*/
#include "mdadm.h"
+#include "udev.h"
#include "md_p.h"
#include "md_u.h"
#include <sys/wait.h>
-#include <signal.h>
#include <limits.h>
#include <syslog.h>
-/* The largest number of disks current arrays can manage is 384
- * This really should be dynamically, but that will have to wait
- * At least it isn't MD_SB_DISKS.
+#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
*/
-#define MaxDisks 384
struct state {
- char *devname;
- int devnum; /* to sync with mdstat info */
- long utime;
+ 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[MaxDisks];
- dev_t devid[MaxDisks];
+ int devstate[MAX_DISKS];
+ dev_t devid[MAX_DISKS];
int percent;
- int parent_dev; /* For subarray, devnum of parent.
- * For others, NoMdDev
- */
+ char parent_devnm[MD_NAME_MAX];
struct supertype *metadata;
- struct state *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 */
- struct state *parent; /* for a subarray it is a link to its container
- */
+ 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
};
-static int make_daemon(char *pidfile);
+
+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 alert(char *event, char *dev, char *disc, struct alert_info *info);
-static int check_array(struct state *st, struct mdstat_ent *mdstat,
- int test, struct alert_info *info,
- int increments);
-static int add_new_arrays(struct mdstat_ent *mdstat, struct state **statelist,
- int test, struct alert_info *info);
-static void try_spare_migration(struct state *statelist, struct alert_info *info);
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,
- int period, int daemonise, int scan, int oneshot,
- int dosyslog, int test, char *pidfile, int increments,
+ struct context *c,
+ int daemonise, int oneshot,
+ int dosyslog, char *pidfile, int increments,
int share)
{
/*
* 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 because --scan
+ * 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;
- struct state *st2;
int finished = 0;
struct mdstat_ent *mdstat = NULL;
- char *mailfrom = NULL;
- struct alert_info info;
+ char *mailfrom;
+ struct mddev_ident *mdlist;
+ int delay_for_event = c->delay;
- if (!mailaddr) {
- mailaddr = conf_get_mailaddr();
- if (mailaddr && ! scan)
- fprintf(stderr, Name ": Monitor using email address \"%s\" from config file\n",
- mailaddr);
+ if (devlist && c->scan) {
+ pr_err("Devices list and --scan option cannot be combined - not monitoring.\n");
+ return 1;
}
- mailfrom = conf_get_mailfrom();
- if (!alert_cmd) {
+ if (!mailaddr)
+ mailaddr = conf_get_mailaddr();
+
+ if (!alert_cmd)
alert_cmd = conf_get_program();
- if (alert_cmd && ! scan)
- fprintf(stderr, Name ": Monitor using program \"%s\" from config file\n",
- alert_cmd);
- }
- if (scan && !mailaddr && !alert_cmd && !dosyslog) {
- fprintf(stderr, Name ": No mail address or alert command - not monitoring.\n");
+
+ 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 (share){
+ if (check_one_sharer(c->scan) == 2)
+ return 1;
+ }
if (daemonise) {
int rv = make_daemon(pidfile);
return rv;
}
- if (share)
- if (check_one_sharer(scan))
+ if (share)
+ if (write_autorebuild_pid() != 0)
return 1;
if (devlist == NULL) {
- struct mddev_ident *mdlist = conf_get_ident(NULL);
- for (; mdlist; mdlist=mdlist->next) {
+ mdlist = conf_get_ident(NULL);
+ for (; mdlist; mdlist = mdlist->next) {
struct state *st;
+
if (mdlist->devname == NULL)
continue;
- if (strcasecmp(mdlist->devname, "<ignore>") == 0)
+ if (is_devname_ignore(mdlist->devname) == true)
continue;
- st = calloc(1, sizeof *st);
- if (st == NULL)
+ if (!is_mddev(mdlist->devname))
continue;
- if (mdlist->devname[0] == '/')
- st->devname = strdup(mdlist->devname);
- else {
- st->devname = malloc(8+strlen(mdlist->devname)+1);
- strcpy(strcpy(st->devname, "/dev/md/"),
- mdlist->devname);
- }
+
+ 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->devnum = INT_MAX;
- st->percent = -2;
+ 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 = strdup(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 mddev_ident *mdlist = conf_get_ident(dv->devname);
- struct state *st = calloc(1, sizeof *st);
- if (st == NULL)
+
+ for (dv = devlist; dv; dv = dv->next) {
+ struct state *st;
+
+ if (!is_mddev(dv->devname))
continue;
- st->devname = strdup(dv->devname);
+
+ 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->devnum = INT_MAX;
- st->percent = -2;
+ 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 = strdup(mdlist->spare_group);
+ st->spare_group = xstrdup(mdlist->spare_group);
}
statelist = st;
}
}
-
- while (! finished) {
+ while (!finished) {
int new_found = 0;
- struct state *st;
+ struct state *st, **stp;
int anydegraded = 0;
+ int anyredundant = 0;
if (mdstat)
free_mdstat(mdstat);
- mdstat = mdstat_read(oneshot?0:1, 0);
+ mdstat = mdstat_read(oneshot ? 0 : 1, 0);
- for (st=statelist; st; st=st->next)
- if (check_array(st, mdstat, test, &info, increments))
+ 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 (scan)
- new_found = add_new_arrays(mdstat, &statelist, test,
- &info);
+ 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 found, choose a device and hotremove/hotadd
*/
if (share && anydegraded)
- try_spare_migration(statelist, &info);
+ try_spare_migration(statelist);
if (!new_found) {
if (oneshot)
break;
- else
- mdstat_wait(period);
+ 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;
}
- test = 0;
- }
- for (st2 = statelist; st2; st2 = statelist) {
- statelist = st2->next;
- free(st2);
}
+ 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:
if (!pidfile)
printf("%d\n", pid);
else {
- FILE *pid_file;
- pid_file=fopen(pidfile, "w");
+ 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 {
perror("daemonise");
return 1;
}
- close(0);
- open("/dev/null", O_RDWR);
- dup2(0,1);
- dup2(0,2);
+ manage_fork_fds(0);
setsid();
return -1;
}
+/*
+ * check_one_sharer() - Checks for other mdmon processes running.
+ *
+ * Return:
+ * 0 - no other processes running,
+ * 1 - warning,
+ * 2 - error, or when scan mode is enabled, and one mdmon process already exists
+ */
static int check_one_sharer(int scan)
{
- int pid, rv;
- FILE *fp;
- char dir[20];
- struct stat buf;
- fp = fopen("/var/run/mdadm/autorebuild.pid", "r");
- if (fp) {
- if (fscanf(fp, "%d", &pid) != 1)
- pid = -1;
- sprintf(dir, "/proc/%d", pid);
- rv = stat(dir, &buf);
- if (rv != -1) {
- if (scan) {
- fprintf(stderr, Name ": Only one "
- "autorebuild process allowed"
- " in scan mode, aborting\n");
- fclose(fp);
- return 1;
- } else {
- fprintf(stderr, Name ": Warning: One"
- " autorebuild process already"
- " running.\n");
- }
- }
+ 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) {
+ 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);
+ return 2;
+ }
+
+ if (fscanf(fp, "%d", &pid) != 1) {
+ pr_err("Cannot read pid from %s file.\n", AUTOREBUILD_PID_PATH);
fclose(fp);
+ return 2;
}
- if (scan) {
- if (mkdir("/var/run/mdadm", S_IRWXU) < 0 &&
- errno != EEXIST) {
- fprintf(stderr, Name ": Can't create "
- "autorebuild.pid file\n");
- } else {
- fp = fopen("/var/run/mdadm/autorebuild.pid", "w");
- if (!fp)
- fprintf(stderr, Name ": Cannot create"
- " autorebuild.pid"
- "file\n");
- else {
- pid = getpid();
- fprintf(fp, "%d\n", pid);
- fclose(fp);
- }
+
+ 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;
}
-static void alert(char *event, char *dev, char *disc, struct alert_info *info)
+/*
+ * write_autorebuild_pid() - Writes pid to autorebuild.pid file.
+ *
+ * Return: 0 on success, 1 on error
+ */
+static int write_autorebuild_pid(void)
{
- int priority;
+ FILE *fp;
+ int fd;
- if (!info->alert_cmd && !info->mailaddr && !info->dosyslog) {
- time_t now = time(0);
+ if (mkdir(MDMON_DIR, 0700) < 0 && errno != EEXIST) {
+ pr_err("%s: %s\n", strerror(errno), MDMON_DIR);
+ return 1;
+ }
- printf("%1.15s: %s on %s %s\n", ctime(&now)+4, event, dev, disc?disc:"unknown device");
+ if (!is_directory(MDMON_DIR)) {
+ pr_err("%s is not a regular directory.\n", MDMON_DIR);
+ return 1;
}
- if (info->alert_cmd) {
- int pid = fork();
- switch(pid) {
- default:
- waitpid(pid, NULL, 0);
- break;
- case -1:
- break;
- case 0:
- execl(info->alert_cmd, info->alert_cmd,
- event, dev, disc, NULL);
- exit(2);
- }
+
+ 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;
}
- if (info->mailaddr &&
- (strncmp(event, "Fail", 4)==0 ||
- strncmp(event, "Test", 4)==0 ||
- strncmp(event, "Spares", 6)==0 ||
- strncmp(event, "Degrade", 7)==0)) {
- FILE *mp = popen(Sendmail, "w");
- if (mp) {
- FILE *mdstat;
- char hname[256];
- gethostname(hname, sizeof(hname));
- signal(SIGPIPE, SIG_IGN);
- if (info->mailfrom)
- fprintf(mp, "From: %s\n", info->mailfrom);
- else
- fprintf(mp, "From: " Name " monitoring <root>\n");
- 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");
- fprintf(mp, "running on %s\n\n", hname);
-
- fprintf(mp,
- "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);
- if (disc && disc[0] == ' ')
- fprintf(mp, "Extra information:%s.\n\n", disc);
-
- fprintf(mp, "Faithfully yours, etc.\n");
-
- mdstat = fopen("/proc/mdstat", "r");
- if (mdstat) {
- char buf[8192];
- int n;
- fprintf(mp,
- "\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);
- }
- pclose(mp);
- }
+
+ fp = fdopen(fd, "w");
+
+ if (!fp) {
+ pr_err("Error opening fd for %s file.\n", AUTOREBUILD_PID_PATH);
+ return 1;
}
- /* log the event to syslog maybe */
- if (info->dosyslog) {
- /* Log at a different severity depending on the event.
- *
- * These are the critical events: */
- if (strncmp(event, "Fail", 4)==0 ||
- strncmp(event, "Degrade", 7)==0 ||
- strncmp(event, "DeviceDisappeared", 17)==0)
- priority = LOG_CRIT;
- /* Good to know about, but are not failures: */
- else if (strncmp(event, "Rebuild", 7)==0 ||
- strncmp(event, "MoveSpare", 9)==0 ||
- strncmp(event, "Spares", 6) != 0)
- priority = LOG_WARNING;
- /* Everything else: */
- else
- priority = LOG_INFO;
+ fprintf(fp, "%d\n", getpid());
- if (disc)
- syslog(priority,
- "%s event detected on md device %s,"
- " component device %s", event, dev, disc);
- else
- syslog(priority,
- "%s event detected on md device %s",
- event, dev);
+ 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 test, struct alert_info *ainfo,
- int increments)
+ 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; } info[MaxDisks];
+ 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 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;
- if (test)
- alert("TestMessage", dev, NULL, ainfo);
fd = open(dev, O_RDONLY);
- if (fd < 0) {
- if (!st->err)
- alert("DeviceDisappeared", dev, NULL, ainfo);
- st->err=1;
- return 0;
- }
- 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;
- }
- /* 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 (!st->err)
- alert("DeviceDisappeared", dev, "Wrong-Level", ainfo);
- st->err = 1;
- close(fd);
- return 0;
- }
- if (st->devnum == INT_MAX) {
- struct stat stb;
- if (fstat(fd, &stb) == 0 &&
- (S_IFMT&stb.st_mode)==S_IFBLK) {
- if (major(stb.st_rdev) == MD_MAJOR)
- st->devnum = minor(stb.st_rdev);
- else
- st->devnum = -1- (minor(stb.st_rdev)>>6);
- }
- }
+ 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 (mse2->devnum == st->devnum) {
- mse2->devnum = INT_MAX; /* flag it as "used" */
+ 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 = 1;
- close(fd);
- return 0;
+ * 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;
+
+ fcntl(fd, F_SETFD, FD_CLOEXEC);
+ 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->utime == array.utime &&
- st->failed == array.failed_disks &&
- st->working == array.working_disks &&
- st->spare == array.spare_disks &&
- (mse == NULL || (
- mse->percent == st->percent
- ))) {
- close(fd);
+ 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)
- return 1;
- else
- return 0;
+ retval = 1;
+ goto out;
}
if (st->utime == 0 && /* new array */
- mse->pattern && strchr(mse->pattern, '_') /* degraded */
- )
- alert("DegradedArray", dev, NULL, ainfo);
+ mse->pattern && strchr(mse->pattern, '_') /* degraded */)
+ alert(EVENT_DEGRADED_ARRAY, NULL, 0, dev, NULL);
- if (st->utime == 0 && /* new array */
- st->expected_spares > 0 &&
- array.spare_disks < st->expected_spares)
- alert("SparesMissing", dev, NULL, ainfo);
- if (st->percent == -1 &&
+ 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("RebuildStarted", dev, NULL, ainfo);
- if (st->percent >= 0 &&
- mse->percent >= 0 &&
+ alert(EVENT_REBUILD_STARTED, NULL, 0, dev, NULL);
+ if (st->percent >= 0 && mse->percent >= 0 &&
(mse->percent / increments) > (st->percent / increments)) {
- char percentalert[15]; // "RebuildNN" (10 chars) or "RebuildStarted" (15 chars)
-
if((mse->percent / increments) == 0)
- snprintf(percentalert, sizeof(percentalert), "RebuildStarted");
+ alert(EVENT_REBUILD_STARTED, NULL, 0, dev, NULL);
else
- snprintf(percentalert, sizeof(percentalert), "Rebuild%02d", mse->percent);
-
- alert(percentalert, dev, NULL, ainfo);
+ alert(EVENT_REBUILD, NULL, mse->percent, dev, NULL);
}
- if (mse->percent == -1 &&
- 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->devnum, 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);
- alert("RebuildFinished", dev, cnt, ainfo);
+ sra->mismatch_cnt, sra->array.level);
+ alert(EVENT_REBUILD_FINISHED, NULL, 0, dev, cnt);
} else
- alert("RebuildFinished", dev, NULL, ainfo);
- if (sra)
- free(sra);
+ alert(EVENT_REBUILD_FINISHED, NULL, 0, dev, NULL);
}
st->percent = mse->percent;
- remaining_disks = array.nr_disks;
- for (i=0; i<MaxDisks && 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) {
- info[i].state = disc.state;
- info[i].major = disc.major;
- info[i].minor = disc.minor;
+ 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
- info[i].major = info[i].minor = 0;
+ disks_info[i].major = disks_info[i].minor = 0;
}
last_disk = i;
if (mse->metadata_version &&
strncmp(mse->metadata_version, "external:", 9) == 0 &&
- is_subarray(mse->metadata_version+9))
- st->parent_dev =
- devname2devnum(mse->metadata_version+10);
- else
- st->parent_dev = NoMdDev;
- if (st->metadata == NULL &&
- st->parent_dev == NoMdDev)
+ is_subarray(mse->metadata_version+9)) {
+ 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);
- close(fd);
-
- for (i=0; i<MaxDisks; i++) {
- mdu_disk_info_t disc = {0,0,0,0,0};
- int newstate=0;
+ 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) {
- newstate = 0;
- disc.major = disc.minor = 0;
- } else if (info[i].major || info[i].minor) {
- newstate = info[i].state;
- dv = map_dev(info[i].major, info[i].minor, 1);
+ 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 = info[i].major;
- disc.minor = info[i].minor;
- } else if (mse && mse->pattern && i < (int)strlen(mse->pattern)) {
- switch(mse->pattern[i]) {
- case 'U': newstate = 6 /* ACTIVE/SYNC */; break;
- case '_': newstate = 8 /* REMOVED */; break;
- }
- disc.major = disc.minor = 0;
- }
+ 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(major(st->devid[i]),
- minor(st->devid[i]), 1);
+ 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) {
- if (i < array.raid_disks &&
- (((newstate&change)&(1<<MD_DISK_FAULTY)) ||
- ((st->devstate[i]&change)&(1<<MD_DISK_ACTIVE)) ||
- ((st->devstate[i]&change)&(1<<MD_DISK_SYNC)))
- )
- alert("Fail", dev, dv, ainfo);
- else if (i >= array.raid_disks &&
+ 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) &&
- ((newstate&change)&(1<<MD_DISK_FAULTY))
- )
- alert("FailSpare", dev, dv, ainfo);
- else if (i < array.raid_disks &&
- ! (newstate & (1<<MD_DISK_REMOVED)) &&
- (((st->devstate[i]&change)&(1<<MD_DISK_FAULTY)) ||
- ((newstate&change)&(1<<MD_DISK_ACTIVE)) ||
- ((newstate&change)&(1<<MD_DISK_SYNC)))
- )
- alert("SpareActive", dev, dv, ainfo);
+ 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 = array.active_disks;
- st->working = array.working_disks;
- st->spare = array.spare_disks;
- st->failed = array.failed_disks;
+ 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 = 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 && !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,
- int test, struct alert_info *info)
+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->devnum != INT_MAX &&
- (!mse->level || /* retrieve containers */
- (strcmp(mse->level, "raid0") != 0 &&
- strcmp(mse->level, "linear") != 0))
- ) {
- struct state *st = calloc(1, sizeof *st);
+ 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;
- if (st == NULL)
+
+ name = get_md_name(mse->devnm);
+ if (!name) {
+ free(st);
continue;
- st->devname = strdup(get_md_name(mse->devnum));
+ }
+
+ snprintf(st->devname, MD_NAME_MAX + sizeof(DEV_MD_DIR), "%s", 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) {
st->metadata->ss->free_super(st->metadata);
free(st->metadata);
close(fd);
st->next = *statelist;
st->err = 1;
- st->devnum = mse->devnum;
- st->percent = -2;
+ st->from_auto = 1;
+ snprintf(st->devnm, MD_NAME_MAX, "%s", mse->devnm);
+ st->percent = RESYNC_UNKNOWN;
st->expected_spares = -1;
if (mse->metadata_version &&
- strncmp(mse->metadata_version, "external:", 9) == 0 &&
- is_subarray(mse->metadata_version+9))
- st->parent_dev =
- devname2devnum(mse->metadata_version+10);
- else
- st->parent_dev = NoMdDev;
+ strncmp(mse->metadata_version,
+ "external:", 9) == 0 &&
+ is_subarray(mse->metadata_version+9)) {
+ char *sl;
+ snprintf(st->parent_devnm, MD_NAME_MAX,
+ "%s", mse->metadata_version + 10);
+ sl = strchr(st->parent_devnm, '/');
+ *sl = 0;
+ } else
+ st->parent_devnm[0] = 0;
*statelist = st;
- if (test)
- alert("TestMessage", st->devname, NULL, info);
- alert("NewArray", st->devname, NULL, info);
+ if (info.test)
+ alert(EVENT_TEST_MESSAGE, NULL, 0, st->devname, NULL);
new_found = 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;
+ if (!st->metadata || !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;
- for (d = from->raid; !dev && d < MaxDisks; d++) {
- if (from->devid[d] > 0 &&
- from->devstate[d] == 0) {
+ for (d = from->raid; !dev && d < MAX_DISKS; d++) {
+ if (from->devid[d] > 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 = devnum_policy(from->devid[d]);
+ pol = devid_policy(from->devid[d]);
if (from->spare_group)
pol_add(&pol, pol_domain,
from->spare_group, NULL);
- if (domain_test(domlist, pol, to->metadata->ss->name) == 1)
+ if (domain_test(domlist, pol,
+ to->metadata->ss->name) == 1)
dev = from->devid[d];
dev_policy_free(pol);
}
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
close(fd);
return 0;
}
-
+
err = st->ss->load_container(st, fd, NULL);
close(fd);
if (err)
return 0;
-
+
if (from == to) {
/* We must check if number of active disks has not increased
* since ioctl in main loop. mdmon may have added spare
}
dp = list->devs;
while (dp) {
- if (dp->disk.state & (1<<MD_DISK_SYNC) &&
- !(dp->disk.state & (1<<MD_DISK_FAULTY)))
+ if (dp->disk.state & (1 << MD_DISK_SYNC) &&
+ !(dp->disk.state & (1 << MD_DISK_FAULTY)))
active_cnt++;
dp = dp->next;
}
}
/* 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;
return dev;
}
-
-static void try_spare_migration(struct state *statelist, struct alert_info *info)
+static void try_spare_migration(struct state *statelist)
{
struct state *from;
struct state *st;
+ struct spare_criteria sc;
link_containers_with_subarrays(statelist);
for (st = statelist; st; st = st->next)
- if (st->active < st->raid &&
- st->spare == 0 && !st->err) {
+ if (st->active < st->raid && st->spare == 0 && !st->err) {
struct domainlist *domlist = NULL;
int d;
struct state *to = st;
- unsigned long long min_size;
- if (to->parent_dev != NoMdDev && !to->parent)
+ if (to->parent_devnm[0] && !to->parent)
/* subarray monitored without parent container
* we can't move spares here */
continue;
-
+
if (to->parent)
/* 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;
}
- for (d = 0; d < MaxDisks; d++)
+ for (d = 0; d < MAX_DISKS; d++)
if (to->devid[d])
domainlist_add_dev(&domlist,
to->devid[d],
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);
- if (devid > 0
- && move_spare(from->devname, to->devname, devid)) {
- alert("MoveSpare", to->devname, from->devname, info);
+ &sc);
+ if (devid > 0 &&
+ move_spare(from->devname, to->devname,
+ devid)) {
+ alert(EVENT_MOVE_SPARE, NULL, 0, to->devname, from->devname);
break;
}
}
st->subarray = NULL;
}
for (st = list; st; st = st->next)
- if (st->parent_dev != NoMdDev)
+ if (st->parent_devnm[0])
for (cont = list; cont; cont = cont->next)
- if (!cont->err &&
- cont->parent_dev == NoMdDev &&
- cont->devnum == st->parent_dev) {
+ if (!cont->err && cont->parent_devnm[0] == 0 &&
+ strcmp(cont->devnm, st->parent_devnm) == 0) {
st->parent = cont;
st->subarray = cont->subarray;
cont->subarray = st;
}
}
+/**
+ * free_statelist() - Frees statelist.
+ * @statelist: statelist to free
+ */
+static void free_statelist(struct state *statelist)
+{
+ struct state *tmp = NULL;
+
+ while (statelist) {
+ if (statelist->spare_group)
+ free(statelist->spare_group);
+
+ tmp = statelist;
+ statelist = statelist->next;
+ free(tmp);
+ }
+}
+
/* Not really Monitor but ... */
int Wait(char *dev)
{
- struct stat stb;
- int devnum;
+ char devnm[32];
+ dev_t rdev;
+ char *tmp;
int rv = 1;
+ int frozen_remaining = 3;
+
+ if (!stat_is_blkdev(dev, &rdev))
+ return 2;
- if (stat(dev, &stb) != 0) {
- fprintf(stderr, Name ": Cannot find %s: %s\n", dev,
- strerror(errno));
+ tmp = devid2devnm(rdev);
+ if (!tmp) {
+ pr_err("Cannot get md device name.\n");
return 2;
}
- devnum = stat2devnum(&stb);
+
+ strcpy(devnm, tmp);
while(1) {
struct mdstat_ent *ms = mdstat_read(1, 0);
struct mdstat_ent *e;
- for (e=ms ; e; e=e->next)
- if (e->devnum == devnum)
+ for (e = ms; e; e = e->next)
+ if (strcmp(e->devnm, devnm) == 0)
break;
- if (!e || e->percent < 0) {
+ 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[SYSFS_MAX_BUF_SIZE];
+
+ if (sysfs_init(&mdi, -1, devnm))
+ return 2;
+ if (sysfs_get_str(&mdi, NULL, "sync_action",
+ buf, sizeof(buf)) > 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 &&
strncmp(e->metadata_version, "external:", 9) == 0) {
if (is_subarray(&e->metadata_version[9]))
ping_monitor(&e->metadata_version[9]);
else
- ping_monitor_by_id(devnum);
+ ping_monitor(devnm);
}
free_mdstat(ms);
return rv;
}
}
-#ifndef MDASSEMBLE
-
+/* The state "broken" is used only for RAID0/LINEAR - it's the same as
+ * "clean", but used in case the array has one or more members missing.
+ */
static char *clean_states[] = {
- "clear", "inactive", "readonly", "read-auto", "clean", NULL };
+ "clear", "inactive", "readonly", "read-auto", "clean", "broken", NULL };
-int WaitClean(char *dev, int sock, int verbose)
+int WaitClean(char *dev, int verbose)
{
int fd;
struct mdinfo *mdi;
int rv = 1;
- int devnum;
+ char devnm[32];
+ if (!stat_is_blkdev(dev, NULL))
+ return 2;
fd = open(dev, O_RDONLY);
if (fd < 0) {
if (verbose)
- fprintf(stderr, Name ": Couldn't open %s: %s\n", dev, strerror(errno));
+ pr_err("Couldn't open %s: %s\n", dev, strerror(errno));
return 1;
}
- devnum = fd2devnum(fd);
- mdi = sysfs_read(fd, devnum, GET_VERSION|GET_LEVEL|GET_SAFEMODE);
+ strcpy(devnm, fd2devnm(fd));
+ mdi = sysfs_read(fd, devnm, GET_VERSION|GET_LEVEL|GET_SAFEMODE);
if (!mdi) {
if (verbose)
- fprintf(stderr, Name ": Failed to read sysfs attributes for "
- "%s\n", dev);
+ pr_err("Failed to read sysfs attributes for %s\n", dev);
close(fd);
return 0;
}
rv = 0;
if (rv) {
- int state_fd = sysfs_open(fd2devnum(fd), NULL, "array_state");
- char buf[20];
- fd_set fds;
- struct timeval tm;
+ int state_fd = sysfs_open(fd2devnm(fd), NULL, "array_state");
+ char buf[SYSFS_MAX_BUF_SIZE];
+ int delay = 5000;
/* minimize the safe_mode_delay and prepare to wait up to 5s
* for writes to quiesce
*/
sysfs_set_safemode(mdi, 1);
- tm.tv_sec = 5;
- tm.tv_usec = 0;
-
- FD_ZERO(&fds);
/* wait for array_state to be clean */
while (1) {
rv = read(state_fd, buf, sizeof(buf));
if (rv < 0)
break;
- if (sysfs_match_word(buf, clean_states) <= 4)
+ if (sysfs_match_word(buf, clean_states) <
+ (int)ARRAY_SIZE(clean_states) - 1)
break;
- FD_SET(state_fd, &fds);
- rv = select(state_fd + 1, NULL, NULL, &fds, &tm);
+ rv = sysfs_wait(state_fd, &delay);
if (rv < 0 && errno != EINTR)
break;
lseek(state_fd, 0, SEEK_SET);
}
if (rv < 0)
rv = 1;
- else if (fping_monitor(sock) == 0 ||
- ping_monitor(mdi->text_version) == 0) {
+ else if (ping_monitor(mdi->text_version) == 0) {
/* we need to ping to close the window between array
* state transitioning to clean and the metadata being
* marked clean
*/
rv = 0;
- } else
+ } else {
rv = 1;
+ pr_err("Error connecting monitor with %s\n", dev);
+ }
if (rv && verbose)
- fprintf(stderr, Name ": Error waiting for %s to be clean\n",
- dev);
+ pr_err("Error waiting for %s to be clean\n", dev);
/* restore the original safe_mode_delay */
sysfs_set_safemode(mdi, mdi->safe_mode_delay);
return rv;
}
-#endif /* MDASSEMBLE */