diff options
| author | Jens Axboe <axboe@suse.de> | 2006-06-13 08:26:10 +0200 |
|---|---|---|
| committer | Jens Axboe <axboe@nelson.home.kernel.dk> | 2006-06-23 17:10:39 +0200 |
| commit | b31dc66a54ad986b6b73bdc49c8efc17cbad1833 (patch) | |
| tree | 5591383c1cbffe11512da889c971f899333f1a44 /mm | |
| parent | [PATCH] cfq-iosched: Don't set the queue batching limits (diff) | |
| download | linux-b31dc66a54ad986b6b73bdc49c8efc17cbad1833.tar.xz linux-b31dc66a54ad986b6b73bdc49c8efc17cbad1833.zip | |
[PATCH] Kill PF_SYNCWRITE flag
A process flag to indicate whether we are doing sync io is incredibly
ugly. It also causes performance problems when one does a lot of async
io and then proceeds to sync it. Part of the io will go out as async,
and the other part as sync. This causes a disconnect between the
previously submitted io and the synced io. For io schedulers such as CFQ,
this will cause us lost merges and suboptimal behaviour in scheduling.
Remove PF_SYNCWRITE completely from the fsync/msync paths, and let
the O_DIRECT path just directly indicate that the writes are sync
by using WRITE_SYNC instead.
Signed-off-by: Jens Axboe <axboe@suse.de>
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/msync.c | 3 |
1 files changed, 0 insertions, 3 deletions
diff --git a/mm/msync.c b/mm/msync.c index bc6c95376366..d083544df21b 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -170,8 +170,6 @@ asmlinkage long sys_msync(unsigned long start, size_t len, int flags) * just ignore them, but return -ENOMEM at the end. */ down_read(¤t->mm->mmap_sem); - if (flags & MS_SYNC) - current->flags |= PF_SYNCWRITE; vma = find_vma(current->mm, start); if (!vma) { error = -ENOMEM; @@ -228,7 +226,6 @@ asmlinkage long sys_msync(unsigned long start, size_t len, int flags) } } while (vma && !done); out_unlock: - current->flags &= ~PF_SYNCWRITE; up_read(¤t->mm->mmap_sem); out: return error; |