Return-Path: Received: from out1-smtp.messagingengine.com ([66.111.4.25]:46113 "EHLO out1-smtp.messagingengine.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751629AbdIUSbS (ORCPT ); Thu, 21 Sep 2017 14:31:18 -0400 From: Nikolaus Rath To: Maxim Patlasov Cc: mszeredi@redhat.com, "fuse-devel\@lists.sourceforge.net" , linux-fsdevel Subject: Re: [fuse-devel] [fuse] getattr() results ignored when writeback cache is active References: <87zi9pk2ra.fsf@vostro.rath.org> <87vakdjsjj.fsf@vostro.rath.org> <87y3p8uzpw.fsf@vostro.rath.org> <11acc9f1-12e5-9806-48ff-de261acae979@virtuozzo.com> <87wp4s9bva.fsf@vostro.rath.org> <97fa18f6-84ab-7723-42a8-84e2bc2d92ed@virtuozzo.com> Date: Thu, 21 Sep 2017 19:31:15 +0100 In-Reply-To: <97fa18f6-84ab-7723-42a8-84e2bc2d92ed@virtuozzo.com> (Maxim Patlasov's message of "Thu, 21 Sep 2017 11:24:59 -0700") Message-ID: <87o9q3aop8.fsf@vostro.rath.org> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Sep 21 2017, Maxim Patlasov wrote: > On 09/21/2017 10:53 AM, Nikolaus Rath wrote: > >> On Sep 21 2017, Maxim Patlasov wrote: >>> On 09/21/2017 03:12 AM, Nikolaus Rath wrote: >>> >>>> On Sep 20 2017, Miklos Szeredi wrote: >>>>> In writeback-cache mode (enabled by the FUSE_WRITEBACK_CACHE flaga) w= rites go to >>>>> the cache only, which means that the write(2) syscall can often compl= ete very >>>>> fast. The dirty pages are later sent to userspace using write reques= ts. This >>>>> mode assumes that the file is never changed outside the mounted files= ystem, so >>>>> it's not suitable for any network fs. >>>> .."this mode of operation is not suitable for any network filesystem >>>> even if no write operations are actually carried out". >>> Not true. A network filesystem can guarantee that the file is never >>> changed outside by implementing exclusive write lease semantics: when >>> someone opens file for writing first time the metadata server grants >>> exclusive rights for that mount, then declines all subsequent open >>> requests from other mounts; and similarly while a file is being kept >>> opened for reading, the metadata server declines all open-for-writing >>> requests from other mounts. >> In practice that doesn't seem to work, see the example in my first >> message. The file is only ever accessed on one mount at a time, yet the >> changes do not propagate (and would result in data corruption if another >> mount would attempt to read or modify the file afterwards). > > In your example you modified file bypassing fuse mount: > >> echo -e "\nrevision 2" >> /tmp/issue_93/file_1 > > That's like mangling block device while ordinary local fs is running > on top of it. Huh? That's exactly what a network filesystem would see when another host writes to the filesystem. The change doesn't come through the local FUSE layer. Best, -Nikolaus --=20 GPG Fingerprint: ED31 791B 2C5C 1613 AF38 8B8A D113 FCAC 3C4E 599F =C2=BBTime flies like an arrow, fruit flies like a Banana.=C2= =AB