f2fs: reorder nat cache lock in cache_nat_entry

When lookuping nat entry in cache_nat_entry, if we fail to hit nat cache,
we try to load nat entries a) from journal of current segment cache or b)
from NAT pages for updating, during the process, write lock of
nat_tree_lock will be held to avoid inconsistent condition in between
nid cache and nat cache caused by racing among nat entry shrinker,
checkpointer, nat entry updater.

But this way may cause low efficient when updating nat cache, because it
serializes accessing in journal cache or reading NAT pages.

Here, we reorder lock and update flow as below to enhance accessing
concurrency:

 - get_node_info
  - down_read(nat_tree_lock)
  - lookup nat cache --- hit -> unlock & return
  - lookup journal cache --- hit -> unlock & goto update
  - up_read(nat_tree_lock)
update:
  - down_write(nat_tree_lock)
  - cache_nat_entry
   - lookup nat cache --- nohit -> update
  - up_write(nat_tree_lock)

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 94b8016db04eb5b89fa7ec05d253e79084907eab..966176b4027a3b98a11a549ad9f07d06381aba43 100644 (file)
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -257,15 +257,20 @@ static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
        return new;
 }
 
-static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
+static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
                                                struct f2fs_nat_entry *ne)
 {
+       struct f2fs_nm_info *nm_i = NM_I(sbi);
        struct nat_entry *e;
 
        e = __lookup_nat_cache(nm_i, nid);
        if (!e) {
                e = grab_nat_entry(nm_i, nid);
                node_info_from_raw_nat(&e->ni, ne);
+       } else {
+               f2fs_bug_on(sbi, nat_get_ino(e) != ne->ino ||
+                               nat_get_blkaddr(e) != ne->block_addr ||
+                               nat_get_version(e) != ne->version);
        }
 }
 
@@ -371,15 +376,12 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
                ni->ino = nat_get_ino(e);
                ni->blk_addr = nat_get_blkaddr(e);
                ni->version = nat_get_version(e);
-       }
-       up_read(&nm_i->nat_tree_lock);
-       if (e)
+               up_read(&nm_i->nat_tree_lock);
                return;
+       }
 
        memset(&ne, 0, sizeof(struct f2fs_nat_entry));
 
-       down_write(&nm_i->nat_tree_lock);
-
        /* Check current segment summary */
        down_read(&curseg->journal_rwsem);
        i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0);
@@ -398,8 +400,10 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
        node_info_from_raw_nat(ni, &ne);
        f2fs_put_page(page, 1);
 cache:
+       up_read(&nm_i->nat_tree_lock);
        /* cache nat entry */
-       cache_nat_entry(NM_I(sbi), nid, &ne);
+       down_write(&nm_i->nat_tree_lock);
+       cache_nat_entry(sbi, nid, &ne);
        up_write(&nm_i->nat_tree_lock);
 }