diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-07-26 14:48:55 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-07-26 14:48:55 -0700 |
commit | e2aed8dfa50bb061747eeb14e6af099554a03b76 (patch) | |
tree | 900c96a2dfe7195e56ec3c1f027418029d0a8444 /fs/btrfs/extent_io.c | |
parent | 476525004ac7e2f990b6956efcd44d0780c2ab4c (diff) | |
parent | b24baf6917a376420d535548e1f88744028bcf24 (diff) | |
download | blackbird-op-linux-e2aed8dfa50bb061747eeb14e6af099554a03b76.tar.gz blackbird-op-linux-e2aed8dfa50bb061747eeb14e6af099554a03b76.zip |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs
Pull large btrfs update from Chris Mason:
"This pull request is very large, and the two main features in here
have been under testing/devel for quite a while.
We have subvolume quotas from the strato developers. This enables
full tracking of how many blocks are allocated to each subvolume (and
all snapshots) and you can set limits on a per-subvolume basis. You
can also create quota groups and toss multiple subvolumes into a big
group. It's everything you need to be a web hosting company and give
each user their own subvolume.
The userland side of the quotas is being refreshed, they'll send out
details on where to grab it soon.
Next is the kernel side of btrfs send/receive from Alexander Block.
This leverages the same infrastructure as the quota code to figure out
relationships between blocks and their owners. It can then compute
the difference between two snapshots and sends the diffs in a neutral
format into userland.
The basic model:
create a snapshot
send that snapshot as the initial backup
make changes
create a second snapshot
send the incremental as a backup
delete the first snapshot
(use the second snapshot for the next incremental)
The receive portion is all in userland, and in the 'next' branch of my
btrfs-progs repo.
There's still some work to do in terms of optimizing the send side
from kernel to userland. The really important part is figuring out
how two snapshots are different, and this is where we are
concentrating right now. The initial send of a dataset is a little
slower than tar, but the incremental sends are dramatically faster
than what rsync can do.
On top of all of that, we have a nice queue of fixes, cleanups and
optimizations."
Fix up trivial modify/del conflict in fs/btrfs/ioctl.c
Also fix up semantic conflict in fs/btrfs/send.c: the interface to
dentry_open() changed in commit 765927b2d508 ("switch dentry_open() to
struct path, make it grab references itself"), and since it now grabs
whatever references it needs, we should no longer do the mntget() on the
mnt (and we need to dput() the dentry reference we took).
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (65 commits)
Btrfs: uninit variable fixes in send/receive
Btrfs: introduce BTRFS_IOC_SEND for btrfs send/receive
Btrfs: add btrfs_compare_trees function
Btrfs: introduce subvol uuids and times
Btrfs: make iref_to_path non static
Btrfs: add a barrier before a waitqueue_active check
Btrfs: call the ordered free operation without any locks held
Btrfs: Check INCOMPAT flags on remount and add helper function
Btrfs: add helper for tree enumeration
btrfs: allow cross-subvolume file clone
Btrfs: improve multi-thread buffer read
Btrfs: make btrfs's allocation smoothly with preallocation
Btrfs: lock the transition from dirty to writeback for an eb
Btrfs: fix potential race in extent buffer freeing
Btrfs: don't return true in releasepage unless we actually freed the eb
Btrfs: suppress printk() if all device I/O stats are zero
Btrfs: remove unwanted printk() for btrfs device I/O stats
Btrfs: rewrite BTRFS_SETGET_FUNCS
Btrfs: zero unused bytes in inode item
Btrfs: kill free_space pointer from inode structure
...
Conflicts:
fs/btrfs/ioctl.c
Diffstat (limited to 'fs/btrfs/extent_io.c')
-rw-r--r-- | fs/btrfs/extent_io.c | 58 |
1 files changed, 42 insertions, 16 deletions
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index deafe19c34b5..45c81bb4ac82 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1919,7 +1919,7 @@ int repair_io_failure(struct btrfs_mapping_tree *map_tree, u64 start, return -EIO; } - printk_in_rcu(KERN_INFO "btrfs read error corrected: ino %lu off %llu " + printk_ratelimited_in_rcu(KERN_INFO "btrfs read error corrected: ino %lu off %llu " "(dev %s sector %llu)\n", page->mapping->host->i_ino, start, rcu_str_deref(dev->name), sector); @@ -3078,8 +3078,15 @@ static int lock_extent_buffer_for_io(struct extent_buffer *eb, } } + /* + * We need to do this to prevent races in people who check if the eb is + * under IO since we can end up having no IO bits set for a short period + * of time. + */ + spin_lock(&eb->refs_lock); if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) { set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); + spin_unlock(&eb->refs_lock); btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); spin_lock(&fs_info->delalloc_lock); if (fs_info->dirty_metadata_bytes >= eb->len) @@ -3088,6 +3095,8 @@ static int lock_extent_buffer_for_io(struct extent_buffer *eb, WARN_ON(1); spin_unlock(&fs_info->delalloc_lock); ret = 1; + } else { + spin_unlock(&eb->refs_lock); } btrfs_tree_unlock(eb); @@ -3558,19 +3567,38 @@ int extent_readpages(struct extent_io_tree *tree, struct bio *bio = NULL; unsigned page_idx; unsigned long bio_flags = 0; + struct page *pagepool[16]; + struct page *page; + int i = 0; + int nr = 0; for (page_idx = 0; page_idx < nr_pages; page_idx++) { - struct page *page = list_entry(pages->prev, struct page, lru); + page = list_entry(pages->prev, struct page, lru); prefetchw(&page->flags); list_del(&page->lru); - if (!add_to_page_cache_lru(page, mapping, + if (add_to_page_cache_lru(page, mapping, page->index, GFP_NOFS)) { - __extent_read_full_page(tree, page, get_extent, - &bio, 0, &bio_flags); + page_cache_release(page); + continue; } - page_cache_release(page); + + pagepool[nr++] = page; + if (nr < ARRAY_SIZE(pagepool)) + continue; + for (i = 0; i < nr; i++) { + __extent_read_full_page(tree, pagepool[i], get_extent, + &bio, 0, &bio_flags); + page_cache_release(pagepool[i]); + } + nr = 0; + } + for (i = 0; i < nr; i++) { + __extent_read_full_page(tree, pagepool[i], get_extent, + &bio, 0, &bio_flags); + page_cache_release(pagepool[i]); } + BUG_ON(!list_empty(pages)); if (bio) return submit_one_bio(READ, bio, 0, bio_flags); @@ -4124,11 +4152,10 @@ static void check_buffer_tree_ref(struct extent_buffer *eb) * So bump the ref count first, then set the bit. If someone * beat us to it, drop the ref we added. */ - if (!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) { + spin_lock(&eb->refs_lock); + if (!test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) atomic_inc(&eb->refs); - if (test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) - atomic_dec(&eb->refs); - } + spin_unlock(&eb->refs_lock); } static void mark_extent_buffer_accessed(struct extent_buffer *eb) @@ -4240,9 +4267,7 @@ again: goto free_eb; } /* add one reference for the tree */ - spin_lock(&eb->refs_lock); check_buffer_tree_ref(eb); - spin_unlock(&eb->refs_lock); spin_unlock(&tree->buffer_lock); radix_tree_preload_end(); @@ -4301,7 +4326,7 @@ static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head) } /* Expects to have eb->eb_lock already held */ -static void release_extent_buffer(struct extent_buffer *eb, gfp_t mask) +static int release_extent_buffer(struct extent_buffer *eb, gfp_t mask) { WARN_ON(atomic_read(&eb->refs) == 0); if (atomic_dec_and_test(&eb->refs)) { @@ -4322,9 +4347,11 @@ static void release_extent_buffer(struct extent_buffer *eb, gfp_t mask) btrfs_release_extent_buffer_page(eb, 0); call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu); - return; + return 1; } spin_unlock(&eb->refs_lock); + + return 0; } void free_extent_buffer(struct extent_buffer *eb) @@ -4963,7 +4990,6 @@ int try_release_extent_buffer(struct page *page, gfp_t mask) spin_unlock(&eb->refs_lock); return 0; } - release_extent_buffer(eb, mask); - return 1; + return release_extent_buffer(eb, mask); } |