diff options
author | Chris Mason <chris.mason@oracle.com> | 2008-06-25 20:14:04 (GMT) |
---|---|---|
committer | Chris Mason <chris.mason@oracle.com> | 2008-09-25 15:04:04 (GMT) |
commit | f9efa9c784aa3b801feb367f72c6867d26fb348e (patch) | |
tree | d9f678310c6c8a4daf2003fa4f6b4164111dbbd7 /fs/btrfs/locking.c | |
parent | 3f157a2fd2ad731e1ed9964fecdc5f459f04a4a4 (diff) | |
download | linux-fsl-qoriq-f9efa9c784aa3b801feb367f72c6867d26fb348e.tar.xz |
Btrfs: Reduce contention on the root node
This calls unlock_up sooner in btrfs_search_slot in order to decrease the
amount of work done with the higher level tree locks held.
Also, it changes btrfs_tree_lock to spin for a big against the page lock
before scheduling. This makes a big difference in context switch rate under
highly contended workloads.
Longer term, a better locking structure is needed than the page lock.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Diffstat (limited to 'fs/btrfs/locking.c')
-rw-r--r-- | fs/btrfs/locking.c | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 80813a3..058a506 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -27,6 +27,16 @@ int btrfs_tree_lock(struct extent_buffer *eb) { + int i; + + if (!TestSetPageLocked(eb->first_page)) + return 0; + for (i = 0; i < 512; i++) { + cpu_relax(); + if (!TestSetPageLocked(eb->first_page)) + return 0; + } + cpu_relax(); lock_page(eb->first_page); return 0; } |