diff options
Diffstat (limited to '')
| -rwxr-xr-x | heartbeat/oracle | 789 |
1 files changed, 789 insertions, 0 deletions
diff --git a/heartbeat/oracle b/heartbeat/oracle new file mode 100755 index 0000000..8cf4e36 --- /dev/null +++ b/heartbeat/oracle @@ -0,0 +1,789 @@ +#!/bin/sh +# +# +# oracle +# +# Description: Manages an Oracle Database as a High-Availability +# resource +# +# +# Author: Dejan Muhamedagic +# Support: users@clusterlabs.org +# License: GNU General Public License (GPL) +# Copyright: (C) 2006 International Business Machines, Inc. +# +# This code inspired by the DB2 resource script +# written by Alan Robertson +# +# An example usage in /etc/ha.d/haresources: +# node1 10.0.0.170 oracle::RK1::/oracle/10.2::orark1 +# +# See oracle_usage() function below for more details... +# +# OCF instance parameters: +# OCF_RESKEY_sid +# OCF_RESKEY_home (optional; else read it from /etc/oratab) +# OCF_RESKEY_user (optional; figure it out by checking file ownership) +# OCF_RESKEY_ipcrm (optional; defaults to "instance") +# OCF_RESKEY_clear_backupmode (optional; default to "false") +# OCF_RESKEY_shutdown_method (optional; default to "checkpoint/abort") +# OCF_RESKEY_monuser (optional; defaults to "OCFMON") +# OCF_RESKEY_monpassword (optional; defaults to "OCFMON") +# OCF_RESKEY_monprofile (optional; defaults to "OCFMONPROFILE") +# +# Initialization: + +: ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/lib/heartbeat} +. ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs +. ${OCF_FUNCTIONS_DIR}/ora-common.sh + +####################################################################### + +oracle_usage() { + methods=`oracle_methods` + methods=`echo $methods | tr ' ' '|'` + cat <<-! + usage: $0 {$methods} + + $0 manages an Oracle Database instance as an HA resource. + + The 'start' operation starts the database. + The 'stop' operation stops the database. + The 'status' operation reports whether the database is running + The 'monitor' operation reports whether the database seems to be working + The 'dumpinstipc' operation prints IPC resources used by the instance + The 'cleanup' operation tries to clean up after Oracle was brutally stopped + The 'validate-all' operation reports whether the parameters are valid + The 'methods' operation reports on the methods $0 supports + + ! +} + +# Defaults +OCF_RESKEY_sid_default="" +OCF_RESKEY_home_default="" +OCF_RESKEY_user_default="" +OCF_RESKEY_monuser_default="OCFMON" +OCF_RESKEY_monpassword_default="OCFMON" +OCF_RESKEY_monprofile_default="OCFMONPROFILE" +OCF_RESKEY_ipcrm_default="instance" +OCF_RESKEY_clear_backupmode_default="false" +OCF_RESKEY_shutdown_method_default="checkpoint/abort" + +oracle_meta_data() { + cat <<END +<?xml version="1.0"?> +<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd"> +<resource-agent name="oracle" version="1.0"> +<version>1.0</version> + +<longdesc lang="en"> +Resource script for oracle. Manages an Oracle Database instance +as an HA resource. +</longdesc> +<shortdesc lang="en">Manages an Oracle Database instance</shortdesc> + +<parameters> + +<parameter name="sid" unique="1" required="1"> +<longdesc lang="en"> +The Oracle SID (aka ORACLE_SID). +</longdesc> +<shortdesc lang="en">sid</shortdesc> +<content type="string" default="${OCF_RESKEY_sid_default}" /> +</parameter> + +<parameter name="home" unique="0"> +<longdesc lang="en"> +The Oracle home directory (aka ORACLE_HOME). +If not specified, then the SID along with its home should be listed in +/etc/oratab. +</longdesc> +<shortdesc lang="en">home</shortdesc> +<content type="string" default="${OCF_RESKEY_home_default}" /> +</parameter> + +<parameter name="user" unique="0"> +<longdesc lang="en"> +The Oracle owner (aka ORACLE_OWNER). +If not specified, then it is set to the owner of +file \$ORACLE_HOME/dbs/*\${ORACLE_SID}.ora. +If this does not work for you, just set it explicitely. +</longdesc> +<shortdesc lang="en">user</shortdesc> +<content type="string" default="${OCF_RESKEY_user_default}" /> +</parameter> + +<parameter name="monuser" unique="0"> +<longdesc lang="en"> +Monitoring user name. Every connection as +sysdba is logged in an audit log. This can +result in a large number of new files created. +A new user is created (if it doesn't exist) in +the start action and subsequently used in monitor. +It should have very limited rights. Make sure +that the password for this user does not expire. +</longdesc> +<shortdesc lang="en">monuser</shortdesc> +<content type="string" default="$OCF_RESKEY_monuser_default" /> +</parameter> + +<parameter name="monpassword" unique="0"> +<longdesc lang="en"> +Password for the monitoring user. Make sure +that the password for this user does not expire. +Need to explicitly set a password to a new monitor +user for the security reason. +</longdesc> +<shortdesc lang="en">monpassword</shortdesc> +<content type="string" default="$OCF_RESKEY_monpassword_default" /> +</parameter> + +<parameter name="monprofile" unique="0"> +<longdesc lang="en"> +Profile used by the monitoring user. If the +profile does not exist, it will be created +with a non-expiring password. +</longdesc> +<shortdesc lang="en">monprofile</shortdesc> +<content type="string" default="$OCF_RESKEY_monprofile_default" /> +</parameter> + +<parameter name="ipcrm" unique="0"> +<longdesc lang="en"> +Sometimes IPC objects (shared memory segments and semaphores) +belonging to an Oracle instance might be left behind which +prevents the instance from starting. It is not easy to figure out +which shared segments belong to which instance, in particular when +more instances are running as same user. + +What we use here is the "oradebug" feature and its "ipc" trace +utility. It is not optimal to parse the debugging information, but +I am not aware of any other way to find out about the IPC +information. In case the format or wording of the trace report +changes, parsing might fail. There are some precautions, however, +to prevent stepping on other peoples toes. There is also a +dumpinstipc option which will make us print the IPC objects which +belong to the instance. Use it to see if we parse the trace file +correctly. + +Three settings are possible: + +- none: don't mess with IPC and hope for the best (beware: you'll + probably be out of luck, sooner or later) +- instance: try to figure out the IPC stuff which belongs to the + instance and remove only those (default; should be safe) +- orauser: remove all IPC belonging to the user which runs the + instance (don't use this if you run more than one instance as same + user or if other apps running as this user use IPC) + +The default setting "instance" should be safe to use, but in that +case we cannot guarantee that the instance will start. In case IPC +objects were already left around, because, for instance, someone +mercilessly killing Oracle processes, there is no way any more to +find out which IPC objects should be removed. In that case, human +intervention is necessary, and probably _all_ instances running as +same user will have to be stopped. The third setting, "orauser", +guarantees IPC objects removal, but it does that based only on IPC +objects ownership, so you should use that only if every instance +runs as separate user. + +Please report any problems. Suggestions/fixes welcome. +</longdesc> +<shortdesc lang="en">ipcrm</shortdesc> +<content type="string" default="${OCF_RESKEY_ipcrm_default}" /> +</parameter> + +<parameter name="clear_backupmode" unique="0" required="0"> +<longdesc lang="en"> +The clear of the backup mode of ORACLE. +</longdesc> +<shortdesc lang="en">clear_backupmode</shortdesc> +<content type="boolean" default="${OCF_RESKEY_clear_backupmode_default}" /> +</parameter> + +<parameter name="shutdown_method" unique="0" required="0"> +<longdesc lang="en"> +How to stop Oracle is a matter of taste it seems. The default +method ("checkpoint/abort") is: + + alter system checkpoint; + shutdown abort; + +This should be the fastest safe way bring the instance down. If +you find "shutdown abort" distasteful, set this attribute to +"immediate" in which case we will + + shutdown immediate; + +If you still think that there's even better way to shutdown an +Oracle instance we are willing to listen. +</longdesc> +<shortdesc lang="en">shutdown_method</shortdesc> +<content type="string" default="${OCF_RESKEY_shutdown_method_default}" /> +</parameter> + +</parameters> + +<actions> +<action name="start" timeout="120s" /> +<action name="stop" timeout="120s" /> +<action name="status" timeout="5s" /> +<action name="monitor" depth="0" timeout="30s" interval="120s" /> +<action name="validate-all" timeout="5s" /> +<action name="methods" timeout="5s" /> +<action name="meta-data" timeout="5s" /> +</actions> +</resource-agent> +END +} + + +# +# methods: What methods/operations do we support? +# +oracle_methods() { + cat <<-! + start + stop + status + monitor + dumpinstipc + showdbstat + cleanup + validate-all + methods + meta-data + usage + ! +} + +# +# Run commands as the Oracle owner... +# +execsql() { + if [ "$US" = "$ORACLE_OWNER" ]; then + sqlplus -S /nolog + else + su - $ORACLE_OWNER -s /bin/sh -c ". $ORA_ENVF; sqlplus -S /nolog" + fi +} + +# +# Run commands in the oracle admin sqlplus... +# +common_sql_opts() { + cat<<EOF +set feedback off +set heading off +set pagesize 0 +EOF +} +common_sql_filter() { + grep -v '^Connected' | + grep -v '^ENV MSG:' | + grep -v 'Your password will expire in' +} +runsql() { + local conn_s="$1" + shift 1 + local func + ( + echo "$conn_s" + common_sql_opts + for func; do $func; done + ) | + execsql | common_sql_filter +} +dbasql() { + runsql "connect / as sysdba" $* +} +monsql() { + runsql "connect \"$MONUSR\"/\"$MONPWD\"" $* +} +# use dbasql_one if the query should result in a single line output +# at times people stuff commands in oracle .profile +# which may produce extra output +dbasql_one() { + dbasql $* | tail -1 +} +monsql_one() { + monsql $* | tail -1 +} + +# +# various interesting sql +# +dbstat() { + echo 'select status from v$instance;' +} +dbmount() { + echo 'alter database mount;' +} +dbopen() { + echo 'alter database open;' +} +dbstop_immediate() { + echo 'shutdown immediate' +} +dbstop_checkpoint_abort() { + echo 'alter system checkpoint;' + echo 'shutdown abort' +} +dbstop() { + case "${shutdown_method}" in + "immediate") + dbstop_immediate + ;; + "checkpoint/abort") + dbstop_checkpoint_abort + ;; + esac +} +dbstart() { + echo 'startup' +} +dbstart_mount() { + echo 'startup mount' +} +dbendbackup() { + echo 'alter database end backup;' +} +db_backup_mode() { + echo "select 'COUNT'||count(*) from v\$backup where status='ACTIVE';" +} +is_clear_backupmode_set(){ + ocf_is_true "${clear_backupmode}" +} +is_instance_in_backup_mode() { + local count + count="`dbasql_one db_backup_mode | sed 's/COUNT//'`" + [ x"$count" != x"0" ] +} +clear_backup_mode() { + local output + output="`dbasql dbendbackup`" + ocf_log info "Oracle instance $ORACLE_SID alter database end backup: $output" +} +getdumpdest() { + #echo 'select value from v$parameter where name = \'user_dump_dest\';' + echo "select value from v\$parameter where name = 'user_dump_dest';" +} +getipc() { + echo "oradebug setmypid" + echo "oradebug tracefile_name" + echo "oradebug ipc" +} +show_mon_profile() { + echo "select PROFILE from dba_profiles where PROFILE='$MONPROFILE';" +} +mk_mon_profile() { + cat<<EOF +create profile "$MONPROFILE" limit FAILED_LOGIN_ATTEMPTS UNLIMITED PASSWORD_LIFE_TIME UNLIMITED; +EOF +} +show_mon_user() { + echo "select USERNAME, ACCOUNT_STATUS from dba_users where USERNAME='$MONUSR';" +} +mk_mon_user() { + cat<<EOF +create user "$MONUSR" identified by "$MONPWD" profile "$MONPROFILE"; +grant create session to "$MONUSR"; +grant select on v_\$instance to "$MONUSR"; +EOF +} +show_mon_user_profile() { + echo "select PROFILE from dba_users where USERNAME='$MONUSR';" +} +set_mon_user_profile() { + echo "alter user "$MONUSR" profile "$MONPROFILE";" +} +reset_mon_user_password() { + echo "alter user "$MONUSR" identified by "$MONPWD";" +} +check_mon_profile() { + local output + output=`dbasql show_mon_profile` + if echo "$output" | grep -iw "^$MONPROFILE" >/dev/null; then + return 0 + fi + output=`dbasql mk_mon_profile show_mon_profile` + if echo "$output" | grep -iw "^$MONPROFILE" >/dev/null; then + return 0 + elif echo "$output" | grep ORA-65140 >/dev/null 2>&1; then + ocf_exit_reason "monprofile must start with C## for container databases" + return $OCF_ERR_CONFIGURED + else + ocf_exit_reason "could not create $MONPROFILE oracle profile" + ocf_log err "sqlplus output: $output" + return 1 + fi +} +check_mon_user() { + local output + local output2 + + output=`dbasql show_mon_user` + if echo "$output" | grep -iw "^$MONUSR" >/dev/null; then + if echo "$output" | grep -w "EXPIRED" >/dev/null; then + dbasql reset_mon_user_password + fi + output=`dbasql show_mon_user_profile` + if echo "$output" | grep -iw "^$MONPROFILE" >/dev/null; then + return 0 + else + output=`dbasql set_mon_user_profile` + output2=`dbasql show_mon_user_profile` + if echo "$output2" | grep -iw "^$MONPROFILE" >/dev/null; then + return 0 + fi + ocf_exit_reason "could not set profile for $MONUSR oracle user" + ocf_log err "sqlplus output: $output( $output2 )" + return 1 + fi + fi + + if [ -z "$OCF_RESKEY_monpassword" ]; then + ocf_exit_reason "Resource param 'monpassword' not set. Please configure monpassword for $MONUSR oracle user" + exit $OCF_ERR_CONFIGURED + fi + + output=`dbasql mk_mon_user show_mon_user` + if echo "$output" | grep -iw "^$MONUSR" >/dev/null; then + return 0 + elif echo "$output" | grep ORA-65096 >/dev/null 2>&1; then + ocf_exit_reason "monuser must start with C## for container databases" + return $OCF_ERR_CONFIGURED + else + ocf_exit_reason "could not create $MONUSR oracle user" + ocf_log err "sqlplus output: $output" + return 1 + fi +} +# +# print the output of dbstat (for debugging) +# +showdbstat() { + echo "Full output:" + dbstat | execsql + echo "Stripped output:" + echo "<`dbasql dbstat`>" +} + +# +# IPC stuff: not overly complex, but quite involved :-/ +# + +# Part 1: Oracle +other_trace_junk() { + echo $1 | sed 's/trc$/trm/' +} +dumpinstipc() { + local output tracef + output=`dbasql getipc` # filename in the 2nd line + tracef=`echo "$output" | awk 'NR==2' | grep '^/.*trc$'` + if [ "$tracef" ]; then + echo $tracef + else + ocf_log warn "'dbasql getipc' failed: $output" + return 1 + fi +} +parseipc() { + local inf=$1 + if [ ! -f "$1" ]; then + ocf_log warn "$1: no such ipc trace file" + return 1 + fi + awk ' + $3 == "Shmid" {n=1;next} + n { + if( $3~/^[0-9]+$/ ) print $3; + n=0 + } + ' $inf | + sort -u | sed 's/^/m:/' + awk ' + /Semaphore List/ {insems=1;next} + insems { + for( i=1; i<=NF; i++ ) + if( $i~/^[0-9]+$/ ) print $i; + } + /system semaphore information/ {exit} + ' $inf | + sort -u | sed 's/^/s:/' + TMPFILES="$TMPFILES $inf `other_trace_junk $inf`" +} + +# Part 2: OS (ipcs,ipcrm) +filteroraipc() { # this portable? + grep -w $ORACLE_OWNER | awk '{print $2}' +} +ipcdesc() { + local what=$1 + case $what in + m) echo "shared memory segment";; + s) echo "semaphore";; + q) echo "message queue";; + esac +} +rmipc() { + local what=$1 id=$2 + ipcs -$what | filteroraipc | grep -iw $id >/dev/null 2>&1 || + return + ocf_log info "Removing `ipcdesc $what` $id." + ipcrm -$what $id +} +ipcrm_orauser() { + local what id + for what in m s q; do + for id in `ipcs -$what | filteroraipc`; do + rmipc $what $id + done + done +} +ipcrm_instance() { + local ipcobj + for ipcobj; do + rmipc `echo $ipcobj | sed 's/:/ /'` + done +} + +# +# oracle_status: is the Oracle instance running? +# +# quick check to see if the instance is up +is_proc_running() { + ps -ef | grep -wiqs "[^ ]*[_]pmon_${ORACLE_SID}" +} +# instance in OPEN state? +instance_live() { + local status=`monsql_one dbstat` + [ "$status" = OPEN ] && return 0 + ocf_log warn "Unable to login as \"$MONUSR\", using \"sysdba\" user instead" + status=`dbasql_one dbstat` + if [ "$status" = OPEN ]; then + return 0 + else + ocf_log info "$ORACLE_SID instance state is not OPEN (dbstat output: $status)" + return 1 + fi +} + +ora_cleanup() { + #rm -fr /tmp/.oracle #??? + rm -f `ls $ORACLE_HOME/dbs/lk* | grep -i "$ORACLE_SID\$"` + #return + + case $IPCRM in + none) + ;; + instance) + ipcrm_instance $* + ;; + orauser) + ipcrm_orauser $* + ;; + esac +} + +oracle_getconfig() { + ora_common_getconfig "$OCF_RESKEY_sid" "$OCF_RESKEY_home" "$OCF_RESKEY_user" + + clear_backupmode=${OCF_RESKEY_clear_backupmode:-${OCF_RESKEY_clear_backupmode_default}} + shutdown_method=${OCF_RESKEY_shutdown_method:-${OCF_RESKEY_shutdown_method_default}} + IPCRM=${OCF_RESKEY_ipcrm:-${OCF_RESKEY_ipcrm_default}} +} + +# +# oracle_start: Start the Oracle instance +# +# NOTE: We handle instance in the MOUNTED and STARTED states +# efficiently +# We *do not* handle instance in the restricted or read-only +# mode, i.e. it appears as running, but its availability is +# "not for general use" +# + +oracle_start() { + local status output + if is_proc_running; then + status="`dbasql_one dbstat`" + case "$status" in + "OPEN") + : nothing to be done, we can leave right now + ocf_log info "Oracle instance $ORACLE_SID already running" + return $OCF_SUCCESS + ;; + "STARTED") + output=`dbasql dbmount` + ;; + "MOUNTED") + : we proceed if mounted + ;; + *) # status unknown + output=`dbasql dbstop dbstart_mount` + ;; + esac + else + output="`dbasql dbstart_mount`" + # try to cleanup in case of + # ORA-01081: cannot start already-running ORACLE - shut it down first + if echo "$output" | grep ORA-01081 >/dev/null 2>&1; then + ocf_log info "ORA-01081 error found, trying to cleanup oracle (dbstart_mount output: $output)" + ora_cleanup + output=`dbasql dbstop_immediate` + output=`dbasql dbstart_mount` + fi + fi + + # oracle instance should be mounted. + status="`dbasql_one dbstat`" + case "$status" in + "MOUNTED") + ;; + *) + : error!! + ocf_exit_reason "oracle $ORACLE_SID can not be mounted (status: $status)" + return $OCF_ERR_GENERIC + ;; + esac + + # It is examined whether mode is "online backup mode", + # and if it is true, makes clear the mode. + # Afterwards, DB is opened. + if is_clear_backupmode_set && is_instance_in_backup_mode; then + clear_backup_mode + fi + output=`dbasql dbopen` + + # check/create the monitor profile + if ! check_mon_profile; then + # dbopen was failed if there is any $output + [ -n "$output" ] && ocf_exit_reason "oracle $ORACLE_SID can not be opened: $output" + return $OCF_ERR_GENERIC + fi + + # check/create the monitor user + if ! check_mon_user; then + # dbopen was failed if there is any $output + [ -n "$output" ] && ocf_exit_reason "oracle $ORACLE_SID can not be opened: $output" + return $OCF_ERR_GENERIC + fi + + if ! is_proc_running; then + ocf_exit_reason "oracle process not running: $output" + return $OCF_ERR_GENERIC + elif ! instance_live; then + ocf_exit_reason "oracle instance $ORACLE_SID not started: $output" + return $OCF_ERR_GENERIC + else + : cool, we are up and running + ocf_log info "Oracle instance $ORACLE_SID started: $output" + return $OCF_SUCCESS + fi +} + +# +# oracle_stop: Stop the Oracle instance +# +oracle_stop() { + local status output ipc="" + if is_proc_running; then + [ "$IPCRM" = "instance" ] && ipc=$(parseipc `dumpinstipc`) + output=`dbasql dbstop` + else + ocf_log info "Oracle instance $ORACLE_SID already stopped" + return $OCF_SUCCESS + fi + ocf_stop_processes TERM $PROCS_CLEANUP_TIME `proc_pids` # kill the procs if they hanged + if is_proc_running; then + ocf_exit_reason "Oracle instance $ORACLE_SID not stopped: $output" + return $OCF_ERR_GENERIC + else + ocf_log info "Oracle instance $ORACLE_SID stopped: $output" + sleep 1 # give em a chance to cleanup + ocf_log info "Cleaning up for $ORACLE_SID" + ora_cleanup "$ipc" + return $OCF_SUCCESS + fi +} + +# +# oracle_monitor: Can the Oracle instance do anything useful? +# +oracle_monitor() { + if ! is_proc_running; then + ocf_log info "oracle process not running" + return $OCF_NOT_RUNNING + fi + if ! instance_live; then + ocf_exit_reason "oracle instance $ORACLE_SID is down" + return $OCF_ERR_GENERIC + fi + #ocf_log info "Oracle instance $ORACLE_SID is alive" + return $OCF_SUCCESS +} + +# other supported actions +oracle_status() { + if is_proc_running + then + echo Oracle instance $ORACLE_SID is running + exit $OCF_SUCCESS + else + echo Oracle instance $ORACLE_SID is stopped + exit $OCF_NOT_RUNNING + fi +} +oracle_dumpinstipc() { + is_proc_running && parseipc `dumpinstipc` +} +oracle_showdbstat() { + showdbstat +} +oracle_cleanup() { + if [ "$IPCRM" = "instance" ]; then + ora_cleanup $(parseipc `dumpinstipc`) + else + ora_cleanup + fi +} +oracle_validate_all() { + case "${shutdown_method}" in + "immediate") ;; + "checkpoint/abort") ;; + *) ocf_exit_reason "unsupported shutdown_method, please read meta-data" + return $OCF_ERR_CONFIGURED + ;; + esac + + case "${IPCRM}" in + "none"|"instance"|"orauser") ;; + *) ocf_exit_reason "unsupported ipcrm setting, please read meta-data" + return $OCF_ERR_CONFIGURED + ;; + esac + + ora_common_validate_all +} + +# used in ora-common.sh +show_procs() { + ps -e -o pid,args | grep -i "[o]ra[a-zA-Z0-9_]*$ORACLE_SID$" +} +proc_pids() { show_procs | awk '{print $1}'; } +PROCS_CLEANUP_TIME="30" + +MONUSR=${OCF_RESKEY_monuser:-$OCF_RESKEY_monuser_default} +MONPWD=${OCF_RESKEY_monpassword:-$OCF_RESKEY_monpassword_default} +MONPROFILE=${OCF_RESKEY_monprofile:-$OCF_RESKEY_monprofile_default} + +MONUSR=$(echo "$MONUSR" | awk '{print toupper($0)}') +MONPROFILE=$(echo "$MONPROFILE" | awk '{print toupper($0)}') +OCF_REQUIRED_PARAMS="sid" +OCF_REQUIRED_BINARIES="sqlplus" +ocf_rarun $* + +# +# vim:tabstop=4:shiftwidth=4:textwidth=0:wrapmargin=0 |