提交 1515aef0 编写于 作者: C Chao Yu 提交者: Jaegeuk Kim

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: NChao Yu <chao2.yu@samsung.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>
上级 b7ad7512
......@@ -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);
}
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册