struct state {
char *devname;
char devnm[32]; /* to sync with mdstat info */
- long utime;
+ 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];
while (! finished) {
int new_found = 0;
- struct state *st;
+ struct state *st, **stp;
int anydegraded = 0;
if (mdstat)
free_mdstat(mdstat);
mdstat = mdstat_read(oneshot?0:1, 0);
+ if (!mdstat)
+ mdstat_close();
for (st=statelist; st; st=st->next)
if (check_array(st, mdstat, c->test, &info,
mdstat_wait(c->delay);
}
c->test = 0;
+
+ for (stp = &statelist; (st = *stp) != NULL; ) {
+ if (st->from_auto && st->err > 5) {
+ *stp = st->next;
+ free(st->devname);
+ free(st->spare_group);
+ free(st);
+ } else
+ stp = &st->next;
+ }
}
for (st2 = statelist; st2; st2 = statelist) {
statelist = st2->next;
rv = stat(dir, &buf);
if (rv != -1) {
if (scan) {
- pr_err("Only one "
- "autorebuild process allowed"
- " in scan mode, aborting\n");
+ pr_err("Only one autorebuild process allowed in scan mode, aborting\n");
fclose(fp);
return 1;
} else {
- pr_err("Warning: One"
- " autorebuild process already"
- " running.\n");
+ pr_err("Warning: One autorebuild process already running.\n");
}
}
fclose(fp);
if (scan) {
if (mkdir(MDMON_DIR, S_IRWXU) < 0 &&
errno != EEXIST) {
- pr_err("Can't create "
- "autorebuild.pid file\n");
+ pr_err("Can't create autorebuild.pid file\n");
} else {
fp = fopen(path, "w");
if (!fp)
- pr_err("Cannot create"
- " autorebuild.pid"
- "file\n");
+ pr_err("Cannot create autorebuild.pidfile\n");
else {
pid = getpid();
fprintf(fp, "%d\n", pid);
if (info->mailfrom)
fprintf(mp, "From: %s\n", info->mailfrom);
else
- fprintf(mp, "From: " Name " monitoring <root>\n");
+ 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",
event, dev, hname);
fprintf(mp,
- "This is an automatically generated"
- " mail message from " Name "\n");
+ "This is an automatically generated mail message from %s\n", Name);
fprintf(mp, "running on %s\n\n", hname);
fprintf(mp,
- "A %s event had been detected on"
- " md device %s.\n\n", event, dev);
+ "A %s event had been detected on md device %s.\n\n", event, dev);
if (disc && disc[0] != ' ')
fprintf(mp,
- "It could be related to"
- " component device %s.\n\n", disc);
+ "It could be related to component device %s.\n\n", disc);
if (disc && disc[0] == ' ')
fprintf(mp, "Extra information:%s.\n\n", disc);
char buf[8192];
int n;
fprintf(mp,
- "\nP.S. The /proc/mdstat file"
- " currently contains the following:\n\n");
+ "\nP.S. 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);
else
priority = LOG_INFO;
- if (disc)
+ if (disc && disc[0] != ' ')
+ syslog(priority,
+ "%s event detected on md device %s, component device %s", event, dev, disc);
+ else if (disc)
syslog(priority,
- "%s event detected on md device %s,"
- " component device %s", event, dev, disc);
+ "%s event detected on md device %s: %s",
+ event, dev, disc);
else
syslog(priority,
"%s event detected on md device %s",
* '1' if the array is degraded, or '0' if it is optimal (or dead).
*/
struct { int state, major, minor; } info[MAX_DISKS];
+ struct mdinfo *sra = NULL;
mdu_array_info_t array;
struct mdstat_ent *mse = NULL, *mse2;
char *dev = st->devname;
int remaining_disks;
int last_disk;
int new_array = 0;
+ int retval;
if (test)
alert("TestMessage", dev, NULL, ainfo);
+
+ retval = 0;
+
fd = open(dev, O_RDONLY);
- if (fd < 0) {
- if (!st->err)
- alert("DeviceDisappeared", dev, NULL, ainfo);
- st->err=1;
- return 0;
- }
+ if (fd < 0)
+ goto disappeared;
+
+ if (!md_array_active(fd))
+ goto disappeared;
+
fcntl(fd, F_SETFD, FD_CLOEXEC);
- if (ioctl(fd, GET_ARRAY_INFO, &array)<0) {
- if (!st->err)
- alert("DeviceDisappeared", dev, NULL, ainfo);
- st->err=1;
- close(fd);
- return 0;
- }
+ if (md_get_array_info(fd, &array) < 0)
+ goto disappeared;
+
+ if (st->devnm[0] == 0)
+ strcpy(st->devnm, fd2devnm(fd));
+
+ sra = sysfs_read(-1, st->devnm, GET_LEVEL | GET_DISKS | GET_DEGRADED |
+ GET_MISMATCH | GET_DEVS | GET_STATE);
+ 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 (array.level == 0 || array.level == -1) {
+ if (sra->array.level == 0 || sra->array.level == -1) {
if (!st->err && !st->from_config)
- alert("DeviceDisappeared", dev, "Wrong-Level", ainfo);
- st->err = 1;
- close(fd);
- return 0;
+ alert("DeviceDisappeared", dev, " Wrong-Level", ainfo);
+ st->err++;
+ goto out;
}
- if (st->devnm[0] == 0)
- strcpy(st->devnm, fd2devnm(fd));
for (mse2 = mdstat ; mse2 ; mse2=mse2->next)
if (strcmp(mse2->devnm, st->devnm) == 0) {
if (!mse) {
/* duplicated array in statelist
* or re-created after reading mdstat*/
- st->err = 1;
+ st->err++;
close(fd);
- return 0;
+ goto out;
}
/* this array is in /proc/mdstat */
if (array.utime == 0)
array.utime = st->utime + 1;;
if (st->err) {
- /* New array appeared where previously had and error */
+ /* New array appeared where previously had an error */
st->err = 0;
st->percent = RESYNC_NONE;
new_array = 1;
alert("NewArray", st->devname, NULL, ainfo);
}
- if (st->utime == array.utime &&
- st->failed == array.failed_disks &&
+ if (st->utime == array.utime && st->failed == sra->array.failed_disks &&
st->working == array.working_disks &&
- st->spare == array.spare_disks &&
- (mse == NULL || (
- mse->percent == st->percent
- ))) {
- close(fd);
+ st->spare == sra->array.spare_disks &&
+ (mse == NULL || (mse->percent == st->percent))) {
if ((st->active < st->raid) && st->spare == 0)
- return 1;
- else
- return 0;
+ retval = 1;
+ goto out;
}
if (st->utime == 0 && /* new array */
- mse->pattern && strchr(mse->pattern, '_') /* degraded */
- )
+ mse->pattern && strchr(mse->pattern, '_') /* degraded */)
alert("DegradedArray", dev, NULL, ainfo);
- if (st->utime == 0 && /* new array */
- st->expected_spares > 0 &&
- array.spare_disks < st->expected_spares)
+ if (st->utime == 0 && /* new array */ st->expected_spares > 0 &&
+ sra->array.spare_disks < st->expected_spares)
alert("SparesMissing", dev, NULL, ainfo);
if (st->percent < 0 && st->percent != RESYNC_UNKNOWN &&
mse->percent >= 0)
alert("RebuildStarted", dev, NULL, ainfo);
- if (st->percent >= 0 &&
- mse->percent >= 0 &&
+ if (st->percent >= 0 && mse->percent >= 0 &&
(mse->percent / increments) > (st->percent / increments)) {
- char percentalert[15]; // "RebuildNN" (10 chars) or "RebuildStarted" (15 chars)
+ char percentalert[15];
+ /*
+ * "RebuildNN" (10 chars) or "RebuildStarted" (15 chars)
+ */
if((mse->percent / increments) == 0)
- snprintf(percentalert, sizeof(percentalert), "RebuildStarted");
+ snprintf(percentalert, sizeof(percentalert),
+ "RebuildStarted");
else
- snprintf(percentalert, sizeof(percentalert), "Rebuild%02d", mse->percent);
+ snprintf(percentalert, sizeof(percentalert),
+ "Rebuild%02d", mse->percent);
alert(percentalert, dev, NULL, ainfo);
}
- if (mse->percent == RESYNC_NONE &&
- st->percent >= 0) {
+ 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.
*/
- struct mdinfo *sra =
- sysfs_read(-1, st->devnm, GET_MISMATCH);
if (sra && sra->mismatch_cnt > 0) {
char cnt[80];
snprintf(cnt, sizeof(cnt),
" mismatches found: %d (on raid level %d)",
- sra->mismatch_cnt, array.level);
+ sra->mismatch_cnt, sra->array.level);
alert("RebuildFinished", dev, cnt, ainfo);
} else
alert("RebuildFinished", dev, NULL, ainfo);
- if (sra)
- free(sra);
}
st->percent = mse->percent;
- remaining_disks = array.nr_disks;
- for (i=0; i<MAX_DISKS && remaining_disks > 0;
- i++) {
+ 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 (ioctl(fd, GET_DISK_INFO, &disc) >= 0) {
+ if (md_get_disk_info(fd, &disc) >= 0) {
info[i].state = disc.state;
info[i].major = disc.major;
info[i].minor = disc.minor;
strncmp(mse->metadata_version, "external:", 9) == 0 &&
is_subarray(mse->metadata_version+9)) {
char *sl;
- strcpy(st->parent_devnm,
- mse->metadata_version+10);
+ strcpy(st->parent_devnm, 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)
+ if (st->metadata == NULL && st->parent_devnm[0] == 0)
st->metadata = super_by_fd(fd, NULL);
- close(fd);
-
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 &&
- (info[i].major || info[i].minor)) {
+ if (i < last_disk && (info[i].major || info[i].minor)) {
newstate = info[i].state;
- dv = map_dev_preferred(
- info[i].major, info[i].minor, 1,
- prefer);
+ dv = map_dev_preferred(info[i].major, info[i].minor, 1,
+ prefer);
disc.state = newstate;
disc.major = info[i].major;
disc.minor = info[i].minor;
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);
+ 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))
+ if ((st->devstate[i]&change) & (1 << MD_DISK_SYNC))
alert("Fail", dev, dv, ainfo);
- else if ((newstate & (1<<MD_DISK_FAULTY)) &&
+ else if ((newstate & (1 << MD_DISK_FAULTY)) &&
(disc.major || disc.minor) &&
- st->devid[i] == makedev(disc.major, disc.minor))
+ st->devid[i] == makedev(disc.major,
+ disc.minor))
alert("FailSpare", dev, dv, ainfo);
- else if ((newstate&change)&(1<<MD_DISK_SYNC))
+ else if ((newstate&change) & (1 << MD_DISK_SYNC))
alert("SpareActive", dev, dv, ainfo);
}
st->devstate[i] = newstate;
st->devid[i] = makedev(disc.major, disc.minor);
}
- st->active = array.active_disks;
+ st->active = sra->array.active_disks;
st->working = array.working_disks;
- st->spare = array.spare_disks;
- st->failed = array.failed_disks;
+ st->spare = sra->array.spare_disks;
+ st->failed = sra->array.failed_disks;
st->utime = array.utime;
- st->raid = array.raid_disks;
+ st->raid = sra->array.raid_disks;
st->err = 0;
if ((st->active < st->raid) && st->spare == 0)
- return 1;
- return 0;
+ retval = 1;
+
+ out:
+ if (sra)
+ sysfs_free(sra);
+ if (fd > 0)
+ close(fd);
+ return retval;
+
+ disappeared:
+ if (!st->err)
+ alert("DeviceDisappeared", dev, NULL, ainfo);
+ 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] &&
struct state *st = xcalloc(1, sizeof *st);
mdu_array_info_t array;
int fd;
- st->devname = xstrdup(get_md_name(mse->devnm));
+
+ name = get_md_name(mse->devnm);
+ if (!name) {
+ free(st);
+ continue;
+ }
+
+ st->devname = xstrdup(name);
if ((fd = open(st->devname, O_RDONLY)) < 0 ||
- ioctl(fd, GET_ARRAY_INFO, &array)< 0) {
+ md_get_array_info(fd, &array) < 0) {
/* no such array */
- if (fd >=0) close(fd);
+ if (fd >= 0)
+ close(fd);
put_md_name(st->devname);
free(st->devname);
if (st->metadata) {
close(fd);
st->next = *statelist;
st->err = 1;
+ st->from_auto = 1;
strcpy(st->devnm, mse->devnm);
st->percent = RESYNC_UNKNOWN;
st->expected_spares = -1;
return new_found;
}
-static int get_min_spare_size_required(struct state *st, unsigned long long *sizep)
+static int get_required_spare_criteria(struct state *st,
+ struct spare_criteria *sc)
{
int fd;
if (!st->metadata ||
- !st->metadata->ss->min_acceptable_spare_size) {
- *sizep = 0;
+ !st->metadata->ss->get_spare_criteria) {
+ sc->min_size = 0;
+ sc->sector_size = 0;
return 0;
}
close(fd);
if (!st->metadata->sb)
return 1;
- *sizep = st->metadata->ss->min_acceptable_spare_size(st->metadata);
+
+ st->metadata->ss->get_spare_criteria(st->metadata, sc);
st->metadata->ss->free_super(st->metadata);
return 0;
}
static dev_t choose_spare(struct state *from, struct state *to,
- struct domainlist *domlist, unsigned long long min_size)
+ struct domainlist *domlist, struct spare_criteria *sc)
{
int d;
dev_t dev = 0;
from->devstate[d] == 0) {
struct dev_policy *pol;
unsigned long long dev_size;
+ unsigned int dev_sector_size;
if (to->metadata->ss->external &&
test_partition_from_id(from->devid[d]))
continue;
- if (min_size &&
+ if (sc->min_size &&
dev_size_from_id(from->devid[d], &dev_size) &&
- dev_size < min_size)
+ dev_size < sc->min_size)
+ continue;
+
+ if (sc->sector_size &&
+ dev_sector_size_from_id(from->devid[d],
+ &dev_sector_size) &&
+ sc->sector_size != dev_sector_size)
continue;
pol = devid_policy(from->devid[d]);
static dev_t container_choose_spare(struct state *from, struct state *to,
struct domainlist *domlist,
- unsigned long long min_size, int active)
+ struct spare_criteria *sc, int active)
{
/* This is similar to choose_spare, but we cannot trust devstate,
* so we need to read the metadata instead
}
/* We only need one spare so full list not needed */
- list = container_choose_spares(st, min_size, domlist, from->spare_group,
+ list = container_choose_spares(st, sc, domlist, from->spare_group,
to->metadata->ss->name, 1);
if (list) {
struct mdinfo *disks = list->devs;
{
struct state *from;
struct state *st;
+ struct spare_criteria sc;
link_containers_with_subarrays(statelist);
for (st = statelist; st; st = st->next)
struct domainlist *domlist = NULL;
int d;
struct state *to = st;
- unsigned long long min_size;
if (to->parent_devnm[0] && !to->parent)
/* subarray monitored without parent container
/* member of a container */
to = to->parent;
- if (get_min_spare_size_required(to, &min_size))
+ if (get_required_spare_criteria(to, &sc))
continue;
if (to->metadata->ss->external) {
/* We must make sure there is
* no suitable spare in container already.
* If there is we don't add more */
dev_t devid = container_choose_spare(
- to, to, NULL, min_size, st->active);
+ to, to, NULL, &sc, st->active);
if (devid > 0)
continue;
}
continue;
if (from->metadata->ss->external)
devid = container_choose_spare(
- from, to, domlist, min_size, 0);
+ from, to, domlist, &sc, 0);
else
devid = choose_spare(from, to, domlist,
- min_size);
+ &sc);
if (devid > 0
&& move_spare(from->devname, to->devname, devid)) {
alert("MoveSpare", to->devname, from->devname, info);
/* Not really Monitor but ... */
int Wait(char *dev)
{
- struct stat stb;
char devnm[32];
int rv = 1;
+ int frozen_remaining = 3;
- if (stat(dev, &stb) != 0) {
- pr_err("Cannot find %s: %s\n", dev,
- strerror(errno));
+ if (!stat_is_blkdev(dev, NULL))
return 2;
- }
- strcpy(devnm, stat2devnm(&stb));
+ strcpy(devnm, dev);
while(1) {
struct mdstat_ent *ms = mdstat_read(1, 0);
if (strcmp(e->devnm, devnm) == 0)
break;
- if (e->percent == RESYNC_NONE) {
+ if (e && e->percent == RESYNC_NONE) {
/* We could be in the brief pause before something
* starts. /proc/mdstat doesn't show that, but
* sync_action does.
*/
struct mdinfo mdi;
char buf[21];
- sysfs_init(&mdi, -1, devnm);
+
+ if (sysfs_init(&mdi, -1, devnm))
+ return 2;
if (sysfs_get_str(&mdi, NULL, "sync_action",
buf, 20) > 0 &&
- strcmp(buf,"idle\n") != 0)
+ strcmp(buf,"idle\n") != 0) {
e->percent = RESYNC_UNKNOWN;
+ if (strcmp(buf, "frozen\n") == 0) {
+ if (frozen_remaining == 0)
+ e->percent = RESYNC_NONE;
+ else
+ frozen_remaining -= 1;
+ }
+ }
}
if (!e || e->percent == RESYNC_NONE) {
if (e && e->metadata_version &&
}
}
-#ifndef MDASSEMBLE
-
static char *clean_states[] = {
"clear", "inactive", "readonly", "read-auto", "clean", NULL };
int rv = 1;
char devnm[32];
+ if (!stat_is_blkdev(dev, NULL))
+ return 2;
fd = open(dev, O_RDONLY);
if (fd < 0) {
if (verbose)
mdi = sysfs_read(fd, devnm, GET_VERSION|GET_LEVEL|GET_SAFEMODE);
if (!mdi) {
if (verbose)
- pr_err("Failed to read sysfs attributes for "
- "%s\n", dev);
+ pr_err("Failed to read sysfs attributes for %s\n", dev);
close(fd);
return 0;
}
return rv;
}
-#endif /* MDASSEMBLE */
projects / thirdparty / mdadm.git / blobdiff