@@ -6,6 +6,97 @@
#include "space-info.h"
#include "transaction.h"
+/*
+ * HOW DO BLOCK RSVS WORK
+ *
+ * Think of block_rsv's as buckets for logically grouped metadata
+ * reservations. Each block_rsv has a ->size and a ->reserved. ->size is how
+ * large we want our block rsv to be, ->reserved is how much space is
+ * currently reserved for this block reserve.
+ *
+ * ->failfast exists for the truncate case, and is described below.
+ *
+ * NORMAL OPERATION
+ *
+ * -> Reserve
+ * Entrance: btrfs_block_rsv_add, btrfs_block_rsv_refill
+ *
+ * We call into btrfs_reserve_metadata_bytes() with our bytes, which is
+ * accounted for in space_info->bytes_may_use, and then add the bytes to
+ * ->reserved, and ->size in the case of btrfs_block_rsv_add.
+ *
+ * ->size is an over-estimation of how much we may use for a particular
+ * operation.
+ *
+ * -> Use
+ * Entrance: btrfs_use_block_rsv
+ *
+ * When we do a btrfs_alloc_tree_block() we call into btrfs_use_block_rsv()
+ * to determine the appropriate block_rsv to use, and then verify that
+ * ->reserved has enough space for our tree block allocation. Once
+ * successful we subtract fs_info->nodesize from ->reserved.
+ *
+ * -> Finish
+ * Entrance: btrfs_block_rsv_release
+ *
+ * We are finished with our operation, subtract our individual reservation
+ * from ->size, and then subtract ->size from ->reserved and free up the
+ * excess if there is any.
+ *
+ * There is some logic here to refill the delayed refs rsv or the global rsv
+ * as needed, otherwise the excess is subtracted from
+ * space_info->bytes_may_use.
+ *
+ * TYPES OF BLOCK RSVS
+ *
+ * BLOCK_RSV_TRANS, BLOCK_RSV_DELOPS, BLOCK_RSV_CHUNK
+ * These behave normally, as described above, just within the confines of the
+ * lifetime of their particular operation (transaction for the whole trans
+ * handle lifetime, for example).
+ *
+ * BLOCK_RSV_GLOBAL
+ * It is impossible to properly account for all the space that may be required
+ * to make our extent tree updates. This block reserve acts as an overflow
+ * buffer in case our delayed refs rsv does not reserve enough space to update
+ * the extent tree.
+ *
+ * We can steal from this in some cases as well, notably on evict() or
+ * truncate() in order to help users recover from ENOSPC conditions.
+ *
+ * BLOCK_RSV_DELALLOC
+ * The individual item sizes are determined by the per-inode size
+ * calculations, which are described with the delalloc code. This is pretty
+ * straightforward, it's just the calculation of ->size encodes a lot of
+ * different items, and thus it gets used when updating inodes, inserting file
+ * extents, and inserting checksums.
+ *
+ * BLOCK_RSV_DELREFS
+ * We keep a running tally of how many delayed refs we have on the system.
+ * We assume each one of these delayed refs are going to use a full
+ * reservation. We use the transaction items and pre-reserve space for every
+ * operation, and use this reservation to refill any gap between ->size and
+ * ->reserved that may exist.
+ *
+ * From there it's straightforward, removing a delayed ref means we remove its
+ * count from ->size and free up reservations as necessary. Since this is the
+ * most dynamic block rsv in the system, we will try to refill this block rsv
+ * first with any excess returned by any other block reserve.
+ *
+ * BLOCK_RSV_EMPTY
+ * This is the fallback block rsv to make us try to reserve space if we don't
+ * have a specific bucket for this allocation. It is mostly used for updating
+ * the device tree and such, since that is a separate pool we're content to
+ * just reserve space from the space_info on demand.
+ *
+ * BLOCK_RSV_TEMP
+ * This is used by things like truncate and iput. We will temporarily
+ * allocate a block rsv, set it to some size, and then truncate bytes until we
+ * have no space left. With ->failfast set we'll simply return ENOSPC from
+ * btrfs_use_block_rsv() to signal that we need to unwind and try to make a
+ * new reservation. This is because these operations are unbounded, so we
+ * want to do as much work as we can, and then back off and re-reserve.
+ */
+
static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *block_rsv,
struct btrfs_block_rsv *dest, u64 num_bytes,
This is a giant comment at the top of block-rsv.c describing generally how block rsvs work. It is purely about the block rsv's themselves, and nothing to do with how the actual reservation system works. Signed-off-by: Josef Bacik <josef@toxicpanda.com> --- fs/btrfs/block-rsv.c | 91 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 91 insertions(+)