-
Notifications
You must be signed in to change notification settings - Fork 14
/
mdmonitor.c
1411 lines (1249 loc) · 35 KB
/
mdmonitor.c
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
/*
* mdadm - manage Linux "md" devices aka RAID arrays.
*
* Copyright (C) 2001-2009 Neil Brown <[email protected]>
*
*
* 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
* (at your option) 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Author: Neil Brown
* Email: <[email protected]>
*/
#include "mdadm.h"
#include "md_p.h"
#include "md_u.h"
#include "udev.h"
#include "xmalloc.h"
#include <sys/wait.h>
#include <limits.h>
#include <syslog.h>
#define TASK_COMM_LEN 16
#define EVENT_NAME_MAX 32
#define AUTOREBUILD_PID_PATH MDMON_DIR "/autorebuild.pid"
#define FALLBACK_DELAY 5
/**
* struct state - external array or container properties.
* @devname: has length of %DEV_MD_DIR + device name + terminating byte
* @devnm: to sync with mdstat info
* @parent_devnm: or subarray, devnm of parent, for others, ""
* @subarray: for a container it is a link to first subarray, for a subarray it is a link to next
* subarray in the same container
* @parent: for a subarray it is a link to its container
*/
struct state {
char devname[MD_NAME_MAX + sizeof(DEV_MD_DIR)];
char devnm[MD_NAME_MAX];
unsigned int utime;
int err;
char *spare_group;
int active, working, failed, spare, raid;
int from_config;
int from_auto;
int expected_spares;
int devstate[MAX_DISKS];
dev_t devid[MAX_DISKS];
int percent;
char parent_devnm[MD_NAME_MAX];
struct supertype *metadata;
struct state *subarray;
struct state *parent;
struct state *next;
};
struct alert_info {
char hostname[HOST_NAME_MAX];
char *mailaddr;
char *mailfrom;
char *alert_cmd;
int dosyslog;
int test;
} info;
enum event {
EVENT_SPARE_ACTIVE = 0,
EVENT_NEW_ARRAY,
EVENT_MOVE_SPARE,
EVENT_TEST_MESSAGE,
__SYSLOG_PRIORITY_WARNING,
EVENT_REBUILD_STARTED,
EVENT_REBUILD,
EVENT_REBUILD_FINISHED,
EVENT_SPARES_MISSING,
__SYSLOG_PRIORITY_CRITICAL,
EVENT_DEVICE_DISAPPEARED,
EVENT_FAIL,
EVENT_FAIL_SPARE,
EVENT_DEGRADED_ARRAY,
EVENT_UNKNOWN
};
mapping_t events_map[] = {
{"SpareActive", EVENT_SPARE_ACTIVE},
{"NewArray", EVENT_NEW_ARRAY},
{"MoveSpare", EVENT_MOVE_SPARE},
{"TestMessage", EVENT_TEST_MESSAGE},
{"RebuildStarted", EVENT_REBUILD_STARTED},
{"Rebuild", EVENT_REBUILD},
{"RebuildFinished", EVENT_REBUILD_FINISHED},
{"SparesMissing", EVENT_SPARES_MISSING},
{"DeviceDisappeared", EVENT_DEVICE_DISAPPEARED},
{"Fail", EVENT_FAIL},
{"FailSpare", EVENT_FAIL_SPARE},
{"DegradedArray", EVENT_DEGRADED_ARRAY},
{NULL, EVENT_UNKNOWN}
};
struct event_data {
enum event event_enum;
/*
* @event_name: Rebuild event name must be in form "RebuildXX", where XX is rebuild progress.
*/
char event_name[EVENT_NAME_MAX];
char message[BUFSIZ];
const char *description;
const char *dev;
const char *disc;
};
static int add_new_arrays(struct mdstat_ent *mdstat, struct state **statelist);
static void try_spare_migration(struct state *statelist);
static void link_containers_with_subarrays(struct state *list);
static void free_statelist(struct state *statelist);
static int check_array(struct state *st, struct mdstat_ent *mdstat, int increments, char *prefer);
static int check_one_sharer(int scan);
static void link_containers_with_subarrays(struct state *list);
static int make_daemon(char *pidfile);
static void try_spare_migration(struct state *statelist);
static void wait_for_events(int *delay_for_event, int c_delay);
static void wait_for_events_mdstat(int *delay_for_event, int c_delay);
static int write_autorebuild_pid(void);
int Monitor(struct mddev_dev *devlist,
char *mailaddr, char *alert_cmd,
struct context *c,
int daemonise, int oneshot,
int dosyslog, char *pidfile, int increments,
int share)
{
/*
* Every few seconds, scan every md device looking for changes
* When a change is found, log it, possibly run the alert command,
* and possibly send Email
*
* For each array, we record:
* Update time
* active/working/failed/spare drives
* State of each device.
* %rebuilt if rebuilding
*
* If the update time changes, check out all the data again
* It is possible that we cannot get the state of each device
* due to bugs in the md kernel module.
* We also read /proc/mdstat to get rebuild percent,
* and to get state on all active devices incase of kernel bug.
*
* Events are:
* Fail
* An active device had Faulty set or Active/Sync removed
* FailSpare
* A spare device had Faulty set
* SpareActive
* An active device had a reverse transition
* RebuildStarted
* percent went from -1 to +ve
* RebuildNN
* percent went from below to not-below NN%
* DeviceDisappeared
* Couldn't access a device which was previously visible
*
* if we detect an array with active<raid and spare==0
* we look at other arrays that have same spare-group
* If we find one with active==raid and spare>0,
* and if we can get_disk_info and find a name
* Then we hot-remove and hot-add to the other array
*
* If devlist is NULL, then we can monitor everything if --scan
* was given. We get an initial list from config file and add anything
* that appears in /proc/mdstat
*/
struct state *statelist = NULL;
int finished = 0;
struct mdstat_ent *mdstat = NULL;
char *mailfrom;
struct mddev_ident *mdlist;
int delay_for_event = c->delay;
if (devlist && c->scan) {
pr_err("Devices list and --scan option cannot be combined - not monitoring.\n");
return 1;
}
if (!mailaddr)
mailaddr = conf_get_mailaddr();
if (!alert_cmd)
alert_cmd = conf_get_program();
mailfrom = conf_get_mailfrom();
if (c->scan && !mailaddr && !alert_cmd && !dosyslog) {
pr_err("No mail address or alert command - not monitoring.\n");
return 1;
}
if (c->verbose) {
pr_err("Monitor is started with delay %ds\n", c->delay);
if (mailaddr)
pr_err("Monitor using email address %s\n", mailaddr);
if (alert_cmd)
pr_err("Monitor using program %s\n", alert_cmd);
}
info.alert_cmd = alert_cmd;
info.mailaddr = mailaddr;
info.mailfrom = mailfrom;
info.dosyslog = dosyslog;
info.test = c->test;
if (s_gethostname(info.hostname, sizeof(info.hostname)) != 0) {
pr_err("Cannot get hostname.\n");
return 1;
}
if (mkdir(MDMON_DIR, 0700) < 0 && errno != EEXIST) {
pr_err("Failed to create directory " MDMON_DIR ": %s\n", strerror(errno));
return 1;
}
if (share){
if (check_one_sharer(c->scan) == 2)
return 1;
}
if (daemonise) {
int rv = make_daemon(pidfile);
if (rv >= 0)
return rv;
}
if (share)
if (write_autorebuild_pid() != 0)
return 1;
if (devlist == NULL) {
mdlist = conf_get_ident(NULL);
for (; mdlist; mdlist = mdlist->next) {
struct state *st;
if (mdlist->devname == NULL)
continue;
if (is_devname_ignore(mdlist->devname) == true)
continue;
if (!is_mddev(mdlist->devname))
continue;
st = xcalloc(1, sizeof *st);
snprintf(st->devname, MD_NAME_MAX + sizeof(DEV_MD_DIR), DEV_MD_DIR "%s",
basename(mdlist->devname));
st->next = statelist;
st->devnm[0] = 0;
st->percent = RESYNC_UNKNOWN;
st->from_config = 1;
st->expected_spares = mdlist->spare_disks;
if (mdlist->spare_group)
st->spare_group = xstrdup(mdlist->spare_group);
statelist = st;
}
} else {
struct mddev_dev *dv;
for (dv = devlist; dv; dv = dv->next) {
struct state *st;
if (!is_mddev(dv->devname))
continue;
st = xcalloc(1, sizeof *st);
mdlist = conf_get_ident(dv->devname);
snprintf(st->devname, MD_NAME_MAX + sizeof(DEV_MD_DIR), "%s", dv->devname);
st->next = statelist;
st->devnm[0] = 0;
st->percent = RESYNC_UNKNOWN;
st->expected_spares = -1;
if (mdlist) {
st->expected_spares = mdlist->spare_disks;
if (mdlist->spare_group)
st->spare_group = xstrdup(mdlist->spare_group);
}
statelist = st;
}
}
while (!finished) {
int new_found = 0;
struct state *st, **stp;
int anydegraded = 0;
int anyredundant = 0;
if (mdstat)
free_mdstat(mdstat);
mdstat = mdstat_read(oneshot ? 0 : 1, 0);
for (st = statelist; st; st = st->next) {
if (check_array(st, mdstat, increments, c->prefer))
anydegraded = 1;
/* for external arrays, metadata is filled for
* containers only
*/
if (st->metadata && st->metadata->ss->external)
continue;
if (st->err == 0 && !anyredundant)
anyredundant = 1;
}
/* now check if there are any new devices found in mdstat */
if (c->scan)
new_found = add_new_arrays(mdstat, &statelist);
/* If an array has active < raid && spare == 0 && spare_group != NULL
* Look for another array with spare > 0 and active == raid and same spare_group
* if found, choose a device and hotremove/hotadd
*/
if (share && anydegraded)
try_spare_migration(statelist);
if (!new_found) {
if (oneshot)
break;
if (!anyredundant) {
pr_err("No array with redundancy detected, stopping\n");
break;
}
wait_for_events(&delay_for_event, c->delay);
}
info.test = 0;
for (stp = &statelist; (st = *stp) != NULL; ) {
if (st->from_auto && st->err > 5) {
*stp = st->next;
if (st->spare_group)
free(st->spare_group);
free(st);
} else
stp = &st->next;
}
}
free_statelist(statelist);
if (pidfile)
unlink(pidfile);
return 0;
}
/*
* wait_for_events() - Waits for events on md devices.
* @delay_for_event: pointer to current event delay
* @c_delay: delay from config
*/
static void wait_for_events(int *delay_for_event, int c_delay)
{
#ifndef NO_LIBUDEV
if (udev_is_available()) {
if (udev_wait_for_events(*delay_for_event) == UDEV_STATUS_ERROR)
pr_err("Error while waiting for udev events.\n");
return;
}
#endif
wait_for_events_mdstat(delay_for_event, c_delay);
}
/*
* wait_for_events_mdstat() - Waits for events on mdstat.
* @delay_for_event: pointer to current event delay
* @c_delay: delay from config
*/
static void wait_for_events_mdstat(int *delay_for_event, int c_delay)
{
int wait_result = mdstat_wait(*delay_for_event);
if (wait_result < 0) {
pr_err("Error while waiting for events on mdstat.\n");
return;
}
/*
* Give chance to process new device
*/
if (wait_result != 0) {
if (c_delay > FALLBACK_DELAY)
*delay_for_event = FALLBACK_DELAY;
} else {
*delay_for_event = c_delay;
}
mdstat_close();
}
static int make_daemon(char *pidfile)
{
/* Return:
* -1 in the forked daemon
* 0 in the parent
* 1 on error
* so a none-negative becomes the exit code.
*/
int pid = fork();
if (pid > 0) {
if (!pidfile)
printf("%d\n", pid);
else {
FILE *pid_file = NULL;
int fd = open(pidfile, O_WRONLY | O_CREAT | O_TRUNC,
0644);
if (fd >= 0)
pid_file = fdopen(fd, "w");
if (!pid_file)
perror("cannot create pid file");
else {
fprintf(pid_file,"%d\n", pid);
fclose(pid_file);
}
}
return 0;
}
if (pid < 0) {
perror("daemonise");
return 1;
}
manage_fork_fds(0);
setsid();
return -1;
}
/*
* check_one_sharer() - Checks for other mdmonitor processes running.
*
* Return:
* 0 - no other processes running,
* 1 - warning,
* 2 - error, or when scan mode is enabled, and one mdmonitor process already exists
*/
static int check_one_sharer(int scan)
{
int pid;
FILE *fp, *comm_fp;
char comm_path[PATH_MAX];
char comm[TASK_COMM_LEN];
if (!is_directory(MDMON_DIR)) {
pr_err("%s is not a regular directory.\n", MDMON_DIR);
return 2;
}
fp = fopen(AUTOREBUILD_PID_PATH, "r");
if (!fp) {
/* PID file does not exist */
if (errno == ENOENT)
return 0;
pr_err("Cannot open %s file.\n", AUTOREBUILD_PID_PATH);
return 2;
}
if (!is_file(AUTOREBUILD_PID_PATH)) {
pr_err("%s is not a regular file.\n", AUTOREBUILD_PID_PATH);
fclose(fp);
return 2;
}
if (fscanf(fp, "%d", &pid) != 1) {
pr_err("Cannot read pid from %s file.\n", AUTOREBUILD_PID_PATH);
fclose(fp);
return 2;
}
snprintf(comm_path, sizeof(comm_path), "/proc/%d/comm", pid);
comm_fp = fopen(comm_path, "r");
if (!comm_fp) {
dprintf("Warning: Cannot open %s, continuing\n", comm_path);
fclose(fp);
return 1;
}
if (fscanf(comm_fp, "%15s", comm) == 0) {
dprintf("Warning: Cannot read comm from %s, continuing\n", comm_path);
fclose(comm_fp);
fclose(fp);
return 1;
}
if (strncmp(basename(comm), Name, strlen(Name)) == 0) {
if (scan) {
pr_err("Only one autorebuild process allowed in scan mode, aborting\n");
fclose(comm_fp);
fclose(fp);
return 2;
}
pr_err("Warning: One autorebuild process already running.\n");
}
fclose(comm_fp);
fclose(fp);
return 0;
}
/*
* write_autorebuild_pid() - Writes pid to autorebuild.pid file.
*
* Return: 0 on success, 1 on error
*/
static int write_autorebuild_pid(void)
{
FILE *fp;
int fd;
if (!is_directory(MDMON_DIR)) {
pr_err("%s is not a regular directory.\n", MDMON_DIR);
return 1;
}
fd = open(AUTOREBUILD_PID_PATH, O_WRONLY | O_CREAT | O_TRUNC, 0700);
if (fd < 0) {
pr_err("Error opening %s file.\n", AUTOREBUILD_PID_PATH);
return 1;
}
fp = fdopen(fd, "w");
if (!fp) {
pr_err("Error opening fd for %s file.\n", AUTOREBUILD_PID_PATH);
return 1;
}
fprintf(fp, "%d\n", getpid());
fclose(fp);
return 0;
}
#define BASE_MESSAGE "%s event detected on md device %s"
#define COMPONENT_DEVICE_MESSAGE ", component device %s"
#define DESCRIPTION_MESSAGE ": %s"
/*
* sprint_event_message() - Writes basic message about detected event to destination ptr.
* @dest: message destination, should be at least the size of BUFSIZ
* @data: event data
*
* Return: 0 on success, 1 on error
*/
static int sprint_event_message(char *dest, const struct event_data *data)
{
if (!dest || !data)
return 1;
if (data->disc && data->description)
snprintf(dest, BUFSIZ, BASE_MESSAGE COMPONENT_DEVICE_MESSAGE DESCRIPTION_MESSAGE,
data->event_name, data->dev, data->disc, data->description);
else if (data->disc)
snprintf(dest, BUFSIZ, BASE_MESSAGE COMPONENT_DEVICE_MESSAGE,
data->event_name, data->dev, data->disc);
else if (data->description)
snprintf(dest, BUFSIZ, BASE_MESSAGE DESCRIPTION_MESSAGE,
data->event_name, data->dev, data->description);
else
snprintf(dest, BUFSIZ, BASE_MESSAGE, data->event_name, data->dev);
return 0;
}
/*
* get_syslog_event_priority() - Determines event priority.
* @event_enum: event to be checked
*
* Return: LOG_CRIT, LOG_WARNING or LOG_INFO
*/
static int get_syslog_event_priority(const enum event event_enum)
{
if (event_enum > __SYSLOG_PRIORITY_CRITICAL)
return LOG_CRIT;
if (event_enum > __SYSLOG_PRIORITY_WARNING)
return LOG_WARNING;
return LOG_INFO;
}
/*
* is_email_event() - Determines whether email for event should be sent or not.
* @event_enum: event to be checked
*
* Return: true if email should be sent, false otherwise
*/
static bool is_email_event(const enum event event_enum)
{
static const enum event email_events[] = {
EVENT_FAIL,
EVENT_FAIL_SPARE,
EVENT_DEGRADED_ARRAY,
EVENT_SPARES_MISSING,
EVENT_TEST_MESSAGE
};
unsigned int i;
for (i = 0; i < ARRAY_SIZE(email_events); ++i) {
if (event_enum == email_events[i])
return true;
}
return false;
}
/*
* execute_alert_cmd() - Forks and executes command provided as alert_cmd.
* @data: event data
*/
static void execute_alert_cmd(const struct event_data *data)
{
int pid = fork();
switch (pid) {
default:
waitpid(pid, NULL, 0);
break;
case -1:
pr_err("Cannot fork to execute alert command");
break;
case 0:
execl(info.alert_cmd, info.alert_cmd, data->event_name, data->dev, data->disc, NULL);
exit(2);
}
}
/*
* send_event_email() - Sends an email about event detected by monitor.
* @data: event data
*/
static void send_event_email(const struct event_data *data)
{
FILE *mp, *mdstat;
char buf[BUFSIZ];
int n;
mp = popen(Sendmail, "w");
if (!mp) {
pr_err("Cannot open pipe stream for sendmail.\n");
return;
}
signal(SIGPIPE, SIG_IGN);
if (info.mailfrom)
fprintf(mp, "From: %s\n", info.mailfrom);
else
fprintf(mp, "From: %s monitoring <root>\n", Name);
fprintf(mp, "To: %s\n", info.mailaddr);
fprintf(mp, "Subject: %s event on %s:%s\n\n", data->event_name, data->dev, info.hostname);
fprintf(mp, "This is an automatically generated mail message.\n");
fprintf(mp, "%s\n", data->message);
mdstat = fopen("/proc/mdstat", "r");
if (!mdstat) {
pr_err("Cannot open /proc/mdstat\n");
pclose(mp);
return;
}
fprintf(mp, "The /proc/mdstat file currently contains the following:\n\n");
while ((n = fread(buf, 1, sizeof(buf), mdstat)) > 0)
n = fwrite(buf, 1, n, mp);
fclose(mdstat);
pclose(mp);
}
/*
* log_event_to_syslog() - Logs an event into syslog.
* @data: event data
*/
static void log_event_to_syslog(const struct event_data *data)
{
int priority;
priority = get_syslog_event_priority(data->event_enum);
syslog(priority, "%s\n", data->message);
}
/*
* alert() - Alerts about the monitor event.
* @event_enum: event to be sent
* @description: event description
* @progress: rebuild progress
* @dev: md device name
* @disc: component device
*
* If needed function executes alert command, sends an email or logs event to syslog.
*/
static void alert(const enum event event_enum, const char *description, const uint8_t progress,
const char *dev, const char *disc)
{
struct event_data data = {.dev = dev, .disc = disc, .description = description};
if (!dev)
return;
if (event_enum == EVENT_REBUILD) {
snprintf(data.event_name, sizeof(data.event_name), "%s%02d",
map_num_s(events_map, EVENT_REBUILD), progress);
} else {
snprintf(data.event_name, sizeof(data.event_name), "%s", map_num_s(events_map, event_enum));
}
data.event_enum = event_enum;
if (sprint_event_message(data.message, &data) != 0) {
pr_err("Cannot create event message.\n");
return;
}
pr_err("%s\n", data.message);
if (info.alert_cmd)
execute_alert_cmd(&data);
if (info.mailaddr && is_email_event(event_enum))
send_event_email(&data);
if (info.dosyslog)
log_event_to_syslog(&data);
}
static int check_array(struct state *st, struct mdstat_ent *mdstat,
int increments, char *prefer)
{
/* Update the state 'st' to reflect any changes shown in mdstat,
* or found by directly examining the array, and return
* '1' if the array is degraded, or '0' if it is optimal (or dead).
*/
struct { int state, major, minor; } disks_info[MAX_DISKS];
struct mdinfo *sra = NULL;
mdu_array_info_t array;
struct mdstat_ent *mse = NULL, *mse2;
char *dev = st->devname;
int fd;
int i;
int remaining_disks;
int last_disk;
int new_array = 0;
int retval;
int is_container = 0;
unsigned long redundancy_only_flags = 0;
if (info.test)
alert(EVENT_TEST_MESSAGE, NULL, 0, dev, NULL);
retval = 0;
fd = open(dev, O_RDONLY);
if (fd < 0)
goto disappeared;
if (st->devnm[0] == 0)
snprintf(st->devnm, MD_NAME_MAX, "%s", fd2devnm(fd));
for (mse2 = mdstat; mse2; mse2 = mse2->next)
if (strcmp(mse2->devnm, st->devnm) == 0) {
mse2->devnm[0] = 0; /* flag it as "used" */
mse = mse2;
}
if (!mse) {
/* duplicated array in statelist
* or re-created after reading mdstat
*/
st->err++;
goto out;
}
if (mse->level == NULL)
is_container = 1;
if (!is_container && !md_array_active(fd))
goto disappeared;
if (fcntl(fd, F_SETFD, FD_CLOEXEC) < 0)
goto out;
if (md_get_array_info(fd, &array) < 0)
goto disappeared;
if (!is_container && map_name(pers, mse->level) > 0)
redundancy_only_flags |= GET_MISMATCH;
sra = sysfs_read(-1, st->devnm, GET_LEVEL | GET_DISKS | GET_DEVS |
GET_STATE | redundancy_only_flags);
if (!sra)
goto disappeared;
/* It's much easier to list what array levels can't
* have a device disappear than all of them that can
*/
if (sra->array.level == 0 || sra->array.level == -1) {
if (!st->err && !st->from_config)
alert(EVENT_DEVICE_DISAPPEARED, "Wrong-Level", 0, dev, NULL);
st->err++;
goto out;
}
/* this array is in /proc/mdstat */
if (array.utime == 0)
/* external arrays don't update utime, so
* just make sure it is always different. */
array.utime = st->utime + 1;;
if (st->err) {
/* New array appeared where previously had an error */
st->err = 0;
st->percent = RESYNC_NONE;
new_array = 1;
if (!is_container)
alert(EVENT_NEW_ARRAY, NULL, 0, st->devname, NULL);
}
if (st->utime == array.utime && st->failed == sra->array.failed_disks &&
st->working == sra->array.working_disks &&
st->spare == sra->array.spare_disks &&
(mse == NULL || (mse->percent == st->percent))) {
if ((st->active < st->raid) && st->spare == 0)
retval = 1;
goto out;
}
if (st->utime == 0 && /* new array */
mse->pattern && strchr(mse->pattern, '_') /* degraded */)
alert(EVENT_DEGRADED_ARRAY, NULL, 0, dev, NULL);
if (st->utime == 0 && /* new array */ st->expected_spares > 0 &&
sra->array.spare_disks < st->expected_spares)
alert(EVENT_SPARES_MISSING, NULL, 0, dev, NULL);
if (st->percent < 0 && st->percent != RESYNC_UNKNOWN &&
mse->percent >= 0)
alert(EVENT_REBUILD_STARTED, NULL, 0, dev, NULL);
if (st->percent >= 0 && mse->percent >= 0 &&
(mse->percent / increments) > (st->percent / increments)) {
if((mse->percent / increments) == 0)
alert(EVENT_REBUILD_STARTED, NULL, 0, dev, NULL);
else
alert(EVENT_REBUILD, NULL, mse->percent, dev, NULL);
}
if (mse->percent == RESYNC_NONE && st->percent >= 0) {
/* Rebuild/sync/whatever just finished.
* If there is a number in /mismatch_cnt,
* we should report that.
*/
if (sra && sra->mismatch_cnt > 0) {
char cnt[80];
snprintf(cnt, sizeof(cnt),
" mismatches found: %d (on raid level %d)",
sra->mismatch_cnt, sra->array.level);
alert(EVENT_REBUILD_FINISHED, NULL, 0, dev, cnt);
} else
alert(EVENT_REBUILD_FINISHED, NULL, 0, dev, NULL);
}
st->percent = mse->percent;
remaining_disks = sra->array.nr_disks;
for (i = 0; i < MAX_DISKS && remaining_disks > 0; i++) {
mdu_disk_info_t disc;
disc.number = i;
if (md_get_disk_info(fd, &disc) >= 0) {
disks_info[i].state = disc.state;
disks_info[i].major = disc.major;
disks_info[i].minor = disc.minor;
if (disc.major || disc.minor)
remaining_disks --;
} else
disks_info[i].major = disks_info[i].minor = 0;
}
last_disk = i;
if (is_mdstat_ent_subarray(mse)) {
char *sl;
snprintf(st->parent_devnm, MD_NAME_MAX, "%s", mse->metadata_version + 10);
sl = strchr(st->parent_devnm, '/');
if (sl)
*sl = 0;
} else
st->parent_devnm[0] = 0;
if (st->metadata == NULL && st->parent_devnm[0] == 0)
st->metadata = super_by_fd(fd, NULL);
for (i = 0; i < MAX_DISKS; i++) {
mdu_disk_info_t disc = {0, 0, 0, 0, 0};
int newstate = 0;
int change;
char *dv = NULL;
disc.number = i;
if (i < last_disk && (disks_info[i].major || disks_info[i].minor)) {
newstate = disks_info[i].state;
dv = map_dev_preferred(disks_info[i].major, disks_info[i].minor, 1,
prefer);
disc.state = newstate;
disc.major = disks_info[i].major;
disc.minor = disks_info[i].minor;
} else
newstate = (1 << MD_DISK_REMOVED);
if (dv == NULL && st->devid[i])
dv = map_dev_preferred(major(st->devid[i]),
minor(st->devid[i]), 1, prefer);
change = newstate ^ st->devstate[i];
if (st->utime && change && !st->err && !new_array) {
if ((st->devstate[i]&change) & (1 << MD_DISK_SYNC))
alert(EVENT_FAIL, NULL, 0, dev, dv);
else if ((newstate & (1 << MD_DISK_FAULTY)) &&
(disc.major || disc.minor) &&
st->devid[i] == makedev(disc.major,
disc.minor))
alert(EVENT_FAIL_SPARE, NULL, 0, dev, dv);
else if ((newstate&change) & (1 << MD_DISK_SYNC))
alert(EVENT_SPARE_ACTIVE, NULL, 0, dev, dv);
}
st->devstate[i] = newstate;
st->devid[i] = makedev(disc.major, disc.minor);
}
st->active = sra->array.active_disks;
st->working = sra->array.working_disks;
st->spare = sra->array.spare_disks;
st->failed = sra->array.failed_disks;
st->utime = array.utime;
st->raid = sra->array.raid_disks;
st->err = 0;
if ((st->active < st->raid) && st->spare == 0)
retval = 1;
out:
if (sra)
sysfs_free(sra);
if (fd >= 0)
close(fd);
return retval;
disappeared:
if (!st->err && !is_container)
alert(EVENT_DEVICE_DISAPPEARED, NULL, 0, dev, NULL);
st->err++;
goto out;
}
static int add_new_arrays(struct mdstat_ent *mdstat, struct state **statelist)
{
struct mdstat_ent *mse;
int new_found = 0;
char *name;
for (mse = mdstat; mse; mse = mse->next)
if (mse->devnm[0] && (!mse->level || /* retrieve containers */
(strcmp(mse->level, "raid0") != 0 &&
strcmp(mse->level, "linear") != 0))) {
struct state *st = xcalloc(1, sizeof *st);
mdu_array_info_t array;
int fd;
name = get_md_name(mse->devnm);
if (!name) {
free(st);
continue;
}
snprintf(st->devname, MD_NAME_MAX + sizeof(DEV_MD_DIR), "%s", name);
if ((fd = open(st->devname, O_RDONLY)) < 0 ||
md_get_array_info(fd, &array) < 0) {
/* no such array */
if (fd >= 0)
close(fd);
put_md_name(st->devname);
if (st->metadata) {
st->metadata->ss->free_super(st->metadata);
free(st->metadata);
}
free(st);
continue;
}
close(fd);
st->next = *statelist;
st->err = 1;
st->from_auto = 1;
snprintf(st->devnm, MD_NAME_MAX, "%s", mse->devnm);
st->percent = RESYNC_UNKNOWN;
st->expected_spares = -1;
if (is_mdstat_ent_subarray(mse)) {
char *sl;
snprintf(st->parent_devnm, MD_NAME_MAX, "%s",
mse->metadata_version + 10);
sl = strchr(st->parent_devnm, '/');