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/disk-io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f1e905f7e701..ece8d1e26b5e 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1629,7 +1629,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, fs_info->sb = sb; fs_info->max_extent = (u64)-1; fs_info->max_inline = 8192 * 1024; - fs_info->metadata_ratio = 8; + fs_info->metadata_ratio = 0; fs_info->thread_pool_size = min_t(unsigned long, num_online_cpus() + 2, 8); -- cgit v1.2.2 From 35d62a942db5ae03104929fe7397835b572c4bc4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 16:47:08 -0400 Subject: Btrfs: fix arguments to btrfs_wait_on_page_writeback_range wait_on_page_writeback_range/btrfs_wait_on_page_writeback_range takes a pagecache offset, not a byte offset into the file. Shift the arguments around to wait for the correct range Signed-off-by: Christoph Hellwig Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index ece8d1e26b5e..69dce50aabd2 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -829,7 +829,9 @@ int btrfs_write_tree_block(struct extent_buffer *buf) int btrfs_wait_tree_block_writeback(struct extent_buffer *buf) { return btrfs_wait_on_page_writeback_range(buf->first_page->mapping, - buf->start, buf->start + buf->len - 1); + buf->start >> PAGE_CACHE_SHIFT, + (buf->start + buf->len - 1) >> + PAGE_CACHE_SHIFT); } struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr, -- cgit v1.2.2 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 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'fs/btrfs/disk-io.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, -- cgit v1.2.2 From 61d92c328c16419fc96dc50dd16f8b8c695409ec Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Fri, 2 Oct 2009 19:11:56 -0400 Subject: Btrfs: fix deadlock on async thread startup The btrfs async worker threads are used for a wide variety of things, including processing bio end_io functions. This means that when the endio threads aren't running, the rest of the FS isn't able to do the final processing required to clear PageWriteback. The endio threads also try to exit as they become idle and start more as the work piles up. The problem is that starting more threads means kthreadd may need to allocate ram, and that allocation may wait until the global number of writeback pages on the system is below a certain limit. The result of that throttling is that end IO threads wait on kthreadd, who is waiting on IO to end, which will never happen. This commit fixes the deadlock by handing off thread startup to a dedicated thread. It also fixes a bug where the on-demand thread creation was creating far too many threads because it didn't take into account threads being started by other procs. Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 42 +++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 69dce50aabd2..9903f042765d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1746,21 +1746,22 @@ struct btrfs_root *open_ctree(struct super_block *sb, err = -EINVAL; goto fail_iput; } -printk("thread pool is %d\n", fs_info->thread_pool_size); - /* - * we need to start all the end_io workers up front because the - * queue work function gets called at interrupt time, and so it - * cannot dynamically grow. - */ + + btrfs_init_workers(&fs_info->generic_worker, + "genwork", 1, NULL); + btrfs_init_workers(&fs_info->workers, "worker", - fs_info->thread_pool_size); + fs_info->thread_pool_size, + &fs_info->generic_worker); btrfs_init_workers(&fs_info->delalloc_workers, "delalloc", - fs_info->thread_pool_size); + fs_info->thread_pool_size, + &fs_info->generic_worker); btrfs_init_workers(&fs_info->submit_workers, "submit", min_t(u64, fs_devices->num_devices, - fs_info->thread_pool_size)); + fs_info->thread_pool_size), + &fs_info->generic_worker); /* a higher idle thresh on the submit workers makes it much more * likely that bios will be send down in a sane order to the @@ -1774,15 +1775,20 @@ printk("thread pool is %d\n", fs_info->thread_pool_size); fs_info->delalloc_workers.idle_thresh = 2; fs_info->delalloc_workers.ordered = 1; - btrfs_init_workers(&fs_info->fixup_workers, "fixup", 1); + btrfs_init_workers(&fs_info->fixup_workers, "fixup", 1, + &fs_info->generic_worker); btrfs_init_workers(&fs_info->endio_workers, "endio", - fs_info->thread_pool_size); + fs_info->thread_pool_size, + &fs_info->generic_worker); btrfs_init_workers(&fs_info->endio_meta_workers, "endio-meta", - fs_info->thread_pool_size); + fs_info->thread_pool_size, + &fs_info->generic_worker); btrfs_init_workers(&fs_info->endio_meta_write_workers, - "endio-meta-write", fs_info->thread_pool_size); + "endio-meta-write", fs_info->thread_pool_size, + &fs_info->generic_worker); btrfs_init_workers(&fs_info->endio_write_workers, "endio-write", - fs_info->thread_pool_size); + fs_info->thread_pool_size, + &fs_info->generic_worker); /* * endios are largely parallel and should have a very @@ -1794,12 +1800,8 @@ printk("thread pool is %d\n", fs_info->thread_pool_size); fs_info->endio_write_workers.idle_thresh = 2; fs_info->endio_meta_write_workers.idle_thresh = 2; - fs_info->endio_workers.atomic_worker_start = 1; - fs_info->endio_meta_workers.atomic_worker_start = 1; - fs_info->endio_write_workers.atomic_worker_start = 1; - fs_info->endio_meta_write_workers.atomic_worker_start = 1; - btrfs_start_workers(&fs_info->workers, 1); + btrfs_start_workers(&fs_info->generic_worker, 1); btrfs_start_workers(&fs_info->submit_workers, 1); btrfs_start_workers(&fs_info->delalloc_workers, 1); btrfs_start_workers(&fs_info->fixup_workers, 1); @@ -2012,6 +2014,7 @@ fail_chunk_root: free_extent_buffer(chunk_root->node); free_extent_buffer(chunk_root->commit_root); fail_sb_buffer: + btrfs_stop_workers(&fs_info->generic_worker); btrfs_stop_workers(&fs_info->fixup_workers); btrfs_stop_workers(&fs_info->delalloc_workers); btrfs_stop_workers(&fs_info->workers); @@ -2437,6 +2440,7 @@ int close_ctree(struct btrfs_root *root) iput(fs_info->btree_inode); + btrfs_stop_workers(&fs_info->generic_worker); btrfs_stop_workers(&fs_info->fixup_workers); btrfs_stop_workers(&fs_info->delalloc_workers); btrfs_stop_workers(&fs_info->workers); -- cgit v1.2.2 From e3ccfa989752c083ceb23c823a84f7ce3a081e61 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 7 Oct 2009 20:44:34 -0400 Subject: Btrfs: async delalloc flushing under space pressure This patch moves the delalloc flushing that occurs when we are under space pressure off to a async thread pool. This helps since we only free up metadata space when we actually insert the extent item, which means it takes quite a while for space to be free'ed up if we wait on all ordered extents. However, if space is freed up due to inline extents being inserted, we can wake people who are waiting up early, and they can finish their work. Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9903f042765d..ac8927bdc33d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1762,6 +1762,9 @@ struct btrfs_root *open_ctree(struct super_block *sb, min_t(u64, fs_devices->num_devices, fs_info->thread_pool_size), &fs_info->generic_worker); + btrfs_init_workers(&fs_info->enospc_workers, "enospc", + fs_info->thread_pool_size, + &fs_info->generic_worker); /* a higher idle thresh on the submit workers makes it much more * likely that bios will be send down in a sane order to the @@ -1809,6 +1812,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, btrfs_start_workers(&fs_info->endio_meta_workers, 1); btrfs_start_workers(&fs_info->endio_meta_write_workers, 1); btrfs_start_workers(&fs_info->endio_write_workers, 1); + btrfs_start_workers(&fs_info->enospc_workers, 1); fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super); fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages, @@ -2023,6 +2027,7 @@ fail_sb_buffer: btrfs_stop_workers(&fs_info->endio_meta_write_workers); btrfs_stop_workers(&fs_info->endio_write_workers); btrfs_stop_workers(&fs_info->submit_workers); + btrfs_stop_workers(&fs_info->enospc_workers); fail_iput: invalidate_inode_pages2(fs_info->btree_inode->i_mapping); iput(fs_info->btree_inode); @@ -2449,6 +2454,7 @@ int close_ctree(struct btrfs_root *root) btrfs_stop_workers(&fs_info->endio_meta_write_workers); btrfs_stop_workers(&fs_info->endio_write_workers); btrfs_stop_workers(&fs_info->submit_workers); + btrfs_stop_workers(&fs_info->enospc_workers); btrfs_close_devices(fs_info->fs_devices); btrfs_mapping_tree_free(&fs_info->mapping_tree); -- cgit v1.2.2