From f9efa9c784aa3b801feb367f72c6867d26fb348e Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Wed, 25 Jun 2008 16:14:04 -0400 Subject: 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 --- fs/btrfs/locking.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'fs/btrfs/locking.c') diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 80813a307b4..058a506a0dd 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; } -- cgit v1.2.3