~ubuntu-branches/debian/jessie/resource-agents/jessie : revision 7

1

#!/bin/sh

2

#

3

# SAPInstance

4

#

5

# Description: Manages a single SAP Instance as a High-Availability

6

# resource. One SAP Instance is defined by one

7

# SAP Instance-Profile. start/stop handels all services

8

# of the START-Profile, status and monitor care only

9

# about essential services.

10

#

11

# Author: Alexander Krauth, June 2006

12

# Support: linux@sap.com

13

# License: GNU General Public License (GPL)

14

15

#

16

# An example usage:

17

# See usage() function below for more details...

18

#

19

# OCF instance parameters:

20

# OCF_RESKEY_InstanceName

21

# OCF_RESKEY_DIR_EXECUTABLE (optional, well known directories will be searched by default)

22

# OCF_RESKEY_DIR_PROFILE (optional, well known directories will be searched by default)

23

# OCF_RESKEY_START_PROFILE (optional, well known directories will be searched by default)

24

# OCF_RESKEY_START_WAITTIME (optional, to solve timing problems during J2EE-Addin start)

25

# OCF_RESKEY_AUTOMATIC_RECOVER (optional, automatic startup recovery using cleanipc, default is false)

26

# OCF_RESKEY_MONITOR_SERVICES (optional, default is to monitor critical services only)

27

# OCF_RESKEY_SHUTDOWN_METHOD (optional, defaults to NORMAL, KILL: terminate the SAP instance with OS commands - faster, at your own risk)

28

# OCF_RESKEY_ERS_InstanceName (optional, InstanceName of the ERS instance in a Master/Slave configuration)

29

# OCF_RESKEY_ERS_START_PROFILE (optional, START_PROFILE of the ERS instance in a Master/Slave configuration)

30

# OCF_RESKEY_PRE_START_USEREXIT (optional, lists a script which can be executed before the resource is started)

31

# OCF_RESKEY_POST_START_USEREXIT (optional, lists a script which can be executed after the resource is started)

32

# OCF_RESKEY_PRE_STOP_USEREXIT (optional, lists a script which can be executed before the resource is stopped)

33

# OCF_RESKEY_POST_STOP_USEREXIT (optional, lists a script which can be executed after the resource is stopped)

34

#

35

# TODO: - Option to shutdown sapstartsrv for non-active instances -> that means: do probes only with OS tools (sapinstance_status)

36

# - Option for better standalone enqueue server monitoring, using ensmon (test enque-deque)

37

# - Option for cleanup abandoned enqueue replication tables

38

#

39

#######################################################################

40

# Initialization:

41

42

: ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/lib/heartbeat}

43

. ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs

44

45

#######################################################################

46

47

SH=/bin/sh

48

49

sapinstance_usage() {

50

methods=`sapinstance_methods`

51

methods=`echo $methods | tr ' ' '|'`

52

cat <<-!

53

usage: $0 ($methods)

54

55

$0 manages a SAP Instance as an HA resource.

56

57

The 'start' operation starts the instance or the ERS instance in a Master/Slave configuration

58

The 'stop' operation stops the instance

59

The 'status' operation reports whether the instance is running

60

The 'monitor' operation reports whether the instance seems to be working

61

The 'promote' operation starts the primary instance in a Master/Slave configuration

62

The 'demote' operation stops the primary instance and starts the ERS instance

63

The 'notify' operation always returns SUCCESS

64

The 'validate-all' operation reports whether the parameters are valid

65

The 'methods' operation reports on the methods $0 supports

66

67

!

68

}

69

70

sapinstance_meta_data() {

71

cat <<END

72

<?xml version="1.0"?>

73

<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">

74

<resource-agent name="SAPInstance">

75

76

77

<shortdesc lang="en">Manages a SAP instance as an HA resource.</shortdesc>

78

79

Usually a SAP system consists of one database and at least one or more SAP instances (sometimes called application servers). One SAP Instance is defined by having exactly one instance profile. The instance profiles can usually be found in the directory /sapmnt/SID/profile. Each instance must be configured as it's own resource in the cluster configuration.

80

The resource agent supports the following SAP versions:

81

- SAP WebAS ABAP Release 6.20 - 7.30

82

- SAP WebAS Java Release 6.40 - 7.30

83

- SAP WebAS ABAP + Java Add-In Release 6.20 - 7.30 (Java is not monitored by the cluster in that case)

84

When using a SAP Kernel 6.40 please check and implement the actions from the section "Manual postprocessing" from SAP note 995116 (http://sdn.sap.com).

85

86

All operations of the SAPInstance resource agent are done by using the startup framework called SAP Management Console or sapstartsrv that was introduced with SAP kernel release 6.40. Find more information about the SAP Management Console in SAP note 1014480. Using this framework defines a clear interface for the Heartbeat cluster, how it sees the SAP system. The options for monitoring the SAP system are also much better than other methods like just watching the ps command for running processes or doing some pings to the application. sapstartsrv uses SOAP messages to request the status of running SAP processes. Therefore it can actually ask a process itself what it's status is, independent from other problems that might exist at the same time.

87

88

sapstartsrv knows 4 status colours:

89

- GREEN = everything is fine

90

- YELLOW = something is wrong, but the service is still working

91

- RED = the service does not work

92

- GRAY = the service has not been started

93

94

The SAPInstance resource agent will interpret GREEN and YELLOW as OK. That means that minor problems will not be reported to the Heartbeat cluster. This prevents the cluster from doing an unwanted failover.

95

The statuses RED and GRAY are reported as NOT_RUNNING to the cluster. Depending on the status the cluster expects from the resource, it will do a restart, failover or just nothing.

96

</longdesc>

97

98

99

<longdesc lang="en">The full qualified SAP instance name. e.g. P01_DVEBMGS00_sapp01ci. Usually this is the name of the SAP instance profile.</longdesc>

100

<shortdesc lang="en">Instance name: SID_INSTANCE_VIR-HOSTNAME</shortdesc>

101

102

</parameter>

103

104

<longdesc lang="en">The full qualified path where to find sapstartsrv and sapcontrol. Specify this parameter, if you have changed the SAP kernel directory location after the default SAP installation.</longdesc>

105

<shortdesc lang="en">Path of sapstartsrv and sapcontrol</shortdesc>

106

107

</parameter>

108

109

<longdesc lang="en">The full qualified path where to find the SAP START profile. Specify this parameter, if you have changed the SAP profile directory location after the default SAP installation.</longdesc>

110

<shortdesc lang="en">Path of start profile</shortdesc>

111

112

</parameter>

113

114

<longdesc lang="en">The name of the SAP START profile. Specify this parameter, if you have changed the name of the SAP START profile after the default SAP installation. As SAP release 7.10 does not have a START profile anymore, you need to specify the Instance Profile than.</longdesc>

115

<shortdesc lang="en">Start profile name</shortdesc>

116

117

</parameter>

118

119

<longdesc lang="en">After that time in seconds a monitor operation is executed by the resource agent. Does the monitor return SUCCESS, the start ishandled as SUCCESS. This is useful to resolve timing problems with e.g. the J2EE-Addin instance.Usually the resource agent waits until all services are started and the SAP Management Console reports a GREEN status. A double stack installation (ABAP + Java AddIn) consists of an ABAP dispatcher and aJAVA instance. Normally the start of the JAVA instance takes much longer than the start of the ABAP instance. For a JAVA Instance you may need to configure a much higher timeout for the start operation of the resource in Heartbeat. The disadvantage here is, that the discovery of a failed start by the cluster takes longer. Somebody might say: For me it is important, that the ABAP instance is up and running. A failure of the JAVA instance shall not cause a failover of the SAP instance.

120

Actually the SAP MC reports a YELLOW status, if the JAVA instance of a double stack system fails. From the resource agent point of view YELLOW means:everything is OK. Setting START_WAITTIME to a lower value determines the resource agent to check the status of the instance during a start operation after that time. As it would wait normally for a GREEN status, now it reports SUCCESS to the cluster in case of a YELLOW status already after the specified time.

121

122

That is only useful for double stack systems.

123

</longdesc>

124

<shortdesc lang="en">Check the successful start after that time (do not wait for J2EE-Addin)</shortdesc>

125

126

</parameter>

127

128

<longdesc lang="en">The SAPInstance resource agent tries to recover a failed start attempt automaticaly one time. This is done by killing runing instance processes, removing the kill.sap file and executing cleanipc. Sometimes a crashed SAP instance leaves some processes and/or shared memory segments behind. Setting this option to true will try to remove those leftovers during a start operation. That is to reduce manual work for the administrator.</longdesc>

129

<shortdesc lang="en">Enable or disable automatic startup recovery</shortdesc>

130

131

</parameter>

132

133

<longdesc lang="en">Within a SAP instance there can be several services. Usually you will find the defined services in the START profile of the related instance (Attention: with SAP Release 7.10 the START profile content was moved to the instance profile). Not all of those services are worth to monitor by the cluster. For example you properly do not like to failover your SAP instance, if the central syslog collector daemon fails.

134

Those services are monitored within the SAPInstance resource agent:

135

136

- disp+work

137

- msg_server

138

- enserver

139

- enrepserver

140

- jcontrol

141

- jstart

142

143

That names match the strings used in the output of the command 'sapcontrol -nr [Instance-Nr] -function GetProcessList'.

144

The default should fit most cases where you want to manage a SAP Instance from the cluster. You may change this with this parameter, if you like to monitor more/less or other services that sapstartsrv supports.

145

You may specify multiple services seperated by a | (pipe) sign in this parameter: disp+work|msg_server|enserver

146

</longdesc>

147

<shortdesc lang="en">Services to monitor</shortdesc>

148

149

</parameter>

150

151

<longdesc lang="en">Usual a SAP Instance is stopped by the command 'sapcontrol -nr InstanceNr -function Stop'. SHUTDOWN_METHOD=KILL means to kill the SAP Instance using OS commands. SAP processes of the instance are terminated with 'kill -9', shared memory is deleted with 'cleanipc' and the 'kill.sap' file will be deleted. That method is much faster than the gracefull stop, but the instance does not have the chance to say goodbye to other SAPinstances in the same system. USE AT YOUR OWN RISK !!</longdesc>

152

<shortdesc lang="en">Shutdown graceful or kill a SAP instance by terminating the processes. (normal|KILL)</shortdesc>

153

154

</parameter>

155

156

<longdesc lang="en">Only used in a Master/Slave resource configuration:

157

The full qualified SAP enqueue replication instance name. e.g. P01_ERS02_sapp01ers. Usually this is the name of the SAP instance profile.

158

The enqueue replication instance must be installed, before you want to configure a master-slave cluster recource.

159

160

The master-slave configuration in the cluster must use this properties:

161

clone_max = 2

162

clone_node_max = 1

163

master_node_max = 1

164

master_max = 1

165

</longdesc>

166

<shortdesc lang="en">Enqueue replication instance name: SID_INSTANCE_VIR-HOSTNAME</shortdesc>

167

168

</parameter>

169

170

<longdesc lang="en">Only used in a Master/Slave resource configuration:

171

The parameter ERS_InstanceName must also be set in this configuration.

172

The name of the SAP START profile. Specify this parameter, if you have changed the name of the SAP START profile after the default SAP installation. As SAP release 7.10 does not have a START profile anymore, you need to specify the Instance Profile than.

173

</longdesc>

174

<shortdesc lang="en">Enqueue replication start profile name</shortdesc>

175

176

</parameter>

177

178

<longdesc lang="en">The full qualified path where to find a script or program which should be executed before this resource gets started.</longdesc>

179

<shortdesc lang="en">Path to a pre-start script</shortdesc>

180

181

</parameter>

182

183

<longdesc lang="en">The full qualified path where to find a script or program which should be executed after this resource got started.</longdesc>

184

<shortdesc lang="en">Path to a post-start script</shortdesc>

185

186

</parameter>

187

188

<longdesc lang="en">The full qualified path where to find a script or program which should be executed before this resource gets stopped.</longdesc>

189

<shortdesc lang="en">Path to a pre-start script</shortdesc>

190

191

</parameter>

192

193

<longdesc lang="en">The full qualified path where to find a script or program which should be executed after this resource got stopped.</longdesc>

194

<shortdesc lang="en">Path to a post-start script</shortdesc>

195

196

</parameter>

197

</parameters>

198

199

200

201

202

203

204

205

206

207

208

209

</actions>

210

</resource-agent>

211

END

212

}

213

214

215

#

216

# methods: What methods/operations do we support?

217

#

218

sapinstance_methods() {

219

cat <<-!

220

start

221

stop

222

status

223

monitor

224

promote

225

demote

226

notify

227

validate-all

228

methods

229

meta-data

230

usage

231

!

232

}

233

234

235

236

#

237

# is_clone : find out if we are configured to run in a Master/Slave configuration

238

#

239

is_clone() {

240

if [ -n "$OCF_RESKEY_CRM_meta_clone_max" ] \

241

&& [ "$OCF_RESKEY_CRM_meta_clone_max" -gt 0 ]

242

then

243

if [ "$OCF_RESKEY_CRM_meta_clone_max" -ne 2 ] || \

244

[ "$OCF_RESKEY_CRM_meta_clone_node_max" -ne 1 ] || \

245

[ "$OCF_RESKEY_CRM_meta_master_node_max" -ne 1 ] || \

246

[ "$OCF_RESKEY_CRM_meta_master_max" -ne 1 ]

247

then

248

ocf_log err "Clone options misconfigured. (expect: clone_max=2,clone_node_max=1,master_node_max=1,master_max=1)"

249

exit $OCF_ERR_CONFIGURED

250

fi

251

252

if [ -z "$OCF_RESKEY_ERS_InstanceName" ]

253

then

254

ocf_log err "In a Master/Slave configuration the ERS_InstanceName parameter is mandatory."

255

exit $OCF_ERR_ARGS

256

fi

257

else

258

return 0

259

fi

260

return 1

261

}

262

263

264

#

265

# abnormal_end : essential things are missing, but in the natur of a SAP installation - which can be very different

266

# from customer to customer - we cannot handle this always as an error

267

# This would be the case, if the software is installed on shared disks and not visible

268

# to all cluster nodes at all times.

269

#

270

abnormal_end() {

271

err_msg=$1

272

273

ocf_is_probe && {

274

sapinstance_status

275

exit $?

276

}

277

278

if [ "$ACTION" = "stop" ]

279

then

280

cleanup_instance

281

exit $OCF_SUCCESS

282

fi

283

284

ocf_log err $err_msg

285

exit $OCF_ERR_CONFIGURED

286

}

287

288

#

289

# sapinstance_init : Define global variables with default values, if optional parameters are not set

290

#

291

#

292

sapinstance_init() {

293

294

myInstanceName="$1"

295

296

SID=`echo "$myInstanceName" | cut -d_ -f1`

297

InstanceName=`echo "$myInstanceName" | cut -d_ -f2`

298

InstanceNr=`echo "$InstanceName" | sed 's/.*$[0-9][0-9]$$/\1/'`

299

SAPVIRHOST=`echo "$myInstanceName" | cut -d_ -f3`

300

301

# optional OCF parameters, we try to guess which directories are correct

302

if [ -z "$OCF_RESKEY_DIR_EXECUTABLE" ]

303

then

304

if have_binary /usr/sap/$SID/$InstanceName/exe/sapstartsrv && have_binary /usr/sap/$SID/$InstanceName/exe/sapcontrol

305

then

306

DIR_EXECUTABLE="/usr/sap/$SID/$InstanceName/exe"

307

SAPSTARTSRV="/usr/sap/$SID/$InstanceName/exe/sapstartsrv"

308

SAPCONTROL="/usr/sap/$SID/$InstanceName/exe/sapcontrol"

309

elif have_binary /usr/sap/$SID/SYS/exe/run/sapstartsrv && have_binary /usr/sap/$SID/SYS/exe/run/sapcontrol

310

then

311

DIR_EXECUTABLE="/usr/sap/$SID/SYS/exe/run"

312

SAPSTARTSRV="/usr/sap/$SID/SYS/exe/run/sapstartsrv"

313

SAPCONTROL="/usr/sap/$SID/SYS/exe/run/sapcontrol"

314

fi

315

else

316

if have_binary "$OCF_RESKEY_DIR_EXECUTABLE/sapstartsrv" && have_binary "$OCF_RESKEY_DIR_EXECUTABLE/sapcontrol"

317

then

318

DIR_EXECUTABLE="$OCF_RESKEY_DIR_EXECUTABLE"

319

SAPSTARTSRV="$OCF_RESKEY_DIR_EXECUTABLE/sapstartsrv"

320

SAPCONTROL="$OCF_RESKEY_DIR_EXECUTABLE/sapcontrol"

321

fi

322

fi

323

324

[ -z "$DIR_EXECUTABLE" ] && abnormal_end "Cannot find sapstartsrv and sapcontrol executable, please set DIR_EXECUTABLE parameter!"

325

326

if [ -z "$OCF_RESKEY_DIR_PROFILE" ]

327

then

328

DIR_PROFILE="/usr/sap/$SID/SYS/profile"

329

else

330

DIR_PROFILE="$OCF_RESKEY_DIR_PROFILE"

331

fi

332

333

if [ "$myInstanceName" != "$OCF_RESKEY_InstanceName" ]

334

then

335

currentSTART_PROFILE=$OCF_RESKEY_ERS_START_PROFILE

336

else

337

currentSTART_PROFILE=$OCF_RESKEY_START_PROFILE

338

fi

339

340

if [ -z "$currentSTART_PROFILE" ]

341

then

342

SAPSTARTPROFILE="$DIR_PROFILE/START_${InstanceName}_${SAPVIRHOST}"

343

else

344

SAPSTARTPROFILE="$currentSTART_PROFILE"

345

fi

346

347

if [ -z "$OCF_RESKEY_START_WAITTIME" ]

348

then

349

export OCF_RESKEY_START_WAITTIME=3600

350

fi

351

352

if [ -z "$OCF_RESKEY_MONITOR_SERVICES" ]

353

then

354

355

fi

356

357

# as root user we need the library path to the SAP kernel to be able to call sapcontrol

358

if [ `echo $LD_LIBRARY_PATH | grep -c "^$DIR_EXECUTABLE\>"` -eq 0 ]; then

359

LD_LIBRARY_PATH=$DIR_EXECUTABLE${LD_LIBRARY_PATH:+:}$LD_LIBRARY_PATH

360

export LD_LIBRARY_PATH

361

fi

362

363

sidadm="`echo $SID | tr '[:upper:]' '[:lower:]'`adm"

364

365

return $OCF_SUCCESS

366

}

367

368

369

#

370

# check_sapstartsrv : Before using sapcontrol we make sure that the sapstartsrv is running for the correct instance.

371

# We cannot use sapinit and the /usr/sap/sapservices file in case of an enquerep instance,

372

# because then we have two instances with the same instance number.

373

#

374

check_sapstartsrv() {

375

restart=0

376

runninginst=""

377

chkrc=$OCF_SUCCESS

378

379

output=`$SAPCONTROL -nr $InstanceNr -function ParameterValue INSTANCE_NAME -format script`

380

if [ $? -eq 0 ]

381

then

382

runninginst=`echo "$output" | grep '^0 : ' | cut -d' ' -f3`

383

if [ "$runninginst" != "$InstanceName" ]

384

then

385

ocf_log warn "sapstartsrv is running for instance $runninginst, that service will be killed"

386

restart=1

387

fi

388

else

389

ocf_log warn "sapstartsrv is not running for instance $SID-$InstanceName, it will be started now"

390

restart=1

391

fi

392

393

if [ -z "$runninginst" ]; then runninginst=$InstanceName; fi

394

395

if [ $restart -eq 1 ]

396

then

397

398

if [ -d /usr/sap/$SID/SYS/profile/ ]

399

then

400

DIR_PROFILE="/usr/sap/$SID/SYS/profile"

401

else

402

abnormal_end "Expected /usr/sap/$SID/SYS/profile/ to be a directory, please set DIR_PROFILE parameter!"

403

fi

404

405

[ ! -r $SAPSTARTPROFILE ] && abnormal_end "Expected $SAPSTARTPROFILE to be the instance START profile, please set START_PROFILE parameter!"

406

407

pkill -9 -f "sapstartsrv.*$runninginst"

408

$SAPSTARTSRV pf=$SAPSTARTPROFILE -D -u $sidadm

409

410

# now make sure the daemon has been started and is able to respond

411

srvrc=1

412

while [ $srvrc -eq 1 -a `pgrep -f "sapstartsrv.*$runninginst" | wc -l` -gt 0 ]

413

do

414

sleep 1

415

$SAPCONTROL -nr $InstanceNr -function GetProcessList > /dev/null 2>&1

416

srvrc=$?

417

done

418

419

if [ $srvrc -ne 1 ]

420

then

421

ocf_log info "sapstartsrv for instance $SID-$InstanceName was restarted !"

422

chkrc=$OCF_SUCCESS

423

else

424

ocf_log error "sapstartsrv for instance $SID-$InstanceName could not be started!"

425

chkrc=$OCF_ERR_GENERIC

426

ocf_is_probe && chkrc=$OCF_NOT_RUNNING

427

fi

428

fi

429

430

return $chkrc

431

}

432

433

434

#

435

# sapuserexit : Many SAP customers need some additional processes/tools to run their SAP systems.

436

# This specialties do not allow a totally generic SAP cluster resource agent.

437

# Someone should write a resource agent for each additional process you need, if it

438

# is required to monitor that process within the cluster manager. To enable

439

# you to extent this resource agent without developing a new one, this user exit

440

# was introduced.

441

#

442

sapuserexit() {

443

NAME="$1"

444

VALUE="$2"

445

446

if [ -n "$VALUE" ]

447

then

448

if have_binary "$VALUE"

449

then

450

ocf_log info "Calling userexit ${NAME} with customer script file ${VALUE}"

451

"$VALUE" >/dev/null 2>&1

452

ocf_log info "Exiting userexit ${NAME} with customer script file ${VALUE}, returncode: $?"

453

else

454

ocf_log warn "Attribute ${NAME} is set to ${VALUE}, but this file is not executable"

455

fi

456

fi

457

return 0

458

}

459

460

461

#

462

# cleanup_instance : remove resources (processes and shared memory) from a crashed instance)

463

#

464

cleanup_instance() {

465

pkill -9 -f -U $sidadm $InstanceName

466

ocf_log info "Terminated instance using 'pkill -9 -f -U $sidadm $InstanceName'"

467

468

# it is necessary to call cleanipc as user sidadm if the system has 'vmcj/enable = ON' set - otherwise SHM-segments in /dev/shm/SAP_ES2* cannot beremoved

469

su - $sidadm -c "cleanipc $InstanceNr remove"

470

ocf_log info "Tried to remove shared memory resources using 'cleanipc $InstanceNr remove' as user $sidadm"

471

472

if [ -f "/usr/sap/$SID/$InstanceName/work/kill.sap" ]

473

then

474

rm -f /usr/sap/$SID/$InstanceName/work/kill.sap

475

ocf_log info "Deleted /usr/sap/$SID/$InstanceName/work/kill.sap"

476

fi

477

478

return 0

479

}

480

481

#

482

# sapinstance_start : Start the SAP instance

483

#

484

sapinstance_start() {

485

486

sapuserexit PRE_START_USEREXIT "$OCF_RESKEY_PRE_START_USEREXIT"

487

488

rc=$OCF_NOT_RUNNING

489

loopcount=0

490

while [ $loopcount -lt 2 ]

491

do

492

loopcount=$(($loopcount + 1))

493

494

check_sapstartsrv

495

rc=$?

496

if [ $rc -eq $OCF_SUCCESS ]; then

497

output=`$SAPCONTROL -nr $InstanceNr -function Start`

498

rc=$?

499

ocf_log info "Starting SAP Instance $SID-$InstanceName: $output"

500

fi

501

502

if [ $rc -ne 0 ]

503

then

504

ocf_log err "SAP Instance $SID-$InstanceName start failed."

505

return $OCF_ERR_GENERIC

506

fi

507

508

startrc=1

509

while [ $startrc -gt 0 ]

510

do

511

waittime_start=`date +%s`

512

output=`$SAPCONTROL -nr $InstanceNr -function WaitforStarted $OCF_RESKEY_START_WAITTIME 10`

513

startrc=$?

514

waittime_stop=`date +%s`

515

516

if [ $startrc -ne 0 ]

517

then

518

if [ $(($waittime_stop - $waittime_start)) -ge $OCF_RESKEY_START_WAITTIME ]

519

then

520

sapinstance_monitor NOLOG

521

if [ $? -eq $OCF_SUCCESS ]

522

then

523

output="START_WAITTIME ($OCF_RESKEY_START_WAITTIME) has elapsed, but instance monitor returned SUCCESS. Instance considered running."

524

startrc=0; loopcount=2

525

fi

526

else

527

if [ $loopcount -eq 1 ] && ocf_is_true $OCF_RESKEY_AUTOMATIC_RECOVER

528

then

529

ocf_log warn "SAP Instance $SID-$InstanceName start failed: $output"

530

ocf_log warn "Try to recover $SID-$InstanceName"

531

cleanup_instance

532

else

533

loopcount=2

534

fi

535

startrc=-1

536

fi

537

else

538

loopcount=2

539

fi

540

done

541

done

542

543

if [ $startrc -eq 0 ]

544

then

545

ocf_log info "SAP Instance $SID-$InstanceName started: $output"

546

rc=$OCF_SUCCESS

547

sapuserexit POST_START_USEREXIT "$OCF_RESKEY_POST_START_USEREXIT"

548

else

549

ocf_log err "SAP Instance $SID-$InstanceName start failed: $output"

550

rc=$OCF_NOT_RUNNING

551

fi

552

553

return $rc

554

}

555

556

557

#

558

# sapinstance_recover: Try startup of failed instance by cleaning up resources

559

#

560

sapinstance_recover() {

561

cleanup_instance

562

sapinstance_start

563

return $?

564

}

565

566

567

#

568

# sapinstance_stop: Stop the SAP instance

569

#

570

sapinstance_stop() {

571

sapuserexit PRE_STOP_USEREXIT "$OCF_RESKEY_PRE_STOP_USEREXIT"

572

573

if [ "$OCF_RESKEY_SHUTDOWN_METHOD" = "KILL" ]

574

then

575

ocf_log info "Stopping SAP Instance $SID-$InstanceName with shutdown method KILL!"

576

cleanup_instance

577

return $OCF_SUCCESS

578

fi

579

580

check_sapstartsrv

581

rc=$?

582

if [ $rc -eq $OCF_SUCCESS ]; then

583

output=`$SAPCONTROL -nr $InstanceNr -function Stop`

584

rc=$?

585

ocf_log info "Stopping SAP Instance $SID-$InstanceName: $output"

586

fi

587

588

if [ $? -eq 0 ]

589

then

590

output=`$SAPCONTROL -nr $InstanceNr -function WaitforStopped 3600 1`

591

if [ $? -eq 0 ]

592

then

593

ocf_log info "SAP Instance $SID-$InstanceName stopped: $output"

594

rc=$OCF_SUCCESS

595

else

596

ocf_log err "SAP Instance $SID-$InstanceName stop failed: $output"

597

rc=$OCF_ERR_GENERIC

598

fi

599

else

600

ocf_log err "SAP Instance $SID-$InstanceName stop failed: $output"

601

rc=$OCF_ERR_GENERIC

602

fi

603

604

sapuserexit POST_STOP_USEREXIT "$OCF_RESKEY_POST_STOP_USEREXIT"

605

606

return $rc

607

}

608

609

610

#

611

# sapinstance_monitor: Can the given SAP instance do anything useful?

612

#

613

sapinstance_monitor() {

614

MONLOG=$1

615

check_sapstartsrv

616

rc=$?

617

618

if [ $rc -eq $OCF_SUCCESS ]

619

then

620

count=0

621

output=`$SAPCONTROL -nr $InstanceNr -function GetProcessList -format script`

622

623

# we have to parse the output, because the returncode doesn't tell anything about the instance status

624

for SERVNO in `echo "$output" | grep '^[0-9] ' | cut -d' ' -f1 | sort -u`

625

do

626

COLOR=`echo "$output" | grep "^$SERVNO dispstatus: " | cut -d' ' -f3`

627

SERVICE=`echo "$output" | grep "^$SERVNO name: " | cut -d' ' -f3`

628

STATE=0

629

630

case $COLOR in

631

GREEN|YELLOW) STATE=$OCF_SUCCESS;;

632

*) STATE=$OCF_NOT_RUNNING;;

633

esac

634

635

SEARCH=`echo "$OCF_RESKEY_MONITOR_SERVICES" | sed 's/\+/\\\+/g' | sed 's/\./\\\./g'`

636

if [ `echo "$SERVICE" | egrep -c "$SEARCH"` -eq 1 ]

637

then

638

if [ $STATE -eq $OCF_NOT_RUNNING ]

639

then

640

[ "$MONLOG" != "NOLOG" ] && ocf_log err "SAP instance service $SERVICE is not running with status $COLOR !"

641

rc=$STATE

642

fi

643

count=1

644

fi

645

done

646

647

if [ $count -eq 0 -a $rc -eq $OCF_SUCCESS ]

648

then

649

if ocf_is_probe

650

then

651

rc=$OCF_NOT_RUNNING

652

else

653

[ "$MONLOG" != "NOLOG" ] && ocf_log err "The SAP instance does not run any services which this RA could monitor!"

654

rc=$OCF_ERR_GENERIC

655

fi

656

fi

657

fi

658

659

return $rc

660

}

661

662

663

#

664

# sapinstance_status: Lightweight check of SAP instance only with OS tools

665

#

666

sapinstance_status() {

667

[ ! -f "/usr/sap/$SID/$InstanceName/work/kill.sap" ] && return $OCF_NOT_RUNNING

668

pids=`grep '^kill -[0-9]' /usr/sap/$SID/$InstanceName/work/kill.sap | awk '{print $3}'`

669

for pid in $pids

670

do

671

[ `pgrep -f -U $sidadm $InstanceName | grep -c $pid` -gt 0 ] && return $OCF_SUCCESS

672

done

673

return $OCF_NOT_RUNNING

674

}

675

676

677

#

678

# sapinstance_validate: Check the symantic of the input parameters

679

#

680

sapinstance_validate() {

681

rc=$OCF_SUCCESS

682

if [ `echo "$SID" | grep -c '^[A-Z][A-Z0-9][A-Z0-9]$'` -ne 1 ]

683

then

684

ocf_log err "Parsing instance profile name: '$SID' is not a valid system ID!"

685

rc=$OCF_ERR_ARGS

686

fi

687

688

if [ `echo "$InstanceName" | grep -c '^[A-Z].*[0-9][0-9]$'` -ne 1 ]

689

then

690

ocf_log err "Parsing instance profile name: '$InstanceName' is not a valid instance name!"

691

rc=$OCF_ERR_ARGS

692

fi

693

694

if [ `echo "$InstanceNr" | grep -c '^[0-9][0-9]$'` -ne 1 ]

695

then

696

ocf_log err "Parsing instance profile name: '$InstanceNr' is not a valid instance number!"

697

rc=$OCF_ERR_ARGS

698

fi

699

700

if [ `echo "$SAPVIRHOST" | grep -c '^[A-Za-z][A-Za-z0-9_-]*$'` -ne 1 ]

701

then

702

ocf_log err "Parsing instance profile name: '$SAPVIRHOST' is not a valid hostname!"

703

rc=$OCF_ERR_ARGS

704

fi

705

706

return $rc

707

}

708

709

710

#

711

# sapinstance_start_clone

712

#

713

sapinstance_start_clone() {

714

sapinstance_init $OCF_RESKEY_ERS_InstanceName

715

${HA_SBIN_DIR}/crm_master -v 50 -l reboot

716

sapinstance_start

717

return $?

718

}

719

720

721

#

722

# sapinstance_stop_clone

723

#

724

sapinstance_stop_clone() {

725

sapinstance_init $OCF_RESKEY_ERS_InstanceName

726

${HA_SBIN_DIR}/crm_master -v 0 -l reboot

727

sapinstance_stop

728

return $?

729

}

730

731

732

#

733

# sapinstance_monitor_clone

734

#

735

sapinstance_monitor_clone() {

736

# first check with the status function (OS tools) if there could be something like a SAP instance running

737

# as we do not know here, if we are in master or slave state we do not want to start our monitoring

738

# agents (sapstartsrv) on the wrong host

739

740

sapinstance_init $OCF_RESKEY_InstanceName

741

if sapinstance_status; then

742

if sapinstance_monitor; then

743

${HA_SBIN_DIR}/crm_master -Q -v 100 -l reboot

744

return $OCF_RUNNING_MASTER

745

fi

746

# by nature of the SAP enqueue server we have to make sure

747

# that we do a failover to the slave (enqueue replication server)

748

# in case the enqueue process has failed. We signal this to the

749

# cluster by setting our master preference to a lower value than the slave.

750

${HA_SBIN_DIR}/crm_master -v 10 -l reboot

751

return $OCF_FAILED_MASTER

752

fi

753

754

sapinstance_init $OCF_RESKEY_ERS_InstanceName

755

sapinstance_status && sapinstance_monitor

756

rc=$?

757

if [ $rc -eq $OCF_SUCCESS ]; then

758

${HA_SBIN_DIR}/crm_master -Q -v 100 -l reboot

759

fi

760

return $rc

761

}

762

763

764

#

765

# sapinstance_promote_clone: In a Master/Slave configuration get Master by starting the SCS instance and stopping the ERS instance

766

# The order is important here to behave correct from the application levels view

767

#

768

sapinstance_promote_clone() {

769

sapinstance_init $OCF_RESKEY_InstanceName

770

ocf_log info "Promoting $SID-$InstanceName to running Master."

771

sapinstance_start

772

rc=$?

773

774

if [ $rc -eq $OCF_SUCCESS ]; then

775

sapinstance_init $OCF_RESKEY_ERS_InstanceName

776

sapinstance_stop

777

rc=$?

778

fi

779

780

return $rc

781

}

782

783

784

#

785

# sapinstance_demote_clone: In a Master/Slave configuration get Slave by stopping the SCS instance and starting the ERS instance

786

#

787

sapinstance_demote_clone() {

788

sapinstance_init $OCF_RESKEY_InstanceName

789

ocf_log info "Demoting $SID-$InstanceName to a slave."

790

sapinstance_stop

791

rc=$?

792

793

if [ $rc -eq $OCF_SUCCESS ]; then

794

sapinstance_init $OCF_RESKEY_ERS_InstanceName

795

sapinstance_start

796

rc=$?

797

fi

798

799

return $rc

800

}

801

802

803

#

804

# sapinstance_notify: Handle master scoring - to make sure a slave gets the next master

805

#

806

sapinstance_notify() {

807

local n_type="$OCF_RESKEY_CRM_meta_notify_type"

808

local n_op="$OCF_RESKEY_CRM_meta_notify_operation"

809

810

if [ "${n_type}_${n_op}" = "post_promote" ]; then

811

# After promotion of one master in the cluster, we make sure that all clones reset their master

812

# value back to 100. This is because a failed monitor on a master might have degree one clone

813

# instance to score 10.

814

${HA_SBIN_DIR}/crm_master -v 100 -l reboot

815

elif [ "${n_type}_${n_op}" = "pre_demote" ]; then

816

# if we are a slave and a demote event is anounced, make sure we have the highes wish to became master

817

# that is, when a slave resource was startet after the promote event of a already running master (e.g. node of slave was down)

818

# We also have to make sure to overrule the globaly set resource_stickiness or any fail-count factors => INFINITY

819

local n_uname="$OCF_RESKEY_CRM_meta_notify_demote_uname"

820

if [ ${n_uname} != ${HOSTNAME} ]; then

821

${HA_SBIN_DIR}/crm_master -v INFINITY -l reboot

822

fi

823

fi

824

}

825

826

827

#

828

# 'main' starts here...

829

#

830

831

## GLOBALS

832

SID=""

833

sidadm=""

834

InstanceName=""

835

InstanceNr=""

836

SAPVIRHOST=""

837

DIR_EXECUTABLE=""

838

SAPSTARTSRV=""

839

SAPCONTROL=""

840

DIR_PROFILE=""

841

SAPSTARTPROFILE=""

842

CLONE=0

843

844

845

if

846

( [ $# -ne 1 ] )

847

then

848

sapinstance_usage

849

exit $OCF_ERR_ARGS

850

fi

851

852

ACTION=$1

853

if [ "$ACTION" = "status" ]; then

854

ACTION=monitor

855

fi

856

857

# These operations don't require OCF instance parameters to be set

858

case "$ACTION" in

859

usage|methods) sapinstance_$ACTION

860

exit $OCF_SUCCESS;;

861

meta-data) sapinstance_meta_data

862

exit $OCF_SUCCESS;;

863

notify) sapinstance_notify

864

exit $OCF_SUCCESS;;

865

*);;

866

esac

867

868

if ! ocf_is_root

869

then

870

ocf_log err "$0 must be run as root"

871

exit $OCF_ERR_PERM

872

fi

873

874

# parameter check

875

if [ -z "$OCF_RESKEY_InstanceName" ]

876

then

877

ocf_log err "Please set OCF_RESKEY_InstanceName to the name to the SAP instance profile!"

878

exit $OCF_ERR_ARGS

879

fi

880

881

is_clone; CLONE=$?

882

if [ ${CLONE} -eq 1 ]

883

then

884

CLACT=_clone

885

else

886

if [ "$ACTION" = "promote" -o "$ACTION" = "demote" ]

887

then

888

ocf_log err "$ACTION called in a non master/slave environment"

889

exit $OCF_ERR_ARGS

890

fi

891

sapinstance_init $OCF_RESKEY_InstanceName

892

fi

893

894

# What kind of method was invoked?

895

case "$ACTION" in

896

start|stop|monitor|promote|demote) sapinstance_$ACTION$CLACT

897

exit $?;;

898

validate-all) sapinstance_validate

899

exit $?;;

900

*) sapinstance_methods

901

exit $OCF_ERR_UNIMPLEMENTED;;

902

esac