diff options
| author | Andrew Morton <akpm@linux-foundation.org> | 2008-12-09 13:14:14 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2008-12-10 08:01:52 -0800 |
| commit | 02d211688727ad02bb4555b1aa8ae2de16b21b39 (patch) | |
| tree | 2ee10b2f0cbfb615c40a2df98627426b8543d6cd /fs/ext4 | |
| parent | 71c5576fbd809f2015f4eddf72e501e298720cf3 (diff) | |
| download | kernel_samsung_aries-02d211688727ad02bb4555b1aa8ae2de16b21b39.zip kernel_samsung_aries-02d211688727ad02bb4555b1aa8ae2de16b21b39.tar.gz kernel_samsung_aries-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')
| -rw-r--r-- | fs/ext4/balloc.c | 4 |
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", |