aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext4/balloc.c
diff options
context:
space:
mode:
authorAndrew Morton <akpm@linux-foundation.org>2008-12-09 13:14:14 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2008-12-10 08:01:52 -0800
commit02d211688727ad02bb4555b1aa8ae2de16b21b39 (patch)
tree2ee10b2f0cbfb615c40a2df98627426b8543d6cd /fs/ext4/balloc.c
parent71c5576fbd809f2015f4eddf72e501e298720cf3 (diff)
downloadkernel_samsung_smdk4412-02d211688727ad02bb4555b1aa8ae2de16b21b39.zip
kernel_samsung_smdk4412-02d211688727ad02bb4555b1aa8ae2de16b21b39.tar.gz
kernel_samsung_smdk4412-02d211688727ad02bb4555b1aa8ae2de16b21b39.tar.bz2
revert "percpu_counter: new function percpu_counter_sum_and_set"
Revert commit e8ced39d5e8911c662d4d69a342b9d053eaaac4e Author: Mingming Cao <cmm@us.ibm.com> Date: Fri Jul 11 19:27:31 2008 -0400 percpu_counter: new function percpu_counter_sum_and_set As described in revert "percpu counter: clean up percpu_counter_sum_and_set()" the new percpu_counter_sum_and_set() is racy against updates to the cpu-local accumulators on other CPUs. Revert that change. This means that ext4 will be slow again. But correct. Reported-by: Eric Dumazet <dada1@cosmosbay.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mingming Cao <cmm@us.ibm.com> Cc: <linux-ext4@vger.kernel.org> Cc: <stable@kernel.org> [2.6.27.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/ext4/balloc.c')
-rw-r--r--fs/ext4/balloc.c4
1 files changed, 2 insertions, 2 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index c17f69b..db35cfd 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -609,8 +609,8 @@ int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
EXT4_FREEBLOCKS_WATERMARK) {
- free_blocks = percpu_counter_sum_and_set(fbc);
- dirty_blocks = percpu_counter_sum_and_set(dbc);
+ free_blocks = percpu_counter_sum_positive(fbc);
+ dirty_blocks = percpu_counter_sum_positive(dbc);
if (dirty_blocks < 0) {
printk(KERN_CRIT "Dirty block accounting "
"went wrong %lld\n",