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
|
/*
Copyright (c) 2011 Gluster, Inc. <http://www.gluster.com>
This file is part of GlusterFS.
GlusterFS 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 3 of the License,
or (at your option) any later version.
GlusterFS 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, see
<http://www.gnu.org/licenses/>.
*/
#ifndef _CONFIG_H
#define _CONFIG_H
#include "config.h"
#endif
#include "common-utils.h"
#include "cli1-xdr.h"
#include "xdr-generic.h"
#include "glusterd.h"
#include "glusterd-op-sm.h"
#include "glusterd-store.h"
#include "glusterd-utils.h"
#include "glusterd-volgen.h"
#include "run.h"
int
glusterd_handle_add_brick (rpcsvc_request_t *req)
{
int32_t ret = -1;
gf1_cli_add_brick_req cli_req = {0,};
dict_t *dict = NULL;
glusterd_brickinfo_t *brickinfo = NULL;
char *brick = NULL;
char *bricks = NULL;
char *volname = NULL;
int brick_count = 0;
char *tmpptr = NULL;
int i = 0;
char *brick_list = NULL;
void *cli_rsp = NULL;
char err_str[2048] = {0,};
gf1_cli_add_brick_rsp rsp = {0,};
glusterd_volinfo_t *volinfo = NULL;
xlator_t *this = NULL;
char *free_ptr = NULL;
glusterd_brickinfo_t *tmpbrkinfo = NULL;
glusterd_volinfo_t tmpvolinfo = {{0},};
int total_bricks = 0;
this = THIS;
GF_ASSERT(this);
GF_ASSERT (req);
INIT_LIST_HEAD (&tmpvolinfo.bricks);
if (!xdr_to_generic (req->msg[0], &cli_req,
(xdrproc_t)xdr_gf1_cli_add_brick_req)) {
//failed to decode msg;
req->rpc_err = GARBAGE_ARGS;
snprintf (err_str, sizeof (err_str), "Garbage args received");
goto out;
}
gf_cmd_log ("Volume add-brick", "on volname: %s attempted",
cli_req.volname);
gf_log ("glusterd", GF_LOG_INFO, "Received add brick req");
if (cli_req.bricks.bricks_len) {
/* Unserialize the dictionary */
dict = dict_new ();
ret = dict_unserialize (cli_req.bricks.bricks_val,
cli_req.bricks.bricks_len,
&dict);
if (ret < 0) {
gf_log ("glusterd", GF_LOG_ERROR,
"failed to "
"unserialize req-buffer to dictionary");
snprintf (err_str, sizeof (err_str), "Unable to decode "
"the buffer");
goto out;
} else {
dict->extra_stdfree = cli_req.bricks.bricks_val;
}
}
ret = dict_get_str (dict, "volname", &volname);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get volume name");
snprintf (err_str, sizeof (err_str), "Unable to get volume "
"name");
goto out;
}
if (!(ret = glusterd_check_volume_exists (volname))) {
ret = -1;
snprintf(err_str, 2048, "Volume %s does not exist", volname);
gf_log ("glusterd", GF_LOG_ERROR, "%s", err_str);
goto out;
}
ret = dict_get_int32 (dict, "count", &brick_count);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get count");
snprintf (err_str, sizeof (err_str), "Unable to get volume "
"brick count");
goto out;
}
ret = glusterd_volinfo_find (volname, &volinfo);
if (ret) {
snprintf (err_str, sizeof (err_str), "Unable to get volinfo "
"for volume name %s", volname);
gf_log ("glusterd", GF_LOG_ERROR, "%s", err_str);
goto out;
}
if (volinfo->type == GF_CLUSTER_TYPE_NONE)
goto brick_val;
/* If any of this is true, some thing is wrong */
if (!brick_count || !volinfo->sub_count) {
ret = -1;
snprintf (err_str, sizeof (err_str), "number of brick count "
"for volume name %s is wrong", volname);
goto out;
}
total_bricks = volinfo->brick_count + brick_count;
/* If the brick count is less than dist_leaf_count then, allow
add-brick only for plain replicate volume since in plain stripe
brick_count becoming less than the dist_leaf_count is not allowed */
if (volinfo->brick_count < volinfo->dist_leaf_count &&
(volinfo->type == GF_CLUSTER_TYPE_REPLICATE)) {
if (total_bricks <= volinfo->replica_count)
goto brick_val;
}
if ((brick_count % volinfo->dist_leaf_count) != 0) {
snprintf(err_str, 2048, "Incorrect number of bricks"
" supplied %d with count %d",
brick_count, volinfo->dist_leaf_count);
gf_log("glusterd", GF_LOG_ERROR, "%s", err_str);
ret = -1;
goto out;
}
brick_val:
ret = dict_get_str (dict, "bricks", &bricks);
if (ret) {
snprintf (err_str, sizeof (err_str), "Unable to get volume "
"bricks");
gf_log ("glusterd", GF_LOG_ERROR, "%s", err_str);
goto out;
}
if (bricks)
brick_list = gf_strdup (bricks);
if (!brick_list) {
ret = -1;
snprintf (err_str, sizeof (err_str), "Out of memory");
goto out;
} else {
free_ptr = brick_list;
}
gf_cmd_log ("Volume add-brick", "volname: %s type %d count:%d bricks:%s"
,volname, volinfo->type, brick_count, brick_list);
while ( i < brick_count) {
i++;
brick= strtok_r (brick_list, " \n", &tmpptr);
brick_list = tmpptr;
brickinfo = NULL;
ret = glusterd_brickinfo_from_brick (brick, &brickinfo);
if (ret) {
snprintf (err_str, sizeof (err_str), "Unable to get "
"brick info from brick %s", brick);
goto out;
}
ret = glusterd_new_brick_validate (brick, brickinfo, err_str,
sizeof (err_str));
if (ret)
goto out;
ret = glusterd_volume_brickinfo_get (brickinfo->uuid,
brickinfo->hostname,
brickinfo->path,
&tmpvolinfo, &tmpbrkinfo,
GF_PATH_PARTIAL);
if (!ret) {
ret = -1;
snprintf (err_str, sizeof (err_str), "Brick: %s:%s, %s"
" one of the bricks contain the other",
tmpbrkinfo->hostname, tmpbrkinfo->path, brick);
goto out;
}
list_add_tail (&brickinfo->brick_list, &tmpvolinfo.bricks);
brickinfo = NULL;
}
ret = glusterd_op_begin (req, GD_OP_ADD_BRICK, dict);
gf_cmd_log ("Volume add-brick","on volname: %s %s", volname,
(ret != 0)? "FAILED" : "SUCCESS");
out:
if (ret) {
if (dict)
dict_unref (dict);
rsp.op_ret = -1;
rsp.op_errno = 0;
rsp.volname = "";
if (err_str[0] == '\0')
snprintf (err_str, sizeof (err_str), "Operation failed");
rsp.op_errstr = err_str;
cli_rsp = &rsp;
glusterd_submit_reply(req, cli_rsp, NULL, 0, NULL,
(xdrproc_t)xdr_gf1_cli_add_brick_rsp);
ret = 0; //sent error to cli, prevent second reply
}
glusterd_friend_sm ();
glusterd_op_sm ();
if (free_ptr)
GF_FREE (free_ptr);
glusterd_volume_brickinfos_delete (&tmpvolinfo);
if (brickinfo)
glusterd_brickinfo_delete (brickinfo);
if (cli_req.volname)
free (cli_req.volname); //its malloced by xdr
return ret;
}
int
glusterd_handle_remove_brick (rpcsvc_request_t *req)
{
int32_t ret = -1;
gf1_cli_remove_brick_req cli_req = {0,};
dict_t *dict = NULL;
int32_t count = 0;
char *brick = NULL;
char key[256] = {0,};
char *brick_list = NULL;
int i = 1;
glusterd_volinfo_t *volinfo = NULL;
glusterd_brickinfo_t *brickinfo = NULL;
int32_t pos = 0;
int32_t sub_volume = 0;
int32_t sub_volume_start = 0;
int32_t sub_volume_end = 0;
glusterd_brickinfo_t *tmp = NULL;
char err_str[2048] = {0};
gf1_cli_remove_brick_rsp rsp = {0,};
void *cli_rsp = NULL;
char vol_type[256] = {0,};
GF_ASSERT (req);
if (!xdr_to_generic (req->msg[0], &cli_req,
(xdrproc_t)xdr_gf1_cli_remove_brick_req)) {
//failed to decode msg;
req->rpc_err = GARBAGE_ARGS;
goto out;
}
gf_cmd_log ("Volume remove-brick","on volname: %s attempted",cli_req.volname);
gf_log ("glusterd", GF_LOG_INFO, "Received rem brick req");
if (cli_req.bricks.bricks_len) {
/* Unserialize the dictionary */
dict = dict_new ();
ret = dict_unserialize (cli_req.bricks.bricks_val,
cli_req.bricks.bricks_len,
&dict);
if (ret < 0) {
gf_log ("glusterd", GF_LOG_ERROR,
"failed to "
"unserialize req-buffer to dictionary");
goto out;
} else {
dict->extra_stdfree = cli_req.bricks.bricks_val;
}
}
ret = dict_get_int32 (dict, "count", &count);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get count");
goto out;
}
ret = glusterd_volinfo_find (cli_req.volname, &volinfo);
if (ret) {
snprintf (err_str, 2048, "Volume %s does not exist",
cli_req.volname);
gf_log ("", GF_LOG_ERROR, "%s", err_str);
goto out;
}
if (volinfo->type == GF_CLUSTER_TYPE_REPLICATE)
strcpy (vol_type, "replica");
else if (volinfo->type == GF_CLUSTER_TYPE_STRIPE)
strcpy (vol_type, "stripe");
else
strcpy (vol_type, "distribute");
/* Do not allow remove-brick if the volume is plain stripe */
if ((volinfo->type == GF_CLUSTER_TYPE_STRIPE) &&
(volinfo->brick_count == volinfo->stripe_count)) {
snprintf (err_str, 2048, "Removing brick from a plain stripe is not allowed");
gf_log ("glusterd", GF_LOG_ERROR, "%s", err_str);
ret = -1;
goto out;
}
/* Do not allow remove-brick if the bricks given is less than the replica count
or stripe count */
if ((volinfo->type != GF_CLUSTER_TYPE_NONE) &&
!(volinfo->brick_count <= volinfo->dist_leaf_count)) {
if (volinfo->dist_leaf_count &&
(count % volinfo->dist_leaf_count)) {
snprintf (err_str, 2048, "Remove brick incorrect"
" brick count of %d for %s %d",
count, vol_type, volinfo->dist_leaf_count);
gf_log ("", GF_LOG_ERROR, "%s", err_str);
ret = -1;
goto out;
}
}
brick_list = GF_MALLOC (120000 * sizeof(*brick_list),gf_common_mt_char);
if (!brick_list) {
ret = -1;
goto out;
}
strcpy (brick_list, " ");
while ( i <= count) {
snprintf (key, 256, "brick%d", i);
ret = dict_get_str (dict, key, &brick);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get %s", key);
goto out;
}
gf_log ("", GF_LOG_DEBUG, "Remove brick count %d brick: %s",
i, brick);
ret = glusterd_volume_brickinfo_get_by_brick(brick, volinfo,
&brickinfo,
GF_PATH_COMPLETE);
if (ret) {
snprintf(err_str, 2048,"Incorrect brick %s for volume"
" %s", brick, cli_req.volname);
gf_log ("", GF_LOG_ERROR, "%s", err_str);
goto out;
}
strcat(brick_list, brick);
strcat(brick_list, " ");
i++;
if ((volinfo->type == GF_CLUSTER_TYPE_NONE) ||
(volinfo->brick_count <= volinfo->dist_leaf_count))
continue;
pos = 0;
list_for_each_entry (tmp, &volinfo->bricks, brick_list) {
if (strcmp (tmp->hostname,brickinfo->hostname) ||
strcmp (tmp->path, brickinfo->path)) {
pos++;
continue;
}
gf_log ("", GF_LOG_INFO, "Found brick");
if (!sub_volume && (volinfo->dist_leaf_count > 1)) {
sub_volume = (pos / volinfo->dist_leaf_count) + 1;
sub_volume_start = (volinfo->dist_leaf_count *
(sub_volume - 1));
sub_volume_end = (volinfo->dist_leaf_count *
sub_volume) - 1;
} else {
if (pos < sub_volume_start ||
pos >sub_volume_end) {
ret = -1;
snprintf(err_str, 2048,"Bricks not from"
" same subvol for %s",
vol_type);
gf_log ("", GF_LOG_ERROR,
"%s", err_str);
goto out;
}
}
break;
}
}
gf_cmd_log ("Volume remove-brick","volname: %s count:%d bricks:%s",
cli_req.volname, count, brick_list);
ret = glusterd_op_begin (req, GD_OP_REMOVE_BRICK, dict);
gf_cmd_log ("Volume remove-brick","on volname: %s %s",cli_req.volname,
(ret) ? "FAILED" : "SUCCESS");
out:
if (ret) {
if (dict)
dict_unref (dict);
rsp.op_ret = -1;
rsp.op_errno = 0;
rsp.volname = "";
if (err_str[0] == '\0')
snprintf (err_str, sizeof (err_str), "Operation failed");
gf_log ("", GF_LOG_ERROR, "%s", err_str);
rsp.op_errstr = err_str;
cli_rsp = &rsp;
glusterd_submit_reply(req, cli_rsp, NULL, 0, NULL,
(xdrproc_t)xdr_gf1_cli_remove_brick_rsp);
ret = 0; //sent error to cli, prevent second reply
}
if (brick_list)
GF_FREE (brick_list);
if (cli_req.volname)
free (cli_req.volname); //its malloced by xdr
glusterd_friend_sm ();
glusterd_op_sm ();
return ret;
}
/* op-sm */
int
glusterd_op_perform_add_bricks (glusterd_volinfo_t *volinfo, int32_t count,
char *bricks)
{
glusterd_brickinfo_t *brickinfo = NULL;
char *brick = NULL;
int32_t i = 1;
char *brick_list = NULL;
char *free_ptr1 = NULL;
char *free_ptr2 = NULL;
char *saveptr = NULL;
int32_t ret = -1;
GF_ASSERT (volinfo);
if (bricks) {
brick_list = gf_strdup (bricks);
free_ptr1 = brick_list;
}
if (count)
brick = strtok_r (brick_list+1, " \n", &saveptr);
while ( i <= count) {
ret = glusterd_brickinfo_from_brick (brick, &brickinfo);
if (ret)
goto out;
ret = glusterd_resolve_brick (brickinfo);
if (ret)
goto out;
list_add_tail (&brickinfo->brick_list, &volinfo->bricks);
brick = strtok_r (NULL, " \n", &saveptr);
i++;
volinfo->brick_count++;
}
brick_list = gf_strdup (bricks);
free_ptr2 = brick_list;
i = 1;
if (count)
brick = strtok_r (brick_list+1, " \n", &saveptr);
ret = glusterd_create_volfiles_and_notify_services (volinfo);
if (ret)
goto out;
while (i <= count) {
ret = glusterd_volume_brickinfo_get_by_brick (brick, volinfo,
&brickinfo,
GF_PATH_PARTIAL);
if (ret)
goto out;
if (GLUSTERD_STATUS_STARTED == volinfo->status) {
ret = glusterd_brick_start (volinfo, brickinfo);
if (ret)
goto out;
}
i++;
brick = strtok_r (NULL, " \n", &saveptr);
}
out:
if (free_ptr1)
GF_FREE (free_ptr1);
if (free_ptr2)
GF_FREE (free_ptr2);
gf_log ("", GF_LOG_DEBUG, "Returning %d", ret);
return ret;
}
int
glusterd_op_perform_remove_brick (glusterd_volinfo_t *volinfo, char *brick,
int force, int *need_migrate)
{
glusterd_brickinfo_t *brickinfo = NULL;
char *dup_brick = NULL;
int32_t ret = -1;
glusterd_conf_t *priv = NULL;
GF_ASSERT (volinfo);
GF_ASSERT (brick);
priv = THIS->private;
GF_ASSERT (priv);
dup_brick = gf_strdup (brick);
if (!dup_brick)
goto out;
ret = glusterd_volume_brickinfo_get_by_brick (dup_brick, volinfo,
&brickinfo, GF_PATH_COMPLETE);
if (ret)
goto out;
ret = glusterd_resolve_brick (brickinfo);
if (ret)
goto out;
if (!uuid_compare (brickinfo->uuid, priv->uuid)) {
/* Only if the brick is in this glusterd, do the rebalance */
if (need_migrate)
*need_migrate = 1;
}
if (force) {
if (GLUSTERD_STATUS_STARTED == volinfo->status) {
ret = glusterd_brick_stop (volinfo, brickinfo);
if (ret) {
gf_log (THIS->name, GF_LOG_ERROR, "Unable to stop "
"glusterfs, ret: %d", ret);
goto out;
}
}
glusterd_delete_brick (volinfo, brickinfo);
goto out;
}
brickinfo->decommissioned = 1;
out:
if (dup_brick)
GF_FREE (dup_brick);
gf_log ("", GF_LOG_DEBUG, "Returning %d", ret);
return ret;
}
int
glusterd_op_stage_add_brick (dict_t *dict, char **op_errstr)
{
int ret = 0;
char *volname = NULL;
int count = 0;
int i = 0;
char *bricks = NULL;
char *brick_list = NULL;
char *saveptr = NULL;
char *free_ptr = NULL;
char *brick = NULL;
glusterd_brickinfo_t *brickinfo = NULL;
glusterd_volinfo_t *volinfo = NULL;
char cmd_str[1024];
glusterd_conf_t *priv = NULL;
char msg[2048] = {0,};
gf_boolean_t brick_alloc = _gf_false;
char *all_bricks = NULL;
char *str_ret = NULL;
priv = THIS->private;
if (!priv)
goto out;
ret = dict_get_str (dict, "volname", &volname);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get volume name");
goto out;
}
ret = glusterd_volinfo_find (volname, &volinfo);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to find volume: %s", volname);
goto out;
}
if (glusterd_is_defrag_on(volinfo)) {
snprintf (msg, sizeof(msg), "Volume name %s rebalance is in "
"progress. Please retry after completion", volname);
gf_log ("glusterd", GF_LOG_ERROR, "%s", msg);
*op_errstr = gf_strdup (msg);
ret = -1;
goto out;
}
ret = dict_get_int32 (dict, "count", &count);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get count");
goto out;
}
ret = dict_get_str (dict, "bricks", &bricks);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get bricks");
goto out;
}
if (bricks) {
brick_list = gf_strdup (bricks);
all_bricks = gf_strdup (bricks);
free_ptr = brick_list;
}
/* Check whether any of the bricks given is the destination brick of the
replace brick running */
str_ret = glusterd_check_brick_rb_part (all_bricks, count, volinfo);
if (str_ret) {
gf_log ("glusterd", GF_LOG_ERROR,
"%s", str_ret);
*op_errstr = gf_strdup (str_ret);
ret = -1;
goto out;
}
if (count)
brick = strtok_r (brick_list+1, " \n", &saveptr);
while ( i < count) {
if (!glusterd_store_is_valid_brickpath (volname, brick) ||
!glusterd_is_valid_volfpath (volname, brick)) {
snprintf (msg, sizeof (msg), "brick path %s is too "
"long.", brick);
gf_log ("", GF_LOG_ERROR, "%s", msg);
*op_errstr = gf_strdup (msg);
ret = -1;
goto out;
}
ret = glusterd_volume_brickinfo_get_by_brick (brick, volinfo,
&brickinfo,
GF_PATH_PARTIAL);
if (!ret) {
gf_log ("", GF_LOG_ERROR, "Adding duplicate brick: %s",
brick);
ret = -1;
goto out;
} else {
ret = glusterd_brickinfo_from_brick (brick, &brickinfo);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Add-brick: Unable"
" to get brickinfo");
goto out;
}
brick_alloc = _gf_true;
}
snprintf (cmd_str, 1024, "%s", brickinfo->path);
ret = glusterd_resolve_brick (brickinfo);
if (ret) {
gf_log ("glusterd", GF_LOG_ERROR,
"resolve brick failed");
goto out;
}
if (!uuid_compare (brickinfo->uuid, priv->uuid)) {
ret = glusterd_brick_create_path (brickinfo->hostname,
brickinfo->path,
volinfo->volume_id,
0777, op_errstr);
if (ret)
goto out;
}
glusterd_brickinfo_delete (brickinfo);
brick_alloc = _gf_false;
brickinfo = NULL;
brick = strtok_r (NULL, " \n", &saveptr);
i++;
}
out:
if (free_ptr)
GF_FREE (free_ptr);
if (brick_alloc && brickinfo)
glusterd_brickinfo_delete (brickinfo);
if (str_ret)
GF_FREE (str_ret);
if (all_bricks)
GF_FREE (all_bricks);
gf_log ("", GF_LOG_DEBUG, "Returning %d", ret);
return ret;
}
int
glusterd_op_stage_remove_brick (dict_t *dict, char **op_errstr)
{
int ret = -1;
char *volname = NULL;
glusterd_volinfo_t *volinfo = NULL;
char *errstr = NULL;
int32_t brick_count = 0;
char msg[2048] = {0,};
int32_t flag = 0;
gf1_op_commands cmd = GF_OP_CMD_NONE;
ret = dict_get_str (dict, "volname", &volname);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get volume name");
goto out;
}
ret = glusterd_volinfo_find (volname, &volinfo);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Volume %s does not exist", volname);
goto out;
}
ret = dict_get_int32 (dict, "command", &flag);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get brick count");
goto out;
}
cmd = flag;
ret = -1;
switch (cmd) {
case GF_OP_CMD_NONE:
errstr = gf_strdup ("no remove-brick command issued");
goto out;
case GF_OP_CMD_STATUS:
ret = 0;
goto out;
case GF_OP_CMD_START:
{
if (GLUSTERD_STATUS_STARTED != volinfo->status) {
snprintf (msg, sizeof (msg), "Volume %s needs to be started "
"before remove-brick (you can use 'force' or "
"'commit' to override this behavior)",
volinfo->volname);
errstr = gf_strdup (msg);
gf_log (THIS->name, GF_LOG_ERROR, "%s", errstr);
goto out;
}
if (glusterd_is_defrag_on(volinfo)) {
errstr = gf_strdup("Rebalance is in progress. Please retry"
" after completion");
gf_log ("glusterd", GF_LOG_ERROR, "%s", errstr);
goto out;
}
break;
}
case GF_OP_CMD_PAUSE:
case GF_OP_CMD_ABORT:
{
if (!volinfo->decommission_in_progress) {
errstr = gf_strdup("remove-brick is not in progress");
gf_log ("glusterd", GF_LOG_ERROR, "%s", errstr);
goto out;
}
break;
}
case GF_OP_CMD_COMMIT:
if (volinfo->decommission_in_progress) {
errstr = gf_strdup ("use 'force' option as migration "
"is in progress");
goto out;
}
break;
case GF_OP_CMD_COMMIT_FORCE:
break;
}
ret = dict_get_int32 (dict, "count", &brick_count);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get brick count");
goto out;
}
ret = 0;
if (volinfo->brick_count == brick_count) {
errstr = gf_strdup ("Deleting all the bricks of the "
"volume is not allowed");
ret = -1;
goto out;
}
out:
gf_log ("", GF_LOG_DEBUG, "Returning %d", ret);
if (ret && errstr) {
if (op_errstr)
*op_errstr = errstr;
}
return ret;
}
int
glusterd_remove_brick_migrate_cbk (glusterd_volinfo_t *volinfo,
gf_defrag_status_t status)
{
int ret = 0;
#if 0 /* TODO: enable this behavior once cluster-wide awareness comes for
defrag cbk function */
glusterd_brickinfo_t *brickinfo = NULL;
glusterd_brickinfo_t *tmp = NULL;
switch (status) {
case GF_DEFRAG_STATUS_PAUSED:
case GF_DEFRAG_STATUS_FAILED:
/* No changes required in the volume file.
everything should remain as is */
break;
case GF_DEFRAG_STATUS_STOPPED:
/* Fall back to the old volume file */
list_for_each_entry_safe (brickinfo, tmp, &volinfo->bricks, brick_list) {
if (!brickinfo->decommissioned)
continue;
brickinfo->decommissioned = 0;
}
break;
case GF_DEFRAG_STATUS_COMPLETE:
/* Done with the task, you can remove the brick from the
volume file */
list_for_each_entry_safe (brickinfo, tmp, &volinfo->bricks, brick_list) {
if (!brickinfo->decommissioned)
continue;
gf_log (THIS->name, GF_LOG_INFO, "removing the brick %s",
brickinfo->path);
brickinfo->decommissioned = 0;
if (GLUSTERD_STATUS_STARTED == volinfo->status) {
ret = glusterd_brick_stop (volinfo, brickinfo);
if (ret) {
gf_log (THIS->name, GF_LOG_ERROR,
"Unable to stop glusterfs (%d)", ret);
}
}
glusterd_delete_brick (volinfo, brickinfo);
}
break;
default:
GF_ASSERT (!"cbk function called with wrong status");
break;
}
ret = glusterd_create_volfiles_and_notify_services (volinfo);
if (ret)
gf_log (THIS->name, GF_LOG_ERROR,
"Unable to write volume files (%d)", ret);
ret = glusterd_store_volinfo (volinfo, GLUSTERD_VOLINFO_VER_AC_INCREMENT);
if (ret)
gf_log (THIS->name, GF_LOG_ERROR,
"Unable to store volume info (%d)", ret);
if (GLUSTERD_STATUS_STARTED == volinfo->status) {
ret = glusterd_check_generate_start_nfs ();
if (ret)
gf_log (THIS->name, GF_LOG_ERROR,
"Unable to start nfs process (%d)", ret);
}
#endif
volinfo->decommission_in_progress = 0;
return ret;
}
int
glusterd_op_add_brick (dict_t *dict, char **op_errstr)
{
int ret = 0;
char *volname = NULL;
glusterd_conf_t *priv = NULL;
glusterd_volinfo_t *volinfo = NULL;
xlator_t *this = NULL;
char *bricks = NULL;
int32_t count = 0;
this = THIS;
GF_ASSERT (this);
priv = this->private;
GF_ASSERT (priv);
ret = dict_get_str (dict, "volname", &volname);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get volume name");
goto out;
}
ret = glusterd_volinfo_find (volname, &volinfo);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to allocate memory");
goto out;
}
ret = dict_get_int32 (dict, "count", &count);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get count");
goto out;
}
ret = dict_get_str (dict, "bricks", &bricks);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get bricks");
goto out;
}
ret = glusterd_op_perform_add_bricks (volinfo, count, bricks);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to add bricks");
goto out;
}
/* Need to reset the defrag/rebalance status accordingly */
switch (volinfo->defrag_status) {
case GF_DEFRAG_STATUS_FAILED:
case GF_DEFRAG_STATUS_COMPLETE:
case GF_DEFRAG_STATUS_LAYOUT_FIX_COMPLETE:
case GF_DEFRAG_STATUS_MIGRATE_DATA_COMPLETE:
volinfo->defrag_status = 0;
default:
break;
}
ret = glusterd_store_volinfo (volinfo, GLUSTERD_VOLINFO_VER_AC_INCREMENT);
if (ret)
goto out;
if (GLUSTERD_STATUS_STARTED == volinfo->status)
ret = glusterd_nodesvcs_handle_graph_change (volinfo);
out:
return ret;
}
int
glusterd_op_remove_brick (dict_t *dict, char **op_errstr)
{
int ret = -1;
char *volname = NULL;
glusterd_volinfo_t *volinfo = NULL;
char *brick = NULL;
int32_t count = 0;
int32_t i = 1;
char key[256] = {0,};
int32_t flag = 0;
char err_str[4096] = {0,};
int need_rebalance = 0;
int force = 0;
gf1_op_commands cmd = 0;
glusterd_brickinfo_t *brickinfo = NULL;
glusterd_brickinfo_t *tmp = NULL;
ret = dict_get_str (dict, "volname", &volname);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get volume name");
goto out;
}
ret = glusterd_volinfo_find (volname, &volinfo);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to allocate memory");
goto out;
}
ret = dict_get_int32 (dict, "command", &flag);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get brick count");
goto out;
}
cmd = flag;
ret = -1;
switch (cmd) {
case GF_OP_CMD_NONE:
goto out;
case GF_OP_CMD_STATUS:
ret = 0;
goto out;
case GF_OP_CMD_PAUSE:
{
if (volinfo->decommission_in_progress) {
if (volinfo->defrag) {
LOCK (&volinfo->defrag->lock);
volinfo->defrag_status = GF_DEFRAG_STATUS_PAUSED;
UNLOCK (&volinfo->defrag->lock);
}
}
/* no need to update anything */
ret = 0;
goto out;
}
case GF_OP_CMD_ABORT:
{
if (volinfo->decommission_in_progress) {
if (volinfo->defrag) {
LOCK (&volinfo->defrag->lock);
volinfo->defrag_status = GF_DEFRAG_STATUS_STOPPED;
UNLOCK (&volinfo->defrag->lock);
}
}
/* Fall back to the old volume file */
list_for_each_entry_safe (brickinfo, tmp, &volinfo->bricks, brick_list) {
if (!brickinfo->decommissioned)
continue;
brickinfo->decommissioned = 0;
}
ret = 0;
break;
}
case GF_OP_CMD_START:
force = 0;
break;
case GF_OP_CMD_COMMIT:
force = 1;
break;
case GF_OP_CMD_COMMIT_FORCE:
if (volinfo->decommission_in_progress) {
if (volinfo->defrag) {
LOCK (&volinfo->defrag->lock);
/* Fake 'rebalance-complete' so the graph change
happens right away */
volinfo->defrag_status = GF_DEFRAG_STATUS_COMPLETE;
UNLOCK (&volinfo->defrag->lock);
}
/* Graph change happens in rebalance _cbk function,
no need to do anything here */
/* TODO: '_cbk' function is not doing anything for now */
}
ret = 0;
force = 1;
break;
}
ret = dict_get_int32 (dict, "count", &count);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get count");
goto out;
}
while ( i <= count) {
snprintf (key, 256, "brick%d", i);
ret = dict_get_str (dict, key, &brick);
if (ret) {
gf_log ("", GF_LOG_ERROR, "Unable to get %s", key);
goto out;
}
ret = glusterd_op_perform_remove_brick (volinfo, brick, force,
(i == 1) ? &need_rebalance : NULL);
if (ret)
goto out;
i++;
}
ret = glusterd_create_volfiles_and_notify_services (volinfo);
if (ret) {
gf_log (THIS->name, GF_LOG_WARNING, "failed to create volfiles");
goto out;
}
ret = glusterd_store_volinfo (volinfo, GLUSTERD_VOLINFO_VER_AC_INCREMENT);
if (ret) {
gf_log (THIS->name, GF_LOG_WARNING, "failed to store volinfo");
goto out;
}
/* Need to reset the defrag/rebalance status accordingly */
switch (volinfo->defrag_status) {
case GF_DEFRAG_STATUS_FAILED:
case GF_DEFRAG_STATUS_COMPLETE:
case GF_DEFRAG_STATUS_LAYOUT_FIX_COMPLETE:
case GF_DEFRAG_STATUS_MIGRATE_DATA_COMPLETE:
volinfo->defrag_status = 0;
default:
break;
}
if (!force && need_rebalance) {
/* perform the rebalance operations */
ret = glusterd_handle_defrag_start (volinfo, err_str, 4096,
GF_DEFRAG_CMD_START_FORCE,
glusterd_remove_brick_migrate_cbk);
if (!ret)
volinfo->decommission_in_progress = 1;
if (ret) {
gf_log (THIS->name, GF_LOG_ERROR,
"failed to start the rebalance");
}
} else {
if (GLUSTERD_STATUS_STARTED == volinfo->status)
ret = glusterd_nodesvcs_handle_graph_change (volinfo);
}
out:
if (ret && err_str[0] && op_errstr)
*op_errstr = gf_strdup (err_str);
return ret;
}
|