crsctl status res ora.crf -init -f

/oracle/asm/bin/crsctl status res ora.crf -init

*****************************************************生产环境可以不执行重启集群操作************************************************************

4 重启集群测试

/oracle/asm/bin/crsctl stop crs

/oracle/asm/bin/crsctl start crs

/oracle/asm/bin/crsctl status res ora.crf -init

相关文章