summaryrefslogtreecommitdiffstats
path: root/heartbeat/nfsserver
blob: 8838195aa7b7bd33f7317d6f1a7e42a9599fdede (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
#!/bin/sh
# nfsserver
#
# Description: Manages nfs server as OCF resource
# by hxinwei@gmail.com
# License: GNU General Public License v2 (GPLv2) and later


# I don't know for certain whether all services actuall _need_ this,
# I know that at least nfs-server needs it.
# The rgmanager resource agent in rgmanager/src/resources/nfsserver.sh.in
# did the unshare for gssd and idmapd as well, even though it seems unclear why.
# Let's start with just the nfs-server, and add others if/when we have clear
# indication they need it.
#NFSD_RELATED_SYSTEMD_SERVICE_FOR_UNSHARE_UTS_NAMESPACE="nfs-idmapd.service nfs-mountd.service nfs-server.service nfsdcld.service rpc-gssd.service rpc-statd.service rpc-statd-notify.service rpcbind.service"
NFSD_RELATED_SYSTEMD_SERVICE_FOR_UNSHARE_UTS_NAMESPACE="nfs-server.service"
SYSTEMD_ENVIRONMENT_FILE_NFS_SERVER_SCOPE=/run/sysconfig/nfs-server-scope
SYSTEMD_UNSHARE_UTS_DROPIN=51-resource-agents-unshare-uts.conf

if [ -n "$OCF_DEBUG_LIBRARY" ]; then
    . $OCF_DEBUG_LIBRARY
else
    : ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/lib/heartbeat}
. ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs
fi

if is_redhat_based; then
	. ${OCF_FUNCTIONS_DIR}/nfsserver-redhat.sh
fi

DEFAULT_INIT_SCRIPT_LIST="/etc/init.d/nfsserver /etc/init.d/nfs /etc/init.d/nfs-kernel-server"
DEFAULT_INIT_SCRIPT="/etc/init.d/nfsserver"
for script in $DEFAULT_INIT_SCRIPT_LIST
do
	if [ -f $script -a -x $script ]; then
		DEFAULT_INIT_SCRIPT=$script
		break
	fi
done

DEFAULT_NOTIFY_CMD=`which sm-notify`
DEFAULT_NOTIFY_CMD=${DEFAULT_NOTIFY_CMD:-"/sbin/sm-notify"}
DEFAULT_NOTIFY_FOREGROUND="false"
DEFAULT_RPCPIPEFS_DIR="/var/lib/nfs/rpc_pipefs"
EXEC_MODE=0
SELINUX_ENABLED=-1
STATD_PATH="/var/lib/nfs"
STATD_DIR=""

nfsserver_meta_data() {
	cat <<END
<?xml version="1.0"?>
<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
<resource-agent name="nfsserver" version="1.0">
<version>1.0</version>

<longdesc lang="en">
Nfsserver helps one to manage the Linux nfs server as a failover-able resource in Linux-HA.
It depends on Linux specific NFS implementation details, so is considered not portable to other platforms yet.
</longdesc>

<shortdesc lang="en">Manages an NFS server</shortdesc>

<parameters>

<parameter name="nfs_init_script" unique="0" required="0">
<longdesc lang="en">
The default init script shipped with the Linux distro.
The nfsserver resource agent offloads the start/stop/monitor 
work to the init script because the procedure to start/stop/monitor 
nfsserver varies on different Linux distro. In the event that this
option is not set, this agent will attempt to use an init script at 
this location, ${DEFAULT_INIT_SCRIPT}, or detect a systemd unit-file 
to use in the event that no init script is detected.
</longdesc>
<shortdesc lang="en">
Init script for nfsserver
</shortdesc>
<content type="string" default="auto detected" />
</parameter>

<parameter name="nfsv4_only" unique="0" required="0">
<longdesc lang="en">
Run in NFSv4 only mode (rpc-statd and rpcbind services masked).
</longdesc>
<shortdesc lang="en">
NFSv4 only mode.
</shortdesc>
<content type="boolean" default="false" />
</parameter>

<parameter name="nfs_no_notify" unique="0" required="0">
<longdesc lang="en">
Do not send reboot notifications to NFSv3 clients during server startup.
</longdesc>
<shortdesc lang="en">
Disable NFSv3 server reboot notifications
</shortdesc>
<content type="boolean" default="false" />
</parameter>

<parameter name="nfs_notify_foreground" unique="0" required="0">
<longdesc lang="en">
Keeps the sm-notify attached to its controlling terminal and running in the foreground.
</longdesc>
<shortdesc lang="en">
Keeps the notify tool running in the foreground.
</shortdesc>
<content type="boolean" default="$DEFAULT_NOTIFY_FOREGROUND" />
</parameter>

<parameter name="nfs_smnotify_retry_time" unique="0" required="0">
<longdesc lang="en">
Specifies the length of sm-notify retry time, in minutes, to continue retrying notifications to unresponsive hosts.  
If this option is not specified, sm-notify attempts to send notifications for 15 minutes. Specifying a value of 0 
causes sm-notify to continue sending notifications to unresponsive peers until it is manually killed.
</longdesc>
<shortdesc lang="en">
Specifies the length of sm-notify retry time (minutes).
</shortdesc>
<content type="integer" default="" />
</parameter>

<parameter name="nfs_server_scope" unique="0" required="0">
<longdesc lang="en">
RFC8881, 8.4.2.1 State Reclaim:

If the server scope is different, the client should not attempt to
reclaim locks. In this situation, no lock reclaim is possible.
Any attempt to re-obtain the locks with non-reclaim operations is
problematic since there is no guarantee that the existing
filehandles will be recognized by the new server, or that if
recognized, they denote the same objects. It is best to treat the
locks as having been revoked by the reconfiguration event.

For lock reclaim to even be attempted, we have to define and set the same
server scope for NFSD on all cluster nodes in the NFS failover cluster.

This agent won't "guess" a suitable server scope name for you, you need to
explicitly specify this. But without it, NFSv4 lock reclaim after failover
won't work properly.  Suggested value: the failover "service IP".
</longdesc>
<shortdesc lang="en">
RFC8881 NFS server scope for (lock) state reclaim after failover.
</shortdesc>
<content type="string"/>
</parameter>

<parameter name="nfs_ip" unique="0" required="0">
<longdesc lang="en">
Comma separated list of floating IP addresses used to access the nfs service
</longdesc>
<shortdesc lang="en">
IP addresses.
</shortdesc>
<content type="string"/>
</parameter>

<parameter name="nfs_shared_infodir" unique="0" required="0">
<longdesc lang="en">
The nfsserver resource agent will save nfs related information in this specific directory.
And this directory must be able to fail-over before nfsserver itself.
</longdesc>
<shortdesc lang="en">
Directory to store nfs server related information.
</shortdesc>
<content type="string" default="" />
</parameter>

<parameter name="rpcpipefs_dir" unique="0" required="0">
<longdesc lang="en">
The mount point for the sunrpc file system. Default is $DEFAULT_RPCPIPEFS_DIR. 
This script will mount (bind) nfs_shared_infodir on /var/lib/nfs/ (cannot be changed),
and this script will mount the sunrpc file system on $DEFAULT_RPCPIPEFS_DIR (default, can be changed by this parameter).
If you want to move only rpc_pipefs/ (e.g. to keep rpc_pipefs/ local) from default, please set this value.
</longdesc>
<shortdesc lang="en">
The mount point for the sunrpc file system.
</shortdesc>
<content type="string" default="$DEFAULT_RPCPIPEFS_DIR" />
</parameter>

$(
is_redhat_based && nfsserver_redhat_meta_data
)

</parameters>

<actions>
<action name="start"   timeout="40s" />
<action name="stop"    timeout="20s" />
<action name="monitor" depth="0"  timeout="20s" interval="10s" />
<action name="meta-data"  timeout="5s" />
<action name="validate-all"  timeout="30s" />
</actions>
</resource-agent>
END

return $OCF_SUCCESS
}

nfsserver_usage() {
	cat <<END
		usage: $0 {start|stop|monitor|status|validate-all|meta-data}
END
}

if [ $# -ne 1 ]; then
	nfsserver_usage
	exit $OCF_ERR_ARGS
fi

case $__OCF_ACTION in
	meta-data)  nfsserver_meta_data
		exit $OCF_SUCCESS
		;;
	usage|help) nfsserver_usage
		exit $OCF_SUCCESS
		;;
	*)
		;;	
esac

fp="$OCF_RESKEY_nfs_shared_infodir"
: ${OCF_RESKEY_nfs_notify_cmd="$DEFAULT_NOTIFY_CMD"}
: ${OCF_RESKEY_nfs_notify_foreground="$DEFAULT_NOTIFY_FOREGROUND"}
: ${OCF_RESKEY_rpcpipefs_dir="$DEFAULT_RPCPIPEFS_DIR"}
OCF_RESKEY_rpcpipefs_dir=${OCF_RESKEY_rpcpipefs_dir%/}

# Use statd folder if it exists
if [ -d "/var/lib/nfs/statd" ]; then
	STATD_DIR="statd"
	STATD_PATH="/var/lib/nfs/statd"
fi

# SELinux information. We are taking the permissions from
# the current statd dir and applying it to the HA one that is
# being mounted in its place.
which restorecon > /dev/null 2>&1 && selinuxenabled
SELINUX_ENABLED=$?
if [ $SELINUX_ENABLED -eq 0 ]; then
	export SELINUX_LABEL="$(ls -dZ $STATD_PATH | grep -o '\S\+:\S\+:\S\+')"
fi

##
# EXEC_MODE values
# 1  user init script or default init script
# 2  systemd (with nfs-lock.service)
# 3  systemd (with rpc-statd.service)
#
# On error, this function will terminate the process
# with error code $OCF_ERR_INSTALLED
##
set_exec_mode()
{

	##
	# If EXEC_MODE is already set, we don't need to run this function again.
	## 
	if [ $EXEC_MODE -ne 0 ]; then
		return 0;
	fi

	##
	# If the user defined an init script, It must exist for us to continue
	##
	if [ -n "$OCF_RESKEY_nfs_init_script" ]; then
		# check_binary will exit the process if init script does not exist
		check_binary ${OCF_RESKEY_nfs_init_script}
		EXEC_MODE=1
		return 0
	fi

	##
	# Check to see if the default init script exists, if so we'll use that.
	##
	if which $DEFAULT_INIT_SCRIPT > /dev/null 2>&1; then
		OCF_RESKEY_nfs_init_script=$DEFAULT_INIT_SCRIPT
		EXEC_MODE=1
		return 0
	fi

	if which systemctl > /dev/null 2>&1; then
		if systemctl --no-legend list-unit-files 'nfs-*' | grep nfs-server > /dev/null; then

			##
			# Attempt systemd (with nfs-lock.service).
			##
			if systemctl --no-legend list-unit-files 'nfs-*' | grep nfs-lock > /dev/null; then
				EXEC_MODE=2
				# when using systemd, the nfs-lock service file handles nfsv3 locking daemons for us.
				return 0
			fi

			##
			# Attempt systemd (with rpc-statd.service).
			##
			if systemctl --no-legend list-unit-files 'rpc-*' | grep rpc-statd > /dev/null; then
				EXEC_MODE=3
				return 0
			fi
		fi
	fi

	ocf_exit_reason "No init script or systemd unit file detected for nfs server"
	exit $OCF_ERR_INSTALLED
}

##
# wrapper for init script and systemd calls.
##
nfs_exec()
{
	local cmd=$1
	local svc=$2
	set_exec_mode

	case $EXEC_MODE in 
		1) if [ -z "$OCF_RESKEY_nfs_server_scope" ] ; then
			${OCF_RESKEY_nfs_init_script} $cmd
		   else
			unshare -u /bin/sh -c "hostname ${OCF_RESKEY_nfs_server_scope}; exec ${OCF_RESKEY_nfs_init_script} $cmd"
		   fi ;;
		2) if ! echo $svc | grep -q "\."; then
			svc="${svc}.service"
		   fi
		   systemctl -n0 $cmd $svc
		   ;;
		3) if ! echo $svc | grep -q "\."; then
			svc="${svc}.service"
		   fi
		   systemctl -n0 $cmd $svc
		   ;;
	esac
}

v3locking_exec()
{
	local cmd=$1
	set_exec_mode

	if [ $EXEC_MODE -eq 2 ]; then
		nfs_exec $cmd nfs-lock.service
	elif [ $EXEC_MODE -eq 3 ]; then
		nfs_exec $cmd rpc-statd.service
	else 
		case $cmd in
			start) locking_start;;
			stop) locking_stop;;
			status) locking_status;;
		esac
	fi
}

nfsserver_systemd_monitor()
{
	local threads_num
	local rc
	local fn

	if ! ocf_is_true "$OCF_RESKEY_nfsv4_only"; then
		ocf_log debug "Status: rpcbind"
		rpcinfo > /dev/null 2>&1
		rc=$?
		if [ "$rc" -ne "0" ]; then
			ocf_exit_reason "rpcbind is not running"
			return $OCF_NOT_RUNNING
		fi

		ocf_log debug "Status: nfs-mountd"
		ps axww | grep -q "[r]pc.mountd"
		rc=$?
		if [ "$rc" -ne "0" ]; then
			ocf_exit_reason "nfs-mountd is not running"
			return $OCF_NOT_RUNNING
		fi
	fi

	ocf_log debug "Status: nfs-idmapd"
	fn=`mktemp`
	nfs_exec status nfs-idmapd > $fn 2>&1
	rc=$?
	ocf_log debug "$(cat $fn)"
	rm -f $fn
	if [ "$rc" -ne "0" ]; then
		ocf_exit_reason "nfs-idmapd is not running"
		return $OCF_NOT_RUNNING
	fi

	if ! ocf_is_true "$OCF_RESKEY_nfsv4_only"; then
		ocf_log debug "Status: rpc-statd"
		rpcinfo -t localhost 100024 > /dev/null 2>&1
		rc=$?
		if [ "$rc" -ne "0" ]; then
			ocf_exit_reason "rpc-statd is not running"
			return $OCF_NOT_RUNNING
		fi
	fi

	nfs_exec is-active nfs-server
	rc=$?

	# Now systemctl is-active can't detect the failure of kernel process like nfsd.
	# So, if the return value of systemctl is-active is 0, check the threads number
	# to make sure the process is running really.
	# /proc/fs/nfsd/threads has the numbers of the nfsd threads.
	if [ $rc -eq 0 ]; then
		threads_num=`cat /proc/fs/nfsd/threads 2>/dev/null`
		if [ $? -eq 0 ]; then
			if [ $threads_num -gt 0 ]; then
				return $OCF_SUCCESS
			else
				return 3
			fi
		else
			return $OCF_ERR_GENERIC
		fi
	fi

	return $rc
}

nfsserver_monitor ()
{
	local fn

	set_exec_mode
	fn=`mktemp`
	case $EXEC_MODE in
               1) nfs_exec status nfs-server > $fn 2>&1;;
            [23]) nfsserver_systemd_monitor > $fn 2>&1;;
	esac
	rc=$?
	ocf_log debug "$(cat $fn)"
	rm -f $fn

	#Adapte LSB status code to OCF return code
	if [ $rc -eq 0 ]; then
		# don't report success if nfs servers are up
		# without locking daemons.
		ocf_is_true "$OCF_RESKEY_nfsv4_only" || v3locking_exec "status"
		rc=$?
		if [ $rc -ne 0 ]; then
			ocf_exit_reason "NFS server is up, but the locking daemons are down"
			rc=$OCF_ERR_GENERIC
		fi
		return $rc
	elif [ $rc -eq 3 ] || [ $rc -eq $OCF_NOT_RUNNING ]; then
		return $OCF_NOT_RUNNING
	else
		return $OCF_ERR_GENERIC
	fi
}

prepare_directory ()
{
	if [ -z "$fp" ]; then
		fp="/var/lib/nfs"
	fi

	[ -d "$OCF_RESKEY_rpcpipefs_dir" ] || mkdir -p $OCF_RESKEY_rpcpipefs_dir
	[ -d "$fp/v4recovery" ] || mkdir -p $fp/v4recovery

	[ -d "$fp/$STATD_DIR" ] || mkdir -p "$fp/$STATD_DIR"
	[ -d "$fp/$STATD_DIR/sm" ] || mkdir -p "$fp/$STATD_DIR/sm"
	[ -d "$fp/$STATD_DIR/sm.ha" ] || mkdir -p "$fp/$STATD_DIR/sm.ha"
	[ -d "$fp/$STATD_DIR/sm.bak" ] || mkdir -p "$fp/$STATD_DIR/sm.bak"
	[ -n "`id -u rpcuser 2>/dev/null`" -a "`id -g rpcuser 2>/dev/null`" ] &&
		chown -R rpcuser.rpcuser "$fp/$STATD_DIR"

	[ -f "$fp/etab" ] || touch "$fp/etab"
	[ -f "$fp/xtab" ] || touch "$fp/xtab"
	[ -f "$fp/rmtab" ] || touch "$fp/rmtab"

	dd if=/dev/urandom of=$fp/$STATD_DIR/state bs=1 count=4 >/dev/null 2>&1
	[ -n "`id -u rpcuser 2>/dev/null`" -a "`id -g rpcuser 2>/dev/null`" ] && chown rpcuser.rpcuser "$fp/$STATD_DIR/state"
	[ $SELINUX_ENABLED -eq 0 ] && chcon -R "$SELINUX_LABEL" "$fp"
}

is_bound ()
{
	if mount | grep -q "on $1 type"; then
		return 0
	fi

	return 1
}

bind_tree ()
{
	if [ -z "$fp" ]; then
		return
	fi

	[ -d "$fp" ] || mkdir -p $fp

	if is_bound /var/lib/nfs; then
		ocf_log debug "$fp is already bound to /var/lib/nfs"
		return 0
	fi

	case $EXEC_MODE in
	  [23]) if nfs_exec status var-lib-nfs-rpc_pipefs.mount > /dev/null 2>&1; then
			ocf_log debug "/var/lib/nfs/rpc_pipefs already mounted. Unmounting in preparation to bind mount nfs dir"
			systemctl stop var-lib-nfs-rpc_pipefs.mount
		fi
		;;
	esac

	mount --bind $fp /var/lib/nfs
	[ $SELINUX_ENABLED -eq 0 ] && restorecon /var/lib/nfs
}

unbind_tree ()
{
	local i=1
	while `mount | grep -q " on $OCF_RESKEY_rpcpipefs_dir "` && [ "$i" -le 10 ]; do
		ocf_log info "Stop: umount ($i/10 attempts)"
		umount -t rpc_pipefs $OCF_RESKEY_rpcpipefs_dir
		sleep 1
		i=$((i + 1))
	done

	if mount | grep -q " on $OCF_RESKEY_rpcpipefs_dir "; then
		ocf_log err "Failed to unmount $OCF_RESKEY_rpcpipefs_dir"
		return $OCF_ERR_GENERIC
	fi

	if is_bound /var/lib/nfs; then
		if ! umount /var/lib/nfs; then
			ocf_log err "Failed to unmount /var/lib/nfs"
			return $OCF_ERR_GENERIC
		fi
	fi

	return $OCF_SUCCESS
}

binary_status()
{
	local binary=$1
	local pid

	pid=$(pgrep ${binary})
	case $? in
		0)
			echo "$pid"
			return $OCF_SUCCESS;;
		1)
			return $OCF_NOT_RUNNING;;
		*)
			return $OCF_ERR_GENERIC;;
	esac
}

locking_status()
{
	binary_status "rpc.statd" > /dev/null 2>&1
}

locking_start()
{
	local ret=$OCF_SUCCESS

	ocf_log info "Starting rpc.statd."

	rpc.statd $STATDARG

	ret=$?
	if [ $ret -ne 0 ]; then
		ocf_log err "Failed to start rpc.statd"
		return $ret
	fi
	[ -d /var/lock/subsys ] && touch /var/lock/subsys/nfslock

	return $ret
}

terminate()
{
	local pids
	local i=0

	while : ; do
		pids=$(binary_status $1)
		[ -z "$pids" ] && return 0
	 	kill $pids
		sleep 1
		i=$((i + 1))
		[ $i -gt 3 ] && return 1
	done
}


killkill()
{
	local pids
	local i=0

	while : ; do
		pids=$(binary_status $1)
		[ -z "$pids" ] && return 0
	 	kill -9 $pids
		sleep 1
		i=$((i + 1))
		[ $i -gt 3 ] && return 1
	done
}

stop_process()
{
	local process=$1

	ocf_log info "Stopping $process"
	if terminate $process; then
		ocf_log debug "$process is stopped"
	else
		if killkill $process; then
			ocf_log debug "$process is stopped"
		else
			ocf_log debug "Failed to stop $process"
			return 1
		fi
	fi
	return 0
}

locking_stop()
{
	ret=0

	# sm-notify can prevent umount of /var/lib/nfs/statd if
	# it is still trying to notify unresponsive clients.
	stop_process sm-notify
	if [ $? -ne 0 ]; then
		ret=$OCF_ERR_GENERIC
	fi

	stop_process rpc.statd
	if [ $? -ne 0 ]; then
		ret=$OCF_ERR_GENERIC
	fi

	return $ret
}

notify_locks()
{
	if ocf_is_true "$OCF_RESKEY_nfs_no_notify"; then
		# we've been asked not to notify clients
		return;
	fi

	# run in foreground, if requested
	if ocf_is_true "$OCF_RESKEY_nfs_notify_foreground"; then
		opts="-d"
	fi

	if [ -n "$OCF_RESKEY_nfs_smnotify_retry_time" ]; then
		opts="$opts -m $OCF_RESKEY_nfs_smnotify_retry_time"
	fi

	if [ -n "$OCF_RESKEY_statd_outgoing_port" ]; then
		opts="$opts -p $OCF_RESKEY_statd_outgoing_port"
	fi

	# forces re-notificaiton regardless if notifies have already gone out
	opts="$opts -f"

	ocf_log info "executing sm-notify"
	if [ -n "$OCF_RESKEY_nfs_ip" ]; then
		for ip in `echo ${OCF_RESKEY_nfs_ip} | sed 's/,/ /g'`; do
			cp -rpfn $STATD_PATH/sm.ha/* $STATD_PATH/  > /dev/null 2>&1
			sm-notify $opts -v $ip
		done
	else
		sm-notify $opts
	fi
}

# Problem: https://github.com/ClusterLabs/resource-agents/issues/1644
# RFC8881, 8.4.2.1 State Reclaim:
#
# | If the server scope is different, the client should not attempt to
# | reclaim locks. In this situation, no lock reclaim is possible.
# | Any attempt to re-obtain the locks with non-reclaim operations is
# | problematic since there is no guarantee that the existing
# | filehandles will be recognized by the new server, or that if
# | recognized, they denote the same objects. It is best to treat the
# | locks as having been revoked by the reconfiguration event.
#
# That's why for lock reclaim to even be attempted, we have to define and set
# the same server scope for NFSD on all cluster nodes in the NFS failover
# cluster. And in linux, that is done by setting the uts nodename for the
# command that starts the nfsd kernel threads.
#
inject_unshare_uts_name_into_systemd_units ()
{
	local END_TAG="# END OF DROP-IN FOR NFS SERVER SCOPE"
	local services
	services=$(systemctl list-unit-files --no-legend $NFSD_RELATED_SYSTEMD_SERVICE_FOR_UNSHARE_UTS_NAMESPACE | cut -d ' ' -f1)

	local svc dir dropin edited_exec_start do_reload=false
	local old_umask=$(umask)
	umask 0022
	for svc in $services ; do
		dir=/run/systemd/system/$svc.d
		dropin=$dir/$SYSTEMD_UNSHARE_UTS_DROPIN
		grep -sqF "$END_TAG" "$dropin" && continue

		test -d "$dir" || mkdir -p "$dir"
		test -e "$dropin" && rm -f "$dropin"

		# NOTE: additional ExecStart= might exist in the drop-in files, eg. openSUSE
		edited_exec_start=$(systemctl cat $svc | sed -ne "s#^ExecStart=\\([-+:!@]*\\)\\(.\+\\)#ExecStart=\\1/usr/bin/unshare --uts /bin/sh -c 'hostname \${NFS_SERVER_SCOPE}; exec \"\$@\"' -- \\2#p" | tail -1)

		cat > "$dropin" <<___
[Service]
EnvironmentFile=$SYSTEMD_ENVIRONMENT_FILE_NFS_SERVER_SCOPE
# reset list of exec start, then re-populate with unshared uts namespace
ExecStart=
$edited_exec_start
$END_TAG
___
		do_reload=true
		ocf_log debug "injected unshare --uts into $dropin"
	done

	mkdir -p "${SYSTEMD_ENVIRONMENT_FILE_NFS_SERVER_SCOPE%/*}"
	echo "NFS_SERVER_SCOPE=$OCF_RESKEY_nfs_server_scope" > "$SYSTEMD_ENVIRONMENT_FILE_NFS_SERVER_SCOPE"
	umask $old_umask

	$do_reload && systemctl daemon-reload
}

remove_unshare_uts_dropins ()
{
	local services
	services=$(systemctl list-unit-files --no-legend $NFSD_RELATED_SYSTEMD_SERVICE_FOR_UNSHARE_UTS_NAMESPACE | cut -d ' ' -f1)

	local svc dir dropin do_reload=false
	for svc in $services ; do
		dir=/run/systemd/system/$svc.d
		dropin=$dir/$SYSTEMD_UNSHARE_UTS_DROPIN
		test -e "$dropin" || continue
		rm -f "$dropin"
		do_reload=true
		ocf_log debug "removed unshare --uts from $svc"
	done
	rm -f "${SYSTEMD_ENVIRONMENT_FILE_NFS_SERVER_SCOPE}"
	$do_reload && systemctl daemon-reload
}

nfsserver_start ()
{
	local rc;
	local fn

	if nfsserver_monitor; then
		ocf_log debug "NFS server is already started"
		return $OCF_SUCCESS
	fi

	is_redhat_based && set_env_args
	bind_tree
	prepare_directory

	# Debian (and other systems) may provide "init scripts",
	# which will only redirect back to systemd.
	# If we just unshare --uts the init script invocation,
	# the uts namespace is useless in that case.
	# If systemd is running, mangle the nfs-server.service unit,
	# independent of the "EXEC_MODE" we detected.
	if $systemd_is_running ; then
		if [ -z "$OCF_RESKEY_nfs_server_scope" ] ; then
			remove_unshare_uts_dropins
		else
			inject_unshare_uts_name_into_systemd_units
		fi
	fi

	if ! `mount | grep -q " on $OCF_RESKEY_rpcpipefs_dir "`; then
		mount -t rpc_pipefs sunrpc $OCF_RESKEY_rpcpipefs_dir
	fi

	# remove the sm-notify pid so sm-notify will be allowed to run again without requiring a reboot.
	rm -f /var/run/sm-notify.pid
	#
	# Synchronize these before starting statd
	#
	cp -rpfn $STATD_PATH/sm.ha/* $STATD_PATH/ > /dev/null 2>&1
	rm -rf $STATD_PATH/sm.ha/* > /dev/null 2>&1
	cp -rpf $STATD_PATH/sm $STATD_PATH/sm.bak /var/lib/nfs/state $STATD_PATH/sm.ha > /dev/null 2>&1

	ocf_log info "Starting NFS server ..."

	# mounts /proc/fs/nfsd for us
	lsmod | grep -q nfsd
	if [ $? -ne 0 ]; then
		modprobe nfsd
	fi

	# systemd
	case $EXEC_MODE in
            [23]) if ! ocf_is_true "$OCF_RESKEY_nfsv4_only"; then
			nfs_exec start rpcbind
			local i=1
			while : ; do
				ocf_log info "Start: rpcbind i: $i"
				rpcinfo > /dev/null 2>&1
				rc=$?
				if [ "$rc" -eq "0" ]; then
					break
				fi
				sleep 1
				i=$((i + 1))
			done
		  fi
		  ;;
	esac

	if ! ocf_is_true "$OCF_RESKEY_nfsv4_only"; then
		# check to see if we need to start rpc.statd
		v3locking_exec "status"
		if [ $? -ne $OCF_SUCCESS ]; then
			v3locking_exec "start"
			rc=$?
			if [ $rc -ne 0 ]; then
				ocf_exit_reason "Failed to start NFS server locking daemons"
				return $rc
			fi
		else
			ocf_log info "rpc.statd already up"
		fi
	fi

	# systemd
	case $EXEC_MODE in
            [23]) if ! ocf_is_true "$OCF_RESKEY_nfsv4_only"; then
			nfs_exec start nfs-mountd
			local i=1
			while : ; do
				ocf_log info "Start: nfs-mountd i: $i"
				ps axww | grep -q "[r]pc.mountd"
				rc=$?
				if [ "$rc" -eq "0" ]; then
					break
				fi
				sleep 1
				i=$((i + 1))
			done
		  fi

		  nfs_exec start nfs-idmapd
		  local i=1
		  while : ; do
			ocf_log info "Start: nfs-idmapd i: $i"
			fn=`mktemp`
			nfs_exec status nfs-idmapd > $fn 2>&1
			rc=$?
			ocf_log debug "$(cat $fn)"
			rm -f $fn
			if [ "$rc" -eq "0" ]; then
				break
			fi
			sleep 1
			i=$((i + 1))
		  done

		  if ! ocf_is_true "$OCF_RESKEY_nfsv4_only"; then
			nfs_exec start rpc-statd
			local i=1
			while : ; do
				ocf_log info "Start: rpc-statd i: $i"
				rpcinfo -t localhost 100024 > /dev/null 2>&1
				rc=$?
				if [ "$rc" -eq "0" ]; then
					break
				fi
				sleep 1
				i=$((i + 1))
			done
		  fi
	esac


	fn=`mktemp`
	nfs_exec start nfs-server > $fn 2>&1
	rc=$?
	ocf_log debug "$(cat $fn)"
	rm -f $fn

	if [ $rc -ne 0 ]; then
		ocf_exit_reason "Failed to start NFS server"
		return $rc
	fi

	tfn="/proc/fs/nfsd/threads"
	if [ ! -f "$tfn" ] || [ "$(cat $tfn)" -le "0" ]; then
		ocf_exit_reason "Failed to start NFS server: /proc/fs/nfsd/threads"
		return $OCF_ERR_GENERIC
	fi

	notify_locks

	ocf_log info "NFS server started"
	return $OCF_SUCCESS
}

nfsserver_stop ()
{
	local fn

	ocf_log info "Stopping NFS server ..."

	# backup the current sm state information to the ha folder before stopping.
	# the ha folder will be synced after startup, restoring the statd client state
	rm -rf $STATD_PATH/sm.ha/* > /dev/null 2>&1
	cp -rpf $STATD_PATH/sm $STATD_PATH/sm.bak /var/lib/nfs/state $STATD_PATH/sm.ha > /dev/null 2>&1

	fn=`mktemp`
	nfs_exec stop nfs-server > $fn 2>&1
	rc=$?
	ocf_log debug "$(cat $fn)"
	rm -f $fn

	if [ $rc -ne 0 ]; then
		ocf_exit_reason "Failed to stop NFS server"
		return $rc
	fi

	# systemd
	case $EXEC_MODE in
            [23]) ocf_log info "Stop: threads"
		  tfn="/proc/fs/nfsd/threads"
		  while [ -f "$tfn" ] && [ "$(cat $tfn)" -gt "0" ]; do
			ocf_log err "NFS server failed to stop: /proc/fs/nfsd/threads"
			sleep 1
		  done

		  if ! ocf_is_true "$OCF_RESKEY_nfsv4_only"; then
			nfs_exec stop rpc-statd > /dev/null 2>&1
			ocf_log info "Stop: rpc-statd"
			rpcinfo -t localhost 100024 > /dev/null 2>&1
			rc=$?
			if [ "$rc" -eq "0" ]; then
				ocf_exit_reason "Failed to stop rpc-statd"
				return $OCF_ERR_GENERIC
			fi
		  fi

		  nfs_exec stop nfs-idmapd > /dev/null 2>&1
		  ocf_log info "Stop: nfs-idmapd"
		  fn=`mktemp`
		  nfs_exec status nfs-idmapd > $fn 2>&1
		  rc=$?
		  ocf_log debug "$(cat $fn)"
		  rm -f $fn
		  if [ "$rc" -eq "0" ]; then
			ocf_exit_reason "Failed to stop nfs-idmapd"
			return $OCF_ERR_GENERIC
		  fi

		  if ! ocf_is_true "$OCF_RESKEY_nfsv4_only"; then
			nfs_exec stop nfs-mountd > /dev/null 2>&1
			ocf_log info "Stop: nfs-mountd"
			ps axww | grep -q "[r]pc.mountd"
			rc=$?
			if [ "$rc" -eq "0" ]; then
				ocf_exit_reason "Failed to stop nfs-mountd"
				return $OCF_ERR_GENERIC
			fi
		  fi

		  if systemctl --no-legend list-unit-files "nfsdcld*" | grep -q nfsdcld; then
		  	nfs_exec stop nfsdcld > /dev/null 2>&1
		  	ocf_log info "Stop: nfsdcld"
		  	fn=`mktemp`
		  	nfs_exec status nfsdcld > $fn 2>&1
		  	rc=$?
		  	ocf_log debug "$(cat $fn)"
		  	rm -f $fn
		  	if [ "$rc" -eq "0" ]; then
		  		ocf_exit_reason "Failed to stop nfsdcld"
		  		return $OCF_ERR_GENERIC
		  	fi
		  fi
	esac


	if ! ocf_is_true "$OCF_RESKEY_nfsv4_only"; then
		v3locking_exec "stop"
		if [ $? -ne 0 ]; then
			ocf_exit_reason "Failed to stop NFS locking daemons"
			rc=$OCF_ERR_GENERIC
		fi
	fi

	# systemd
	case $EXEC_MODE in
            [23]) nfs_exec stop rpc-gssd > /dev/null 2>&1
		  ocf_log info "Stop: rpc-gssd"
	esac

	unbind_tree
	rc=$?
	if [ "$rc" -ne $OCF_SUCCESS ]; then
		ocf_exit_reason "Failed to unmount a bind mount"
	else
		ocf_log info "NFS server stopped"
	fi

	if $systemd_is_running; then
		remove_unshare_uts_dropins
	fi

	return $rc
}

nfsserver_validate ()
{
	##
	# set_exec_mode will exit if nfs server is not installed
	##
	set_exec_mode
	check_binary ${OCF_RESKEY_nfs_notify_cmd}


	if [ -n "$OCF_RESKEY_CRM_meta_clone" ] && [ -n "$OCF_RESKEY_nfs_shared_infodir" ]; then
		ocf_exit_reason "This RA does not support clone mode when a shared info directory is in use."
		exit $OCF_ERR_CONFIGURED
	fi

	if [ -n "$OCF_RESKEY_nfs_smnotify_retry_time" ]; then
		if ! ocf_is_decimal "$OCF_RESKEY_nfs_smnotify_retry_time"; then
			ocf_exit_reason "Invalid nfs_smnotify_retry_time [$OCF_RESKEY_nfs_smnotify_retry_time]"
			exit $OCF_ERR_CONFIGURED
		fi
	fi

	case ${OCF_RESKEY_nfs_notify_cmd##*/} in
	sm-notify|rpc.statd) ;;
	*)
		ocf_exit_reason "Invalid nfs_notify_cmd [$OCF_RESKEY_nfs_notify_cmd]"
		exit $OCF_ERR_CONFIGURED
		;;
	esac

	return $OCF_SUCCESS
}

nfsserver_validate
systemd_is_running && systemd_is_running=true || systemd_is_running=false

case $__OCF_ACTION in
	start)      nfsserver_start
		;;
	stop)       nfsserver_stop
		;;
	monitor)    nfsserver_monitor
		;;
	validate-all)   exit $OCF_SUCCESS
		;;
	*)      nfsserver_usage
	exit $OCF_ERR_UNIMPLEMENTED
	;;
esac