From 60d2adbb1e7fee1cb4bc67f70bd0bd8ace7b6c3c Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Fri, 9 Sep 2011 17:34:35 +0800 Subject: [PATCH] Btrfs: fix race between multi-task space allocation and caching space The task may fail to get free space though it is enough when multi-task space allocation and caching space happen at the same time. Task1 Caching Thread Task2 ------------------------------------------------------------------------ find_free_extent The space has not be cached, and start caching thread. And wait for it. cache space, if the space is > 2MB wake up Task1 find_free_extent get all the space that is cached. try to allocate space, but there is no space now. trigger BUG_ON() The message is following: btrfs allocation failed flags 1, wanted 4096 space_info has 1040187392 free, is not full space_info total=1082130432, used=4096, pinned=41938944, reserved=0, may_use=40828928, readonly=0 block group 12582912 has 8388608 bytes, 0 used 8388608 pinned 0 reserved block group has cluster?: no 0 blocks of free space at or bigger than bytes is block group 1103101952 has 1073741824 bytes, 4096 used 33550336 pinned 0 reserved block group has cluster?: no 0 blocks of free space at or bigger than bytes is ------------[ cut here ]------------ kernel BUG at fs/btrfs/inode.c:835! [] __extent_writepage+0x1bf/0x5ce [btrfs] [] ? __set_page_dirty_nobuffers+0xfe/0x108 [] ? wait_current_trans+0x23/0xec [btrfs] [] ? find_get_pages_tag+0x73/0xe2 [] extent_write_cache_pages.clone.0+0x176/0x29a [btrfs] [] extent_writepages+0x3e/0x53 [btrfs] [] ? do_sync_write+0xc6/0x103 [] ? btrfs_submit_direct+0x414/0x414 [btrfs] [] ? fsnotify+0x236/0x266 [] btrfs_writepages+0x22/0x24 [btrfs] [] do_writepages+0x1c/0x25 [] __filemap_fdatawrite_range+0x4e/0x50 [] filemap_write_and_wait_range+0x28/0x51 [] btrfs_sync_file+0x7d/0x198 [btrfs] [] ? fsnotify_modify+0x5d/0x65 [] vfs_fsync_range+0x18/0x21 [] vfs_fsync+0x17/0x19 [] do_fsync+0x29/0x3e [] sys_fsync+0xb/0xf [] system_call_fastpath+0x16/0x1b [SNIP] RIP [] cow_file_range+0x1c4/0x32b [btrfs] We fix this bug by trying to allocate the space again if there are block groups in caching. Signed-off-by: Miao Xie --- fs/btrfs/extent-tree.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 6cfcc90..cef355f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4954,6 +4954,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans, bool failed_cluster_refill = false; bool failed_alloc = false; bool use_cluster = true; + bool have_caching_bg = false; u64 ideal_cache_percent = 0; u64 ideal_cache_offset = 0; @@ -5036,6 +5037,7 @@ ideal_cache: } } search: + have_caching_bg = false; down_read(&space_info->groups_sem); list_for_each_entry(block_group, &space_info->block_groups[index], list) { @@ -5244,6 +5246,8 @@ refill_cluster: failed_alloc = true; goto have_block_group; } else if (!offset) { + if (!cached) + have_caching_bg = true; goto loop; } checks: @@ -5294,6 +5298,9 @@ loop: } up_read(&space_info->groups_sem); + if (!ins->objectid && loop >= LOOP_CACHING_WAIT && have_caching_bg) + goto search; + if (!ins->objectid && ++index < BTRFS_NR_RAID_TYPES) goto search; -- 2.7.4