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, 4 Jan 2021 19:24:33 +0000
From:   Matthew Wilcox <willy@infradead.org>
To:     Theodore Ts'o <tytso@mit.edu>
Cc:     Andres Freund <andres@anarazel.de>, linux-fsdevel@vger.kernel.org,
        linux-xfs@vger.kernel.org, linux-ext4@vger.kernel.org,
        linux-block@vger.kernel.org
Subject: Re: fallocate(FALLOC_FL_ZERO_RANGE_BUT_REALLY) to avoid unwritten
 extents?
Message-ID: <20210104192433.GC22407@casper.infradead.org>
References: <20201230062819.yinrrp6uwfegsqo3@alap3.anarazel.de>
 <X/NpsZ8tSPkCwsYE@mit.edu>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <X/NpsZ8tSPkCwsYE@mit.edu>
Precedence: bulk

On Mon, Jan 04, 2021 at 02:17:05PM -0500, Theodore Ts'o wrote:
> One thing to note is that there are some devices which support a write
> zeros operation, but where it is *less* performant than actually
> writing zeros via DMA'ing zero pages.  Yes, that's insane.
> Unfortunately, there are a insane devices out there....

We already have quirks to disable commands, in NVMe, SCSI and ATA.
This sounds like another quirk to throw on the bonfire ("Yes, this
device claims to support Write Zeroes, but don't use it").  Indeed,
NVMe already has precisely this quirk, NVME_QUIRK_DISABLE_WRITE_ZEROES.