summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/file.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-03-02 16:41:54 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-03-02 16:41:54 -0800
commitb695188dd39162a1a6bff11fdbcc4c0b65b933ab (patch)
treea3df7c052d38b5bfaf335fbf3130abcc5c6ca577 /fs/btrfs/file.c
parent48476df99894492a0f7239f2f3c9a2dde4ff38e2 (diff)
parent180e001cd5fc2950dc6a7997dde5b65c954d0e79 (diff)
downloadlinux-b695188dd39162a1a6bff11fdbcc4c0b65b933ab.tar.bz2
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs
Pull btrfs update from Chris Mason: "The biggest feature in the pull is the new (and still experimental) raid56 code that David Woodhouse started long ago. I'm still working on the parity logging setup that will avoid inconsistent parity after a crash, so this is only for testing right now. But, I'd really like to get it out to a broader audience to hammer out any performance issues or other problems. scrub does not yet correct errors on raid5/6 either. Josef has another pass at fsync performance. The big change here is to combine waiting for metadata with waiting for data, which is a big latency win. It is also step one toward using atomics from the hardware during a commit. Mark Fasheh has a new way to use btrfs send/receive to send only the metadata changes. SUSE is using this to make snapper more efficient at finding changes between snapshosts. Snapshot-aware defrag is also included. Otherwise we have a large number of fixes and cleanups. Eric Sandeen wins the award for removing the most lines, and I'm hoping we steal this idea from XFS over and over again." * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (118 commits) btrfs: fixup/remove module.h usage as required Btrfs: delete inline extents when we find them during logging btrfs: try harder to allocate raid56 stripe cache Btrfs: cleanup to make the function btrfs_delalloc_reserve_metadata more logic Btrfs: don't call btrfs_qgroup_free if just btrfs_qgroup_reserve fails Btrfs: remove reduplicate check about root in the function btrfs_clean_quota_tree Btrfs: return ENOMEM rather than use BUG_ON when btrfs_alloc_path fails Btrfs: fix missing deleted items in btrfs_clean_quota_tree btrfs: use only inline_pages from extent buffer Btrfs: fix wrong reserved space when deleting a snapshot/subvolume Btrfs: fix wrong reserved space in qgroup during snap/subv creation Btrfs: remove unnecessary dget_parent/dput when creating the pending snapshot btrfs: remove a printk from scan_one_device Btrfs: fix NULL pointer after aborting a transaction Btrfs: fix memory leak of log roots Btrfs: copy everything if we've created an inline extent btrfs: cleanup for open-coded alignment Btrfs: do not change inode flags in rename Btrfs: use reserved space for creating a snapshot clear chunk_alloc flag on retryable failure ...
Diffstat (limited to 'fs/btrfs/file.c')
-rw-r--r--fs/btrfs/file.c57
1 files changed, 47 insertions, 10 deletions
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 4b241fe9d2fe..af1d0605a5c1 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -30,11 +30,11 @@
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/slab.h>
+#include <linux/btrfs.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
-#include "ioctl.h"
#include "print-tree.h"
#include "tree-log.h"
#include "locking.h"
@@ -374,6 +374,11 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
atomic_inc(&fs_info->defrag_running);
while(1) {
+ /* Pause the auto defragger. */
+ if (test_bit(BTRFS_FS_STATE_REMOUNTING,
+ &fs_info->fs_state))
+ break;
+
if (!__need_auto_defrag(fs_info->tree_root))
break;
@@ -505,8 +510,7 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
loff_t isize = i_size_read(inode);
start_pos = pos & ~((u64)root->sectorsize - 1);
- num_bytes = (write_bytes + pos - start_pos +
- root->sectorsize - 1) & ~((u64)root->sectorsize - 1);
+ num_bytes = ALIGN(write_bytes + pos - start_pos, root->sectorsize);
end_of_last_block = start_pos + num_bytes - 1;
err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
@@ -1544,7 +1548,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
* although we have opened a file as writable, we have
* to stop this write operation to ensure FS consistency.
*/
- if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+ if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) {
mutex_unlock(&inode->i_mutex);
err = -EROFS;
goto out;
@@ -1627,7 +1631,20 @@ int btrfs_release_file(struct inode *inode, struct file *filp)
*/
if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
&BTRFS_I(inode)->runtime_flags)) {
- btrfs_add_ordered_operation(NULL, BTRFS_I(inode)->root, inode);
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+
+ /*
+ * We need to block on a committing transaction to keep us from
+ * throwing a ordered operation on to the list and causing
+ * something like sync to deadlock trying to flush out this
+ * inode.
+ */
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+ btrfs_add_ordered_operation(trans, BTRFS_I(inode)->root, inode);
+ btrfs_end_transaction(trans, root);
if (inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT)
filemap_flush(inode->i_mapping);
}
@@ -1654,16 +1671,21 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret = 0;
struct btrfs_trans_handle *trans;
+ bool full_sync = 0;
trace_btrfs_sync_file(file, datasync);
/*
* We write the dirty pages in the range and wait until they complete
* out of the ->i_mutex. If so, we can flush the dirty pages by
- * multi-task, and make the performance up.
+ * multi-task, and make the performance up. See
+ * btrfs_wait_ordered_range for an explanation of the ASYNC check.
*/
atomic_inc(&BTRFS_I(inode)->sync_writers);
- ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+ ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
+ if (!ret && test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+ &BTRFS_I(inode)->runtime_flags))
+ ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
atomic_dec(&BTRFS_I(inode)->sync_writers);
if (ret)
return ret;
@@ -1675,7 +1697,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* range being left.
*/
atomic_inc(&root->log_batch);
- btrfs_wait_ordered_range(inode, start, end - start + 1);
+ full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+ &BTRFS_I(inode)->runtime_flags);
+ if (full_sync)
+ btrfs_wait_ordered_range(inode, start, end - start + 1);
atomic_inc(&root->log_batch);
/*
@@ -1742,13 +1767,25 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (ret != BTRFS_NO_LOG_SYNC) {
if (ret > 0) {
+ /*
+ * If we didn't already wait for ordered extents we need
+ * to do that now.
+ */
+ if (!full_sync)
+ btrfs_wait_ordered_range(inode, start,
+ end - start + 1);
ret = btrfs_commit_transaction(trans, root);
} else {
ret = btrfs_sync_log(trans, root);
- if (ret == 0)
+ if (ret == 0) {
ret = btrfs_end_transaction(trans, root);
- else
+ } else {
+ if (!full_sync)
+ btrfs_wait_ordered_range(inode, start,
+ end -
+ start + 1);
ret = btrfs_commit_transaction(trans, root);
+ }
}
} else {
ret = btrfs_end_transaction(trans, root);