Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933514AbcKMJLq (ORCPT ); Sun, 13 Nov 2016 04:11:46 -0500 Received: from mail-wm0-f66.google.com ([74.125.82.66]:36822 "EHLO mail-wm0-f66.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932857AbcKMJLl (ORCPT ); Sun, 13 Nov 2016 04:11:41 -0500 MIME-Version: 1.0 In-Reply-To: References: <1477380887-21333-1-git-send-email-mszeredi@redhat.com> <1477380887-21333-4-git-send-email-mszeredi@redhat.com> <20161025115748.ydhkkp5cfcdnjzwn@home.ouaza.com> From: Amir Goldstein Date: Sun, 13 Nov 2016 11:11:37 +0200 Message-ID: Subject: Re: [PATCH 3/3] ovl: redirect on rename-dir To: Miklos Szeredi Cc: Konstantin Khlebnikov , Raphael Hertzog , Miklos Szeredi , "linux-unionfs@vger.kernel.org" , Guillem Jover , linux-fsdevel , Linux Kernel Mailing List Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2608 Lines: 58 On Fri, Nov 11, 2016 at 2:42 PM, Amir Goldstein wrote: > On Fri, Nov 11, 2016 at 12:06 PM, Miklos Szeredi wrote: >> On Fri, Nov 11, 2016 at 10:46 AM, Konstantin Khlebnikov >> wrote: >>> On Fri, Nov 11, 2016 at 1:56 AM, Amir Goldstein wrote: >>>> On Mon, Nov 7, 2016 at 3:38 PM, Amir Goldstein wrote: >>>>> On Mon, Nov 7, 2016 at 12:08 PM, Konstantin Khlebnikov wrote: >>>>>> On Mon, Nov 7, 2016 at 1:04 PM, Miklos Szeredi wrote: >>>>>>> On Mon, Nov 7, 2016 at 10:58 AM, Konstantin Khlebnikov wrote: >>>>>>> >>>>>>>> I've stumbled on somehow related problem - concurrent copy-ups are >>>>>>>> strictly serialized by rename locks. >>>>>>>> Obviously, file copying could be done in parallel: locks are required >>>>>>>> only for final rename. >>>>>>>> Because of that overlay slower that aufs for some workloads. >>>>>>> >>>>>>> Easy to fix: for each copy up create a separate subdir of "work". >>>>>>> Then the contention is only for the time of creating the subdir, which >>>>>>> is very short. >>>>>> >>>>>> Yeah, but lock_rename() also takes per-sb s_vfs_rename_mutex (kludge by Al Viro) >>>>>> I think proper synchronization for concurrent copy-up (for example >>>>>> round flag on ovl_entry) and locking rename only for rename could be >>>>>> better. >>>>> >>>>> Removing s_vfs_rename_mutex from copy-up path is something I have been >>>>> pondering about. >>>>> Assuming that I understand Al's comment above vfs_rename() correctly, >>>>> the sole purpose of per-sb serialization is to prevent loop creations. >>>>> However, how can one create a loop by moving a non-directory? >>>>> So it looks like at least for the non-dir copy up case, a much finer grained >>>>> lock is in order. >>>>> >>>> >>>> >>>> I posted patches to relax the s_vfs_rename_mutex for copy-up and >>>> whiteout in some use cases. >>>> >>>> Konstantin, >>>> >>>> It would be useful to know if those patches help with your use case. >>>> >>> >>> Well.. I think relaxing only s_vfs_rename_mutex wouldn't help much here. >>> Copying is still serialized by i_mutex on workdir? >>> Data copying should be done without rename locks at all. >> >> We do need something to prevent multiple copy-ups starting up in >> parallel on the same file, though. >> > > I guess an inode_lock on the copy-up victim should suffice? Just to follow up on this hijacked thread. I posted patches to lock the overlay inode of copied up file and relaxed the lock_rename during data copy up. Amir.