summaryrefslogtreecommitdiff
path: root/fs/btrfs/block-group.c
diff options
context:
space:
mode:
authorFilipe Manana <fdmanana@suse.com>2021-06-21 13:10:38 +0300
committerDavid Sterba <dsterba@suse.com>2021-06-22 15:11:58 +0300
commit1cea5cf0e664290cc917da9a2c1f8df3716891cd (patch)
treefa5549809528f500b2971565e3b5ec9efe8f48e9 /fs/btrfs/block-group.c
parentcbeaae4f6f6e787b7dac6230a31d9ad93d594f95 (diff)
downloadlinux-1cea5cf0e664290cc917da9a2c1f8df3716891cd.tar.xz
btrfs: ensure relocation never runs while we have send operations running
Relocation and send do not play well together because while send is running a block group can be relocated, a transaction committed and the respective disk extents get re-allocated and written to or discarded while send is about to do something with the extents. This was explained in commit 9e967495e0e0ae ("Btrfs: prevent send failures and crashes due to concurrent relocation"), which prevented balance and send from running in parallel but it did not address one remaining case where chunk relocation can happen: shrinking a device (and device deletion which shrinks a device's size to 0 before deleting the device). We also have now one more case where relocation is triggered: on zoned filesystems partially used block groups get relocated by a background thread, introduced in commit 18bb8bbf13c183 ("btrfs: zoned: automatically reclaim zones"). So make sure that instead of preventing balance from running when there are ongoing send operations, we prevent relocation from happening. This uses the infrastructure recently added by a patch that has the subject: "btrfs: add cancellable chunk relocation support". Also it adds a spinlock used exclusively for the exclusivity between send and relocation, as before fs_info->balance_mutex was used, which would make an attempt to run send to block waiting for balance to finish, which can take a lot of time on large filesystems. Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs/block-group.c')
-rw-r--r--fs/btrfs/block-group.c10
1 files changed, 8 insertions, 2 deletions
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index c42b6528552f..024a1c6e5b40 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1491,7 +1491,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
container_of(work, struct btrfs_fs_info, reclaim_bgs_work);
struct btrfs_block_group *bg;
struct btrfs_space_info *space_info;
- int ret;
+ LIST_HEAD(again_list);
if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
return;
@@ -1502,6 +1502,8 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
mutex_lock(&fs_info->reclaim_bgs_lock);
spin_lock(&fs_info->unused_bgs_lock);
while (!list_empty(&fs_info->reclaim_bgs)) {
+ int ret = 0;
+
bg = list_first_entry(&fs_info->reclaim_bgs,
struct btrfs_block_group,
bg_list);
@@ -1547,9 +1549,13 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
bg->start);
next:
- btrfs_put_block_group(bg);
spin_lock(&fs_info->unused_bgs_lock);
+ if (ret == -EAGAIN && list_empty(&bg->bg_list))
+ list_add_tail(&bg->bg_list, &again_list);
+ else
+ btrfs_put_block_group(bg);
}
+ list_splice_tail(&again_list, &fs_info->reclaim_bgs);
spin_unlock(&fs_info->unused_bgs_lock);
mutex_unlock(&fs_info->reclaim_bgs_lock);
btrfs_exclop_finish(fs_info);