Received-SPF: pass (google.com: domain of linux-ext4-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Mon, 24 Jan 2022 13:23:21 -0500
From:   "Theodore Y. Ts'o" <tytso@mit.edu>
To:     Lyu Tao <tao.lyu@epfl.ch>
Cc:     "linux-ext4@vger.kernel.org" <linux-ext4@vger.kernel.org>
Subject: Re: How does EXT4 ensures two processes don't modify and synchronize
 one page at the same time.
Message-ID: <Ye7umfsRLkxAeUEv@mit.edu>
References: <6fdeab9535134fc18e86968b10e726c6@epfl.ch>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <6fdeab9535134fc18e86968b10e726c6@epfl.ch>
Precedence: bulk

On Mon, Jan 24, 2022 at 05:17:34PM +0000, Lyu Tao wrote:
> 
> I'm new to file system area and have a naive question about the global sync.
> 
> Let's suppose there are two process are writing to the same file. If
> one process issues a sync() syscall, which mechanism can ensures the
> two processes don't modify and synchronize one page at the same
> time.

That's not what the sync() system call purports to do.  To quote from
the sync(2) man page:

       sync() causes all pending modifications to filesystem metadata
       and cached file data to be written to the underlying
       filesystems.

						- Ted