Message-ID: <c3f166d3-35b6-25cf-6ccb-8650e90a5a17@samba.org>
Date:   Fri, 10 Feb 2023 20:29:57 +0100
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.7.1
Subject: Re: copy on write for splice() from file to pipe?
Content-Language: en-US
To:     Jeremy Allison <jra@samba.org>, Andy Lutomirski <luto@kernel.org>
Cc:     Linus Torvalds <torvalds@linux-foundation.org>,
        Jens Axboe <axboe@kernel.dk>,
        Linux API Mailing List <linux-api@vger.kernel.org>,
        Dave Chinner <david@fromorbit.com>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        Matthew Wilcox <willy@infradead.org>,
        Al Viro <viro@zeniv.linux.org.uk>,
        linux-fsdevel <linux-fsdevel@vger.kernel.org>,
        Samba Technical <samba-technical@lists.samba.org>,
        io-uring <io-uring@vger.kernel.org>
References: <0cfd9f02-dea7-90e2-e932-c8129b6013c7@samba.org>
 <CAHk-=wj8rthcQ9gQbvkMzeFt0iymq+CuOzmidx3Pm29Lg+W0gg@mail.gmail.com>
 <20230210021603.GA2825702@dread.disaster.area>
 <20230210040626.GB2825702@dread.disaster.area>
 <Y+XLuYh+kC+4wTRi@casper.infradead.org>
 <20230210065747.GD2825702@dread.disaster.area>
 <CALCETrWjJisipSJA7tPu+h6B2gs3m+g0yPhZ4z+Atod+WOMkZg@mail.gmail.com>
 <CAHk-=wj66F6CdJUAAjqigXMBy7gHquFMzPNAwKCgkrb2mF6U7w@mail.gmail.com>
 <CALCETrU-9Wcb_zCsVWr24V=uCA0+c6x359UkJBOBgkbq+UHAMA@mail.gmail.com>
 <Y+aKuC1PuvX4STEI@jeremy-acer>
From:   Stefan Metzmacher <metze@samba.org>
In-Reply-To: <Y+aKuC1PuvX4STEI@jeremy-acer>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

Am 10.02.23 um 19:19 schrieb Jeremy Allison:
> On Fri, Feb 10, 2023 at 09:57:20AM -0800, Andy Lutomirski via samba-technical wrote:
>>
>> (And if Samba needs to make sure that future writes don't change the
>> outgoing data even two seconds later when the data has been sent but
>> not acked, then maybe a fancy API could be added to help, or maybe
>> Samba shouldn't be using zero copy IO in the first place!)
> 
> Samba doesn't need any of this. The simplest thing to do is
> to restrict splice-based zero-copy IO to files leased by
> a single client, where exclusive access to changes is controled
> by the client redirector.

Yes, I guess we can use it if the file is read-only (from it's acls),
or when the client has a read lease. And of course we can have an I don't care
option, maybe reusing 'use sendfile = yes' as that has the same problem in
the existing code already.

metze