tree 5a1e20ab34f9b5114734ac107c2b4baa1fdba196
parent d1423248734df6d9aff769abffd675dc034e0601
author Stefan Behrens <sbehrens@giantdisaster.de> 1351617376 +0000
committer Josef Bacik <jbacik@fusionio.com> 1355350518 -0500

Btrfs: don't allow degraded mount if too many devices are missing

The current behavior is to allow mounting or remounting a filesystem
writeable in degraded mode if at least one writeable device is
present.
The next failed write access to a missing device which is above
the tolerance of the configured level of redundancy results in an
read-only enforcement. Even without this, the next time
barrier_all_devices() is called and more devices are missing than
tolerable, the switch to read-only mode takes place.

In order to behave predictably and to provide proper feedback to
the user at mount time, this patch compares the number of missing
devices with the number of devices that are tolerated to be missing
according to the configured RAID level. If more devices are missing
than tolerated, e.g. if two devices are missing in case of RAID1,
only a read-only mount and remount is allowed.

Signed-off-by: Stefan Behrens <sbehrens@giantdisaster.de>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>