summaryrefslogtreecommitdiffstats
path: root/extras/ganesha/scripts/ganesha-ha.sh
blob: ccaa3d81338813dd0fcad221d457121d8a54a05c (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
#!/bin/bash

# Copyright 2015 Red Hat Inc.  All Rights Reserved
#
# Pacemaker+Corosync High Availability for NFS-Ganesha
#
# setup, teardown, add, delete, refresh-config, and status
#
# Each participating node in the cluster is assigned a virtual IP (VIP)
# which fails over to another node when its associated ganesha.nfsd dies
# for any reason. After the VIP is moved to another node all the
# ganesha.nfsds are send a signal using DBUS to put them into NFS GRACE.
#
# There are six resource agent types used: ganesha_mon, ganesha_grace,
# ganesha_nfsd, IPaddr, and Dummy. ganesha_mon is used to monitor the
# ganesha.nfsd. ganesha_grace is used to send the DBUS signal to put
# the remaining ganesha.nfsds into grace. ganesha_nfsd is used to start
# and stop the ganesha.nfsd during setup and teardown. IPaddr manages
# the VIP. A Dummy resource named $hostname-trigger_ip-1 is used to
# ensure that the NFS GRACE DBUS signal is sent after the VIP moves to
# the new host.

HA_NUM_SERVERS=0
HA_SERVERS=""
HA_CONFDIR="/etc/ganesha"
HA_VOL_NAME="gluster_shared_storage"
HA_VOL_MNT="/var/run/gluster/shared_storage"
SERVICE_MAN="DISTRO_NOT_FOUND"
cfgline=$(grep ^CONFFILE= /etc/sysconfig/ganesha)
eval $(echo ${cfgline} | grep -F CONFFILE=)
GANESHA_CONF=${CONFFILE:-/etc/ganesha/ganesha.conf}

RHEL6_PCS_CNAME_OPTION="--name"
SECRET_PEM="/var/lib/glusterd/nfs/secret.pem"

usage() {

        echo "Usage      : add|delete|status"
        echo "Add-node   : ganesha-ha.sh --add <HA_CONF_DIR>  \
<NODE-HOSTNAME>  <NODE-VIP>"
        echo "Delete-node: ganesha-ha.sh --delete <HA_CONF_DIR>  \
<NODE-HOSTNAME>"
        echo "Refresh-config : ganesha-ha.sh --refresh-config <HA_CONFDIR>\
 <volume>"
}

determine_service_manager () {

        if [ -e "/usr/bin/systemctl" ];
        then
                SERVICE_MAN="/usr/bin/systemctl"
        elif [ -e "/sbin/invoke-rc.d" ];
        then
                SERVICE_MAN="/sbin/invoke-rc.d"
        elif [ -e "/sbin/service" ];
        then
                SERVICE_MAN="/sbin/service"
        fi
        if [ "$SERVICE_MAN" == "DISTRO_NOT_FOUND" ]
        then
                echo "Service manager not recognized, exiting"
                exit 1
        fi
}

manage_service ()
{
        local action=${1}
        local new_node=${2}
        if [ "$SERVICE_MAN" == "/usr/sbin/systemctl" ]
        then
                ssh -oPasswordAuthentication=no -oStrictHostKeyChecking=no -i \
${SECRET_PEM} root@${new_node} "$SERVICE_MAN  ${action} nfs-ganesha"
        else
                ssh -oPasswordAuthentication=no -oStrictHostKeyChecking=no -i \
${SECRET_PEM} root@${new_node} "$SERVICE_MAN nfs-ganesha ${action}"
        fi
}

check_cluster_exists()
{
    local name=${1}
    local cluster_name=""

    if [ -e /var/run/corosync.pid ]; then
        cluster_name=$(pcs status | grep "Cluster name:" | cut -d ' ' -f 3)
        if [ ${cluster_name} -a ${cluster_name} = ${name} ]; then
            logger "$name already exists, exiting"
            exit 0
        fi
    fi
}


determine_servers()
{
    local cmd=${1}
    local num_servers=0
    local tmp_ifs=${IFS}
    local ha_servers=""

    if [[ "X${cmd}X" != "XsetupX" ]]; then
        ha_servers=$(pcs status | grep "Online:" | grep -o '\[.*\]' | sed -e 's/\[//' | sed -e 's/\]//')
        IFS=$' '
        for server in ${ha_servers} ; do
            num_servers=$(expr ${num_servers} + 1)
        done
        IFS=${tmp_ifs}
        HA_NUM_SERVERS=${num_servers}
        HA_SERVERS="${ha_servers}"
    else
        IFS=$','
        for server in ${HA_CLUSTER_NODES} ; do
            num_servers=$(expr ${num_servers} + 1)
        done
        IFS=${tmp_ifs}
        HA_NUM_SERVERS=${num_servers}
        HA_SERVERS="${HA_CLUSTER_NODES//,/ }"
    fi
}


setup_cluster()
{
    local name=${1}
    local num_servers=${2}
    local servers=${3}
    local unclean=""

    logger "setting up cluster ${name} with the following ${servers}"

    pcs cluster auth ${servers}
# fedora    pcs cluster setup ${name} ${servers}
# rhel6     pcs cluster setup --name ${name} ${servers}
    pcs cluster setup ${RHEL6_PCS_CNAME_OPTION} ${name} ${servers}
    if [ $? -ne 0 ]; then
        logger "pcs cluster setup ${RHEL6_PCS_CNAME_OPTION} ${name} ${servers} failed"
        exit 1;
    fi
    pcs cluster start --all
    if [ $? -ne 0 ]; then
        logger "pcs cluster start failed"
        exit 1;
    fi

    sleep 3
    unclean=$(pcs status | grep -u "UNCLEAN")
    while [[ "${unclean}X" = "UNCLEANX" ]]; do
         sleep 1
         unclean=$(pcs status | grep -u "UNCLEAN")
    done
    sleep 1

    if [ ${num_servers} -lt 3 ]; then
        pcs property set no-quorum-policy=ignore
        if [ $? -ne 0 ]; then
            logger "warning: pcs property set no-quorum-policy=ignore failed"
        fi
    fi
    pcs property set stonith-enabled=false
    if [ $? -ne 0 ]; then
        logger "warning: pcs property set stonith-enabled=false failed"
    fi
}


setup_finalize()
{
    local cibfile=${1}
    local stopped=""

    stopped=$(pcs status | grep -u "Stopped")
    while [[ "${stopped}X" = "StoppedX" ]]; do
         sleep 1
         stopped=$(pcs status | grep -u "Stopped")
    done

    pcs status | grep dead_ip-1 | sort > /var/run/ganesha/pcs_status

}


setup_copy_config()
{
    local short_host=$(hostname -s)
    local tganesha_conf=$(mktemp -u)

    if [ -e ${SECRET_PEM} ]; then
        while [[ ${1} ]]; do
            current_host=`echo ${1} | cut -d "." -f 1`
            if [ ${short_host} != ${current_host} ]; then
                scp -oPasswordAuthentication=no -oStrictHostKeyChecking=no -i \
${SECRET_PEM} ${HA_CONFDIR}/ganesha-ha.conf ${1}:${HA_CONFDIR}/
                if [ $? -ne 0 ]; then
                    logger "warning: scp ganesha-ha.conf to ${1} failed"
                fi
            fi
            shift
        done
    else
        logger "warning: scp ganesha-ha.conf to ${1} failed"
    fi
}

refresh_config ()
{
        local short_host=$(hostname -s)
        local VOL=${1}
        local HA_CONFDIR=${2}

        removed_id=`cat $HA_CONFDIR/exports/export.$VOL.conf |\
grep Export_Id | cut -d " " -f8`

        if [ -e ${SECRET_PEM} ]; then
        while [[ ${3} ]]; do
	    current_host=`echo ${3} | cut -d "." -f 1`
            if [ ${short_host} != ${current_host} ]; then
                scp -oPasswordAuthentication=no -oStrictHostKeyChecking=no -i \
${SECRET_PEM} ${HA_CONFDIR}/exports/export.$VOL.conf \
${current_host}:${HA_CONFDIR}/exports/
                 ssh -oPasswordAuthentication=no -oStrictHostKeyChecking=no -i \
${SECRET_PEM} root@${current_host} "dbus-send --print-reply --system \
--dest=org.ganesha.nfsd /org/ganesha/nfsd/ExportMgr \
org.ganesha.nfsd.exportmgr.RemoveExport uint16:$removed_id"
                 sleep 1
                 ssh -oPasswordAuthentication=no -oStrictHostKeyChecking=no -i \
${SECRET_PEM} root@${current_host} "dbus-send  --system \
--dest=org.ganesha.nfsd  /org/ganesha/nfsd/ExportMgr \
org.ganesha.nfsd.exportmgr.AddExport  string:$HA_CONFDIR/exports/export.$VOL.conf \
string:\"EXPORT(Path=/$VOL)\""
               if [ $? -ne 0 ]; then
                    echo "warning: refresh-config failed on ${current_host}"
               fi
            fi
            shift
        done
    else
        echo "warning: refresh-config failed on ${1}"
    fi

#Run the same command on the localhost,
        dbus-send --print-reply --system \
--dest=org.ganesha.nfsd /org/ganesha/nfsd/ExportMgr \
org.ganesha.nfsd.exportmgr.RemoveExport uint16:$removed_id
        sleep 1
        dbus-send  --system \
--dest=org.ganesha.nfsd  /org/ganesha/nfsd/ExportMgr \
org.ganesha.nfsd.exportmgr.AddExport  string:$HA_CONFDIR/exports/export.$VOL.conf \
string:"EXPORT(Path=/$VOL)"
}

copy_export_config ()
{
    local new_node=${1}
    local tganesha_conf=$(mktemp -u)
    local tganesha_exports=$(mktemp -d)

    # avoid prompting for password, even with password-less scp
    # scp $host1:$file $host2:$file prompts for the password
    scp -oPasswordAuthentication=no -oStrictHostKeyChecking=no -i \
${SECRET_PEM} ${HA_VOL_SERVER}:${GANESHA_CONF} ${tganesha_conf}
    scp -oPasswordAuthentication=no -oStrictHostKeyChecking=no -i \
${SECRET_PEM} ${tganesha_conf} ${new_node}:${GANESHA_CONF}
    rm -f ${tganesha_conf}

    scp -r -oPasswordAuthentication=no -oStrictHostKeyChecking=no -i \
${SECRET_PEM} ${HA_VOL_SERVER}:${HA_CONFDIR}/exports/ ${tganesha_exports}
    scp -r -oPasswordAuthentication=no -oStrictHostKeyChecking=no -i \
${SECRET_PEM} ${tganesha_exports} ${new_node}:${HA_CONFDIR}/
    rm -rf ${tganesha_exports}
}


teardown_cluster()
{
    local name=${1}

    for server in ${HA_SERVERS} ; do
        if [[ ${HA_CLUSTER_NODES} != *${server}* ]]; then
            logger "info: ${server} is not in config, removing"

            pcs cluster stop ${server}
            if [ $? -ne 0 ]; then
                logger "warning: pcs cluster stop ${server} failed"
            fi

            pcs cluster node remove ${server}
            if [ $? -ne 0 ]; then
                logger "warning: pcs cluster node remove ${server} failed"
            fi
        fi
    done

# BZ 1193433 - pcs doesn't reload cluster.conf after modification
# after teardown completes, a subsequent setup will appear to have
# 'remembered' the deleted node. You can work around this by
# issuing another `pcs cluster node remove $node`,
# `crm_node -f -R $server`, or
# `cibadmin --delete --xml-text '<node id="$server"
# uname="$server"/>'

    pcs cluster stop --all
    if [ $? -ne 0 ]; then
        logger "warning pcs cluster stop --all failed"
    fi

    pcs cluster destroy
    if [ $? -ne 0 ]; then
        logger "error pcs cluster destroy failed"
        exit 1
    fi
}


cleanup_ganesha_config ()
{
       rm -rf ${HA_CONFDIR}/exports/*.conf
       rm -rf ${HA_CONFDIR}/.export_added
       rm -rf /etc/cluster/cluster.conf*
       rm -rf /var/lib/pacemaker/cib/*
       sed -r -i -e '/^%include[[:space:]]+".+\.conf"$/d' ${GANESHA_CONF}
}

do_create_virt_ip_constraints()
{
    local cibfile=${1}; shift
    local primary=${1}; shift
    local weight="1000"

    # first a constraint location rule that says the VIP must be where
    # there's a ganesha.nfsd running
    pcs -f ${cibfile} constraint location ${primary}-cluster_ip-1 rule score=-INFINITY ganesha-active ne 1
    if [ $? -ne 0 ]; then
        logger "warning: pcs constraint location ${primary}-cluster_ip-1 rule score=-INFINITY ganesha-active ne 1 failed"
    fi

    # then a set of constraint location prefers to set the prefered order
    # for where a VIP should move
    while [[ ${1} ]]; do
        pcs -f ${cibfile} constraint location ${primary}-cluster_ip-1 prefers ${1}=${weight}
        if [ $? -ne 0 ]; then
            logger "warning: pcs constraint location ${primary}-cluster_ip-1 prefers ${1}=${weight} failed"
        fi
        weight=$(expr ${weight} + 1000)
        shift
    done
    # and finally set the highest preference for the VIP to its home node
    # default weight when created is/was 100.
    # on Fedora setting appears to be additive, so to get the desired
    # value we adjust the weight
    # weight=$(expr ${weight} - 100)
    pcs -f ${cibfile} constraint location ${primary}-cluster_ip-1 prefers ${primary}=${weight}
    if [ $? -ne 0 ]; then
        logger "warning: pcs constraint location ${primary}-cluster_ip-1 prefers ${primary}=${weight} failed"
    fi
}


wrap_create_virt_ip_constraints()
{
    local cibfile=${1}; shift
    local primary=${1}; shift
    local head=""
    local tail=""

    # build a list of peers, e.g. for a four node cluster, for node1,
    # the result is "node2 node3 node4"; for node2, "node3 node4 node1"
    # and so on.
    while [[ ${1} ]]; do
        if [ "${1}" = "${primary}" ]; then
            shift
            while [[ ${1} ]]; do
                tail=${tail}" "${1}
                shift
            done
        else
            head=${head}" "${1}
        fi
        shift
    done
    do_create_virt_ip_constraints ${cibfile} ${primary} ${tail} ${head}
}


create_virt_ip_constraints()
{
    local cibfile=${1}; shift

    while [[ ${1} ]]; do
        wrap_create_virt_ip_constraints ${cibfile} ${1} ${HA_SERVERS}
        shift
    done
}


setup_create_resources()
{
    local cibfile=$(mktemp -u)

    # mount the HA-state volume and start ganesha.nfsd on all nodes
    pcs resource create nfs_start ganesha_nfsd ha_vol_mnt=${HA_VOL_MNT} --clone
    if [ $? -ne 0 ]; then
        logger "warning: pcs resource create nfs_start ganesha_nfsd ha_vol_mnt=${HA_VOL_MNT} --clone failed"
    fi
    sleep 1
    # cloned resources seem to never have their start() invoked when they
    # are created, but stop() is invoked when they are destroyed. Why???.
    # No matter, we don't want this resource agent hanging around anyway
    pcs resource delete nfs_start-clone
    if [ $? -ne 0 ]; then
        logger "warning: pcs resource delete nfs_start-clone failed"
    fi

    pcs resource create nfs-mon ganesha_mon --clone
    if [ $? -ne 0 ]; then
        logger "warning: pcs resource create nfs-mon ganesha_mon --clone failed"
    fi

    pcs resource create nfs-grace ganesha_grace --clone
    if [ $? -ne 0 ]; then
        logger "warning: pcs resource create nfs-grace ganesha_grace --clone failed"
    fi

    pcs cluster cib ${cibfile}

    while [[ ${1} ]]; do

        # this is variable indirection
        # from a nvs like 'VIP_host1=10.7.6.5' or 'VIP_host1="10.7.6.5"'
        # (or VIP_host-1=..., or VIP_host-1.my.domain.name=...)
        # a variable 'clean_name' is created (e.g. w/ value 'VIP_host_1')
        # and a clean nvs (e.g. w/ value 'VIP_host_1="10_7_6_5"')
        # after the `eval ${clean_nvs}` there is a variable VIP_host_1
        # with the value '10_7_6_5', and the following \$$ magic to
        # reference it, i.e. `eval tmp_ipaddr=\$${clean_name}` gives us
        # ${tmp_ipaddr} with 10_7_6_5 and then convert the _s back to .s
        # to give us ipaddr="10.7.6.5". whew!
        name="VIP_${1}"
        clean_name=${name//[-.]/_}
        nvs=$(grep "^${name}=" ${HA_CONFDIR}/ganesha-ha.conf)
        clean_nvs=${nvs//[-.]/_}
        eval ${clean_nvs}
        eval tmp_ipaddr=\$${clean_name}
        ipaddr=${tmp_ipaddr//_/.}

        pcs -f ${cibfile} resource create ${1}-cluster_ip-1 ocf:heartbeat:IPaddr ip=${ipaddr} cidr_netmask=32 op monitor interval=15s
        if [ $? -ne 0 ]; then
            logger "warning pcs resource create ${1}-cluster_ip-1 ocf:heartbeat:IPaddr ip=${ipaddr} cidr_netmask=32 op monitor interval=15s failed"
        fi

        pcs -f ${cibfile} resource create ${1}-trigger_ip-1 ocf:heartbeat:Dummy
        if [ $? -ne 0 ]; then
            logger "warning: pcs resource create ${1}-trigger_ip-1 ocf:heartbeat:Dummy failed"
        fi

        pcs -f ${cibfile} constraint colocation add ${1}-cluster_ip-1 with ${1}-trigger_ip-1
        if [ $? -ne 0 ]; then
            logger "warning: pcs constraint colocation add ${1}-cluster_ip-1 with ${1}-trigger_ip-1 failed"
        fi

        pcs -f ${cibfile} constraint order ${1}-trigger_ip-1 then nfs-grace-clone
        if [ $? -ne 0 ]; then
            logger "warning: pcs constraint order ${1}-trigger_ip-1 then nfs-grace-clone failed"
        fi

        pcs -f ${cibfile} constraint order nfs-grace-clone then ${1}-cluster_ip-1
        if [ $? -ne 0 ]; then
            logger "warning: pcs constraint order nfs-grace-clone then ${1}-cluster_ip-1 failed"
        fi

        shift
    done

    create_virt_ip_constraints ${cibfile} ${HA_SERVERS}

    pcs cluster cib-push ${cibfile}
    if [ $? -ne 0 ]; then
        logger "warning pcs cluster cib-push ${cibfile} failed"
    fi
    rm -f ${cibfile}
}


teardown_resources()
{
    # local mntpt=$(grep ha-vol-mnt ${HA_CONFIG_FILE} | cut -d = -f 2)

    # delete -clone resource agents
    # in particular delete the ganesha monitor so we don't try to
    # trigger anything when we shut down ganesha next.
    pcs resource delete nfs-mon-clone
    if [ $? -ne 0 ]; then
        logger "warning: pcs resource delete nfs-mon-clone failed"
    fi

    pcs resource delete nfs-grace-clone
    if [ $? -ne 0 ]; then
        logger "warning: pcs resource delete nfs-grace-clone failed"
    fi

    # unmount the HA-state volume and terminate ganesha.nfsd on all nodes
    pcs resource create nfs_stop ganesha_nfsd ha_vol_mnt=${HA_VOL_MNT} --clone
    if [ $? -ne 0 ]; then
        logger "warning: pcs resource create nfs_stop ganesha_nfsd ha_vol_mnt=${HA_VOL_MNT} --clone failed"
    fi
    sleep 1
    # cloned resources seem to never have their start() invoked when they
    # are created, but stop() is invoked when they are destroyed. Why???.
    pcs resource delete nfs_stop-clone
    if [ $? -ne 0 ]; then
        logger "warning: pcs resource delete nfs_stop-clone failed"
    fi

    while [[ ${1} ]]; do
        pcs resource delete ${1}-cluster_ip-1
        if [ $? -ne 0 ]; then
            logger "warning: pcs resource delete ${1}-cluster_ip-1 failed"
        fi
        pcs resource delete ${1}-trigger_ip-1
        if [ $? -ne 0 ]; then
            logger "warning: pcs resource delete ${1}-trigger_ip-1 failed"
        fi
        pcs resource delete ${1}-dead_ip-1
        if [ $? -ne 0 ]; then
            logger "info: pcs resource delete ${1}-dead_ip-1 failed"
        fi
        shift
    done

}


recreate_resources()
{
    local cibfile=${1}; shift

    while [[ ${1} ]]; do
        # this is variable indirection
        # see the comment on the same a few lines up
        name="VIP_${1}"
        clean_name=${name//[-.]/_}
        nvs=$(grep "^${name}=" ${HA_CONFDIR}/ganesha-ha.conf)
        clean_nvs=${nvs//[-.]/_}
        eval ${clean_nvs}
        eval tmp_ipaddr=\$${clean_name}
        ipaddr=${tmp_ipaddr//_/.}

        pcs -f ${cibfile} resource create ${1}-cluster_ip-1 ocf:heartbeat:IPaddr ip=${ipaddr} cidr_netmask=32 op monitor interval=15s
        if [ $? -ne 0 ]; then
            logger "warning pcs resource create ${1}-cluster_ip-1 ocf:heartbeat:IPaddr ip=${ipaddr} cidr_netmask=32 op monitor interval=10s failed"
        fi

        pcs -f ${cibfile} resource create ${1}-trigger_ip-1 ocf:heartbeat:Dummy
        if [ $? -ne 0 ]; then
            logger "warning: pcs resource create ${1}-trigger_ip-1 ocf:heartbeat:Dummy failed"
        fi

        pcs -f ${cibfile} constraint colocation add ${1}-cluster_ip-1 with ${1}-trigger_ip-1
        if [ $? -ne 0 ]; then
            logger "warning: pcs constraint colocation add ${1}-cluster_ip-1 with ${1}-trigger_ip-1 failed"
        fi

        pcs -f ${cibfile} constraint order ${1}-trigger_ip-1 then nfs-grace-clone
        if [ $? -ne 0 ]; then
            logger "warning: pcs constraint order ${1}-trigger_ip-1 then nfs-grace-clone failed"
        fi

        pcs -f ${cibfile} constraint order nfs-grace-clone then ${1}-cluster_ip-1
        if [ $? -ne 0 ]; then
            logger "warning: pcs constraint order nfs-grace-clone then ${1}-cluster_ip-1 failed"
        fi

        shift
    done
}


addnode_recreate_resources()
{
    local cibfile=${1}; shift
    local add_node=${1}; shift
    local add_vip=${1}; shift

    recreate_resources ${cibfile} ${HA_SERVERS}

    pcs -f ${cibfile} resource create ${add_node}-cluster_ip-1 ocf:heartbeat:IPaddr ip=${add_vip} cidr_netmask=32 op monitor interval=15s
    if [ $? -ne 0 ]; then
        logger "warning pcs resource create ${add_node}-cluster_ip-1 ocf:heartbeat:IPaddr ip=${add_vip} cidr_netmask=32 op monitor interval=10s failed"
    fi

    pcs -f ${cibfile} resource create ${add_node}-trigger_ip-1 ocf:heartbeat:Dummy
    if [ $? -ne 0 ]; then
        logger "warning: pcs resource create ${add_node}-trigger_ip-1 ocf:heartbeat:Dummy failed"
    fi

    pcs -f ${cibfile} constraint colocation add ${add_node}-cluster_ip-1 with ${add_node}-trigger_ip-1
    if [ $? -ne 0 ]; then
        logger "warning: pcs constraint colocation add ${add_node}-cluster_ip-1 with ${add_node}-trigger_ip-1 failed"
    fi

    pcs -f ${cibfile} constraint order ${add_node}-trigger_ip-1 then nfs-grace-clone
    if [ $? -ne 0 ]; then
        logger "warning: pcs constraint order ${add_node}-trigger_ip-1 then nfs-grace-clone failed"
    fi

    pcs -f ${cibfile} constraint order nfs-grace-clone then ${add_node}-cluster_ip-1
    if [ $? -ne 0 ]; then
        logger "warning: pcs constraint order nfs-grace-clone then ${add_node}-cluster_ip-1 failed"
    fi
}


clear_resources()
{
    local cibfile=${1}; shift

    while [[ ${1} ]]; do
        pcs -f ${cibfile} resource delete ${1}-cluster_ip-1
        if [ $? -ne 0 ]; then
            logger "warning: pcs -f ${cibfile} resource delete ${1}-cluster_ip-1"
        fi

        pcs -f ${cibfile} resource delete ${1}-trigger_ip-1
        if [ $? -ne 0 ]; then
            logger "warning: pcs -f ${cibfile} resource delete ${1}-trigger_ip-1"
        fi

        shift
    done
}


addnode_create_resources()
{
    local add_node=${1}; shift
    local add_vip=${1}; shift
    local cibfile=$(mktemp -u)

    # mount the HA-state volume and start ganesha.nfsd on the new node
    pcs cluster cib ${cibfile}
    if [ $? -ne 0 ]; then
        logger "warning: pcs cluster cib ${cibfile} failed"
    fi

    pcs -f ${cibfile} resource create nfs_start-${add_node} ganesha_nfsd ha_vol_mnt=${HA_VOL_MNT}
    if [ $? -ne 0 ]; then
        logger "warning: pcs -f ${cibfile} resource create nfs_start-${add_node} ganesha_nfsd ha_vol_mnt=${HA_VOL_MNT} failed"
    fi

    pcs -f ${cibfile} constraint location nfs_start-${add_node} prefers ${add_node}=INFINITY
    if [ $? -ne 0 ]; then
        logger "warning: pcs -f ${cibfile} constraint location nfs_start-${add_node} prefers ${add_node}=INFINITY failed"
    fi

    pcs -f ${cibfile} constraint order nfs_start-${add_node} then nfs-mon-clone
    if [ $? -ne 0 ]; then
        logger "warning: pcs -f ${cibfile} constraint order nfs_start-${add_node} then nfs-mon-clone failed"
    fi

    pcs cluster cib-push ${cibfile}
    if [ $? -ne 0 ]; then
        logger "warning: pcs cluster cib-push ${cibfile} failed"
    fi
    rm -f ${cibfile}

    # start HA on the new node
    pcs cluster start ${add_node}
    if [ $? -ne 0 ]; then
       logger "warning: pcs cluster start ${add_node} failed"
    fi

    pcs resource delete nfs_start-${add_node}
    if [ $? -ne 0 ]; then
        logger "warning: pcs resource delete nfs_start-${add_node} failed"
    fi


    pcs cluster cib ${cibfile}
    if [ $? -ne 0 ]; then
        logger "warning: pcs cluster cib ${cibfile} failed"
    fi

    # delete all the -cluster_ip-1 and -trigger_ip-1 resources,
    # clearing their constraints, then create them again so we can
    # recompute their constraints
    clear_resources ${cibfile} ${HA_SERVERS}
    addnode_recreate_resources ${cibfile} ${add_node} ${add_vip}

    HA_SERVERS="${HA_SERVERS} ${add_node}"
    create_virt_ip_constraints ${cibfile} ${HA_SERVERS}

    pcs cluster cib-push ${cibfile}
    if [ $? -ne 0 ]; then
        logger "warning: pcs cluster cib-push ${cibfile} failed"
    fi
    rm -f ${cibfile}
}


deletenode_delete_resources()
{
    local node=${1}; shift
    local ha_servers=$(echo "${HA_SERVERS}" | sed s/${node}//)
    local cibfile=$(mktemp -u)

    pcs cluster cib ${cibfile}
    if [ $? -ne 0 ]; then
        logger "warning: pcs cluster cib ${cibfile} failed"
    fi

    # delete all the -cluster_ip-1 and -trigger_ip-1 resources,
    # clearing their constraints, then create them again so we can
    # recompute their constraints
    clear_resources ${cibfile} ${HA_SERVERS}
    recreate_resources ${cibfile} ${ha_servers}
    HA_SERVERS=$(echo "${ha_servers}" | sed -e "s/  / /")

    create_virt_ip_constraints ${cibfile} ${HA_SERVERS}

    pcs cluster cib-push ${cibfile}
    if [ $? -ne 0 ]; then
        logger "warning: pcs cluster cib-push ${cibfile} failed"
    fi
    rm -f ${cibfile}

    pcs cluster cib ${cibfile}
    if [ $? -ne 0 ]; then
        logger "warning: pcs cluster cib ${cibfile} failed"
    fi

    pcs -f ${cibfile} resource create nfs_stop-${node} ganesha_nfsd ha_vol_mnt=${HA_VOL_MNT}
    if [ $? -ne 0 ]; then
        logger "warning: pcs -f ${cibfile} resource create nfs_stop-${node} ganesha_nfsd ha_vol_mnt=${HA_VOL_MNT} failed"
    fi

    pcs -f ${cibfile} constraint location nfs_stop-${node} prefers ${node}=INFINITY
    if [ $? -ne 0 ]; then
        logger "warning: pcs -f ${cibfile} constraint location nfs_stop-${node} prefers ${node}=INFINITY failed"
    fi

    pcs cluster cib-push ${cibfile}
    if [ $? -ne 0 ]; then
        logger "warning: pcs cluster cib-push ${cibfile} failed"
    fi
    rm -f ${cibfile}

    pcs resource delete nfs_stop-${node}
    if [ $? -ne 0 ]; then
        logger "warning: pcs resource delete nfs_stop-${node} failed"
    fi
}


setup_state_volume()
{
    local mnt=${HA_VOL_MNT}
    local longname=""
    local shortname=""
    local dname=""
    local dirname=""

    longname=$(hostname)
    dname=${longname#$(hostname -s)}

    while [[ ${1} ]]; do

        if [[ ${1} == *${dname} ]]; then
            dirname=${1}
        else
            dirname=${1}${dname}
        fi


        if [ ! -d ${mnt}/nfs-ganesha/${dirname} ]; then
            mkdir ${mnt}/nfs-ganesha/${dirname}
        fi
        if [ ! -d ${mnt}/nfs-ganesha/${dirname}/nfs ]; then
            mkdir ${mnt}/nfs-ganesha/${dirname}/nfs
        fi
        if [ ! -d ${mnt}/nfs-ganesha/${dirname}/nfs/ganesha ]; then
            mkdir ${mnt}/nfs-ganesha/${dirname}/nfs/ganesha
        fi
        if [ ! -d ${mnt}/nfs-ganesha/${dirname}/nfs/statd ]; then
            mkdir ${mnt}/nfs-ganesha/${dirname}/nfs/statd
        fi
        touch ${mnt}/nfs-ganesha/${dirname}/nfs/state
        if [ ! -d ${mnt}/nfs-ganesha/${dirname}/nfs/ganesha/v4recov ]; then
            mkdir ${mnt}/nfs-ganesha/${dirname}/nfs/ganesha/v4recov
        fi
        if [ ! -d ${mnt}/nfs-ganesha/${dirname}/nfs/ganesha/v4old ]; then
            mkdir ${mnt}/nfs-ganesha/${dirname}/nfs/ganesha/v4old
        fi
        if [ ! -d ${mnt}/nfs-ganesha/${dirname}/nfs/statd/sm ]; then
            mkdir ${mnt}/nfs-ganesha/${dirname}/nfs/statd/sm
        fi
        if [ ! -d ${mnt}/nfs-ganesha/${dirname}/nfs/statd/sm.bak ]; then
            mkdir ${mnt}/nfs-ganesha/${dirname}/nfs/statd/sm.bak
        fi
        if [ ! -d ${mnt}/nfs-ganesha/${dirname}/nfs/statd/state ]; then
            mkdir ${mnt}/nfs-ganesha/${dirname}/nfs/statd/state
        fi
        for server in ${HA_SERVERS} ; do
            if [ ${server} != ${dirname} ]; then
                ln -s ${mnt}/nfs-ganesha/${server}/nfs/ganesha ${mnt}/nfs-ganesha/${dirname}/nfs/ganesha/${server}
                ln -s ${mnt}/nfs-ganesha/${server}/nfs/statd ${mnt}/nfs-ganesha/${dirname}/nfs/statd/${server}
            fi
        done
        shift
    done

}



main()
{

    local cmd=${1}; shift
    if [[ ${cmd} == *help ]]
        then
        usage
        exit 0
    fi

    HA_CONFDIR=${1}; shift
    local ha_conf=${HA_CONFDIR}/ganesha-ha.conf
    local node=""
    local vip=""

    # ignore any comment lines
    cfgline=$(grep  ^HA_NAME= ${ha_conf})
    eval $(echo ${cfgline} | grep -F HA_NAME=)
    cfgline=$(grep  ^HA_VOL_SERVER= ${ha_conf})
    eval $(echo ${cfgline} | grep -F HA_VOL_SERVER=)
    cfgline=$(grep  ^HA_CLUSTER_NODES= ${ha_conf})
    eval $(echo ${cfgline} | grep -F HA_CLUSTER_NODES=)

    # we'll pretend that nobody ever edits /etc/os-release
    if [ -e /etc/os-release ]; then
        eval $(grep -F "REDHAT_SUPPORT_PRODUCT=" /etc/os-release)
        [ "$REDHAT_SUPPORT_PRODUCT" == "Fedora" ] && RHEL6_PCS_CNAME_OPTION=""
    fi

    case "${cmd}" in

    setup | --setup)
        logger "setting up ${HA_NAME}"

        check_cluster_exists ${HA_NAME}

        determine_servers "setup"

        if [ "X${HA_NUM_SERVERS}X" != "X1X" ]; then

            setup_cluster ${HA_NAME} ${HA_NUM_SERVERS} "${HA_SERVERS}"

            setup_create_resources ${HA_SERVERS}

            setup_state_volume ${HA_SERVERS}

            setup_copy_config ${HA_SERVERS}

            setup_finalize
        else

            logger "insufficient servers for HA, aborting"
        fi
        ;;

    teardown | --teardown)
        logger "tearing down ${HA_NAME}"

        determine_servers "teardown"

        teardown_resources ${HA_SERVERS}

        teardown_cluster ${HA_NAME}
        ;;

    cleanup | --cleanup)
        cleanup_ganesha_config ${HA_CONFDIR}
        ;;

    add | --add)
        node=${1}; shift
        vip=${1}; shift

        logger "adding ${node} with ${vip} to ${HA_NAME}"

        copy_export_config ${node} ${HA_CONFDIR}

        determine_service_manager

        manage_service "start" ${node}

        determine_servers "add"

        pcs cluster node add ${node}
        if [ $? -ne 0 ]; then
            logger "warning: pcs cluster node add ${node} failed"
        fi

        addnode_create_resources ${node} ${vip}
        #Subsequent add-node recreates resources for all the nodes
        #that already exist in the cluster. The nodes are picked up
        #from the entries in the ganesha-ha.conf file. Adding the
        #newly added node to the file so that the resources specfic
        #to this node is correctly recreated in the future.
        echo "VIP_$node=\"$vip\"" >> ${HA_CONFDIR}/ganesha-ha.conf

        NEW_NODES="$HA_CLUSTER_NODES,$node"

        sed -i s/HA_CLUSTER_NODES.*/"HA_CLUSTER_NODES=\"$NEW_NODES\""/ \
$HA_CONFDIR/ganesha-ha.conf
        HA_SERVERS="${HA_SERVERS} ${node}"

        setup_copy_config ${HA_SERVERS}
        ;;

    delete | --delete)
        node=${1}; shift

        logger "deleting ${node} from ${HA_NAME}"

        determine_servers "delete"

        deletenode_delete_resources ${node}

        pcs cluster node remove ${node}
        if [ $? -ne 0 ]; then
            logger "warning: pcs cluster node remove ${node} failed"
        fi

        ha_servers=$(echo ${HA_SERVERS} | sed -e "s/ /,/")
        sed -i "s/^HA_CLUSTER_NODES=.*$/HA_CLUSTER_NODES=\"${ha_servers// /,}\"/" ${HA_CONFDIR}/ganesha-ha.conf

        setup_copy_config ${HA_SERVERS}

        rm -rf ${HA_VOL_MNT}/nfs-ganesha/{node}

        determine_service_manager

        manage_service "stop" ${node}
        ;;

    status | --status)
        exec pcs status
        ;;

    refresh-config | --refresh-config)
        VOL=${1}

        determine_servers "refresh-config"

        refresh_config ${VOL} ${HA_CONFDIR} ${HA_SERVERS}
        ;;

      *)
        # setup and teardown are not intended to be used by a
        # casual user
        usage
        logger "Usage: ganesha-ha.sh add|delete|status"
        ;;

    esac
}

main $*