From: Jens Axboe <axboe@kernel.dk>
To: Brian Foster <bfoster@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>,
"Kirill A. Shutemov" <kirill@shutemov.name>,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
hannes@cmpxchg.org, clm@meta.com, linux-kernel@vger.kernel.org,
willy@infradead.org
Subject: Re: [PATCH 08/15] mm/filemap: add read support for RWF_UNCACHED
Date: Wed, 13 Nov 2024 07:07:19 -0700 [thread overview]
Message-ID: <27cd53e0-981e-42f0-b965-e9e2cf3d5894@kernel.dk> (raw)
In-Reply-To: <d74ea306-29d6-4829-9b3f-d76dfac0b912@kernel.dk>
On 11/12/24 1:25 PM, Jens Axboe wrote:
>>>>>> BTW, I should have also mentioned that fsx is also useful for longer
>>>>>> soak testing. I.e., fstests will provide a decent amount of coverage as
>>>>>> is via the various preexisting tests, but I'll occasionally run fsx
>>>>>> directly and let it run overnight or something to get the op count at
>>>>>> least up in the 100 millions or so to have a little more confidence
>>>>>> there isn't some rare/subtle bug lurking. That might be helpful with
>>>>>> something like this. JFYI.
>>>>>
>>>>> Good suggestion, I can leave it running overnight here as well. Since
>>>>> I'm not super familiar with it, what would be a good set of parameters
>>>>> to run it with?
>>>>>
>>>>
>>>> Most things are on by default, so I'd probably just go with that. -p is
>>>> useful to get occasional status output on how many operations have
>>>> completed and you could consider increasing the max file size with -l,
>>>> but usually I don't use more than a few MB or so if I increase it at
>>>> all.
>>>
>>> When you say default, I'd run it without arguments. And then it does
>>> nothing :-)
>>>
>>> Not an fs guy, I never run fsx. I run xfstests if I make changes that
>>> may impact the page cache, writeback, or file systems.
>>>
>>> IOW, consider this a "I'm asking my mom to run fsx, I need to be pretty
>>> specific" ;-)
>>>
>>
>> Heh. In that case I'd just run something like this:
>>
>> fsx -p 100000 <file>
>>
>> ... and see how long it survives. It may not necessarily be an uncached
>> I/O problem if it fails, but depending on how reproducible a failure is,
>> that's where a cli knob comes in handy.
>
> OK good, will give that a spin.
Ran overnight, no issues seen. Just terminated the process. For funsies,
I also added RWF_UNCACHED support to qemu and had the vm booted with
that as well, to get some host side testing too. Everything looks fine.
This is running:
https://git.kernel.dk/cgit/linux/log/?h=buffered-uncached.7
which is the current branch.
--
Jens Axboe
next prev parent reply other threads:[~2024-11-13 14:07 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-10 15:27 [PATCHSET v2 0/15] Uncached buffered IO Jens Axboe
2024-11-10 15:27 ` [PATCH 01/15] mm/filemap: change filemap_create_folio() to take a struct kiocb Jens Axboe
2024-11-10 15:27 ` [PATCH 02/15] mm/readahead: add folio allocation helper Jens Axboe
2024-11-10 15:27 ` [PATCH 03/15] mm: add PG_uncached page flag Jens Axboe
2024-11-10 15:27 ` [PATCH 04/15] mm/readahead: add readahead_control->uncached member Jens Axboe
2024-11-10 15:27 ` [PATCH 05/15] mm/filemap: use page_cache_sync_ra() to kick off read-ahead Jens Axboe
2024-11-10 15:27 ` [PATCH 06/15] mm/truncate: make invalidate_complete_folio2() public Jens Axboe
2024-11-10 15:27 ` [PATCH 07/15] fs: add RWF_UNCACHED iocb and FOP_UNCACHED file_operations flag Jens Axboe
2024-11-10 15:28 ` [PATCH 08/15] mm/filemap: add read support for RWF_UNCACHED Jens Axboe
2024-11-11 9:15 ` Kirill A. Shutemov
2024-11-11 14:12 ` Jens Axboe
2024-11-11 15:16 ` Christoph Hellwig
2024-11-11 15:17 ` Jens Axboe
2024-11-11 17:09 ` Jens Axboe
2024-11-11 23:42 ` Jens Axboe
2024-11-12 5:13 ` Christoph Hellwig
2024-11-12 15:14 ` Jens Axboe
2024-11-12 16:39 ` Brian Foster
2024-11-12 17:06 ` Jens Axboe
2024-11-12 17:19 ` Jens Axboe
2024-11-12 18:44 ` Brian Foster
2024-11-12 19:08 ` Jens Axboe
2024-11-12 19:39 ` Brian Foster
2024-11-12 19:45 ` Jens Axboe
2024-11-12 20:21 ` Brian Foster
2024-11-12 20:25 ` Jens Axboe
2024-11-13 14:07 ` Jens Axboe [this message]
2024-11-11 15:25 ` Kirill A. Shutemov
2024-11-11 15:31 ` Jens Axboe
2024-11-11 15:51 ` Kirill A. Shutemov
2024-11-11 15:57 ` Jens Axboe
2024-11-11 16:29 ` Kirill A. Shutemov
2024-11-10 15:28 ` [PATCH 09/15] mm/filemap: drop uncached pages when writeback completes Jens Axboe
2024-11-11 9:17 ` Kirill A. Shutemov
2024-11-10 15:28 ` [PATCH 10/15] mm/filemap: make buffered writes work with RWF_UNCACHED Jens Axboe
2024-11-10 15:28 ` [PATCH 11/15] mm: add FGP_UNCACHED folio creation flag Jens Axboe
2024-11-10 15:28 ` [PATCH 12/15] ext4: add RWF_UNCACHED write support Jens Axboe
2024-11-10 15:28 ` [PATCH 13/15] iomap: make buffered writes work with RWF_UNCACHED Jens Axboe
2024-11-10 15:28 ` [PATCH 14/15] xfs: punt uncached write completions to the completion wq Jens Axboe
2024-11-10 15:28 ` [PATCH 15/15] xfs: flag as supporting FOP_UNCACHED Jens Axboe
2024-11-11 15:27 ` Christoph Hellwig
2024-11-11 15:33 ` Jens Axboe
2024-11-11 17:25 ` [PATCHSET v2 0/15] Uncached buffered IO Matthew Wilcox
2024-11-11 17:39 ` Jens Axboe
2024-11-11 21:24 ` Yu Zhao
2024-11-11 21:48 ` Matthew Wilcox
2024-11-11 22:07 ` Yu Zhao
2024-11-20 23:11 ` Yuanchu Xie
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=27cd53e0-981e-42f0-b965-e9e2cf3d5894@kernel.dk \
--to=axboe@kernel.dk \
--cc=bfoster@redhat.com \
--cc=clm@meta.com \
--cc=hannes@cmpxchg.org \
--cc=hch@infradead.org \
--cc=kirill@shutemov.name \
--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