Message-ID: <b05c66c5-81fe-6398-416a-1dc9bdd3469a@nvidia.com>
Date:   Fri, 11 Feb 2022 11:45:19 +0000
From:   Chaitanya Kulkarni <chaitanyak@...dia.com>
To:     Eric Biggers <ebiggers@...nel.org>,
        "linux-fsdevel@...r.kernel.org" <linux-fsdevel@...r.kernel.org>
CC:     "linux-ext4@...r.kernel.org" <linux-ext4@...r.kernel.org>,
        "linux-f2fs-devel@...ts.sourceforge.net" 
        <linux-f2fs-devel@...ts.sourceforge.net>,
        "linux-xfs@...r.kernel.org" <linux-xfs@...r.kernel.org>,
        "linux-api@...r.kernel.org" <linux-api@...r.kernel.org>,
        "linux-fscrypt@...r.kernel.org" <linux-fscrypt@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [RFC PATCH 1/7] statx: add I/O alignment information

On 2/11/22 3:40 AM, Chaitanya Kulkarni wrote:
> On 2/10/22 10:11 PM, Eric Biggers wrote:
>> From: Eric Biggers <ebiggers@...gle.com>
>>
>> Traditionally, the conditions for when DIO (direct I/O) is supported
>> were fairly simple: filesystems either supported DIO aligned to the
>> block device's logical block size, or didn't support DIO at all.
>>
>> However, due to filesystem features that have been added over time (e.g,
>> data journalling, inline data, encryption, verity, compression,
>> checkpoint disabling, log-structured mode), the conditions for when DIO
>> is allowed on a file have gotten increasingly complex.  Whether a
>> particular file supports DIO, and with what alignment, can depend on
>> various file attributes and filesystem mount options, as well as which
>> block device(s) the file's data is located on.
>>
>> XFS has an ioctl XFS_IOC_DIOINFO which exposes this information to
>> applications.  However, as discussed
>> (https://lore.kernel.org/linux-fsdevel/20220120071215.123274-1-ebiggers@kernel.org/T/#u),
>> this ioctl is rarely used and not known to be used outside of
>> XFS-specific code.  It also was never intended to indicate when a file
>> doesn't support DIO at all, and it only exposes the minimum I/O
>> alignment, not the optimal I/O alignment which has been requested too.
>>
>> Therefore, let's expose this information via statx().  Add the
>> STATX_IOALIGN flag and three fields associated with it:
>>
>> * stx_mem_align_dio: the alignment (in bytes) required for user memory
>>     buffers for DIO, or 0 if DIO is not supported on the file.
>>
>> * stx_offset_align_dio: the alignment (in bytes) required for file
>>     offsets and I/O segment lengths for DIO, or 0 if DIO is not supported
>>     on the file.  This will only be nonzero if stx_mem_align_dio is
>>     nonzero, and vice versa.
>>
>> * stx_offset_align_optimal: the alignment (in bytes) suggested for file
>>     offsets and I/O segment lengths to get optimal performance.  This
>>     applies to both DIO and buffered I/O.  It differs from stx_blocksize
>>     in that stx_offset_align_optimal will contain the real optimum I/O
>>     size, which may be a large value.  In contrast, for compatibility
>>     reasons stx_blocksize is the minimum size needed to avoid page cache
>>     read/write/modify cycles, which may be much smaller than the optimum
>>     I/O size.  For more details about the motivation for this field, see
>>     https://lore.kernel.org/r/20220210040304.GM59729@dread.disaster.area
>>
>> Note that as with other statx() extensions, if STATX_IOALIGN isn't set
>> in the returned statx struct, then these new fields won't be filled in.
>> This will happen if the filesystem doesn't support STATX_IOALIGN, or if
>> the file isn't a regular file.  (It might be supported on block device
>> files in the future.)  It might also happen if the caller didn't include
>> STATX_IOALIGN in the request mask, since statx() isn't required to
>> return information that wasn't requested.
>>
>> This commit adds the VFS-level plumbing for STATX_IOALIGN.  Individual
>> filesystems will still need to add code to support it.
>>
>> Signed-off-by: Eric Biggers <ebiggers@...gle.com>
>> ---
> 
> 
> I've actually worked on similar series to export alignment and
> granularity for non-trivial operations, this implementation
> only exporting I/O alignments (mostly REQ_OP_WRITE/REQ_OP_READ) via
> stax.
> 
> Since it is coming from :-
> bdev_logical_block_size()->q->limits.logical_block_size that is set when
> low level driver like nvme calls blk_queue_logical_block_size().
> 
>   From my experience especially with SSDs, applications want to
> know similar information about different non-trivial requests such as
> REQ_OP_DISCARD/REQ_OP_WRITE_ZEROES/REQ_OP_VERIFY (work in progress see
> [1]) etc.
> 
> It will be great to make this generic userspace interface where user can
> ask for specific REQ_OP_XXX such as generic I/O REQ_OP_READ/REQ_OP_WRITE
> and non generic REQ_OP_XX such as REQ_OP_DISCARD/REQ_OP_VERIFY etc ....
> 
> Since I've worked on implementing REQ_OP_VERIFY support I don't want to
> implement separate interface for querying the REQ_OP_VERIFY or any other
> non-trivial REQ_OP_XXX granularity or alignment.
> 
> -ck
> 
> [1] https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.spinics.net%2Flists%2Flinux-xfs%2Fmsg56826.html&amp;data=04%7C01%7Cchaitanyak%40nvidia.com%7C252d78e009ad49bd522208d9ed534dcf%7C43083d15727340c1b7db39efd9ccc17a%7C0%7C0%7C637801764313014840%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&amp;sdata=1owqIDlcst4h%2FGr9Azteaiy22vfHFZojRipKmk6A%2FCg%3D&amp;reserved=0
> 

Adding right link for REQ_OP_VERIFY ...

[1] https://www.spinics.net/lists/linux-xfs/msg56826.html

Powered by blists - more mailing lists