#include "mdmon.h"
#include <sys/syscall.h>
#include <sys/select.h>
-#include <signal.h>
static char *array_states[] = {
"clear", "inactive", "suspended", "readonly", "read-auto",
- "clean", "active", "write-pending", "active-idle", NULL };
+ "clean", "active", "write-pending", "active-idle", "broken", NULL };
static char *sync_actions[] = {
"idle", "reshape", "resync", "recover", "check", "repair", NULL
};
+enum bb_action {
+ RECORD_BB = 1,
+ COMPARE_BB,
+};
+
static int write_attr(char *attr, int fd)
{
return write(fd, attr, strlen(attr));
if (fd < 0)
return;
if (fstat(fd, &st) == -1) {
- dprintf("%s: Invalid fd %d\n", __func__, fd);
+ dprintf("Invalid fd %d\n", fd);
return;
}
if (st.st_nlink == 0) {
- dprintf("%s: fd %d was deleted\n", __func__, fd);
+ dprintf("fd %d was deleted\n", fd);
return;
}
if (fd > *maxfd)
static void read_resync_start(int fd, unsigned long long *v)
{
- char buf[30];
+ char buf[SYSFS_MAX_BUF_SIZE];
int n;
- n = read_attr(buf, 30, fd);
+ n = read_attr(buf, sizeof(buf), fd);
if (n <= 0) {
- dprintf("%s: Failed to read resync_start (%d)\n",
- __func__, fd);
+ dprintf("Failed to read resync_start (%d)\n", fd);
return;
}
- if (strncmp(buf, "none", 4) == 0)
+ if (str_is_none(buf) == true)
*v = MaxSector;
else
*v = strtoull(buf, NULL, 10);
static unsigned long long read_sync_completed(int fd)
{
unsigned long long val;
- char buf[50];
+ char buf[SYSFS_MAX_BUF_SIZE];
int n;
char *ep;
- n = read_attr(buf, 50, fd);
+ n = read_attr(buf, sizeof(buf), fd);
if (n <= 0)
return 0;
static enum array_state read_state(int fd)
{
- char buf[20];
- int n = read_attr(buf, 20, fd);
+ char buf[SYSFS_MAX_BUF_SIZE];
+ int n = read_attr(buf, sizeof(buf), fd);
if (n <= 0)
return bad_word;
static enum sync_action read_action( int fd)
{
- char buf[20];
- int n = read_attr(buf, 20, fd);
+ char buf[SYSFS_MAX_BUF_SIZE];
+ int n = read_attr(buf, sizeof(buf), fd);
if (n <= 0)
return bad_action;
int read_dev_state(int fd)
{
- char buf[60];
- int n = read_attr(buf, 60, fd);
+ char buf[SYSFS_MAX_BUF_SIZE];
+ int n = read_attr(buf, sizeof(buf), fd);
char *cp;
int rv = 0;
return rv;
}
+int process_ubb(struct active_array *a, struct mdinfo *mdi, const unsigned long
+ long sector, const int length, const char *buf,
+ const int buf_len)
+{
+ struct superswitch *ss = a->container->ss;
+
+ /*
+ * record bad block in metadata first, then acknowledge it to the driver
+ * via sysfs file
+ */
+ if ((ss->record_bad_block(a, mdi->disk.raid_disk, sector, length)) &&
+ (write(mdi->bb_fd, buf, buf_len) == buf_len))
+ return 1;
+
+ /*
+ * failed to store or acknowledge bad block, switch of bad block support
+ * to get it out of blocked state
+ */
+ sysfs_set_str(&a->info, mdi, "state", "-external_bbl");
+ return -1;
+}
+
+int compare_bb(struct active_array *a, struct mdinfo *mdi, const unsigned long
+ long sector, const unsigned int length, void *arg)
+{
+ struct superswitch *ss = a->container->ss;
+ struct md_bb *bb = (struct md_bb *) arg;
+ int record = 1;
+ int i;
+
+ for (i = 0; i < bb->count; i++) {
+ unsigned long long start = bb->entries[i].sector;
+ unsigned long long len = bb->entries[i].length;
+
+ /*
+ * bad block in metadata exactly matches bad block in kernel
+ * list, just remove it from a list
+ */
+ if ((start == sector) && (len == length)) {
+ if (i < bb->count - 1)
+ bb->entries[i] = bb->entries[bb->count - 1];
+ bb->count -= 1;
+ record = 0;
+ break;
+ }
+ /*
+ * bad block in metadata spans bad block in kernel list,
+ * clear it and record new bad block
+ */
+ if ((sector >= start) && (sector + length <= start + len)) {
+ ss->clear_bad_block(a, mdi->disk.raid_disk, start, len);
+ break;
+ }
+ }
+
+ /* record all bad blocks not in metadata list */
+ if (record && (ss->record_bad_block(a, mdi->disk.raid_disk, sector,
+ length) <= 0)) {
+ sysfs_set_str(&a->info, mdi, "state", "-external_bbl");
+ return -1;
+ }
+
+ return 1;
+}
+
+static int read_bb_file(int fd, struct active_array *a, struct mdinfo *mdi,
+ enum bb_action action, void *arg)
+{
+ char buf[30];
+ int n = 0;
+ int ret = 0;
+ int read_again = 0;
+ int off = 0;
+ int pos = 0;
+ int preserve_pos = (action == RECORD_BB ? 0 : 1);
+
+ if (lseek(fd, 0, SEEK_SET) == (off_t) -1)
+ return -1;
+
+ do {
+ read_again = 0;
+ n = read(fd, buf + pos, sizeof(buf) - 1 - pos);
+ if (n < 0)
+ return -1;
+ n += pos;
+
+ buf[n] = '\0';
+ off = 0;
+
+ while (off < n) {
+ unsigned long long sector;
+ int length;
+ char newline;
+ int consumed;
+ int matched;
+ int rc;
+
+ /* kernel sysfs file format: "sector length\n" */
+ matched = sscanf(buf + off, "%llu %d%c%n", §or,
+ &length, &newline, &consumed);
+ if ((matched != 3) && (off > 0)) {
+ /* truncated entry, read again */
+ if (preserve_pos) {
+ pos = sizeof(buf) - off - 1;
+ memmove(buf, buf + off, pos);
+ } else {
+ if (lseek(fd, 0, SEEK_SET) ==
+ (off_t) -1)
+ return -1;
+ }
+ read_again = 1;
+ break;
+ }
+ if (matched != 3)
+ return -1;
+ if (newline != '\n')
+ return -1;
+ if (length <= 0)
+ return -1;
+
+ if (action == RECORD_BB)
+ rc = process_ubb(a, mdi, sector, length,
+ buf + off, consumed);
+ else if (action == COMPARE_BB)
+ rc = compare_bb(a, mdi, sector, length, arg);
+ else
+ rc = -1;
+
+ if (rc < 0)
+ return rc;
+ ret += rc;
+ off += consumed;
+ }
+ } while (read_again);
+
+ return ret;
+}
+
+static int process_dev_ubb(struct active_array *a, struct mdinfo *mdi)
+{
+ return read_bb_file(mdi->ubb_fd, a, mdi, RECORD_BB, NULL);
+}
+
+static int check_for_cleared_bb(struct active_array *a, struct mdinfo *mdi)
+{
+ struct superswitch *ss = a->container->ss;
+ struct md_bb *bb;
+ int i;
+
+ if (!ss->get_bad_blocks)
+ return -1;
+
+ /*
+ * Get a list of bad blocks for an array, then read list of
+ * acknowledged bad blocks from kernel and compare it against metadata
+ * list, clear all bad blocks remaining in metadata list
+ */
+ bb = ss->get_bad_blocks(a, mdi->disk.raid_disk);
+ if (!bb)
+ return -1;
+
+ if (read_bb_file(mdi->bb_fd, a, mdi, COMPARE_BB, bb) < 0)
+ return -1;
+
+ for (i = 0; i < bb->count; i++) {
+ unsigned long long sector = bb->entries[i].sector;
+ int length = bb->entries[i].length;
+
+ ss->clear_bad_block(a, mdi->disk.raid_disk, sector, length);
+ }
+
+ return 0;
+}
+
static void signal_manager(void)
{
/* tgkill(getpid(), mon_tid, SIGUSR1); */
#define ARRAY_DIRTY 1
#define ARRAY_BUSY 2
-static int read_and_act(struct active_array *a)
+static int read_and_act(struct active_array *a, fd_set *fds)
{
unsigned long long sync_completed;
int check_degraded = 0;
struct mdinfo *mdi;
int ret = 0;
int count = 0;
+ struct timeval tv;
+ bool write_checkpoint = false;
a->next_state = bad_word;
a->next_action = bad_action;
&mdi->recovery_start);
mdi->curr_state = read_dev_state(mdi->state_fd);
}
- }
-
- if (a->curr_state > inactive &&
- a->prev_state == inactive) {
- /* array has been started
- * possible that container operation has to be completed
+ /*
+ * If array is blocked and metadata handler is able to handle
+ * BB, check if you can acknowledge them to md driver. If
+ * successful, clear faulty state and unblock the array.
*/
- a->container->ss->set_array_state(a, 0);
+ if ((mdi->curr_state & DS_BLOCKED) &&
+ a->container->ss->record_bad_block &&
+ (process_dev_ubb(a, mdi) > 0)) {
+ mdi->next_state |= DS_UNBLOCK;
+ }
+ if (FD_ISSET(mdi->bb_fd, fds))
+ check_for_cleared_bb(a, mdi);
}
+
+ gettimeofday(&tv, NULL);
+ dprintf("(%d): %ld.%06ld state:%s prev:%s action:%s prev: %s start:%llu\n",
+ a->info.container_member,
+ tv.tv_sec, tv.tv_usec,
+ array_states[a->curr_state],
+ array_states[a->prev_state],
+ sync_actions[a->curr_action],
+ sync_actions[a->prev_action],
+ a->info.resync_start
+ );
+
if ((a->curr_state == bad_word || a->curr_state <= inactive) &&
a->prev_state > inactive) {
/* array has been stopped */
a->next_state = clean;
ret |= ARRAY_DIRTY;
}
- if (a->curr_state == clean) {
+ if ((a->curr_state == clean) || (a->curr_state == broken)) {
a->container->ss->set_array_state(a, 1);
}
if (a->curr_state == active ||
}
}
- /* Check for recovery checkpoint notifications. We need to be a
- * minimum distance away from the last checkpoint to prevent
- * over checkpointing. Note reshape checkpointing is handled
- * in the second branch.
- */
- if (sync_completed > a->last_checkpoint &&
- sync_completed - a->last_checkpoint > a->info.component_size >> 4 &&
- a->curr_action > reshape) {
- /* A (non-reshape) sync_action has reached a checkpoint.
- * Record the updated position in the metadata
- */
- a->last_checkpoint = sync_completed;
- a->container->ss->set_array_state(a, a->curr_state <= clean);
- } else if ((a->curr_action == idle && a->prev_action == reshape) ||
- (a->curr_action == reshape
- && sync_completed > a->last_checkpoint) ) {
- /* Reshape has progressed or completed so we need to
- * update the array state - and possibly the array size
- */
+ /* Update reshape checkpoint, depending if it finished or progressed */
+ if (a->curr_action == idle && a->prev_action == reshape) {
+ char buf[SYSFS_MAX_BUF_SIZE];
+
if (sync_completed != 0)
a->last_checkpoint = sync_completed;
- /* We might need to update last_checkpoint depending on
- * the reason that reshape finished.
- * if array reshape is really finished:
- * set check point to the end, this allows
- * set_array_state() to finalize reshape in metadata
- * if reshape if broken: do not set checkpoint to the end
- * this allows for reshape restart from checkpoint
+
+ /*
+ * If reshape really finished, set checkpoint to the end to finalize it.
+ * Do not set checkpoint if reshape is broken.
+ * Reshape will restart from last checkpoint.
*/
- if ((a->curr_action != reshape) &&
- (a->prev_action == reshape)) {
- char buf[40];
- if ((sysfs_get_str(&a->info, NULL,
- "reshape_position",
- buf,
- sizeof(buf)) >= 0) &&
- strncmp(buf, "none", 4) == 0)
+ if (sysfs_get_str(&a->info, NULL, "reshape_position", buf, sizeof(buf)) >= 0)
+ if (str_is_none(buf) == true)
a->last_checkpoint = a->info.component_size;
- }
- a->container->ss->set_array_state(a, a->curr_state <= clean);
- a->last_checkpoint = sync_completed;
+
+ write_checkpoint = true;
}
- if (sync_completed > a->last_checkpoint)
+ if (a->curr_action >= reshape && sync_completed > a->last_checkpoint) {
+ /* Update checkpoint if neither reshape nor idle action */
a->last_checkpoint = sync_completed;
+ write_checkpoint = true;
+ }
+
+ /* Save checkpoint */
+ if (write_checkpoint) {
+ a->container->ss->set_array_state(a, a->curr_state <= clean);
+
+ if (a->curr_action <= reshape)
+ a->last_checkpoint = sync_completed;
+ }
+
+ if (sync_completed >= a->info.component_size)
+ a->last_checkpoint = 0;
+
a->container->ss->sync_metadata(a->container);
- dprintf("%s(%d): state:%s action:%s next(", __func__, a->info.container_member,
+ dprintf("(%d): state:%s action:%s next(", a->info.container_member,
array_states[a->curr_state], sync_actions[a->curr_action]);
/* Effect state changes in the array */
if (a->next_state != bad_word) {
- dprintf(" state:%s", array_states[a->next_state]);
+ dprintf_cont(" state:%s", array_states[a->next_state]);
write_attr(array_states[a->next_state], a->info.state_fd);
}
if (a->next_action != bad_action) {
write_attr(sync_actions[a->next_action], a->action_fd);
- dprintf(" action:%s", sync_actions[a->next_action]);
+ dprintf_cont(" action:%s", sync_actions[a->next_action]);
}
for (mdi = a->info.devs; mdi ; mdi = mdi->next) {
if (mdi->next_state & DS_UNBLOCK) {
- dprintf(" %d:-blocked", mdi->disk.raid_disk);
+ dprintf_cont(" %d:-blocked", mdi->disk.raid_disk);
write_attr("-blocked", mdi->state_fd);
}
*/
remove_result = write_attr("remove", mdi->state_fd);
if (remove_result > 0) {
- dprintf(" %d:removed", mdi->disk.raid_disk);
+ dprintf_cont(" %d:removed", mdi->disk.raid_disk);
close(mdi->state_fd);
close(mdi->recovery_fd);
+ close(mdi->bb_fd);
+ close(mdi->ubb_fd);
mdi->state_fd = -1;
} else
ret |= ARRAY_BUSY;
}
if (mdi->next_state & DS_INSYNC) {
write_attr("+in_sync", mdi->state_fd);
- dprintf(" %d:+in_sync", mdi->disk.raid_disk);
+ dprintf_cont(" %d:+in_sync", mdi->disk.raid_disk);
}
}
- dprintf(" )\n");
+ dprintf_cont(" )\n");
/* move curr_ to prev_ */
a->prev_state = a->curr_state;
add_fd(&rfds, &maxfd, a->info.state_fd);
add_fd(&rfds, &maxfd, a->action_fd);
add_fd(&rfds, &maxfd, a->sync_completed_fd);
- for (mdi = a->info.devs ; mdi ; mdi = mdi->next)
+ for (mdi = a->info.devs ; mdi ; mdi = mdi->next) {
add_fd(&rfds, &maxfd, mdi->state_fd);
+ add_fd(&rfds, &maxfd, mdi->bb_fd);
+ add_fd(&rfds, &maxfd, mdi->ubb_fd);
+ }
ap = &(*ap)->next;
}
monitor_loop_cnt |= 1;
rv = pselect(maxfd+1, NULL, NULL, &rfds, &ts, &set);
monitor_loop_cnt += 1;
- if (rv == -1 && errno == EINTR)
- rv = 0;
+ if (rv == -1) {
+ if (errno == EINTR) {
+ rv = 0;
+ FD_ZERO(&rfds);
+ dprintf("monitor: caught signal\n");
+ } else
+ dprintf("monitor: error %d in pselect\n",
+ errno);
+ }
#ifdef DEBUG
- dprint_wake_reasons(&rfds);
+ else
+ dprint_wake_reasons(&rfds);
#endif
container->retry_soon = 0;
}
signal_manager();
}
if (a->container && !a->to_remove) {
- int ret = read_and_act(a);
+ int ret = read_and_act(a, &rfds);
rv |= 1;
dirty_arrays += !!(ret & ARRAY_DIRTY);
/* when terminating stop manipulating the array after it
projects / thirdparty / mdadm.git / blobdiff