On Sat, Aug 6, 2011 at 4:37 AM, Liu Bo <liubo2009@xxxxxxxxxxxxxx> wrote:
> Introduce a new concept "sub transaction",
> the relation between transaction and sub transaction is
>
> transaction A ---> transid = x
> sub trans a(1) ---> sub_transid = x+1
> sub trans a(2) ---> sub_transid = x+2
> ... ...
> sub trans a(n-1) ---> sub_transid = x+n-1
> sub trans a(n) ---> sub_transid = x+n
> transaction B ---> transid = x+n+1
> ... ...
>
> And the most important is
> a) a trans handler's transid now gets value from sub transid instead of transid.
> b) when a transaction commits, transid may not added by 1, but depend on the
> biggest sub_transaction of the last neighbour transaction,
> i.e.
> B->transid = a(n)->transid + 1,
> (B->transid - A->transid) >= 1
> c) we start a new sub transaction after a fsync.
>
> We also ship some 'trans->transid' to 'trans->transaction->transid' to
> ensure btrfs works well and to get rid of WARNings.
>
> These are used for the new log code.
>
> Signed-off-by: Liu Bo <liubo2009@xxxxxxxxxxxxxx>
> ---
> fs/btrfs/ctree.c | 35 ++++++++++++++++++-----------------
> fs/btrfs/ctree.h | 1 +
> fs/btrfs/disk-io.c | 7 ++++---
> fs/btrfs/extent-tree.c | 10 ++++++----
> fs/btrfs/inode.c | 4 ++--
> fs/btrfs/ioctl.c | 2 +-
> fs/btrfs/relocation.c | 6 +++---
> fs/btrfs/transaction.c | 13 ++++++++-----
> fs/btrfs/transaction.h | 1 +
> fs/btrfs/tree-defrag.c | 2 +-
> fs/btrfs/tree-log.c | 16 ++++++++++++++--
> 11 files changed, 59 insertions(+), 38 deletions(-)
>
> diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
> index 011cab3..41d1d17 100644
> --- a/fs/btrfs/ctree.c
> +++ b/fs/btrfs/ctree.c
> @@ -228,9 +228,9 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
> int level;
> struct btrfs_disk_key disk_key;
>
> - WARN_ON(root->ref_cows && trans->transid !=
> + WARN_ON(root->ref_cows && trans->transaction->transid !=
> root->fs_info->running_transaction->transid);
> - WARN_ON(root->ref_cows && trans->transid != root->last_trans);
> + WARN_ON(root->ref_cows && trans->transid < root->last_trans);
>
> level = btrfs_header_level(buf);
> if (level == 0)
> @@ -425,9 +425,9 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
>
> btrfs_assert_tree_locked(buf);
>
> - WARN_ON(root->ref_cows && trans->transid !=
> + WARN_ON(root->ref_cows && trans->transaction->transid !=
> root->fs_info->running_transaction->transid);
> - WARN_ON(root->ref_cows && trans->transid != root->last_trans);
> + WARN_ON(root->ref_cows && trans->transid < root->last_trans);
>
> level = btrfs_header_level(buf);
>
> @@ -493,7 +493,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
> else
> parent_start = 0;
>
> - WARN_ON(trans->transid != btrfs_header_generation(parent));
> + WARN_ON(btrfs_header_generation(parent) <
> + trans->transaction->transid);
> btrfs_set_node_blockptr(parent, parent_slot,
> cow->start);
> btrfs_set_node_ptr_generation(parent, parent_slot,
> @@ -514,7 +515,7 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
> struct btrfs_root *root,
> struct extent_buffer *buf)
> {
> - if (btrfs_header_generation(buf) == trans->transid &&
> + if (btrfs_header_generation(buf) >= trans->transaction->transid &&
> !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) &&
> !(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
> btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
> @@ -542,7 +543,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
> root->fs_info->running_transaction->transid);
> WARN_ON(1);
> }
> - if (trans->transid != root->fs_info->generation) {
> + if (trans->transaction->transid != root->fs_info->generation) {
> printk(KERN_CRIT "trans %llu running %llu\n",
> (unsigned long long)trans->transid,
> (unsigned long long)root->fs_info->generation);
> @@ -645,7 +646,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
>
> if (trans->transaction != root->fs_info->running_transaction)
> WARN_ON(1);
> - if (trans->transid != root->fs_info->generation)
> + if (trans->transaction->transid != root->fs_info->generation)
> WARN_ON(1);
>
> parent_nritems = btrfs_header_nritems(parent);
> @@ -898,7 +899,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
>
> WARN_ON(path->locks[level] != BTRFS_WRITE_LOCK &&
> path->locks[level] != BTRFS_WRITE_LOCK_BLOCKING);
> - WARN_ON(btrfs_header_generation(mid) != trans->transid);
> + WARN_ON(btrfs_header_generation(mid) < trans->transaction->transid);
>
> orig_ptr = btrfs_node_blockptr(mid, orig_slot);
>
> @@ -1105,7 +1106,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
> return 1;
>
> mid = path->nodes[level];
> - WARN_ON(btrfs_header_generation(mid) != trans->transid);
> + WARN_ON(btrfs_header_generation(mid) < trans->transaction->transid);
>
> if (level < BTRFS_MAX_LEVEL - 1)
> parent = path->nodes[level + 1];
> @@ -1942,8 +1943,8 @@ static int push_node_left(struct btrfs_trans_handle *trans,
> src_nritems = btrfs_header_nritems(src);
> dst_nritems = btrfs_header_nritems(dst);
> push_items = BTRFS_NODEPTRS_PER_BLOCK(root) - dst_nritems;
> - WARN_ON(btrfs_header_generation(src) != trans->transid);
> - WARN_ON(btrfs_header_generation(dst) != trans->transid);
> + WARN_ON(btrfs_header_generation(src) < trans->transaction->transid);
> + WARN_ON(btrfs_header_generation(dst) < trans->transaction->transid);
>
> if (!empty && src_nritems <= 8)
> return 1;
> @@ -2005,8 +2006,8 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
> int dst_nritems;
> int ret = 0;
>
> - WARN_ON(btrfs_header_generation(src) != trans->transid);
> - WARN_ON(btrfs_header_generation(dst) != trans->transid);
> + WARN_ON(btrfs_header_generation(src) < trans->transaction->transid);
> + WARN_ON(btrfs_header_generation(dst) < trans->transaction->transid);
>
> src_nritems = btrfs_header_nritems(src);
> dst_nritems = btrfs_header_nritems(dst);
> @@ -2097,7 +2098,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
> btrfs_set_node_key(c, &lower_key, 0);
> btrfs_set_node_blockptr(c, 0, lower->start);
> lower_gen = btrfs_header_generation(lower);
> - WARN_ON(lower_gen != trans->transid);
> + WARN_ON(lower_gen < trans->transaction->transid);
>
> btrfs_set_node_ptr_generation(c, 0, lower_gen);
>
> @@ -2177,7 +2178,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
> u32 c_nritems;
>
> c = path->nodes[level];
> - WARN_ON(btrfs_header_generation(c) != trans->transid);
> + WARN_ON(btrfs_header_generation(c) < trans->transaction->transid);
> if (c == root->node) {
> /* trying to split the root, lets make a new one */
> ret = insert_new_root(trans, root, path, level + 1);
> @@ -3751,7 +3752,7 @@ static noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans,
> {
> int ret;
>
> - WARN_ON(btrfs_header_generation(leaf) != trans->transid);
> + WARN_ON(btrfs_header_generation(leaf) < trans->transaction->transid);
> ret = del_ptr(trans, root, path, 1, path->slots[1]);
> if (ret)
> return ret;
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index a6263bd..310f586 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -925,6 +925,7 @@ struct btrfs_fs_info {
> struct mutex durable_block_rsv_mutex;
>
> u64 generation;
> + u64 sub_generation;
> u64 last_trans_committed;
>
> /*
> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
> index 94ecac3..50e74b1 100644
> --- a/fs/btrfs/disk-io.c
> +++ b/fs/btrfs/disk-io.c
> @@ -1035,7 +1035,7 @@ int clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
> struct extent_buffer *buf)
> {
> struct inode *btree_inode = root->fs_info->btree_inode;
> - if (btrfs_header_generation(buf) ==
> + if (btrfs_header_generation(buf) >=
> root->fs_info->running_transaction->transid) {
> btrfs_assert_tree_locked(buf);
>
> @@ -1559,7 +1559,7 @@ static int transaction_kthread(void *arg)
>
> trans = btrfs_join_transaction(root);
> BUG_ON(IS_ERR(trans));
> - if (transid == trans->transid) {
> + if (transid == trans->transaction->transid) {
> ret = btrfs_commit_transaction(trans, root);
> BUG_ON(ret);
> } else {
> @@ -2001,6 +2001,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
> csum_root->track_dirty = 1;
>
> fs_info->generation = generation;
> + fs_info->sub_generation = generation;
> fs_info->last_trans_committed = generation;
> fs_info->data_alloc_profile = (u64)-1;
> fs_info->metadata_alloc_profile = (u64)-1;
> @@ -2671,7 +2672,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
> int was_dirty;
>
> btrfs_assert_tree_locked(buf);
> - if (transid != root->fs_info->generation) {
> + if (transid < root->fs_info->generation) {
> printk(KERN_CRIT "btrfs transid mismatch buffer %llu, "
> "found %llu running %llu\n",
> (unsigned long long)buf->start,
> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
> index 66bac22..fa101ab 100644
> --- a/fs/btrfs/extent-tree.c
> +++ b/fs/btrfs/extent-tree.c
> @@ -4363,7 +4363,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
> list_for_each_entry_safe(block_rsv, next_rsv,
> &fs_info->durable_block_rsv_list, list) {
>
> - idx = trans->transid & 0x1;
> + idx = trans->transaction->transid & 0x1;
> if (block_rsv->freed[idx] > 0) {
> block_rsv_add_bytes(block_rsv,
> block_rsv->freed[idx], 0);
> @@ -4680,7 +4680,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
> if (block_rsv->space_info != cache->space_info)
> goto out;
>
> - if (btrfs_header_generation(buf) == trans->transid) {
> + if (btrfs_header_generation(buf) >= trans->transaction->transid) {
> if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
> ret = check_ref_cleanup(trans, root, buf->start);
> if (!ret)
> @@ -4730,7 +4730,8 @@ pin:
>
> if (ret) {
> spin_lock(&block_rsv->lock);
> - block_rsv->freed[trans->transid & 0x1] += buf->len;
> + block_rsv->freed[trans->transaction->transid & 0x1] +=
> + buf->len;
> spin_unlock(&block_rsv->lock);
> }
> }
> @@ -6164,7 +6165,8 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
> }
> /* make block locked assertion in clean_tree_block happy */
> if (!path->locks[level] &&
> - btrfs_header_generation(eb) == trans->transid) {
> + btrfs_header_generation(eb) >=
> + trans->transaction->transid) {
> btrfs_tree_lock(eb);
> btrfs_set_lock_blocking(eb);
> path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
> index 34195f9..99eb0b3 100644
> --- a/fs/btrfs/inode.c
> +++ b/fs/btrfs/inode.c
> @@ -2106,7 +2106,7 @@ void btrfs_orphan_pre_snapshot(struct btrfs_trans_handle *trans,
> * space than it frees. So we should make sure there is enough
> * reserved space.
> */
> - index = trans->transid & 0x1;
> + index = trans->transaction->transid & 0x1;
> if (block_rsv->reserved + block_rsv->freed[index] < block_rsv->size) {
> num_bytes += block_rsv->size -
> (block_rsv->reserved + block_rsv->freed[index]);
> @@ -2130,7 +2130,7 @@ void btrfs_orphan_post_snapshot(struct btrfs_trans_handle *trans,
>
> /* refill source subvolume's orphan block reservation */
> block_rsv = root->orphan_block_rsv;
> - index = trans->transid & 0x1;
> + index = trans->transaction->transid & 0x1;
> if (block_rsv->reserved + block_rsv->freed[index] < block_rsv->size) {
> num_bytes = block_rsv->size -
> (block_rsv->reserved + block_rsv->freed[index]);
> diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
> index 2bb0886..bc9a2ad 100644
> --- a/fs/btrfs/ioctl.c
> +++ b/fs/btrfs/ioctl.c
> @@ -2758,7 +2758,7 @@ static noinline long btrfs_ioctl_start_sync(struct file *file, void __user *argp
> trans = btrfs_start_transaction(root, 0);
> if (IS_ERR(trans))
> return PTR_ERR(trans);
> - transid = trans->transid;
> + transid = trans->transaction->transid;
> ret = btrfs_commit_transaction_async(trans, root, 0);
> if (ret) {
> btrfs_end_transaction(trans, root);
> diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
> index 59bb176..3063be1 100644
> --- a/fs/btrfs/relocation.c
> +++ b/fs/btrfs/relocation.c
> @@ -469,7 +469,7 @@ static int update_backref_cache(struct btrfs_trans_handle *trans,
> return 0;
> }
>
> - if (cache->last_trans == trans->transid)
> + if (cache->last_trans >= trans->transaction->transid)
> return 0;
>
> /*
> @@ -1281,7 +1281,7 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
> BUG_ON(ret);
>
> btrfs_set_root_last_snapshot(&root->root_item,
> - trans->transid - 1);
> + trans->transaction->transid - 1);
> } else {
> /*
> * called by btrfs_reloc_post_snapshot_hook.
> @@ -2271,7 +2271,7 @@ static int record_reloc_root_in_trans(struct btrfs_trans_handle *trans,
> {
> struct btrfs_root *root;
>
> - if (reloc_root->last_trans == trans->transid)
> + if (reloc_root->last_trans >= trans->transaction->transid)
> return 0;
>
> root = read_fs_root(reloc_root->fs_info, reloc_root->root_key.offset);
> diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
> index 7dc36fa..531b0dc 100644
> --- a/fs/btrfs/transaction.c
> +++ b/fs/btrfs/transaction.c
> @@ -113,7 +113,9 @@ static noinline int join_transaction(struct btrfs_root *root, int nofail)
> extent_io_tree_init(&cur_trans->dirty_pages,
> root->fs_info->btree_inode->i_mapping);
> root->fs_info->generation++;
> + root->fs_info->sub_generation = root->fs_info->generation;
> cur_trans->transid = root->fs_info->generation;
> + cur_trans->sub_transid = cur_trans->transid;
> root->fs_info->running_transaction = cur_trans;
> spin_unlock(&root->fs_info->trans_lock);
>
> @@ -129,7 +131,7 @@ static noinline int join_transaction(struct btrfs_root *root, int nofail)
> static int record_root_in_trans(struct btrfs_trans_handle *trans,
> struct btrfs_root *root)
> {
> - if (root->ref_cows && root->last_trans < trans->transid) {
> + if (root->ref_cows && root->last_trans < trans->transaction->transid) {
> WARN_ON(root == root->fs_info->extent_root);
> WARN_ON(root->commit_root != root->node);
>
> @@ -146,7 +148,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
> smp_wmb();
>
> spin_lock(&root->fs_info->fs_roots_radix_lock);
> - if (root->last_trans == trans->transid) {
> + if (root->last_trans >= trans->transaction->transid) {
> spin_unlock(&root->fs_info->fs_roots_radix_lock);
> return 0;
> }
> @@ -194,7 +196,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
> * and barriers
> */
> smp_rmb();
> - if (root->last_trans == trans->transid &&
> + if (root->last_trans >= trans->transaction->transid &&
> !root->in_trans_setup)
> return 0;
>
> @@ -302,7 +304,7 @@ again:
>
> cur_trans = root->fs_info->running_transaction;
>
> - h->transid = cur_trans->transid;
> + h->transid = cur_trans->sub_transid;
> h->transaction = cur_trans;
> h->blocks_used = 0;
> h->bytes_reserved = 0;
> @@ -1346,6 +1348,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
>
> trans->transaction->blocked = 0;
> spin_lock(&root->fs_info->trans_lock);
> + root->fs_info->generation = cur_trans->sub_transid;
> root->fs_info->running_transaction = NULL;
> root->fs_info->trans_no_join = 0;
> spin_unlock(&root->fs_info->trans_lock);
> @@ -1367,7 +1370,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
>
> cur_trans->commit_done = 1;
>
> - root->fs_info->last_trans_committed = cur_trans->transid;
> + root->fs_info->last_trans_committed = cur_trans->sub_transid;
>
> wake_up(&cur_trans->commit_wait);
>
> diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
> index 02564e6..45876b0 100644
> --- a/fs/btrfs/transaction.h
> +++ b/fs/btrfs/transaction.h
> @@ -23,6 +23,7 @@
>
> struct btrfs_transaction {
> u64 transid;
> + u64 sub_transid;
> /*
> * total writers in this transaction, it must be zero before the
> * transaction can end
> diff --git a/fs/btrfs/tree-defrag.c b/fs/btrfs/tree-defrag.c
> index 3b580ee..a2569af 100644
> --- a/fs/btrfs/tree-defrag.c
> +++ b/fs/btrfs/tree-defrag.c
> @@ -139,7 +139,7 @@ done:
> if (ret != -EAGAIN) {
> memset(&root->defrag_progress, 0,
> sizeof(root->defrag_progress));
> - root->defrag_trans_start = trans->transid;
> + root->defrag_trans_start = trans->transaction->transid;
> }
> return ret;
> }
> diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
> index f320641..5a026d2 100644
> --- a/fs/btrfs/tree-log.c
> +++ b/fs/btrfs/tree-log.c
> @@ -134,9 +134,19 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
> static int start_log_trans(struct btrfs_trans_handle *trans,
> struct btrfs_root *root)
> {
> + struct btrfs_transaction *cur_trans;
> int ret;
> int err = 0;
>
> + /* start a new sub transaction */
> + spin_lock(&root->fs_info->trans_lock);
> +
> + cur_trans = root->fs_info->running_transaction;
> + cur_trans->sub_transid++;
> + root->fs_info->sub_generation = cur_trans->sub_transid;
> +
> + spin_unlock(&root->fs_info->trans_lock);
> +
> mutex_lock(&root->log_mutex);
> if (root->log_root) {
> if (!root->log_start_pid) {
> @@ -2007,7 +2017,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
> }
>
> /* bail out if we need to do a full commit */
> - if (root->fs_info->last_trans_log_full_commit == trans->transid) {
> + if (root->fs_info->last_trans_log_full_commit >=
> + trans->transaction->transid) {
> ret = -EAGAIN;
> mutex_unlock(&root->log_mutex);
> goto out;
> @@ -2084,7 +2095,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
> * now that we've moved on to the tree of log tree roots,
> * check the full commit flag again
> */
> - if (root->fs_info->last_trans_log_full_commit == trans->transid) {
> + if (root->fs_info->last_trans_log_full_commit >=
> + trans->transaction->transid) {
> btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
> mutex_unlock(&log_root_tree->log_mutex);
> ret = -EAGAIN;
> --
> 1.6.5.2
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
Portions of this patch conflict with another patch recently posted to
the Mailing List by Josef.
http://www.mail-archive.com/linux-btrfs@xxxxxxxxxxxxxxx/msg11657.html
"[PATCH] Btrfs: kill the durable block rsv stuff" removes portions of
the functions btrfs_finish_extent_commit() and btrfs_free_tree_block()
in fs/btrfs/extent-tree.c that are modified in this patch.
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
