For this callback, btrfs will:
- Go degraded if the fs can still maintain RW operations
And of course mark the target device as missing.
- Shutdown if the fs can not maintain RW operations
I know the shutdown can be a little overkilled, if one has a RAID1
metadata and RAID0 data, in that case one can still read data with 50%
rate to got some good data.
But it can also be as bad as the only device went missing for a single
device btrfs.
So here we go safe other than sorry when handling missing device.
And the remove_bdev callback will be hidden behind experimental features
for now, the reasons are:
- There are not enough btrfs specific bdev removal test cases
The existing test cases are all removing the only device, thus only
exercises the shutdown branch.
- Not yet determined what's the expected behavior
Although the current auto-degrade behavior is no worse than the old
behavior, it may not always be what the end users want.
Before there is a concrete solution, better hide the new feature
from end users.
Signed-off-by: Qu Wenruo <wqu@xxxxxxxx>
---
fs/btrfs/super.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++
fs/btrfs/volumes.c | 2 ++
fs/btrfs/volumes.h | 5 +++++
3 files changed, 62 insertions(+)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 5a07330fb3a6..3fba3d6309a2 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2412,6 +2412,58 @@ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_cont
return 0;
}
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+static void btrfs_remove_bdev(struct super_block *sb, struct block_device *bdev,
+ bool surprise)
+{
+ struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+ struct btrfs_device *device;
+ struct btrfs_dev_lookup_args lookup_args = { .devt = bdev->bd_dev };
+ bool can_rw;
+ int ret;
+
+ if (!surprise) {
+ ret = btrfs_sync_fs(sb, 1);
+ if (ret)
+ btrfs_warn(fs_info,
+ "filesystem failed to sync in preparation for device loss: %d",
+ ret);
+ }
+
+ mutex_lock(&fs_info->fs_devices->device_list_mutex);
+ device = btrfs_find_device(fs_info->fs_devices, &lookup_args);
+ if (!device) {
+ btrfs_warn(fs_info, "unable to find btrfs device for block device '%pg'",
+ bdev);
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ return;
+ }
+ set_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state);
+ device->fs_devices->missing_devices++;
+ if (test_and_clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
+ list_del_init(&device->dev_alloc_list);
+ device->fs_devices->rw_devices--;
+ }
+ can_rw = btrfs_check_rw_degradable(fs_info, device);
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ /*
+ * Now device is considered missing, btrfs_device_name() won't give a
+ * meaningful result anymore.
+ */
+ if (!can_rw) {
+ btrfs_warn(fs_info,
+ "btrfs device id %llu has gone missing, can not maintain read-write",
+ device->devid);
+ btrfs_force_shutdown(fs_info);
+ return;
+ }
+ btrfs_warn(fs_info,
+ "btrfs device id %llu has gone missing, continue as degraded",
+ device->devid);
+ btrfs_set_opt(fs_info->mount_opt, DEGRADED);
+}
+#endif
+
static const struct super_operations btrfs_super_ops = {
.drop_inode = btrfs_drop_inode,
.evict_inode = btrfs_evict_inode,
@@ -2427,6 +2479,9 @@ static const struct super_operations btrfs_super_ops = {
.unfreeze_fs = btrfs_unfreeze,
.nr_cached_objects = btrfs_nr_cached_objects,
.free_cached_objects = btrfs_free_cached_objects,
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+ .remove_bdev = btrfs_remove_bdev,
+#endif
};
static const struct file_operations btrfs_ctl_fops = {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 8ea1a69808a3..8feac0129bdd 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6794,6 +6794,8 @@ static bool dev_args_match_fs_devices(const struct btrfs_dev_lookup_args *args,
static bool dev_args_match_device(const struct btrfs_dev_lookup_args *args,
const struct btrfs_device *device)
{
+ if (args->devt)
+ return device->devt == args->devt;
if (args->missing) {
if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state) &&
!device->bdev)
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 6acb154ccf87..71e570f8337d 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -663,6 +663,11 @@ struct btrfs_dev_lookup_args {
u64 devid;
u8 *uuid;
u8 *fsid;
+ /*
+ * If devt is specified, all other members will be ignored as it is
+ * enough to uniquely locate a device.
+ */
+ dev_t devt;
bool missing;
};
--
2.49.0
