On 08/30/2013 04:26 PM, Al Viro wrote:
On Fri, Aug 30, 2013 at 03:52:49PM -0400, Waiman Long wrote:
So it is the mnput_no_expire() function that is doing all the
lg_global_lock() calls.
Interesting... So you are getting a lot of mntput() with ->mnt_ns being
NULL? I wonder which type it is... Note that anything mounted will
have non-NULL ->mnt_ns until umount and anything obtained via
kern_mount/kern_mount_data will also have a non-NULL ->mnt_ns - until
kern_unmount().
Could you try to gather stats of that sort? Normally that path should
be only hit by fput() when we have a lazy-unmounted fs and close an opened
file on it...
I see one potential stupidity in that area (simple_pin_fs() ought to set
->mnt_ns, with simple_release_fs() clearing it), but there's not a lot
of fs types that would use the damn thing...
The AIM7 test was run on a set of 16 ramdisk formated with ext3
filesystem with the following mount options:
barrier=0,async,noatime,nodiratime. Maybe that is a factor.
Regards,
Longman
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
