From 27346eddeb988675259fa1d4547d5e75e527cc8e Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 14 Jul 2021 14:47:21 -0400 Subject: [PATCH] btrfs: wait on async extents when flushing delalloc BugLink: https://bugs.launchpad.net/bugs/1947781 commit e16460707e94c3d4c1b5418cb68b28b8efa903b2 upstream. I've been debugging an early ENOSPC problem in production and finally root caused it to this problem. When we switched to the per-inode in 38d715f494f2 ("btrfs: use btrfs_start_delalloc_roots in shrink_delalloc") I pulled out the async extent handling, because we were doing the correct thing by calling filemap_flush() if we had async extents set. This would properly wait on any async extents by locking the page in the second flush, thus making sure our ordered extents were properly set up. However when I switched us back to page based flushing, I used sync_inode(), which allows us to pass in our own wbc. The problem here is that sync_inode() is smarter than the filemap_* helpers, it tries to avoid calling writepages at all. This means that our second call could skip calling do_writepages altogether, and thus not wait on the pagelock for the async helpers. This means we could come back before any ordered extents were created and then simply continue on in our flushing mechanisms and ENOSPC out when we have plenty of space to use. Fix this by putting back the async pages logic in shrink_delalloc. This allows us to bulk write out everything that we need to, and then we can wait in one place for the async helpers to catch up, and then wait on any ordered extents that are created. Fixes: e076ab2a2ca7 ("btrfs: shrink delalloc pages instead of full inodes") CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Nikolay Borisov Signed-off-by: Josef Bacik Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman Signed-off-by: Kamal Mostafa Signed-off-by: Kelsey Skunberg --- fs/btrfs/inode.c | 4 ---- fs/btrfs/space-info.c | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b169e22db263..45f88d0975c1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9480,10 +9480,6 @@ static int start_delalloc_inodes(struct btrfs_root *root, &work->work); } else { ret = sync_inode(inode, wbc); - if (!ret && - test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, - &BTRFS_I(inode)->runtime_flags)) - ret = sync_inode(inode, wbc); btrfs_add_delayed_iput(inode); if (ret || wbc->nr_to_write <= 0) goto out; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index e8347461c8dd..85d436373e1a 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -533,9 +533,49 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, loops = 0; while ((delalloc_bytes || dio_bytes) && loops < 3) { u64 nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT; + int async_pages; btrfs_start_delalloc_roots(fs_info, nr_pages, true); + /* + * We need to make sure any outstanding async pages are now + * processed before we continue. This is because things like + * sync_inode() try to be smart and skip writing if the inode is + * marked clean. We don't use filemap_fwrite for flushing + * because we want to control how many pages we write out at a + * time, thus this is the only safe way to make sure we've + * waited for outstanding compressed workers to have started + * their jobs and thus have ordered extents set up properly. + * + * This exists because we do not want to wait for each + * individual inode to finish its async work, we simply want to + * start the IO on everybody, and then come back here and wait + * for all of the async work to catch up. Once we're done with + * that we know we'll have ordered extents for everything and we + * can decide if we wait for that or not. + * + * If we choose to replace this in the future, make absolutely + * sure that the proper waiting is being done in the async case, + * as there have been bugs in that area before. + */ + async_pages = atomic_read(&fs_info->async_delalloc_pages); + if (!async_pages) + goto skip_async; + + /* + * We don't want to wait forever, if we wrote less pages in this + * loop than we have outstanding, only wait for that number of + * pages, otherwise we can wait for all async pages to finish + * before continuing. + */ + if (async_pages > nr_pages) + async_pages -= nr_pages; + else + async_pages = 0; + wait_event(fs_info->async_submit_wait, + atomic_read(&fs_info->async_delalloc_pages) <= + async_pages); +skip_async: loops++; if (wait_ordered && !trans) { btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1); -- 2.39.5