device replace could fail due to another running scrub process or any
other errors btrfs_scrub_dev() may hit, but this failure doesn't get
returned to userspace.
The following steps could reproduce this issue
mkfs -t btrfs -f /dev/sdb1 /dev/sdb2
mount /dev/sdb1 /mnt/btrfs
while true; do btrfs scrub start -B /mnt/btrfs >/dev/null 2>&1; done &
btrfs replace start -Bf /dev/sdb2 /dev/sdb3 /mnt/btrfs
# if this replace succeeded, do the following and repeat until
# you see this log in dmesg
# BTRFS: btrfs_scrub_dev(/dev/sdb2, 2, /dev/sdb3) failed -115
#btrfs replace start -Bf /dev/sdb3 /dev/sdb2 /mnt/btrfs
# once you see the error log in dmesg, check return value of
# replace
echo $?
Introduce a new dev replace result
BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS
to catch -EINPROGRESS explicitly and return other errors directly to
userspace.
Signed-off-by: Eryu Guan <guaneryu@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
&dev_replace->scrub_progress, 0, 1);
ret = btrfs_dev_replace_finishing(root->fs_info, ret);
- WARN_ON(ret);
+ /* don't warn if EINPROGRESS, someone else might be running scrub */
+ if (ret == -EINPROGRESS) {
+ args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
+ ret = 0;
+ } else {
+ WARN_ON(ret);
+ }
- return 0;
+ return ret;
leave:
dev_replace->srcdev = NULL;
btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
- return 0;
+ return scrub_ret;
}
printk_in_rcu(KERN_INFO
#define BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR 0
#define BTRFS_IOCTL_DEV_REPLACE_RESULT_NOT_STARTED 1
#define BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED 2
+#define BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS 3
struct btrfs_ioctl_dev_replace_args {
__u64 cmd; /* in */
__u64 result; /* out */