From 9ed74f2dba6ebf9f30b80554290bfc73cc3ef083 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 11 Sep 2009 16:12:44 -0400 Subject: Btrfs: proper -ENOSPC handling At the start of a transaction we do a btrfs_reserve_metadata_space() and specify how many items we plan on modifying. Then once we've done our modifications and such, just call btrfs_unreserve_metadata_space() for the same number of items we reserved. For keeping track of metadata needed for data I've had to add an extent_io op for when we merge extents. This lets us track space properly when we are doing sequential writes, so we don't end up reserving way more metadata space than what we need. The only place where the metadata space accounting is not done is in the relocation code. This is because Yan is going to be reworking that code in the near future, so running btrfs-vol -b could still possibly result in a ENOSPC related panic. This patch also turns off the metadata_ratio stuff in order to allow users to more efficiently use their disk space. This patch makes it so we track how much metadata we need for an inode's delayed allocation extents by tracking how many extents are currently waiting for allocation. It introduces two new callbacks for the extent_io tree's, merge_extent_hook and split_extent_hook. These help us keep track of when we merge delalloc extents together and split them up. Reservations are handled prior to any actually dirty'ing occurs, and then we unreserve after we dirty. btrfs_unreserve_metadata_for_delalloc() will make the appropriate unreservations as needed based on the number of reservations we currently have and the number of extents we currently have. Doing the reservation outside of doing any of the actual dirty'ing lets us do things like filemap_flush() the inode to try and force delalloc to happen, or as a last resort actually start allocation on all delalloc inodes in the fs. This has survived dbench, fs_mark and an fsx torture test. Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/file.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 571ad3c13b47..1be96ba6f6bb 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -123,7 +123,10 @@ static noinline int dirty_and_release_pages(struct btrfs_trans_handle *trans, root->sectorsize - 1) & ~((u64)root->sectorsize - 1); end_of_last_block = start_pos + num_bytes - 1; - btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block); + err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block); + if (err) + return err; + for (i = 0; i < num_pages; i++) { struct page *p = pages[i]; SetPageUptodate(p); @@ -927,6 +930,11 @@ static ssize_t btrfs_file_write(struct file *file, const char __user *buf, err = file_remove_suid(file); if (err) goto out_nolock; + + err = btrfs_reserve_metadata_for_delalloc(root, inode, 1); + if (err) + goto out_nolock; + file_update_time(file); pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL); @@ -1028,6 +1036,7 @@ out: mutex_unlock(&inode->i_mutex); if (ret) err = ret; + btrfs_unreserve_metadata_for_delalloc(root, inode, 1); out_nolock: kfree(pages); -- cgit v1.2.3 From ab93dbecfba72bbc04b7036343d180aaff1b61a3 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Thu, 1 Oct 2009 12:29:10 -0400 Subject: Btrfs: take i_mutex before generic_write_checks btrfs_file_write was incorrectly calling generic_write_checks without taking i_mutex. This lead to problems with racing around i_size when doing O_APPEND writes. The fix here is to move i_mutex higher. Signed-off-by: Chris Mason --- fs/btrfs/file.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 1be96ba6f6bb..f155179877a6 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -920,26 +920,35 @@ static ssize_t btrfs_file_write(struct file *file, const char __user *buf, start_pos = pos; vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); + + /* do the reserve before the mutex lock in case we have to do some + * flushing. We wouldn't deadlock, but this is more polite. + */ + err = btrfs_reserve_metadata_for_delalloc(root, inode, 1); + if (err) + goto out_nolock; + + mutex_lock(&inode->i_mutex); + current->backing_dev_info = inode->i_mapping->backing_dev_info; err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) - goto out_nolock; + goto out; + if (count == 0) - goto out_nolock; + goto out; err = file_remove_suid(file); if (err) - goto out_nolock; - - err = btrfs_reserve_metadata_for_delalloc(root, inode, 1); - if (err) - goto out_nolock; + goto out; file_update_time(file); pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL); - mutex_lock(&inode->i_mutex); + /* generic_write_checks can change our pos */ + start_pos = pos; + BTRFS_I(inode)->sequence++; first_index = pos >> PAGE_CACHE_SHIFT; last_index = (pos + count) >> PAGE_CACHE_SHIFT; -- cgit v1.2.3 From 8aa38c31b7659e338fee4d9af4c3805acbd9806f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 1 Oct 2009 12:58:30 -0400 Subject: Btrfs: remove duplicates of filemap_ helpers Use filemap_fdatawrite_range and filemap_fdatawait_range instead of local copies of the functions. For filemap_fdatawait_range that also means replacing the awkward old wait_on_page_writeback_range calling convention with the regular filemap byte offsets. Signed-off-by: Christoph Hellwig Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 10 +++--- fs/btrfs/file.c | 5 ++- fs/btrfs/ordered-data.c | 93 +++---------------------------------------------- fs/btrfs/ordered-data.h | 4 --- 4 files changed, 10 insertions(+), 102 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index d20dc05208fe..af0435f79fa6 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -822,16 +822,14 @@ struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root, int btrfs_write_tree_block(struct extent_buffer *buf) { - return btrfs_fdatawrite_range(buf->first_page->mapping, buf->start, - buf->start + buf->len - 1, WB_SYNC_ALL); + return filemap_fdatawrite_range(buf->first_page->mapping, buf->start, + buf->start + buf->len - 1); } int btrfs_wait_tree_block_writeback(struct extent_buffer *buf) { - return btrfs_wait_on_page_writeback_range(buf->first_page->mapping, - buf->start >> PAGE_CACHE_SHIFT, - (buf->start + buf->len - 1) >> - PAGE_CACHE_SHIFT); + return filemap_fdatawait_range(buf->first_page->mapping, + buf->start, buf->start + buf->len - 1); } struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 7351bdbca26f..ca784a7fbeba 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1022,9 +1022,8 @@ static ssize_t btrfs_file_write(struct file *file, const char __user *buf, } if (will_write) { - btrfs_fdatawrite_range(inode->i_mapping, pos, - pos + write_bytes - 1, - WB_SYNC_ALL); + filemap_fdatawrite_range(inode->i_mapping, pos, + pos + write_bytes - 1); } else { balance_dirty_pages_ratelimited_nr(inode->i_mapping, num_pages); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index b5d6d24726b0..897fba835f89 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -458,7 +458,7 @@ void btrfs_start_ordered_extent(struct inode *inode, * start IO on any dirty ones so the wait doesn't stall waiting * for pdflush to find them */ - btrfs_fdatawrite_range(inode->i_mapping, start, end, WB_SYNC_ALL); + filemap_fdatawrite_range(inode->i_mapping, start, end); if (wait) { wait_event(entry->wait, test_bit(BTRFS_ORDERED_COMPLETE, &entry->flags)); @@ -488,17 +488,15 @@ again: /* start IO across the range first to instantiate any delalloc * extents */ - btrfs_fdatawrite_range(inode->i_mapping, start, orig_end, WB_SYNC_ALL); + filemap_fdatawrite_range(inode->i_mapping, start, orig_end); /* The compression code will leave pages locked but return from * writepage without setting the page writeback. Starting again * with WB_SYNC_ALL will end up waiting for the IO to actually start. */ - btrfs_fdatawrite_range(inode->i_mapping, start, orig_end, WB_SYNC_ALL); + filemap_fdatawrite_range(inode->i_mapping, start, orig_end); - btrfs_wait_on_page_writeback_range(inode->i_mapping, - start >> PAGE_CACHE_SHIFT, - orig_end >> PAGE_CACHE_SHIFT); + filemap_fdatawait_range(inode->i_mapping, start, orig_end); end = orig_end; found = 0; @@ -716,89 +714,6 @@ out: } -/** - * taken from mm/filemap.c because it isn't exported - * - * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range - * @mapping: address space structure to write - * @start: offset in bytes where the range starts - * @end: offset in bytes where the range ends (inclusive) - * @sync_mode: enable synchronous operation - * - * Start writeback against all of a mapping's dirty pages that lie - * within the byte offsets inclusive. - * - * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as - * opposed to a regular memory cleansing writeback. The difference between - * these two operations is that if a dirty page/buffer is encountered, it must - * be waited upon, and not just skipped over. - */ -int btrfs_fdatawrite_range(struct address_space *mapping, loff_t start, - loff_t end, int sync_mode) -{ - struct writeback_control wbc = { - .sync_mode = sync_mode, - .nr_to_write = mapping->nrpages * 2, - .range_start = start, - .range_end = end, - }; - return btrfs_writepages(mapping, &wbc); -} - -/** - * taken from mm/filemap.c because it isn't exported - * - * wait_on_page_writeback_range - wait for writeback to complete - * @mapping: target address_space - * @start: beginning page index - * @end: ending page index - * - * Wait for writeback to complete against pages indexed by start->end - * inclusive - */ -int btrfs_wait_on_page_writeback_range(struct address_space *mapping, - pgoff_t start, pgoff_t end) -{ - struct pagevec pvec; - int nr_pages; - int ret = 0; - pgoff_t index; - - if (end < start) - return 0; - - pagevec_init(&pvec, 0); - index = start; - while ((index <= end) && - (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, - PAGECACHE_TAG_WRITEBACK, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) { - unsigned i; - - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; - - /* until radix tree lookup accepts end_index */ - if (page->index > end) - continue; - - wait_on_page_writeback(page); - if (PageError(page)) - ret = -EIO; - } - pagevec_release(&pvec); - cond_resched(); - } - - /* Check for outstanding write errors */ - if (test_and_clear_bit(AS_ENOSPC, &mapping->flags)) - ret = -ENOSPC; - if (test_and_clear_bit(AS_EIO, &mapping->flags)) - ret = -EIO; - - return ret; -} - /* * add a given inode to the list of inodes that must be fully on * disk before a transaction commit finishes. diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 993a7ea45c70..f82e87488ca8 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -153,10 +153,6 @@ btrfs_lookup_first_ordered_extent(struct inode * inode, u64 file_offset); int btrfs_ordered_update_i_size(struct inode *inode, struct btrfs_ordered_extent *ordered); int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, u32 *sum); -int btrfs_wait_on_page_writeback_range(struct address_space *mapping, - pgoff_t start, pgoff_t end); -int btrfs_fdatawrite_range(struct address_space *mapping, loff_t start, - loff_t end, int sync_mode); int btrfs_wait_ordered_extents(struct btrfs_root *root, int nocow_only); int btrfs_run_ordered_operations(struct btrfs_root *root, int wait); int btrfs_add_ordered_operation(struct btrfs_trans_handle *trans, -- cgit v1.2.3