From: Jens Axboe <axboe@kernel.dk>
To: Matthew Wilcox <willy@infradead.org>
Cc: linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
hannes@cmpxchg.org, clm@meta.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 11/13] iomap: make buffered writes work with RWF_UNCACHED
Date: Fri, 8 Nov 2024 13:18:40 -0700 [thread overview]
Message-ID: <00b97317-610a-4ae3-8d97-f5871972a401@kernel.dk> (raw)
In-Reply-To: <Zy5vi-L6Vsn-seRZ@casper.infradead.org>
On 11/8/24 1:07 PM, Matthew Wilcox wrote:
> On Fri, Nov 08, 2024 at 12:49:58PM -0700, Jens Axboe wrote:
>> On 11/8/24 12:26 PM, Jens Axboe wrote:
>>> On 11/8/24 11:46 AM, Matthew Wilcox wrote:
>>>> On Fri, Nov 08, 2024 at 10:43:34AM -0700, Jens Axboe wrote:
>>>>> +++ b/fs/iomap/buffered-io.c
>>>>> @@ -959,6 +959,8 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
>>>>> }
>>>>> if (iter->iomap.flags & IOMAP_F_STALE)
>>>>> break;
>>>>> + if (iter->flags & IOMAP_UNCACHED)
>>>>> + folio_set_uncached(folio);
>>>>
>>>> This seems like it'd convert an existing page cache folio into being
>>>> uncached? Is this just leftover from a previous version or is that a
>>>> design decision you made?
>>>
>>> I'll see if we can improve that. Currently both the read and write side
>>> do drop whatever it touches. We could feasibly just have it drop
>>> newly instantiated pages - iow, uncached just won't create new persistent
>>> folios, but it'll happily use the ones that are there already.
>>
>> Well that was nonsense on the read side, it deliberately only prunes
>> entries that has uncached set. For the write side, this is a bit
>> trickier. We'd essentially need to know if the folio populated by
>> write_begin was found in the page cache, or create from new. Any way we
>> can do that? One way is to change ->write_begin() so it takes a kiocb
>> rather than a file, but that's an amount of churn I'd rather avoid!
>> Maybe there's a way I'm just not seeing?
>
> Umm. We can solve it for iomap with a new FGP_UNCACHED flag and
> checking IOMAP_UNCACHED in iomap_get_folio(). Not sure how we solve it
> for other filesystems though. Any filesystem which uses FGP_NOWAIT has
> _a_ solution, but eg btrfs will need to plumb through a third boolean
> flag (or, more efficiently, just start passing FGP flags to
> prepare_one_folio()).
Yeah that's true, forgot we already have the IOMAP_UNCACHED flag there
and it's available in creation. Thanks, I'll start with that.
--
Jens Axboe
next prev parent reply other threads:[~2024-11-08 20:18 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-08 17:43 [PATCHSET v4] Uncached buffered IO Jens Axboe
2024-11-08 17:43 ` [PATCH 01/13] mm/filemap: change filemap_create_folio() to take a struct kiocb Jens Axboe
2024-11-08 18:18 ` Matthew Wilcox
2024-11-08 19:22 ` Jens Axboe
2024-11-08 17:43 ` [PATCH 02/13] mm/readahead: add folio allocation helper Jens Axboe
2024-11-08 17:43 ` [PATCH 03/13] mm: add PG_uncached page flag Jens Axboe
2024-11-08 19:25 ` Kirill A. Shutemov
2024-11-08 19:39 ` Jens Axboe
2024-11-08 17:43 ` [PATCH 04/13] mm/readahead: add readahead_control->uncached member Jens Axboe
2024-11-08 18:21 ` Matthew Wilcox
2024-11-08 19:22 ` Jens Axboe
2024-11-08 17:43 ` [PATCH 05/13] mm/filemap: use page_cache_sync_ra() to kick off read-ahead Jens Axboe
2024-11-08 17:43 ` [PATCH 06/13] mm/truncate: make invalidate_complete_folio2() public Jens Axboe
2024-11-08 17:43 ` [PATCH 07/13] fs: add FOP_UNCACHED flag Jens Axboe
2024-11-08 18:27 ` Matthew Wilcox
2024-11-08 19:23 ` Jens Axboe
2024-11-08 17:43 ` [PATCH 08/13] fs: add read support for RWF_UNCACHED Jens Axboe
2024-11-08 18:33 ` Matthew Wilcox
2024-11-08 19:25 ` Jens Axboe
2024-11-11 13:04 ` Stefan Metzmacher
2024-11-11 14:10 ` Jens Axboe
2024-11-11 15:44 ` Jens Axboe
2024-11-08 17:43 ` [PATCH 09/13] mm: drop uncached pages when writeback completes Jens Axboe
2024-11-08 17:43 ` [PATCH 10/13] mm/filemap: make buffered writes work with RWF_UNCACHED Jens Axboe
2024-11-08 17:43 ` [PATCH 11/13] iomap: " Jens Axboe
2024-11-08 18:46 ` Matthew Wilcox
2024-11-08 19:26 ` Jens Axboe
2024-11-08 19:49 ` Jens Axboe
2024-11-08 20:07 ` Matthew Wilcox
2024-11-08 20:18 ` Jens Axboe [this message]
2024-11-08 17:43 ` [PATCH 12/13] ext4: flag as supporting FOP_UNCACHED Jens Axboe
2024-11-08 17:43 ` [PATCH 13/13] xfs: " Jens Axboe
2024-11-11 12:55 ` [PATCHSET v4] Uncached buffered IO Stefan Metzmacher
2024-11-11 14:08 ` Jens Axboe
2024-11-11 15:05 ` Jens Axboe
2024-11-11 23:54 ` Jens Axboe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=00b97317-610a-4ae3-8d97-f5871972a401@kernel.dk \
--to=axboe@kernel.dk \
--cc=clm@meta.com \
--cc=hannes@cmpxchg.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox