Btrfs: batch the extent state operation in the end io handle of the read page

Before applying this patch, we set the uptodate flag and unlock the extent
by the page size, it is unnecessary, we can do it in batches, it can reduce
the lock contention of the extent state tree.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6fbacfabb6602d588f20029edc5ed58bb162d7a8..0a77b48c93e5061ce9672a2235113791e0b46c51 100644 (file)
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -762,15 +762,6 @@ static void cache_state(struct extent_state *state,
        }
 }
 
-static void uncache_state(struct extent_state **cached_ptr)
-{
-       if (cached_ptr && (*cached_ptr)) {
-               struct extent_state *state = *cached_ptr;
-               *cached_ptr = NULL;
-               free_extent_state(state);
-       }
-}
-
 /*
  * set some bits on a range in the tree.  This may require allocations or
  * sleeping, so the gfp mask is used to indicate what is allowed.
@@ -2115,7 +2106,8 @@ static int clean_io_failure(u64 start, struct page *page)
                                            EXTENT_LOCKED);
        spin_unlock(&BTRFS_I(inode)->io_tree.lock);
 
-       if (state && state->start == failrec->start) {
+       if (state && state->start <= failrec->start &&
+           state->end >= failrec->start + failrec->len - 1) {
                fs_info = BTRFS_I(inode)->root->fs_info;
                num_copies = btrfs_num_copies(fs_info, failrec->logical,
                                              failrec->len);
@@ -2394,6 +2386,18 @@ static void end_bio_extent_writepage(struct bio *bio, int err)
        bio_put(bio);
 }
 
+static void
+endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len,
+                             int uptodate)
+{
+       struct extent_state *cached = NULL;
+       u64 end = start + len - 1;
+
+       if (uptodate && tree->track_uptodate)
+               set_extent_uptodate(tree, start, end, &cached, GFP_ATOMIC);
+       unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC);
+}
+
 /*
  * after a readpage IO is done, we need to:
  * clear the uptodate bits on error
@@ -2416,6 +2420,8 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
        u64 start;
        u64 end;
        u64 len;
+       u64 extent_start = 0;
+       u64 extent_len = 0;
        int mirror;
        int ret;
 
@@ -2424,8 +2430,6 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 
        do {
                struct page *page = bvec->bv_page;
-               struct extent_state *cached = NULL;
-               struct extent_state *state;
                struct inode *inode = page->mapping->host;
 
                pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
@@ -2451,17 +2455,6 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
                if (++bvec <= bvec_end)
                        prefetchw(&bvec->bv_page->flags);
 
-               spin_lock(&tree->lock);
-               state = find_first_extent_bit_state(tree, start, EXTENT_LOCKED);
-               if (likely(state && state->start == start)) {
-                       /*
-                        * take a reference on the state, unlock will drop
-                        * the ref
-                        */
-                       cache_state(state, &cached);
-               }
-               spin_unlock(&tree->lock);
-
                mirror = io_bio->mirror_num;
                if (likely(uptodate && tree->ops &&
                           tree->ops->readpage_end_io_hook)) {
@@ -2500,18 +2493,11 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
                                        test_bit(BIO_UPTODATE, &bio->bi_flags);
                                if (err)
                                        uptodate = 0;
-                               uncache_state(&cached);
                                continue;
                        }
                }
 readpage_ok:
-               if (uptodate && tree->track_uptodate) {
-                       set_extent_uptodate(tree, start, end, &cached,
-                                           GFP_ATOMIC);
-               }
-               unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC);
-
-               if (uptodate) {
+               if (likely(uptodate)) {
                        loff_t i_size = i_size_read(inode);
                        pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
                        unsigned offset;
@@ -2527,8 +2513,33 @@ readpage_ok:
                }
                unlock_page(page);
                offset += len;
+
+               if (unlikely(!uptodate)) {
+                       if (extent_len) {
+                               endio_readpage_release_extent(tree,
+                                                             extent_start,
+                                                             extent_len, 1);
+                               extent_start = 0;
+                               extent_len = 0;
+                       }
+                       endio_readpage_release_extent(tree, start,
+                                                     end - start + 1, 0);
+               } else if (!extent_len) {
+                       extent_start = start;
+                       extent_len = end + 1 - start;
+               } else if (extent_start + extent_len == start) {
+                       extent_len += end + 1 - start;
+               } else {
+                       endio_readpage_release_extent(tree, extent_start,
+                                                     extent_len, uptodate);
+                       extent_start = start;
+                       extent_len = end + 1 - start;
+               }
        } while (bvec <= bvec_end);
 
+       if (extent_len)
+               endio_readpage_release_extent(tree, extent_start, extent_len,
+                                             uptodate);
        if (io_bio->end_io)
                io_bio->end_io(io_bio, err);
        bio_put(bio);