summaryrefslogtreecommitdiffstats
path: root/tests/functional/afr/heal/test_self_heal.py
blob: 5eb11ff3bbcec8efab8007f7d1e3db911f37f1b3 (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
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
#  Copyright (C) 2015-2016  Red Hat, Inc. <http://www.redhat.com>
#
#  This program is free software; you can redistribute it and/or modify
#  it under the terms of the GNU General Public License as published by
#  the Free Software Foundation; either version 2 of the License, or
#  any later version.
#
#  This program is distributed in the hope that it will be useful,
#  but WITHOUT ANY WARRANTY; without even the implied warranty of
#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#  GNU General Public License for more details.
#
#  You should have received a copy of the GNU General Public License along
#  with this program; if not, write to the Free Software Foundation, Inc.,
#  51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.

# pylint: disable=too-many-lines

from glusto.core import Glusto as g
from glustolibs.gluster.gluster_base_class import (GlusterBaseClass, runs_on)
from glustolibs.gluster.exceptions import ExecutionError
from glustolibs.gluster.volume_ops import set_volume_options
from glustolibs.gluster.volume_libs import (
    verify_all_process_of_volume_are_online,
    wait_for_volume_process_to_be_online)
from glustolibs.gluster.volume_libs import expand_volume
from glustolibs.gluster.brick_libs import (select_bricks_to_bring_offline,
                                           bring_bricks_offline,
                                           bring_bricks_online,
                                           are_bricks_offline,
                                           get_all_bricks,
                                           wait_for_bricks_to_be_online)
from glustolibs.gluster.heal_libs import (
    wait_for_self_heal_daemons_to_be_online,
    monitor_heal_completion,
    is_heal_complete,
    is_volume_in_split_brain,
    is_shd_daemonized)
from glustolibs.gluster.rebalance_ops import (rebalance_start,
                                              wait_for_rebalance_to_complete)
from glustolibs.gluster.heal_ops import trigger_heal
from glustolibs.misc.misc_libs import upload_scripts
from glustolibs.io.utils import (collect_mounts_arequal, validate_io_procs,
                                 wait_for_io_to_complete)


@runs_on([['replicated', 'distributed-replicated'],
          ['glusterfs', 'cifs', 'nfs']])
class TestSelfHeal(GlusterBaseClass):
    """
    Description:
        Arbiter Test cases related to
        healing in default configuration of the volume
    """

    @classmethod
    def setUpClass(cls):
        # Calling GlusterBaseClass setUpClass
        GlusterBaseClass.setUpClass.im_func(cls)

        # Upload io scripts for running IO on mounts
        g.log.info("Upload io scripts to clients %s for running IO on mounts",
                   cls.clients)
        script_local_path = ("/usr/share/glustolibs/io/scripts/"
                             "file_dir_ops.py")
        cls.script_upload_path = ("/usr/share/glustolibs/io/scripts/"
                                  "file_dir_ops.py")
        ret = upload_scripts(cls.clients, [script_local_path])
        if not ret:
            raise ExecutionError("Failed to upload IO scripts to clients %s"
                                 % cls.clients)
        g.log.info("Successfully uploaded IO scripts to clients %s",
                   cls.clients)

        cls.counter = 1
        # int: Value of counter is used for dirname-start-num argument for
        # file_dir_ops.py create_deep_dirs_with_files.

        # The --dir-length argument value for file_dir_ops.py
        # create_deep_dirs_with_files is set to 10 (refer to the cmd in setUp
        # method). This means every mount will create
        # 10 top level dirs. For every mountpoint/testcase to create new set of
        # dirs, we are incrementing the counter by --dir-length value i.e 10
        # in this test suite.

        # If we are changing the --dir-length to new value, ensure the counter
        # is also incremented by same value to create new set of files/dirs.

    def setUp(self):
        # Calling GlusterBaseClass setUp
        GlusterBaseClass.setUp.im_func(self)

        self.all_mounts_procs = []
        self.io_validation_complete = False

        # Setup Volume and Mount Volume
        g.log.info("Starting to Setup Volume and Mount Volume")
        ret = self.setup_volume_and_mount_volume(mounts=self.mounts)
        if not ret:
            raise ExecutionError("Failed to Setup_Volume and Mount_Volume")
        g.log.info("Successful in Setup Volume and Mount Volume")

    def tearDown(self):
        """
        If test method failed before validating IO, tearDown waits for the
        IO's to complete and checks for the IO exit status

        Cleanup and umount volume
        """
        if not self.io_validation_complete:
            g.log.info("Wait for IO to complete as IO validation did not "
                       "succeed in test method")
            ret = wait_for_io_to_complete(self.all_mounts_procs, self.mounts)
            if not ret:
                raise ExecutionError("IO failed on some of the clients")
            g.log.info("IO is successful on all mounts")

        # Cleanup and umount volume
        g.log.info("Starting to Unmount Volume and Cleanup Volume")
        ret = self.unmount_volume_and_cleanup_volume(mounts=self.mounts)
        if not ret:
            raise ExecutionError("Failed to umount the vol & cleanup Volume")
        g.log.info("Successful in umounting the volume and Cleanup")

        # Calling GlusterBaseClass teardown
        GlusterBaseClass.tearDown.im_func(self)

    def test_data_self_heal_daemon_off(self):
        """
        Test Data-Self-Heal (heal command)

        Description:
        - set the volume option
        "metadata-self-heal": "off"
        "entry-self-heal": "off"
        "data-self-heal": "off"
        - create IO
        - Get arequal before getting bricks offline
        - set the volume option
        "self-heal-daemon": "off"
        - bring down all bricks processes from selected set
        - Get areeual after getting bricks offline and compare with
        arequal before getting bricks offline
        - modify the data
        - bring bricks online
        - set the volume option
        "self-heal-daemon": "on"
        - check daemons and start healing
        - check if heal is completed
        - check for split-brain
        - add bricks
        - do rebalance
        - create 5k files
        - while creating files - kill bricks and bring bricks online one by one
        in cycle
        - validate IO
        """
        # pylint: disable=too-many-statements

        # Setting options
        g.log.info('Setting options...')
        options = {"metadata-self-heal": "off",
                   "entry-self-heal": "off",
                   "data-self-heal": "off"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options %s' % options)
        g.log.info("Successfully set %s for volume %s",
                   options, self.volname)

        # Creating files on client side
        for mount_obj in self.mounts:
            g.log.info("Generating data for %s:%s",
                       mount_obj.client_system, mount_obj.mountpoint)
            # Create files
            g.log.info('Creating files...')
            command = ("python %s create_files -f 100 --fixed-file-size 1k %s"
                       % (self.script_upload_path, mount_obj.mountpoint))

            proc = g.run_async(mount_obj.client_system, command,
                               user=mount_obj.user)
            self.all_mounts_procs.append(proc)
        self.io_validation_complete = False

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Get arequal before getting bricks offline
        g.log.info('Getting arequal before getting bricks offline...')
        ret, result_before_offline = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal before getting bricks offline '
                   'is successful')

        # Setting options
        g.log.info('Setting options...')
        options = {"self-heal-daemon": "off"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options %s' % options)
        g.log.info("Option 'self-heal-daemon' is set to 'off' successfully")

        # Select bricks to bring offline
        bricks_to_bring_offline_dict = (select_bricks_to_bring_offline(
            self.mnode, self.volname))
        bricks_to_bring_offline = filter(None, (
            bricks_to_bring_offline_dict['hot_tier_bricks'] +
            bricks_to_bring_offline_dict['cold_tier_bricks'] +
            bricks_to_bring_offline_dict['volume_bricks']))

        # Bring brick offline
        g.log.info('Bringing bricks %s offline...', bricks_to_bring_offline)
        ret = bring_bricks_offline(self.volname, bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
                        bricks_to_bring_offline)

        ret = are_bricks_offline(self.mnode, self.volname,
                                 bricks_to_bring_offline)
        self.assertTrue(ret, 'Bricks %s are not offline'
                        % bricks_to_bring_offline)
        g.log.info('Bringing bricks %s offline is successful',
                   bricks_to_bring_offline)

        # Get arequal after getting bricks offline
        g.log.info('Getting arequal after getting bricks offline...')
        ret, result_after_offline = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks offline '
                   'is successful')

        # Checking arequals before bringing bricks offline
        # and after bringing bricks offline
        self.assertEqual(result_before_offline, result_after_offline,
                         'Checksums before and '
                         'after bringing bricks online are not equal')
        g.log.info('Checksums before and after bringing bricks online '
                   'are equal')

        # Modify the data
        self.all_mounts_procs = []
        for mount_obj in self.mounts:
            g.log.info("Modifying data for %s:%s", mount_obj.client_system,
                       mount_obj.mountpoint)
            # Create files
            g.log.info('Creating files...')
            command = ("python %s create_files -f 100 --fixed-file-size 10k %s"
                       % (self.script_upload_path, mount_obj.mountpoint))

            proc = g.run_async(mount_obj.client_system, command,
                               user=mount_obj.user)
            self.all_mounts_procs.append(proc)
        self.io_validation_complete = False

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Bring brick online
        g.log.info('Bringing bricks %s online...', bricks_to_bring_offline)
        ret = bring_bricks_online(self.mnode, self.volname,
                                  bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s online' %
                        bricks_to_bring_offline)
        g.log.info('Bringing bricks %s online is successful',
                   bricks_to_bring_offline)

        # Setting options
        g.log.info('Setting options...')
        options = {"self-heal-daemon": "on"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options %s' % options)
        g.log.info("Option 'self-heal-daemon' is set to 'on' successfully")

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online"
                              % self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Wait for self-heal-daemons to be online
        g.log.info("Waiting for self-heal-daemons to be online")
        ret = is_shd_daemonized(self.all_servers)
        self.assertTrue(ret, "Either No self heal daemon process found")
        g.log.info("All self-heal-daemons are online")

        # Start healing
        ret = trigger_heal(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not started')
        g.log.info('Healing is started')

        # Monitor heal completion
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal has not yet completed')

        # Check if heal is completed
        ret = is_heal_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not complete')
        g.log.info('Heal is completed successfully')

        # Check for split-brain
        ret = is_volume_in_split_brain(self.mnode, self.volname)
        self.assertFalse(ret, 'Volume is in split-brain state')
        g.log.info('Volume is not in split-brain state')

        # Add bricks
        g.log.info("Start adding bricks to volume...")
        ret = expand_volume(self.mnode, self.volname, self.servers,
                            self.all_servers_info)
        self.assertTrue(ret, ("Failed to expand the volume %s", self.volname))
        g.log.info("Expanding volume is successful on "
                   "volume %s", self.volname)

        # Do rebalance
        ret, _, _ = rebalance_start(self.mnode, self.volname)
        self.assertEqual(ret, 0, 'Failed to start rebalance')
        g.log.info('Rebalance is started')

        ret = wait_for_rebalance_to_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Rebalance is not completed')
        g.log.info('Rebalance is completed successfully')

        # Create 1k files
        self.all_mounts_procs = []
        for mount_obj in self.mounts:
            g.log.info("Modifying data for %s:%s", mount_obj.client_system,
                       mount_obj.mountpoint)
            # Create files
            g.log.info('Creating files...')
            command = ("python %s create_files -f 1000 %s"
                       % (self.script_upload_path, mount_obj.mountpoint))

            proc = g.run_async(mount_obj.client_system, command,
                               user=mount_obj.user)
            self.all_mounts_procs.append(proc)
        self.io_validation_complete = False

        # Kill all bricks in cycle
        bricks_list = get_all_bricks(self.mnode, self.volname)
        for brick in bricks_list:
            # Bring brick offline
            g.log.info('Bringing bricks %s offline', brick)
            ret = bring_bricks_offline(self.volname, [brick])
            self.assertTrue(ret, 'Failed to bring bricks %s offline' % brick)

            ret = are_bricks_offline(self.mnode, self.volname,
                                     [brick])
            self.assertTrue(ret, 'Bricks %s are not offline'
                            % brick)
            g.log.info('Bringing bricks %s offline is successful',
                       bricks_to_bring_offline)

            # Bring brick online
            g.log.info('Bringing bricks %s online...', brick)
            ret = bring_bricks_online(self.mnode, self.volname,
                                      [brick])
            self.assertTrue(ret, 'Failed to bring bricks %s online' %
                            bricks_to_bring_offline)
            g.log.info('Bringing bricks %s online is successful',
                       bricks_to_bring_offline)

            # Wait for volume processes to be online
            g.log.info("Wait for volume processes to be online")
            ret = wait_for_volume_process_to_be_online(self.mnode,
                                                       self.volname)
            self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                                  "be online", self.volname))
            g.log.info("Successful in waiting for volume %s processes to be "
                       "online", self.volname)

            # Verify volume's all process are online
            g.log.info("Verifying volume's all process are online")
            ret = verify_all_process_of_volume_are_online(self.mnode,
                                                          self.volname)
            self.assertTrue(ret, ("Volume %s : All process are not online"
                                  % self.volname))
            g.log.info("Volume %s : All process are online", self.volname)

            # Wait for self-heal-daemons to be online
            g.log.info("Waiting for self-heal-daemons to be online")
            ret = is_shd_daemonized(self.all_servers)
            self.assertTrue(ret, "Either No self heal daemon process found or"
                                 "more than one self heal daemon process"
                                 "found")
            g.log.info("All self-heal-daemons are online")

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

    def test_data_self_heal_algorithm_diff_heal_command(self):
        """
        Test Volume Option - 'cluster.data-self-heal-algorithm' : 'diff'

        Description:
        - set the volume option
        "metadata-self-heal": "off"
        "entry-self-heal": "off"
        "data-self-heal": "off"
        "data-self-heal-algorithm": "diff"
        "self-heal-daemon": "off"
        - create IO
        - calculate arequal
        - bring down all bricks processes from selected set
        - modify the data
        - get arequal before getting bricks online
        - bring bricks online
        - expand volume by adding bricks to the volume
        - do rebalance
        - set the volume option "self-heal-daemon": "on" and check for daemons
        - start healing
        - check if heal is completed
        - check for split-brain
        - calculate arequal and compare with arequal before bringing bricks
        offline and after bringing bricks online
        """
        # pylint: disable=too-many-branches,too-many-statements
        # Setting options
        g.log.info('Setting options...')
        options = {"metadata-self-heal": "off",
                   "entry-self-heal": "off",
                   "data-self-heal": "off",
                   "data-self-heal-algorithm": "diff"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Options "
                   "'metadata-self-heal', "
                   "'entry-self-heal', "
                   "'data-self-heal', "
                   "'self-heal-daemon' "
                   "are set to 'off',"
                   "'data-self-heal-algorithm' "
                   "is set to 'diff' successfully")

        # Creating files on client side
        for mount_object in self.mounts:
            g.log.info("Generating data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)
            # Creating files
            command = ("python %s create_files -f 100 %s"
                       % (self.script_upload_path, mount_object.mountpoint))

            proc = g.run_async(mount_object.client_system, command,
                               user=mount_object.user)
            self.all_mounts_procs.append(proc)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Setting options
        g.log.info('Setting options...')
        options = {"self-heal-daemon": "off"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Option 'self-heal-daemon' is set to 'off' successfully")

        # Select bricks to bring offline
        bricks_to_bring_offline_dict = (select_bricks_to_bring_offline(
            self.mnode, self.volname))
        bricks_to_bring_offline = filter(None, (
            bricks_to_bring_offline_dict['hot_tier_bricks'] +
            bricks_to_bring_offline_dict['cold_tier_bricks'] +
            bricks_to_bring_offline_dict['volume_bricks']))

        # Bring brick offline
        g.log.info('Bringing bricks %s offline...', bricks_to_bring_offline)
        ret = bring_bricks_offline(self.volname, bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
                        bricks_to_bring_offline)

        ret = are_bricks_offline(self.mnode, self.volname,
                                 bricks_to_bring_offline)
        self.assertTrue(ret, 'Bricks %s are not offline'
                        % bricks_to_bring_offline)
        g.log.info('Bringing bricks %s offline is successful',
                   bricks_to_bring_offline)

        # Modify the data
        self.all_mounts_procs = []
        for mount_object in self.mounts:
            g.log.info("Modifying data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)
            command = ("python %s create_files -f 100 --fixed-file-size 1M %s"
                       % (self.script_upload_path, mount_object.mountpoint))

            proc = g.run_async(mount_object.client_system, command,
                               user=mount_object.user)
            self.all_mounts_procs.append(proc)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Get arequal before getting bricks online
        g.log.info('Getting arequal before getting bricks online...')
        ret, result_before_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal before getting bricks online '
                   'is successful')

        # Bring brick online
        g.log.info('Bringing bricks %s online...', bricks_to_bring_offline)
        ret = bring_bricks_online(self.mnode, self.volname,
                                  bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s online' %
                        bricks_to_bring_offline)
        g.log.info('Bringing bricks %s online is successful',
                   bricks_to_bring_offline)

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online"
                              % self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Expand volume by adding bricks to the volume
        g.log.info("Start adding bricks to volume...")
        ret = expand_volume(self.mnode, self.volname, self.servers,
                            self.all_servers_info)
        self.assertTrue(ret, ("Failed to expand the volume when IO in "
                              "progress on volume %s", self.volname))
        g.log.info("Expanding volume is successful on volume %s", self.volname)
        self.bricks_list = get_all_bricks(self.mnode, self.volname)

        # Do rebalance
        ret, _, _ = rebalance_start(self.mnode, self.volname)
        self.assertEqual(ret, 0, 'Failed to start rebalance')
        g.log.info('Rebalance is started')

        ret = wait_for_rebalance_to_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Rebalance is not completed')
        g.log.info('Rebalance is completed successfully')

        # Setting options
        g.log.info('Setting options...')
        options = {"self-heal-daemon": "on"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Option 'self-heal-daemon' is set to 'on' successfully")

        # Wait for self-heal-daemons to be online
        g.log.info("Waiting for self-heal-daemons to be online")
        ret = is_shd_daemonized(self.all_servers)
        self.assertTrue(ret, "Either No self heal daemon process found")
        g.log.info("All self-heal-daemons are online")

        # Start healing
        ret = trigger_heal(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not started')
        g.log.info('Healing is started')

        # Monitor heal completion
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal has not yet completed')

        # Check if heal is completed
        ret = is_heal_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not complete')
        g.log.info('Heal is completed successfully')

        # Check for split-brain
        ret = is_volume_in_split_brain(self.mnode, self.volname)
        self.assertFalse(ret, 'Volume is in split-brain state')
        g.log.info('Volume is not in split-brain state')

        # Get arequal after getting bricks online
        g.log.info('Getting arequal after getting bricks online...')
        ret, result_after_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks online '
                   'is successful')

        # Checking arequals before bringing bricks offline
        # and after bringing bricks online
        self.assertItemsEqual(result_before_online, result_after_online,
                              'Checksums are not equal')
        g.log.info('Checksums are equal')

    def test_data_self_heal_algorithm_diff_default(self):
        """
        Test Volume Option - 'cluster.data-self-heal-algorithm' : 'diff'

        Description:
        - set the volume option "data-self-heal-algorithm" to value "diff"
        - create IO
        - bring down all bricks processes from selected set
        - modify the data
        - calculate arequal
        - bring bricks online
        - start healing
        - calculate arequal and compare with arequal before bringing bricks
        offline and after bringing bricks online
        """
        # pylint: disable=too-many-locals,too-many-statements
        # Setting options
        g.log.info('Setting options "data-self-heal-algorithm": "diff"...')
        options = {"data-self-heal-algorithm": "diff"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Option 'data-self-heal-algorithm' is set to 'diff' "
                   "successfully")

        # Creating files on client side
        for mount_object in self.mounts:
            g.log.info("Generating data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)
            # Creating files
            command = ("python %s create_files -f 100 %s"
                       % (self.script_upload_path, mount_object.mountpoint))

            proc = g.run_async(mount_object.client_system, command,
                               user=mount_object.user)
            self.all_mounts_procs.append(proc)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Select bricks to bring offline
        bricks_to_bring_offline_dict = (select_bricks_to_bring_offline(
            self.mnode, self.volname))
        bricks_to_bring_offline = filter(None, (
            bricks_to_bring_offline_dict['hot_tier_bricks'] +
            bricks_to_bring_offline_dict['cold_tier_bricks'] +
            bricks_to_bring_offline_dict['volume_bricks']))

        # Bring brick offline
        g.log.info('Bringing bricks %s offline...', bricks_to_bring_offline)
        ret = bring_bricks_offline(self.volname, bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
                        bricks_to_bring_offline)

        ret = are_bricks_offline(self.mnode, self.volname,
                                 bricks_to_bring_offline)
        self.assertTrue(ret, 'Bricks %s are not offline'
                        % bricks_to_bring_offline)
        g.log.info('Bringing bricks %s offline is successful',
                   bricks_to_bring_offline)

        # Modify the data
        self.all_mounts_procs = []
        for mount_object in self.mounts:
            g.log.info("Modifying data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)
            command = ("python %s create_files -f 100 --fixed-file-size 1M %s"
                       % (self.script_upload_path, mount_object.mountpoint))

            proc = g.run_async(mount_object.client_system, command,
                               user=mount_object.user)
            self.all_mounts_procs.append(proc)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Get arequal before getting bricks online
        g.log.info('Getting arequal before getting bricks online...')
        ret, result_before_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal before getting bricks online '
                   'is successful')

        # Bring brick online
        g.log.info('Bringing bricks %s online...', bricks_to_bring_offline)
        ret = bring_bricks_online(self.mnode, self.volname,
                                  bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s online' %
                        bricks_to_bring_offline)
        g.log.info('Bringing bricks %s online is successful',
                   bricks_to_bring_offline)

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online"
                              % self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Wait for self-heal-daemons to be online
        g.log.info("Waiting for self-heal-daemons to be online")
        ret = is_shd_daemonized(self.all_servers)
        self.assertTrue(ret, "Either No self heal daemon process found")
        g.log.info("All self-heal-daemons are online")

        # Monitor heal completion
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal has not yet completed')

        # Check if heal is completed
        ret = is_heal_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not complete')
        g.log.info('Heal is completed successfully')

        # Check for split-brain
        ret = is_volume_in_split_brain(self.mnode, self.volname)
        self.assertFalse(ret, 'Volume is in split-brain state')
        g.log.info('Volume is not in split-brain state')

        # Get arequal after getting bricks online
        g.log.info('Getting arequal after getting bricks online...')
        ret, result_after_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks online '
                   'is successful')

        # Checking arequals before bringing bricks online
        # and after bringing bricks online
        self.assertItemsEqual(result_before_online, result_after_online,
                              'Checksums are not equal')
        g.log.info('Checksums before bringing bricks online '
                   'and after bringing bricks online are equal')

    def test_data_self_heal_algorithm_full_default(self):
        """
        Test Volume Option - 'cluster.data-self-heal-algorithm' : 'full'

        Description:
        - set the volume option "data-self-heal-algorithm" to value "full"
        - create IO
        - bring down all bricks processes from selected set
        - modify the data
        - calculate arequal
        - bring bricks online
        - start healing
        - calculate arequal and compare with arequal before bringing bricks
        offline and after bringing bricks online
        """
        # pylint: disable=too-many-locals,too-many-statements
        # Setting options
        g.log.info('Setting options "data-self-heal-algorithm": "full"...')
        options = {"data-self-heal-algorithm": "full"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Option 'data-self-heal-algorithm' is set to 'full' "
                   "successfully")

        # Creating files on client side
        for mount_object in self.mounts:
            g.log.info("Generating data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)
            # Creating files
            command = ("python %s create_files -f 100 %s"
                       % (self.script_upload_path, mount_object.mountpoint))

            proc = g.run_async(mount_object.client_system, command,
                               user=mount_object.user)
            self.all_mounts_procs.append(proc)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Select bricks to bring offline
        bricks_to_bring_offline_dict = (select_bricks_to_bring_offline(
            self.mnode, self.volname))
        bricks_to_bring_offline = filter(None, (
            bricks_to_bring_offline_dict['hot_tier_bricks'] +
            bricks_to_bring_offline_dict['cold_tier_bricks'] +
            bricks_to_bring_offline_dict['volume_bricks']))

        # Bring brick offline
        g.log.info('Bringing bricks %s offline...', bricks_to_bring_offline)
        ret = bring_bricks_offline(self.volname, bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
                        bricks_to_bring_offline)

        ret = are_bricks_offline(self.mnode, self.volname,
                                 bricks_to_bring_offline)
        self.assertTrue(ret, 'Bricks %s are not offline'
                        % bricks_to_bring_offline)
        g.log.info('Bringing bricks %s offline is successful',
                   bricks_to_bring_offline)

        # Modify the data
        self.all_mounts_procs = []
        for mount_object in self.mounts:
            g.log.info("Modifying data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)
            command = ("python %s create_files -f 100 --fixed-file-size 1M %s"
                       % (self.script_upload_path, mount_object.mountpoint))

            proc = g.run_async(mount_object.client_system, command,
                               user=mount_object.user)
            self.all_mounts_procs.append(proc)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Get arequal before getting bricks online
        g.log.info('Getting arequal before getting bricks online...')
        ret, result_before_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal before getting bricks online '
                   'is successful')

        # Bring brick online
        g.log.info('Bringing bricks %s online...', bricks_to_bring_offline)
        ret = bring_bricks_online(self.mnode, self.volname,
                                  bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s online' %
                        bricks_to_bring_offline)
        g.log.info('Bringing bricks %s online is successful',
                   bricks_to_bring_offline)

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online"
                              % self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Wait for self-heal-daemons to be online
        g.log.info("Waiting for self-heal-daemons to be online")
        ret = is_shd_daemonized(self.all_servers)
        self.assertTrue(ret, "Either No self heal daemon process found")
        g.log.info("All self-heal-daemons are online")

        # Monitor heal completion
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal has not yet completed')

        # Check if heal is completed
        ret = is_heal_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not complete')
        g.log.info('Heal is completed successfully')

        # Check for split-brain
        ret = is_volume_in_split_brain(self.mnode, self.volname)
        self.assertFalse(ret, 'Volume is in split-brain state')
        g.log.info('Volume is not in split-brain state')

        # Get arequal after getting bricks online
        g.log.info('Getting arequal after getting bricks online...')
        ret, result_after_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks online '
                   'is successful')

        # Checking arequals before bringing bricks online
        # and after bringing bricks online
        self.assertItemsEqual(result_before_online, result_after_online,
                              'Checksums are not equal')
        g.log.info('Checksums before bringing bricks online '
                   'and after bringing bricks online are equal')

    def test_self_heal_differing_in_file_type(self):
        """
        testing self heal of files with different file types
        with default configuration

        Description:
        - create IO
        - calculate arequal
        - bring down all bricks processes from selected set
        - calculate arequal and compare with arequal before
        getting bricks offline
        - modify the data
        - arequal before getting bricks online
        - bring bricks online
        - check daemons and healing completion
        - start healing
        - calculate arequal and compare with arequal before bringing bricks
        online and after bringing bricks online
        """
        # pylint: disable=too-many-locals,too-many-statements
        # Creating files on client side
        test_file_type_differs_self_heal_folder = \
            'test_file_type_differs_self_heal'
        for mount_object in self.mounts:
            g.log.info("Generating data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)

            # Creating files
            command = ("cd %s/ ; "
                       "mkdir %s ;"
                       "cd %s/ ;"
                       "for i in `seq 1 10` ; "
                       "do mkdir l1_dir.$i ; "
                       "for j in `seq 1 5` ; "
                       "do mkdir l1_dir.$i/l2_dir.$j ; "
                       "for k in `seq 1 10` ; "
                       "do dd if=/dev/urandom of=l1_dir.$i/l2_dir.$j/test.$k "
                       "bs=1k count=$k ; "
                       "done ; "
                       "done ; "
                       "done ; "
                       % (mount_object.mountpoint,
                          test_file_type_differs_self_heal_folder,
                          test_file_type_differs_self_heal_folder))

            proc = g.run_async(mount_object.client_system, command,
                               user=mount_object.user)
            self.all_mounts_procs.append(proc)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Get arequal before getting bricks offline
        g.log.info('Getting arequal before getting bricks offline...')
        ret, result_before_offline = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal before getting bricks offline '
                   'is successful')

        # Select bricks to bring offline
        bricks_to_bring_offline_dict = (select_bricks_to_bring_offline(
            self.mnode, self.volname))
        bricks_to_bring_offline = filter(None, (
            bricks_to_bring_offline_dict['hot_tier_bricks'] +
            bricks_to_bring_offline_dict['cold_tier_bricks'] +
            bricks_to_bring_offline_dict['volume_bricks']))

        # Bring brick offline
        g.log.info('Bringing bricks %s offline...', bricks_to_bring_offline)
        ret = bring_bricks_offline(self.volname, bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
                        bricks_to_bring_offline)

        ret = are_bricks_offline(self.mnode, self.volname,
                                 bricks_to_bring_offline)
        self.assertTrue(ret, 'Bricks %s are not offline'
                        % bricks_to_bring_offline)
        g.log.info('Bringing bricks %s offline is successful',
                   bricks_to_bring_offline)

        # Get arequal after getting bricks offline
        g.log.info('Getting arequal after getting bricks offline...')
        ret, result_after_offline = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks offline '
                   'is successful')

        # Checking arequals before bringing bricks offline
        # and after bringing bricks offline
        self.assertItemsEqual(result_before_offline, result_after_offline,
                              'Checksums before and after '
                              'bringing bricks offline are not equal')
        g.log.info('Checksums before and after '
                   'bringing bricks offline are equal')

        # Modify the data
        self.all_mounts_procs = []
        for mount_object in self.mounts:
            g.log.info("Modifying data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)
            command = ("cd %s/%s/ ; "
                       "for i in `seq 1 10` ; "
                       "do for j in `seq 1 5` ; "
                       "do for k in `seq 1 10` ; "
                       "do rm -f l1_dir.$i/l2_dir.$j/test.$k ; "
                       "mkdir l1_dir.$i/l2_dir.$j/test.$k ; "
                       "done ; "
                       "done ; "
                       "done ;"
                       % (mount_object.mountpoint,
                          test_file_type_differs_self_heal_folder))

            proc = g.run_async(mount_object.client_system, command,
                               user=mount_object.user)
            self.all_mounts_procs.append(proc)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Get arequal before getting bricks online
        g.log.info('Getting arequal before getting bricks online...')
        ret, result_before_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal before getting bricks online '
                   'is successful')

        # Bring brick online
        g.log.info('Bringing bricks %s online', bricks_to_bring_offline)
        ret = bring_bricks_online(self.mnode, self.volname,
                                  bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s online' %
                        bricks_to_bring_offline)
        g.log.info('Bringing bricks %s online is successful',
                   bricks_to_bring_offline)

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online"
                              % self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Wait for self-heal-daemons to be online
        g.log.info("Waiting for self-heal-daemons to be online")
        ret = is_shd_daemonized(self.all_servers)
        self.assertTrue(ret, "Either No self heal daemon process found")
        g.log.info("All self-heal-daemons are online")

        # Monitor heal completion
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal has not yet completed')

        # Check if heal is completed
        ret = is_heal_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not complete')
        g.log.info('Heal is completed successfully')

        # Check for split-brain
        ret = is_volume_in_split_brain(self.mnode, self.volname)
        self.assertFalse(ret, 'Volume is in split-brain state')
        g.log.info('Volume is not in split-brain state')

        # Get arequal after getting bricks online
        g.log.info('Getting arequal after getting bricks online...')
        ret, result_after_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks online '
                   'is successful')

        # Checking arequals before bringing bricks online
        # and after bringing bricks online
        self.assertItemsEqual(result_before_online, result_after_online,
                              'Checksums before and '
                              'after bringing bricks online are not equal')
        g.log.info('Checksums before and after bringing bricks online '
                   'are equal')

    def test_self_heal_symbolic_links(self):
        """
        Test Self-Heal of Symbolic Links (heal command)

        Description:
        - set the volume option
        "metadata-self-heal": "off"
        "entry-self-heal": "off"
        "data-self-heal": "off"
        "data-self-heal-algorithm": "diff"
        "self-heal-daemon": "off"
        - create IO
        - calculate arequal
        - bring down all bricks processes from selected set
        - calculate arequals and compare with arequal
        before bringing bricks offline
        - modify the data and verify whether the links are properly created
        - calculate arequal before getting bricks online
        - bring bricks online
        - set the volume option
        "self-heal-daemon": "on"
        - check daemons and start healing
        - check is heal is complited
        - check for split-brain
        - calculate arequal after getting bricks online and compare with
        arequal before getting bricks online
        """
        # pylint: disable=too-many-locals,too-many-statements
        # Setting options
        g.log.info('Setting options...')
        options = {"metadata-self-heal": "off",
                   "entry-self-heal": "off",
                   "data-self-heal": "off",
                   "self-heal-daemon": "off"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Options "
                   "'metadata-self-heal', "
                   "'entry-self-heal', "
                   "'data-self-heal', "
                   "'self-heal-daemon' "
                   "are set to 'off' successfully")

        # Creating files on client side
        test_sym_link_self_heal_folder = 'test_sym_link_self_heal'
        for mount_object in self.mounts:
            g.log.info("Generating data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)
            # Creating files
            command = ("cd %s/ ; "
                       "mkdir %s ; "
                       "cd %s/ ;"
                       "for i in `seq 1 5` ; "
                       "do mkdir dir.$i ; "
                       "for j in `seq 1 10` ; "
                       "do dd if=/dev/urandom of=dir.$i/file.$j "
                       "bs=1k count=$j ; "
                       "done ; "
                       "done ;"
                       % (mount_object.mountpoint,
                          test_sym_link_self_heal_folder,
                          test_sym_link_self_heal_folder))

            proc = g.run_async(mount_object.client_system, command,
                               user=mount_object.user)
            self.all_mounts_procs.append(proc)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Get arequal before getting bricks offline
        g.log.info('Getting arequal before getting bricks offline...')
        ret, result_before_offline = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal before getting bricks offline '
                   'is successful')

        # Select bricks to bring offline
        bricks_to_bring_offline_dict = (select_bricks_to_bring_offline(
            self.mnode, self.volname))
        bricks_to_bring_offline = filter(None, (
            bricks_to_bring_offline_dict['hot_tier_bricks'] +
            bricks_to_bring_offline_dict['cold_tier_bricks'] +
            bricks_to_bring_offline_dict['volume_bricks']))

        # Bring brick offline
        g.log.info('Bringing bricks %s offline...', bricks_to_bring_offline)
        ret = bring_bricks_offline(self.volname, bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
                        bricks_to_bring_offline)

        ret = are_bricks_offline(self.mnode, self.volname,
                                 bricks_to_bring_offline)
        self.assertTrue(ret, 'Bricks %s are not offline'
                        % bricks_to_bring_offline)
        g.log.info('Bringing bricks %s offline is successful',
                   bricks_to_bring_offline)

        # Get arequal after getting bricks offline
        g.log.info('Getting arequal after getting bricks offline...')
        ret, result_after_offline = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks offline '
                   'is successful')

        # Checking arequals before bringing bricks offline
        # and after bringing bricks offline
        self.assertItemsEqual(result_before_offline, result_after_offline,
                              'Checksums before and '
                              'after bringing bricks online are not equal')
        g.log.info('Checksums before and after bringing bricks online '
                   'are equal')

        # Modify the data
        for mount_object in self.mounts:
            g.log.info("Modifying data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)
            # Create symlinks
            g.log.info('Creating symlinks...')
            command = ("cd %s/%s/ ; "
                       "for i in `seq 1 5` ; "
                       "do ln -s dir.$i sym_link_dir.$i ; "
                       "done ;"
                       % (mount_object.mountpoint,
                          test_sym_link_self_heal_folder))
            ret, _, _ = g.run(mount_object.client_system, command)
            self.assertEqual(ret, 0, 'Failed to modify the data for %s...'
                             % mount_object.mountpoint)
            g.log.info('Modifying the data for %s is successful',
                       mount_object.mountpoint)

            # Verify whether the links are properly created
            # Get symlink list
            command = ("cd %s/%s/ ; "
                       "ls |grep 'sym'"
                       % (mount_object.mountpoint,
                          test_sym_link_self_heal_folder))
            _, out, _ = g.run(mount_object.client_system, command)
            symlink_list = out.strip().split('\n')

            # Get folder list
            command = ("cd %s/%s/ ; "
                       "ls |grep -v 'sym'"
                       % (mount_object.mountpoint,
                          test_sym_link_self_heal_folder))
            _, out, _ = g.run(mount_object.client_system, command)
            folder_list = out.strip().split('\n')

            # Compare symlinks and folders
            for symlink in symlink_list:
                symlink_index = symlink_list.index(symlink)
                command = ("cd %s/%s/ ; "
                           "readlink %s"
                           % (mount_object.mountpoint,
                              test_sym_link_self_heal_folder,
                              symlink))
                _, out, _ = g.run(mount_object.client_system, command)
                symlink_to_folder = out.strip()
                self.assertEqual(symlink_to_folder, folder_list[symlink_index],
                                 'Links are not properly created')
                g.log.info('Links for %s are properly created',
                           mount_object.mountpoint)

        # Get arequal before getting bricks online
        g.log.info('Getting arequal before getting bricks online...')
        ret, result_before_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal before getting bricks online '
                   'is successful')

        # Bring brick online
        g.log.info('Bringing bricks %s online', bricks_to_bring_offline)
        ret = bring_bricks_online(self.mnode, self.volname,
                                  bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s online' %
                        bricks_to_bring_offline)
        g.log.info('Bringing bricks %s online is successful',
                   bricks_to_bring_offline)

        # Setting options
        g.log.info('Setting options...')
        options = {"self-heal-daemon": "on"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options %s' % options)
        g.log.info("Option 'self-heal-daemon' is set to 'on' successfully")

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online"
                              % self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Wait for self-heal-daemons to be online
        g.log.info("Waiting for self-heal-daemons to be online")
        ret = is_shd_daemonized(self.all_servers)
        self.assertTrue(ret, "Either No self heal daemon process found")
        g.log.info("All self-heal-daemons are online")

        # Start healing
        ret = trigger_heal(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not started')
        g.log.info('Healing is started')

        # Monitor heal completion
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal has not yet completed')

        # Check if heal is completed
        ret = is_heal_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not complete')
        g.log.info('Heal is completed successfully')

        # Check for split-brain
        ret = is_volume_in_split_brain(self.mnode, self.volname)
        self.assertFalse(ret, 'Volume is in split-brain state')
        g.log.info('Volume is not in split-brain state')

        # Get arequal after getting bricks online
        g.log.info('Getting arequal after getting bricks online...')
        ret, result_after_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks online '
                   'is successful')

        # Checking arequals before bringing bricks online
        # and after bringing bricks online
        self.assertItemsEqual(result_before_online, result_after_online,
                              'Checksums before and '
                              'after bringing bricks online are not equal')
        g.log.info('Checksums before and after bringing bricks online '
                   'are equal')

    def test_self_heal_50k_files_heal_command_by_add_brick(self):
        """
        Test self-heal of 50k files (heal command
        Description:
        - set the volume option
        "metadata-self-heal": "off"
        "entry-self-heal": "off"
        "data-self-heal": "off"
        "self-heal-daemon": "off"
        - bring down all bricks processes from selected set
        - create IO (50k files)
        - Get arequal before getting bricks online
        - bring bricks online
        - set the volume option
        "self-heal-daemon": "on"
        - check for daemons
        - start healing
        - check if heal is completed
        - check for split-brain
        - get arequal after getting bricks online and compare with
        arequal before getting bricks online
        - add bricks
        - do rebalance
        - get arequal after adding bricks and compare with
        arequal after getting bricks online
        """
        # pylint: disable=too-many-locals,too-many-statements
        # Setting options
        g.log.info('Setting options...')
        options = {"metadata-self-heal": "off",
                   "entry-self-heal": "off",
                   "data-self-heal": "off",
                   "self-heal-daemon": "off"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Successfully set %s for volume %s", options, self.volname)

        # Select bricks to bring offline
        bricks_to_bring_offline_dict = (select_bricks_to_bring_offline(
            self.mnode, self.volname))
        bricks_to_bring_offline = filter(None, (
            bricks_to_bring_offline_dict['hot_tier_bricks'] +
            bricks_to_bring_offline_dict['cold_tier_bricks'] +
            bricks_to_bring_offline_dict['volume_bricks']))

        # Bring brick offline
        g.log.info('Bringing bricks %s offline...', bricks_to_bring_offline)
        ret = bring_bricks_offline(self.volname, bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
                        bricks_to_bring_offline)

        ret = are_bricks_offline(self.mnode, self.volname,
                                 bricks_to_bring_offline)
        self.assertTrue(ret, 'Bricks %s are not offline'
                        % bricks_to_bring_offline)
        g.log.info('Bringing bricks %s offline is successful',
                   bricks_to_bring_offline)

        # Creating files on client side
        for mount_obj in self.mounts:
            g.log.info("Generating data for %s:%s",
                       mount_obj.client_system, mount_obj.mountpoint)
            # Create 50k files
            g.log.info('Creating files...')
            command = ("python %s create_files -f 50000 %s"
                       % (self.script_upload_path, mount_obj.mountpoint))

            proc = g.run_async(mount_obj.client_system, command,
                               user=mount_obj.user)
            self.all_mounts_procs.append(proc)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Get arequal before getting bricks online
        g.log.info('Getting arequal before getting bricks online...')
        ret, result_before_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal before getting bricks online '
                   'is successful')

        # Bring brick online
        g.log.info('Bringing bricks %s online', bricks_to_bring_offline)
        ret = bring_bricks_online(self.mnode, self.volname,
                                  bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s online' %
                        bricks_to_bring_offline)
        g.log.info('Bringing bricks %s online is successful',
                   bricks_to_bring_offline)

        # Setting options
        g.log.info('Setting options...')
        options = {"self-heal-daemon": "on"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options %s' % options)
        g.log.info("Option 'self-heal-daemon' is set to 'on' successfully")

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Failed to wait for volume %s processes to "
                              "be online", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online"
                              % self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Wait for self-heal-daemons to be online
        g.log.info("Waiting for self-heal-daemons to be online")
        ret = is_shd_daemonized(self.all_servers)
        self.assertTrue(ret, "Either No self heal daemon process found")
        g.log.info("All self-heal-daemons are online")

        # Start healing
        ret = trigger_heal(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not started')
        g.log.info('Healing is started')

        # Monitor heal completion
        ret = monitor_heal_completion(self.mnode, self.volname,
                                      timeout_period=3600)
        self.assertTrue(ret, 'Heal has not yet completed')

        # Check if heal is completed
        ret = is_heal_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not complete')
        g.log.info('Heal is completed successfully')

        # Check for split-brain
        ret = is_volume_in_split_brain(self.mnode, self.volname)
        self.assertFalse(ret, 'Volume is in split-brain state')
        g.log.info('Volume is not in split-brain state')

        # Get arequal after getting bricks online
        g.log.info('Getting arequal after getting bricks online...')
        ret, result_after_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks online '
                   'is successful')

        # Checking arequals before bringing bricks online
        # and after bringing bricks online
        self.assertItemsEqual(result_before_online, result_after_online,
                              'Checksums before and '
                              'after bringing bricks online are not equal')
        g.log.info('Checksums before and after bringing bricks online '
                   'are equal')

        # Add bricks
        g.log.info("Start adding bricks to volume...")
        ret = expand_volume(self.mnode, self.volname, self.servers,
                            self.all_servers_info)
        self.assertTrue(ret, ("Failed to expand the volume when IO in "
                              "progress on volume %s", self.volname))
        g.log.info("Expanding volume is successful on volume %s", self.volname)

        # Do rebalance
        ret, _, _ = rebalance_start(self.mnode, self.volname)
        self.assertEqual(ret, 0, 'Failed to start rebalance')
        g.log.info('Rebalance is started')

        ret = wait_for_rebalance_to_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Rebalance is not completed')
        g.log.info('Rebalance is completed successfully')

        # Get arequal after adding bricks
        g.log.info('Getting arequal after adding bricks...')
        ret, result_after_adding_bricks = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks '
                   'is successful')

        # Checking arequals after bringing bricks online
        # and after adding bricks
        self.assertItemsEqual(result_after_online, result_after_adding_bricks,
                              'Checksums after bringing bricks online and '
                              'after adding bricks are not equal')
        g.log.info('Checksums after bringing bricks online and '
                   'after adding bricks are equal')

    def test_self_heal_algorithm_full_daemon_off(self):
        """""
        Description:-
        Checking healing when algorithm is set to "full" and self heal daemon
        is "off".
        """""
        # pylint: disable=too-many-statements

        # Setting volume option of self heal & algorithm
        options = {"metadata-self-heal": "disable",
                   "entry-self-heal": "disable",
                   "data-self-heal": "disable",
                   "data-self-heal-algorithm": "full",
                   "self-heal-daemon": "off"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, "Failed to set the volume options %s" % options)
        g.log.info(" Volume set options success")

        # Select bricks to bring down
        bricks_to_bring_offline_dict = (select_bricks_to_bring_offline(
            self.mnode, self.volname))
        bricks_to_bring_offline = bricks_to_bring_offline_dict['volume_bricks']
        g.log.info("Bringing bricks: %s offline", bricks_to_bring_offline)

        ret = bring_bricks_offline(self.volname, bricks_to_bring_offline)
        self.assertTrue(ret, ("Failed to bring bricks: %s offline",
                              bricks_to_bring_offline))
        g.log.info("Successful in bringing bricks: %s offline",
                   bricks_to_bring_offline)

        # Validate if bricks are offline
        g.log.info("Validating if bricks: %s are offline",
                   bricks_to_bring_offline)
        ret = are_bricks_offline(self.mnode, self.volname,
                                 bricks_to_bring_offline)
        self.assertTrue(ret, "Not all the bricks in list:%s are offline"
                        % bricks_to_bring_offline)
        g.log.info("Successfully validated that bricks %s are all offline",
                   bricks_to_bring_offline)

        # IO on the mount point
        for mount_object in self.mounts:
            g.log.info("Creating Files on %s:%s", mount_object.client_system,
                       mount_object.mountpoint)
            cmd = ("cd %s ;for i in `seq 1 100` ;"
                   "do dd if=/dev/urandom of=file$i bs=1M "
                   "count=1;done" % mount_object.mountpoint)
            ret, _, _ = g.run(mount_object.client_system, cmd)
            self.assertEqual(ret, 0, "Failed to create files")
            g.log.info(" Files created successfully")

        # Collecting Arequal before bring the bricks up
        g.log.info("Collecting Arequal before the bring of bricks down")
        result_before = collect_mounts_arequal(self.mounts)

        # Turning self heal daemon ON
        optionstwo = {"self-heal-daemon": "on"}
        ret = set_volume_options(self.mnode, self.volname, optionstwo)
        self.assertTrue(ret, "Failed to turn self-heal ON")
        g.log.info("Volume set options %s: success", optionstwo)

        # Bring bricks online
        g.log.info("Bring bricks: %s online", bricks_to_bring_offline)
        ret = bring_bricks_online(self.mnode, self.volname,
                                  bricks_to_bring_offline)
        self.assertTrue(ret, "Failed to bring bricks: %s online"
                        % bricks_to_bring_offline)
        g.log.info("Successfully brought all bricks:%s online",
                   bricks_to_bring_offline)

        # Waiting for bricks to come online
        g.log.info("Waiting for brick process to come online")
        timeout = 30
        ret = wait_for_bricks_to_be_online(self.mnode, self.volname, timeout)
        self.assertTrue(ret, "bricks didn't come online after adding bricks")
        g.log.info("Bricks are online")

        # Verifying all bricks online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, "Volume %s : All process are not online"
                        % self.volname)
        g.log.info("Volume %s : All process are online", self.volname)

        # Wait for self heal processes to come online
        g.log.info("Wait for selfheal process to come online")
        timeout = 300
        ret = wait_for_self_heal_daemons_to_be_online(self.mnode,
                                                      self.volname, timeout)
        self.assertTrue(ret, "Self-heal process are not online")
        g.log.info("All self heal process are online")

        # Wait for self-heal to complete
        g.log.info("Wait for self-heal to complete")
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, "Self heal didn't complete even after waiting "
                        "for 20 minutes. 20 minutes is too much a time for "
                        "current test workload")
        g.log.info("self-heal is successful after replace-brick operation")

        # arequal after healing
        g.log.info("Collecting Arequal before the bring of bricks down")
        result_after = collect_mounts_arequal(self.mounts)

        # Comparing the results
        g.log.info("comparing both the results")
        self.assertEqual(result_before, result_after, "Arequals are not equal")


@runs_on([['replicated', 'distributed-replicated'],
          ['glusterfs', 'cifs', 'nfs']])
class TestMetadataSelfHeal(GlusterBaseClass):
    """
    Description:
        Test cases related to metadata delf heal
        in default configuration of the volume
    """

    @classmethod
    def setUpClass(cls):
        # Calling GlusterBaseClass setUpClass
        GlusterBaseClass.setUpClass.im_func(cls)

        # Upload io scripts for running IO on mounts
        g.log.info("Upload io scripts to clients %s for running IO on mounts",
                   cls.clients)
        script_local_path = ("/usr/share/glustolibs/io/scripts/"
                             "file_dir_ops.py")
        cls.script_upload_path = ("/usr/share/glustolibs/io/scripts/"
                                  "file_dir_ops.py")
        ret = upload_scripts(cls.clients, [script_local_path])
        if not ret:
            raise ExecutionError("Failed to upload IO scripts to clients %s"
                                 % cls.clients)
        g.log.info("Successfully uploaded IO scripts to clients %s",
                   cls.clients)

        cls.counter = 1
        # int: Value of counter is used for dirname-start-num argument for
        # file_dir_ops.py create_deep_dirs_with_files.

        # The --dir-length argument value for file_dir_ops.py
        # create_deep_dirs_with_files is set to 10 (refer to the cmd in setUp
        # method). This means every mount will create
        # 10 top level dirs. For every mountpoint/testcase to create new set of
        # dirs, we are incrementing the counter by --dir-length value i.e 10
        # in this test suite.

        # If we are changing the --dir-length to new value, ensure the counter
        # is also incremented by same value to create new set of files/dirs.

    def setUp(self):
        # Calling GlusterBaseClass setUp
        GlusterBaseClass.setUp.im_func(self)

        self.all_mounts_procs = []
        self.io_validation_complete = False

        for mount_object in self.mounts:
            # Create user qa
            g.log.info("Creating user 'qa'...")
            command = "useradd qa"
            ret, _, err = g.run(mount_object.client_system, command)

            if 'already exists' in err:
                g.log.warn("User 'qa' is already exists")
            else:
                g.log.info("User 'qa' is created successfully")

        # Setup Volume and Mount Volume
        g.log.info("Starting to Setup Volume and Mount Volume")
        ret = self.setup_volume_and_mount_volume(mounts=self.mounts)
        if not ret:
            raise ExecutionError("Failed to Setup_Volume and Mount_Volume")
        g.log.info("Successful in Setup Volume and Mount Volume")

    def tearDown(self):
        """
        If test method failed before validating IO, tearDown waits for the
        IO's to complete and checks for the IO exit status

        Cleanup and umount volume
        """
        if not self.io_validation_complete:
            g.log.info("Wait for IO to complete as IO validation did not "
                       "succeed in test method")
            ret = wait_for_io_to_complete(self.all_mounts_procs, self.mounts)
            if not ret:
                raise ExecutionError("IO failed on some of the clients")
            g.log.info("IO is successful on all mounts")

        for mount_object in self.mounts:
            # Delete user
            g.log.info('Deleting user qa...')
            command = "userdel -r qa"
            ret, _, err = g.run(mount_object.client_system, command)

            if 'does not exist' in err:
                g.log.warn('User qa is already deleted')
            else:
                g.log.info('User qa successfully deleted')

        # Cleanup and umount volume
        g.log.info("Starting to Unmount Volume and Cleanup Volume")
        ret = self.unmount_volume_and_cleanup_volume(mounts=self.mounts)
        if not ret:
            raise ExecutionError("Failed to umount the vol & cleanup Volume")
        g.log.info("Successful in umounting the volume and Cleanup")

        # Calling GlusterBaseClass teardown
        GlusterBaseClass.tearDown.im_func(self)

    def test_metadata_self_heal(self):
        """
        Test MetaData Self-Heal (heal command)

        Description:
        - set the volume option
        "metadata-self-heal": "off"
        "entry-self-heal": "off"
        "data-self-heal": "off"
        - create IO
        - set the volume option
        "self-heal-daemon": "off"
        - bring down all bricks processes from selected set
        - Change the permissions, ownership and the group
        of the files under "test_meta_data_self_heal" folder
        - get arequal before getting bricks online
        - bring bricks online
        - set the volume option
        "self-heal-daemon": "on"
        - check daemons and start healing
        - check is heal is completed
        - check for split-brain
        - get arequal after getting bricks online and compare with
        arequal before getting bricks online
        - check group and user are 'qa'
        """
        # pylint: disable=too-many-locals,too-many-statements
        # Setting options
        g.log.info('Setting options...')
        options = {"metadata-self-heal": "off",
                   "entry-self-heal": "off",
                   "data-self-heal": "off"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Options "
                   "'metadata-self-heal', "
                   "'entry-self-heal', "
                   "'data-self-heal', "
                   "are set to 'off' successfully")

        # Creating files on client side
        test_meta_data_self_heal_folder = 'test_meta_data_self_heal'
        for mount_object in self.mounts:
            g.log.info("Generating data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)

            # Create files
            g.log.info('Creating files...')
            command = ("cd %s/ ; "
                       "mkdir %s ;"
                       "cd %s/ ;"
                       "for i in `seq 1 50` ; "
                       "do dd if=/dev/urandom of=test.$i bs=10k count=1 ; "
                       "done ;"
                       % (mount_object.mountpoint,
                          test_meta_data_self_heal_folder,
                          test_meta_data_self_heal_folder))

            proc = g.run_async(mount_object.client_system, command,
                               user=mount_object.user)
            self.all_mounts_procs.append(proc)

        # Validate IO
        self.assertTrue(
            validate_io_procs(self.all_mounts_procs, self.mounts),
            "IO failed on some of the clients"
        )
        self.io_validation_complete = True

        # Setting options
        g.log.info('Setting options...')
        options = {"self-heal-daemon": "off"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Option 'self-heal-daemon' is set to 'off' successfully")

        # Select bricks to bring offline
        bricks_to_bring_offline_dict = (select_bricks_to_bring_offline(
            self.mnode, self.volname))
        bricks_to_bring_offline = filter(None, (
            bricks_to_bring_offline_dict['hot_tier_bricks'] +
            bricks_to_bring_offline_dict['cold_tier_bricks'] +
            bricks_to_bring_offline_dict['volume_bricks']))

        # Bring brick offline
        g.log.info('Bringing bricks %s offline...', bricks_to_bring_offline)
        ret = bring_bricks_offline(self.volname, bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s offline' %
                        bricks_to_bring_offline)

        ret = are_bricks_offline(self.mnode, self.volname,
                                 bricks_to_bring_offline)
        self.assertTrue(ret, 'Bricks %s are not offline'
                        % bricks_to_bring_offline)
        g.log.info('Bringing bricks %s offline is successful',
                   bricks_to_bring_offline)

        # Changing the permissions, ownership and the group
        # of the files under "test_meta_data_self_heal" folder
        for mount_object in self.mounts:
            g.log.info("Modifying data for %s:%s",
                       mount_object.client_system, mount_object.mountpoint)

            # Change permissions to 444
            g.log.info('Changing permissions...')
            command = ("cd %s/%s/ ; "
                       "chmod -R 444 *"
                       % (mount_object.mountpoint,
                          test_meta_data_self_heal_folder))
            ret, out, err = g.run(mount_object.client_system, command)
            self.assertEqual(ret, 0, err)
            g.log.info('Permissions are changed successfully')

            # Change the ownership to qa
            g.log.info('Changing the ownership...')
            command = ("cd %s/%s/ ; "
                       "chown -R qa *"
                       % (mount_object.mountpoint,
                          test_meta_data_self_heal_folder))
            ret, out, err = g.run(mount_object.client_system, command)
            self.assertEqual(ret, 0, err)
            g.log.info('Ownership is changed successfully')

            # Change the group to qa
            g.log.info('Changing the group...')
            command = ("cd %s/%s/ ; "
                       "chgrp -R qa *"
                       % (mount_object.mountpoint,
                          test_meta_data_self_heal_folder))
            ret, out, err = g.run(mount_object.client_system, command)
            self.assertEqual(ret, 0, err)
            g.log.info('Group is changed successfully')

        # Get arequal before getting bricks online
        g.log.info('Getting arequal before getting bricks online...')
        ret, result_before_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal before getting bricks online '
                   'is successful')

        # Bring brick online
        g.log.info('Bringing bricks %s online...', bricks_to_bring_offline)
        ret = bring_bricks_online(self.mnode, self.volname,
                                  bricks_to_bring_offline)
        self.assertTrue(ret, 'Failed to bring bricks %s online' %
                        bricks_to_bring_offline)
        g.log.info('Bringing bricks %s online is successful',
                   bricks_to_bring_offline)

        # Setting options
        g.log.info('Setting options...')
        options = {"self-heal-daemon": "on"}
        ret = set_volume_options(self.mnode, self.volname, options)
        self.assertTrue(ret, 'Failed to set options')
        g.log.info("Option 'self-heal-daemon' is set to 'on' successfully")

        # Wait for volume processes to be online
        g.log.info("Wait for volume processes to be online")
        ret = wait_for_volume_process_to_be_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume process %s not online "
                              "despite waiting for 5 minutes", self.volname))
        g.log.info("Successful in waiting for volume %s processes to be "
                   "online", self.volname)

        # Verify volume's all process are online
        g.log.info("Verifying volume's all process are online")
        ret = verify_all_process_of_volume_are_online(self.mnode, self.volname)
        self.assertTrue(ret, ("Volume %s : All process are not online"
                              % self.volname))
        g.log.info("Volume %s : All process are online", self.volname)

        # Wait for self-heal-daemons to be online
        g.log.info("Waiting for self-heal-daemons to be online")
        ret = is_shd_daemonized(self.all_servers)
        self.assertTrue(ret, "Either No self heal daemon process found")
        g.log.info("All self-heal-daemons are online")

        # Start healing
        ret = trigger_heal(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not started')
        g.log.info('Healing is started')

        # Monitor heal completion
        ret = monitor_heal_completion(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal has not yet completed')

        # Check if heal is completed
        ret = is_heal_complete(self.mnode, self.volname)
        self.assertTrue(ret, 'Heal is not complete')
        g.log.info('Heal is completed successfully')

        # Check for split-brain
        ret = is_volume_in_split_brain(self.mnode, self.volname)
        self.assertFalse(ret, 'Volume is in split-brain state')
        g.log.info('Volume is not in split-brain state')

        # Get arequal after getting bricks online
        g.log.info('Getting arequal after getting bricks online...')
        ret, result_after_online = collect_mounts_arequal(self.mounts)
        self.assertTrue(ret, 'Failed to get arequal')
        g.log.info('Getting arequal after getting bricks online '
                   'is successful')

        # Checking arequals before bringing bricks online
        # and after bringing bricks online
        self.assertItemsEqual(result_before_online, result_after_online,
                              'Checksums are not equal')
        g.log.info('Checksums before bringing bricks online '
                   'and after bringing bricks online are equal')

        # Check for user and group
        for mount_object in self.mounts:
            # Get file list
            command = ("cd %s/%s/ ; "
                       "ls"
                       % (mount_object.mountpoint,
                          test_meta_data_self_heal_folder))
            ret, out, err = g.run(mount_object.client_system, command)
            file_list = out.split()

            # Checking for user and group
            g.log.info('Checking for user and group...')
            conn = g.rpyc_get_connection(mount_object.client_system)
            if conn is None:
                raise Exception("Unable to get connection on node %s" %
                                mount_object.client_system)

            for file_name in file_list:
                file_to_check = '%s/%s/%s' % (mount_object.mountpoint,
                                              test_meta_data_self_heal_folder,
                                              file_name)

                g.log.info('Checking for user and group for %s...', file_name)
                # Check for user
                uid = conn.modules.os.stat(file_to_check).st_uid
                username = conn.modules.pwd.getpwuid(uid).pw_name
                self.assertEqual(username, 'qa', 'User %s is not equal qa'
                                 % username)
                g.log.info("User is 'qa' for %s", file_name)

                # Check for group
                gid = conn.modules.os.stat(file_to_check).st_gid
                groupname = conn.modules.grp.getgrgid(gid).gr_name
                self.assertEqual(groupname, 'qa', 'Group %s is not equal qa'
                                 % groupname)
                g.log.info("Group is 'qa' for %s", file_name)

            g.rpyc_close_connection(host=mount_object.client_system)