const int rw = bio_data_dir(bio);
struct mddev *mddev = q->queuedata;
unsigned int sectors;
+ int cpu;
if (mddev == NULL || mddev->pers == NULL
|| !mddev->ready) {
sectors = bio_sectors(bio);
mddev->pers->make_request(mddev, bio);
- generic_start_io_acct(rw, sectors, &mddev->gendisk->part0);
+ cpu = part_stat_lock();
+ part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
+ part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
+ part_stat_unlock();
if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
wake_up(&mddev->sb_wait);
}
EXPORT_SYMBOL(md_update_sb);
+static int add_bound_rdev(struct md_rdev *rdev)
+{
+ struct mddev *mddev = rdev->mddev;
+ int err = 0;
+
+ if (!mddev->pers->hot_remove_disk) {
+ /* If there is hot_add_disk but no hot_remove_disk
+ * then added disks for geometry changes,
+ * and should be added immediately.
+ */
+ super_types[mddev->major_version].
+ validate_super(mddev, rdev);
+ err = mddev->pers->hot_add_disk(mddev, rdev);
+ if (err) {
+ unbind_rdev_from_array(rdev);
+ export_rdev(rdev);
+ return err;
+ }
+ }
+ sysfs_notify_dirent_safe(rdev->sysfs_state);
+
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ if (mddev->degraded)
+ set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ md_new_event(mddev);
+ md_wakeup_thread(mddev->thread);
+ return 0;
+}
+
/* words written to sysfs files may, or may not, be \n terminated.
* We want to accept with case. For this we use cmd_match.
*/
else {
struct mddev *mddev = rdev->mddev;
if (mddev_is_clustered(mddev))
- md_cluster_ops->metadata_update_start(mddev);
+ md_cluster_ops->remove_disk(mddev, rdev);
md_kick_rdev_from_array(rdev);
+ if (mddev_is_clustered(mddev))
+ md_cluster_ops->metadata_update_start(mddev);
if (mddev->pers)
md_update_sb(mddev, 1);
md_new_event(mddev);
clear_bit(Replacement, &rdev->flags);
err = 0;
}
+ } else if (cmd_match(buf, "re-add")) {
+ if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1)) {
+ /* clear_bit is performed _after_ all the devices
+ * have their local Faulty bit cleared. If any writes
+ * happen in the meantime in the local node, they
+ * will land in the local bitmap, which will be synced
+ * by this node eventually
+ */
+ if (!mddev_is_clustered(rdev->mddev) ||
+ (err = md_cluster_ops->gather_bitmaps(rdev)) == 0) {
+ clear_bit(Faulty, &rdev->flags);
+ err = add_bound_rdev(rdev);
+ }
+ } else
+ err = -EBUSY;
}
if (!err)
sysfs_notify_dirent_safe(rdev->sysfs_state);
return err ? err : len;
}
static struct rdev_sysfs_entry rdev_state =
-__ATTR(state, S_IRUGO|S_IWUSR, state_show, state_store);
+__ATTR_PREALLOC(state, S_IRUGO|S_IWUSR, state_show, state_store);
static ssize_t
errors_show(struct md_rdev *rdev, char *page)
return err ?: len;
}
static struct md_sysfs_entry md_resync_start =
-__ATTR(resync_start, S_IRUGO|S_IWUSR, resync_start_show, resync_start_store);
+__ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR,
+ resync_start_show, resync_start_store);
/*
* The array state can be:
return err ?: len;
}
static struct md_sysfs_entry md_array_state =
-__ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);
+__ATTR_PREALLOC(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);
static ssize_t
max_corrected_read_errors_show(struct mddev *mddev, char *page) {
}
static struct md_sysfs_entry md_metadata =
-__ATTR(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
+__ATTR_PREALLOC(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
static ssize_t
action_show(struct mddev *mddev, char *page)
}
static struct md_sysfs_entry md_scan_mode =
-__ATTR(sync_action, S_IRUGO|S_IWUSR, action_show, action_store);
+__ATTR_PREALLOC(sync_action, S_IRUGO|S_IWUSR, action_show, action_store);
static ssize_t
last_sync_action_show(struct mddev *mddev, char *page)
return sprintf(page, "%llu / %llu\n", resync, max_sectors);
}
-static struct md_sysfs_entry md_sync_completed = __ATTR_RO(sync_completed);
+static struct md_sysfs_entry md_sync_completed =
+ __ATTR_PREALLOC(sync_completed, S_IRUGO, sync_completed_show, NULL);
static ssize_t
min_sync_show(struct mddev *mddev, char *page)
{
unsigned long long min;
int err;
- int chunk;
if (kstrtoull(buf, 10, &min))
return -EINVAL;
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
goto out_unlock;
- /* Must be a multiple of chunk_size */
- chunk = mddev->chunk_sectors;
- if (chunk) {
- sector_t temp = min;
-
- err = -EINVAL;
- if (sector_div(temp, chunk))
- goto out_unlock;
- }
- mddev->resync_min = min;
+ /* Round down to multiple of 4K for safety */
+ mddev->resync_min = round_down(min, 8);
err = 0;
out_unlock:
if (mddev->sysfs_state)
sysfs_put(mddev->sysfs_state);
+ if (mddev->queue)
+ blk_cleanup_queue(mddev->queue);
if (mddev->gendisk) {
del_gendisk(mddev->gendisk);
put_disk(mddev->gendisk);
}
- if (mddev->queue)
- blk_cleanup_queue(mddev->queue);
kfree(mddev);
}
}
if (err) {
mddev_detach(mddev);
- pers->free(mddev, mddev->private);
+ if (mddev->private)
+ pers->free(mddev, mddev->private);
module_put(pers->owner);
bitmap_destroy(mddev);
return err;
rdev->raid_disk = -1;
err = bind_rdev_to_array(rdev, mddev);
- if (!err && !mddev->pers->hot_remove_disk) {
- /* If there is hot_add_disk but no hot_remove_disk
- * then added disks for geometry changes,
- * and should be added immediately.
- */
- super_types[mddev->major_version].
- validate_super(mddev, rdev);
- err = mddev->pers->hot_add_disk(mddev, rdev);
- if (err)
- unbind_rdev_from_array(rdev);
- }
if (err)
export_rdev(rdev);
else
- sysfs_notify_dirent_safe(rdev->sysfs_state);
-
- set_bit(MD_CHANGE_DEVS, &mddev->flags);
- if (mddev->degraded)
- set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- if (!err)
- md_new_event(mddev);
- md_wakeup_thread(mddev->thread);
+ err = add_bound_rdev(rdev);
if (mddev_is_clustered(mddev) &&
(info->state & (1 << MD_DISK_CLUSTER_ADD)))
md_cluster_ops->add_new_disk_finish(mddev);
if (rdev->raid_disk >= 0)
goto busy;
+ if (mddev_is_clustered(mddev))
+ md_cluster_ops->remove_disk(mddev, rdev);
+
md_kick_rdev_from_array(rdev);
md_update_sb(mddev, 1);
md_new_event(mddev);
if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
break;
- sectors = mddev->pers->sync_request(mddev, j, &skipped,
- currspeed < speed_min(mddev));
+ sectors = mddev->pers->sync_request(mddev, j, &skipped);
if (sectors == 0) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
break;
/((jiffies-mddev->resync_mark)/HZ +1) +1;
if (currspeed > speed_min(mddev)) {
- if ((currspeed > speed_max(mddev)) ||
- !is_mddev_idle(mddev, 0)) {
+ if (currspeed > speed_max(mddev)) {
msleep(500);
goto repeat;
}
+ if (!is_mddev_idle(mddev, 0)) {
+ /*
+ * Give other IO more of a chance.
+ * The faster the devices, the less we wait.
+ */
+ wait_event(mddev->recovery_wait,
+ !atomic_read(&mddev->recovery_active));
+ }
}
}
printk(KERN_INFO "md: %s: %s %s.\n",mdname(mddev), desc,
wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
/* tell personality that we are finished */
- mddev->pers->sync_request(mddev, max_sectors, &skipped, 1);
+ mddev->pers->sync_request(mddev, max_sectors, &skipped);
if (mddev_is_clustered(mddev))
md_cluster_ops->resync_finish(mddev);