Re: [PATCH RFC] mnt: umount mounts one by one in umount_tree()

2017-06-14 Thread Eric W. Biederman
Ian Kent writes: > On Fri, 2017-05-12 at 00:08 -0700, Andrei Vagin wrote: >> With this patch, we don't try to umount all mounts of a tree together. >> Instead of this we umount them one by one. In this case, we see a significant >> improvement in performance for the worsе case.

Re: [PATCH RFC] mnt: umount mounts one by one in umount_tree()

2017-06-14 Thread Eric W. Biederman
Ian Kent writes: > On Fri, 2017-05-12 at 00:08 -0700, Andrei Vagin wrote: >> With this patch, we don't try to umount all mounts of a tree together. >> Instead of this we umount them one by one. In this case, we see a significant >> improvement in performance for the worsе case. > > Indeed,

Re: [PATCH RFC] mnt: umount mounts one by one in umount_tree()

2017-06-13 Thread Ian Kent
On Fri, 2017-05-12 at 00:08 -0700, Andrei Vagin wrote: > With this patch, we don't try to umount all mounts of a tree together. > Instead of this we umount them one by one. In this case, we see a significant > improvement in performance for the worsе case. Indeed, umount has been very slow for a

Re: [PATCH RFC] mnt: umount mounts one by one in umount_tree()

2017-06-13 Thread Ian Kent
On Fri, 2017-05-12 at 00:08 -0700, Andrei Vagin wrote: > With this patch, we don't try to umount all mounts of a tree together. > Instead of this we umount them one by one. In this case, we see a significant > improvement in performance for the worsе case. Indeed, umount has been very slow for a

[PATCH RFC] mnt: umount mounts one by one in umount_tree()

2017-05-12 Thread Andrei Vagin
With this patch, we don't try to umount all mounts of a tree together. Instead of this we umount them one by one. In this case, we see a significant improvement in performance for the worsе case. The reason of this optimization is that umount() can hold namespace_sem for a long time, this

[PATCH RFC] mnt: umount mounts one by one in umount_tree()

2017-05-12 Thread Andrei Vagin
With this patch, we don't try to umount all mounts of a tree together. Instead of this we umount them one by one. In this case, we see a significant improvement in performance for the worsе case. The reason of this optimization is that umount() can hold namespace_sem for a long time, this