Skip to content

Commit

Permalink
md-cluster: Perform a lazy update
Browse files Browse the repository at this point in the history 
In a clustered environment, a change such as marking a device faulty,
can be recorded by any of the nodes. This is communicated to all the
nodes and re-recording such a change is unnecessary, and quite often
pretty disruptive.

With this patch, just before the update, we detect for the changes
and if the changes are already in superblock, we abort the update
after clearing all the flags

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
  • Loading branch information
@goldwynr
goldwynr committed Oct 12, 2015
1 parent 70bcecd commit 2aa8219
Showing 1 changed file with 57 additions and 44 deletions.
101 changes: 57 additions & 44 deletions drivers/md/md.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2199,6 +2199,46 @@ static void sync_sbs(struct mddev *mddev, int nospares)
}
}

static bool does_sb_need_changing(struct mddev *mddev)
{
struct md_rdev *rdev;
struct mdp_superblock_1 *sb;
int role;

/* Find a good rdev */
rdev_for_each(rdev, mddev)
if ((rdev->raid_disk >= 0) && !test_bit(Faulty, &rdev->flags))
break;

/* No good device found. */
if (!rdev)
return false;

sb = page_address(rdev->sb_page);
/* Check if a device has become faulty or a spare become active */
rdev_for_each(rdev, mddev) {
role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
/* Device activated? */
if (role == 0xffff && rdev->raid_disk >=0 &&
!test_bit(Faulty, &rdev->flags))
return true;
/* Device turned faulty? */
if (test_bit(Faulty, &rdev->flags) && (role < 0xfffd))
return true;
}

/* Check if any mddev parameters have changed */
if ((mddev->dev_sectors != le64_to_cpu(sb->size)) ||
(mddev->reshape_position != le64_to_cpu(sb->reshape_position)) ||
(mddev->recovery_cp != le64_to_cpu(sb->resync_offset)) ||
(mddev->layout != le64_to_cpu(sb->layout)) ||
(mddev->raid_disks != le32_to_cpu(sb->raid_disks)) ||
(mddev->chunk_sectors != le32_to_cpu(sb->chunksize)))
return true;

return false;
}

void md_update_sb(struct mddev *mddev, int force_change)
{
struct md_rdev *rdev;
Expand All @@ -2211,6 +2251,18 @@ void md_update_sb(struct mddev *mddev, int force_change)
set_bit(MD_CHANGE_DEVS, &mddev->flags);
return;
}

if (mddev_is_clustered(mddev)) {
if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags))
force_change = 1;
md_cluster_ops->metadata_update_start(mddev);
/* Has someone else has updated the sb */
if (!does_sb_need_changing(mddev)) {
md_cluster_ops->metadata_update_cancel(mddev);
clear_bit(MD_CHANGE_PENDING, &mddev->flags);
return;
}
}
repeat:
/* First make sure individual recovery_offsets are correct */
rdev_for_each(rdev, mddev) {
Expand Down Expand Up @@ -2359,6 +2411,9 @@ void md_update_sb(struct mddev *mddev, int force_change)
clear_bit(BlockedBadBlocks, &rdev->flags);
wake_up(&rdev->blocked_wait);
}

if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
}
EXPORT_SYMBOL(md_update_sb);

Expand Down Expand Up @@ -2496,13 +2551,9 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
if (mddev_is_clustered(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);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
err = 0;
}
} else if (cmd_match(buf, "writemostly")) {
Expand Down Expand Up @@ -4063,12 +4114,8 @@ size_store(struct mddev *mddev, const char *buf, size_t len)
if (err)
return err;
if (mddev->pers) {
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
err = update_size(mddev, sectors);
md_update_sb(mddev, 1);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
} else {
if (mddev->dev_sectors == 0 ||
mddev->dev_sectors > sectors)
Expand Down Expand Up @@ -5306,8 +5353,6 @@ static void md_clean(struct mddev *mddev)

static void __md_stop_writes(struct mddev *mddev)
{
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
flush_workqueue(md_misc_wq);
if (mddev->sync_thread) {
Expand All @@ -5326,8 +5371,6 @@ static void __md_stop_writes(struct mddev *mddev)
mddev->in_sync = 1;
md_update_sb(mddev, 1);
}
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
}

void md_stop_writes(struct mddev *mddev)
Expand Down Expand Up @@ -6015,9 +6058,6 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev)
md_update_sb(mddev, 1);
md_new_event(mddev);

if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);

return 0;
busy:
if (mddev_is_clustered(mddev))
Expand Down Expand Up @@ -6073,14 +6113,12 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
goto abort_export;
}

if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
clear_bit(In_sync, &rdev->flags);
rdev->desc_nr = -1;
rdev->saved_raid_disk = -1;
err = bind_rdev_to_array(rdev, mddev);
if (err)
goto abort_clustered;
goto abort_export;

/*
* The rest should better be atomic, we can have disk failures
Expand All @@ -6090,9 +6128,6 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
rdev->raid_disk = -1;

md_update_sb(mddev, 1);

if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
/*
* Kick recovery, maybe this spare has to be added to the
* array immediately.
Expand All @@ -6102,9 +6137,6 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
md_new_event(mddev);
return 0;

abort_clustered:
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_cancel(mddev);
abort_export:
export_rdev(rdev);
return err;
Expand Down Expand Up @@ -6422,8 +6454,6 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
return rv;
}
}
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
if (info->size >= 0 && mddev->dev_sectors / 2 != info->size)
rv = update_size(mddev, (sector_t)info->size * 2);

Expand Down Expand Up @@ -6481,12 +6511,8 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
}
}
md_update_sb(mddev, 1);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
return rv;
err:
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_cancel(mddev);
return rv;
}

Expand Down Expand Up @@ -7599,11 +7625,7 @@ int md_allow_write(struct mddev *mddev)
mddev->safemode == 0)
mddev->safemode = 1;
spin_unlock(&mddev->lock);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
md_update_sb(mddev, 0);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
sysfs_notify_dirent_safe(mddev->sysfs_state);
} else
spin_unlock(&mddev->lock);
Expand Down Expand Up @@ -8182,13 +8204,8 @@ void md_check_recovery(struct mddev *mddev)
sysfs_notify_dirent_safe(mddev->sysfs_state);
}

if (mddev->flags & MD_UPDATE_SB_FLAGS) {
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
if (mddev->flags & MD_UPDATE_SB_FLAGS)
md_update_sb(mddev, 0);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
}

if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
Expand Down Expand Up @@ -8286,8 +8303,6 @@ void md_reap_sync_thread(struct mddev *mddev)
set_bit(MD_CHANGE_DEVS, &mddev->flags);
}
}
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
mddev->pers->finish_reshape)
mddev->pers->finish_reshape(mddev);
Expand All @@ -8300,8 +8315,6 @@ void md_reap_sync_thread(struct mddev *mddev)
rdev->saved_raid_disk = -1;

md_update_sb(mddev, 1);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_finish(mddev);
clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
Expand Down

0 comments on commit 2aa8219

Please sign in to comment.