diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3cccf0f05666..fd3084feb4b5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2779,10 +2779,11 @@ enum btrfs_flush_state { FLUSH_DELAYED_REFS = 4, FLUSH_DELALLOC = 5, FLUSH_DELALLOC_WAIT = 6, - ALLOC_CHUNK = 7, - ALLOC_CHUNK_FORCE = 8, - RUN_DELAYED_IPUTS = 9, - COMMIT_TRANS = 10, + FLUSH_DELALLOC_FULL = 7, + ALLOC_CHUNK = 8, + ALLOC_CHUNK_FORCE = 9, + RUN_DELAYED_IPUTS = 10, + COMMIT_TRANS = 11, }; int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index fbd492fe87f9..eb90a262563f 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -493,6 +493,11 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, long time_left; int loops; + delalloc_bytes = percpu_counter_sum_positive(&fs_info->delalloc_bytes); + ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes); + if (delalloc_bytes == 0 && ordered_bytes == 0) + return; + /* Calc the number of the pages we need flush for space reservation */ if (to_reclaim == U64_MAX) { items = U64_MAX; @@ -500,22 +505,21 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, /* * to_reclaim is set to however much metadata we need to * reclaim, but reclaiming that much data doesn't really track - * exactly, so increase the amount to reclaim by 2x in order to - * make sure we're flushing enough delalloc to hopefully reclaim - * some metadata reservations. + * exactly. What we really want to do is reclaim full inode's + * worth of reservations, however that's not available to us + * here. We will take a fraction of the delalloc bytes for our + * flushing loops and hope for the best. Delalloc will expand + * the amount we write to cover an entire dirty extent, which + * will reclaim the metadata reservation for that range. If + * it's not enough subsequent flush stages will be more + * aggressive. */ + to_reclaim = max(to_reclaim, delalloc_bytes >> 3); items = calc_reclaim_items_nr(fs_info, to_reclaim) * 2; - to_reclaim = items * EXTENT_SIZE_PER_ITEM; } trans = (struct btrfs_trans_handle *)current->journal_info; - delalloc_bytes = percpu_counter_sum_positive( - &fs_info->delalloc_bytes); - ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes); - if (delalloc_bytes == 0 && ordered_bytes == 0) - return; - /* * If we are doing more ordered than delalloc we need to just wait on * ordered extents, otherwise we'll waste time trying to flush delalloc @@ -595,8 +599,11 @@ static void flush_space(struct btrfs_fs_info *fs_info, break; case FLUSH_DELALLOC: case FLUSH_DELALLOC_WAIT: + case FLUSH_DELALLOC_FULL: + if (state == FLUSH_DELALLOC_FULL) + num_bytes = U64_MAX; shrink_delalloc(fs_info, space_info, num_bytes, - state == FLUSH_DELALLOC_WAIT, for_preempt); + state != FLUSH_DELALLOC, for_preempt); break; case FLUSH_DELAYED_REFS_NR: case FLUSH_DELAYED_REFS: @@ -906,6 +913,14 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) commit_cycles--; } + /* + * We do not want to empty the system of delalloc unless we're + * under heavy pressure, so allow one trip through the flushing + * logic before we start doing a FLUSH_DELALLOC_FULL. + */ + if (flush_state == FLUSH_DELALLOC_FULL && !commit_cycles) + flush_state++; + /* * We don't want to force a chunk allocation until we've tried * pretty hard to reclaim space. Think of the case where we @@ -1069,7 +1084,7 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) * so if we now have space to allocate do the force chunk allocation. */ static const enum btrfs_flush_state data_flush_states[] = { - FLUSH_DELALLOC_WAIT, + FLUSH_DELALLOC_FULL, RUN_DELAYED_IPUTS, COMMIT_TRANS, ALLOC_CHUNK_FORCE, @@ -1158,6 +1173,7 @@ static const enum btrfs_flush_state evict_flush_states[] = { FLUSH_DELAYED_REFS, FLUSH_DELALLOC, FLUSH_DELALLOC_WAIT, + FLUSH_DELALLOC_FULL, ALLOC_CHUNK, COMMIT_TRANS, }; diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index c7d19eadecc5..8f58fd95efc7 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -94,6 +94,7 @@ struct btrfs_space_info; EM( FLUSH_DELAYED_ITEMS, "FLUSH_DELAYED_ITEMS") \ EM( FLUSH_DELALLOC, "FLUSH_DELALLOC") \ EM( FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT") \ + EM( FLUSH_DELALLOC_FULL, "FLUSH_DELALLOC_FULL") \ EM( FLUSH_DELAYED_REFS_NR, "FLUSH_DELAYED_REFS_NR") \ EM( FLUSH_DELAYED_REFS, "FLUSH_ELAYED_REFS") \ EM( ALLOC_CHUNK, "ALLOC_CHUNK") \