Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
From:   =?utf-8?Q?Javier_Gonz=C3=A1lez?= <javier@javigon.com>
Mime-Version: 1.0 (1.0)
Subject: Re: [RFC PATCH v5 0/4] add simple copy support
Date:   Sat, 10 Apr 2021 08:32:56 +0200
Message-Id: <5BE5E1D9-675F-4122-A845-B0A29BB74447@javigon.com>
References: <BYAPR04MB49652982D00724001AE758C986729@BYAPR04MB4965.namprd04.prod.outlook.com>
Cc:     Max Gurtovoy <mgurtovoy@nvidia.com>,
        SelvaKumar S <selvakuma.s1@samsung.com>,
        linux-nvme@lists.infradead.org, axboe@kernel.dk,
        Damien Le Moal <damien.lemoal@wdc.com>, kch@kernel.org,
        sagi@grimberg.me, snitzer@redhat.com, selvajove@gmail.com,
        linux-kernel@vger.kernel.org, nj.shetty@samsung.com,
        linux-block@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        dm-devel@redhat.com, joshi.k@samsung.com, javier.gonz@samsung.com,
        kbusch@kernel.org, joshiiitr@gmail.com, hch@lst.de
In-Reply-To: <BYAPR04MB49652982D00724001AE758C986729@BYAPR04MB4965.namprd04.prod.outlook.com>
To:     Chaitanya Kulkarni <Chaitanya.Kulkarni@wdc.com>
Precedence: bulk


> On 10 Apr 2021, at 02.30, Chaitanya Kulkarni <Chaitanya.Kulkarni@wdc.com> w=
rote:
>=20
> =EF=BB=BFOn 4/9/21 17:22, Max Gurtovoy wrote:
>>> On 2/19/2021 2:45 PM, SelvaKumar S wrote:
>>> This patchset tries to add support for TP4065a ("Simple Copy Command"),
>>> v2020.05.04 ("Ratified")
>>>=20
>>> The Specification can be found in following link.
>>> https://nvmexpress.org/wp-content/uploads/NVM-Express-1.4-Ratified-TPs-1=
.zip
>>>=20
>>> Simple copy command is a copy offloading operation and is  used to copy
>>> multiple contiguous ranges (source_ranges) of LBA's to a single destinat=
ion
>>> LBA within the device reducing traffic between host and device.
>>>=20
>>> This implementation doesn't add native copy offload support for stacked
>>> devices rather copy offload is done through emulation. Possible use
>>> cases are F2FS gc and BTRFS relocation/balance.
>>>=20
>>> *blkdev_issue_copy* takes source bdev, no of sources, array of source
>>> ranges (in sectors), destination bdev and destination offset(in sectors)=
.
>>> If both source and destination block devices are same and copy_offload =3D=
 1,
>>> then copy is done through native copy offloading. Copy emulation is used=

>>> in other cases.
>>>=20
>>> As SCSI XCOPY can take two different block devices and no of source rang=
e is
>>> equal to 1, this interface can be extended in future to support SCSI XCO=
PY.
>> Any idea why this TP wasn't designed for copy offload between 2=20
>> different namespaces in the same controller ?
>=20
> Yes, it was the first attempt so to keep it simple.
>=20
> Further work is needed to add incremental TP so that we can also do a copy=

> between the name-spaces of same controller (if we can't already) and to th=
e
> namespaces that belongs to the different controller.
>=20
>> And a simple copy will be the case where the src_nsid =3D=3D dst_nsid ?
>>=20
>> Also why there are multiple source ranges and only one dst range ? We=20
>> could add a bit to indicate if this range is src or dst..

One of the target use cases was ZNS in order to avoid fabric transfers durin=
g host GC. You can see how this plays well with several zone ranges and a si=
ngle zone destination.=20

If we start getting support in Linux through the different past copy offload=
 efforts, I=E2=80=99m sure we can extend this TP in the future.=20