summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-11-01 00:06:40 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2015-11-01 00:14:51 +0100
commitfc90888d07b8e17eec49c04bdb26344fdea96c3b (patch)
treebc5dd1d51b64c378cfed016eefa3046f860fa8c0 /fs
parentvfs: Fix pathological performance case for __alloc_fd() (diff)
downloadlinux-fc90888d07b8e17eec49c04bdb26344fdea96c3b.tar.xz
linux-fc90888d07b8e17eec49c04bdb26344fdea96c3b.zip
vfs: conditionally clear close-on-exec flag
We clear the close-on-exec flag when opening and closing files, and the bit was almost always already clear before. Avoid dirtying the cacheline if the clearning isn't necessary. That avoids unnecessary cacheline dirtying and bouncing in multi-socket environments. Eric Dumazet has a file descriptor benchmark that goes 4% faster from this on his two-socket machine. It's probably partly superlinear improvement due to getting slightly less spinlock contention on the file_lock spinlock due to less work in the critical section. Tested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs')
-rw-r--r--fs/file.c3
1 files changed, 2 insertions, 1 deletions
diff --git a/fs/file.c b/fs/file.c
index 6f6eb2b03af5..c6986dce0334 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -236,7 +236,8 @@ static inline void __set_close_on_exec(int fd, struct fdtable *fdt)
static inline void __clear_close_on_exec(int fd, struct fdtable *fdt)
{
- __clear_bit(fd, fdt->close_on_exec);
+ if (test_bit(fd, fdt->close_on_exec))
+ __clear_bit(fd, fdt->close_on_exec);
}
static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt)