From cbc0e9287d710ce7dce5f8daf667729e83316c45 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 25 Feb 2014 14:15:12 +0000 Subject: Btrfs: remove unneeded field / smaller extent_map structure We don't need to have an unsigned int field in the extent_map struct to tell us whether the extent map is in the inode's extent_map tree or not. We can use the rb_node struct field and the RB_CLEAR_NODE and RB_EMPTY_NODE macros to achieve the same task. This reduces sizeof(struct extent_map) from 152 bytes to 144 bytes (on a 64 bits system). Signed-off-by: Filipe David Borba Manana Reviewed-by: David Sterba Signed-off-by: Josef Bacik --- fs/btrfs/extent_map.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) (limited to 'fs/btrfs/extent_map.c') diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 996ad56b57db..64d08f94485d 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -51,7 +51,7 @@ struct extent_map *alloc_extent_map(void) em = kmem_cache_zalloc(extent_map_cache, GFP_NOFS); if (!em) return NULL; - em->in_tree = 0; + RB_CLEAR_NODE(&em->rb_node); em->flags = 0; em->compress_type = BTRFS_COMPRESS_NONE; em->generation = 0; @@ -73,7 +73,7 @@ void free_extent_map(struct extent_map *em) return; WARN_ON(atomic_read(&em->refs) == 0); if (atomic_dec_and_test(&em->refs)) { - WARN_ON(em->in_tree); + WARN_ON(extent_map_in_tree(em)); WARN_ON(!list_empty(&em->list)); kmem_cache_free(extent_map_cache, em); } @@ -99,8 +99,6 @@ static int tree_insert(struct rb_root *root, struct extent_map *em) parent = *p; entry = rb_entry(parent, struct extent_map, rb_node); - WARN_ON(!entry->in_tree); - if (em->start < entry->start) p = &(*p)->rb_left; else if (em->start >= extent_map_end(entry)) @@ -128,7 +126,6 @@ static int tree_insert(struct rb_root *root, struct extent_map *em) if (end > entry->start && em->start < extent_map_end(entry)) return -EEXIST; - em->in_tree = 1; rb_link_node(&em->rb_node, orig_parent, p); rb_insert_color(&em->rb_node, root); return 0; @@ -153,8 +150,6 @@ static struct rb_node *__tree_search(struct rb_root *root, u64 offset, prev = n; prev_entry = entry; - WARN_ON(!entry->in_tree); - if (offset < entry->start) n = n->rb_left; else if (offset >= extent_map_end(entry)) @@ -240,12 +235,12 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) em->len += merge->len; em->block_len += merge->block_len; em->block_start = merge->block_start; - merge->in_tree = 0; em->mod_len = (em->mod_len + em->mod_start) - merge->mod_start; em->mod_start = merge->mod_start; em->generation = max(em->generation, merge->generation); rb_erase(&merge->rb_node, &tree->map); + RB_CLEAR_NODE(&merge->rb_node); free_extent_map(merge); } } @@ -257,7 +252,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) em->len += merge->len; em->block_len += merge->block_len; rb_erase(&merge->rb_node, &tree->map); - merge->in_tree = 0; + RB_CLEAR_NODE(&merge->rb_node); em->mod_len = (merge->mod_start + merge->mod_len) - em->mod_start; em->generation = max(em->generation, merge->generation); free_extent_map(merge); @@ -319,7 +314,7 @@ out: void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em) { clear_bit(EXTENT_FLAG_LOGGING, &em->flags); - if (em->in_tree) + if (extent_map_in_tree(em)) try_merge_map(tree, em); } @@ -434,6 +429,6 @@ int remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em) rb_erase(&em->rb_node, &tree->map); if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags)) list_del_init(&em->list); - em->in_tree = 0; + RB_CLEAR_NODE(&em->rb_node); return ret; } -- cgit From 176840b3aa3cb795ddec4fc665ffbd707abff906 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 25 Feb 2014 14:15:13 +0000 Subject: Btrfs: more efficient btrfs_drop_extent_cache While droping extent map structures from the extent cache that cover our target range, we would remove each extent map structure from the red black tree and then add either 1 or 2 new extent map structures if the former extent map covered sections outside our target range. This change simply attempts to replace the existing extent map structure with a new one that covers the subsection we're not interested in, instead of doing a red black remove operation followed by an insertion operation. The number of elements in an inode's extent map tree can get very high for large files under random writes. For example, while running the following test: sysbench --test=fileio --file-num=1 --file-total-size=10G \ --file-test-mode=rndrw --num-threads=32 --file-block-size=32768 \ --max-requests=500000 --file-rw-ratio=2 [prepare|run] I captured the following histogram capturing the number of extent_map items in the red black tree while that test was running: Count: 122462 Range: 1.000 - 172231.000; Mean: 96415.831; Median: 101855.000; Stddev: 49700.981 Percentiles: 90th: 160120.000; 95th: 166335.000; 99th: 171070.000 1.000 - 5.231: 452 | 5.231 - 187.392: 87 | 187.392 - 585.911: 206 | 585.911 - 1827.438: 623 | 1827.438 - 5695.245: 1962 # 5695.245 - 17744.861: 6204 #### 17744.861 - 55283.764: 21115 ############ 55283.764 - 172231.000: 91813 ##################################################### Benchmark: sysbench --test=fileio --file-num=1 --file-total-size=10G --file-test-mode=rndwr \ --num-threads=64 --file-block-size=32768 --max-requests=0 --max-time=60 \ --file-io-mode=sync --file-fsync-freq=0 [prepare|run] Before this change: 122.1Mb/sec After this change: 125.07Mb/sec (averages of 5 test runs) Test machine: quad core intel i5-3570K, 32Gb of ram, SSD Signed-off-by: Filipe David Borba Manana Signed-off-by: Josef Bacik --- fs/btrfs/extent_map.c | 39 ++++++++++++++++++++++++++++++--------- fs/btrfs/extent_map.h | 4 ++++ fs/btrfs/file.c | 16 +++++++++++----- 3 files changed, 45 insertions(+), 14 deletions(-) (limited to 'fs/btrfs/extent_map.c') diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 64d08f94485d..1874aee69c86 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -318,6 +318,20 @@ void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em) try_merge_map(tree, em); } +static inline void setup_extent_mapping(struct extent_map_tree *tree, + struct extent_map *em, + int modified) +{ + atomic_inc(&em->refs); + em->mod_start = em->start; + em->mod_len = em->len; + + if (modified) + list_move(&em->list, &tree->modified_extents); + else + try_merge_map(tree, em); +} + /** * add_extent_mapping - add new extent map to the extent tree * @tree: tree to insert new map in @@ -337,15 +351,7 @@ int add_extent_mapping(struct extent_map_tree *tree, if (ret) goto out; - atomic_inc(&em->refs); - - em->mod_start = em->start; - em->mod_len = em->len; - - if (modified) - list_move(&em->list, &tree->modified_extents); - else - try_merge_map(tree, em); + setup_extent_mapping(tree, em, modified); out: return ret; } @@ -432,3 +438,18 @@ int remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em) RB_CLEAR_NODE(&em->rb_node); return ret; } + +void replace_extent_mapping(struct extent_map_tree *tree, + struct extent_map *cur, + struct extent_map *new, + int modified) +{ + WARN_ON(test_bit(EXTENT_FLAG_PINNED, &cur->flags)); + ASSERT(extent_map_in_tree(cur)); + if (!test_bit(EXTENT_FLAG_LOGGING, &cur->flags)) + list_del_init(&cur->list); + rb_replace_node(&cur->rb_node, &new->rb_node, &tree->map); + RB_CLEAR_NODE(&cur->rb_node); + + setup_extent_mapping(tree, new, modified); +} diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h index f0a645a14d6e..e7fd8a56a140 100644 --- a/fs/btrfs/extent_map.h +++ b/fs/btrfs/extent_map.h @@ -68,6 +68,10 @@ struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree, int add_extent_mapping(struct extent_map_tree *tree, struct extent_map *em, int modified); int remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em); +void replace_extent_mapping(struct extent_map_tree *tree, + struct extent_map *cur, + struct extent_map *new, + int modified); struct extent_map *alloc_extent_map(void); void free_extent_map(struct extent_map *em); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 762ca32bd988..31e48b947060 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -591,7 +591,6 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, clear_bit(EXTENT_FLAG_PINNED, &em->flags); clear_bit(EXTENT_FLAG_LOGGING, &flags); modified = !list_empty(&em->list); - remove_extent_mapping(em_tree, em); if (no_splits) goto next; @@ -622,8 +621,7 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, split->bdev = em->bdev; split->flags = flags; split->compress_type = em->compress_type; - ret = add_extent_mapping(em_tree, split, modified); - BUG_ON(ret); /* Logic error */ + replace_extent_mapping(em_tree, em, split, modified); free_extent_map(split); split = split2; split2 = NULL; @@ -661,12 +659,20 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, split->orig_block_len = 0; } - ret = add_extent_mapping(em_tree, split, modified); - BUG_ON(ret); /* Logic error */ + if (extent_map_in_tree(em)) { + replace_extent_mapping(em_tree, em, split, + modified); + } else { + ret = add_extent_mapping(em_tree, split, + modified); + ASSERT(ret == 0); /* Logic error */ + } free_extent_map(split); split = NULL; } next: + if (extent_map_in_tree(em)) + remove_extent_mapping(em_tree, em); write_unlock(&em_tree->lock); /* once for us */ -- cgit