From: Mikulas Patocka <mpatocka@redhat.com>
To: "Marek Marczykowski-Górecki" <marmarek@invisiblethingslab.com>,
"Keith Busch" <kbusch@kernel.org>, "Jens Axboe" <axboe@fb.com>,
"Christoph Hellwig" <hch@lst.de>,
"Sagi Grimberg" <sagi@grimberg.me>
Cc: Jan Kara <jack@suse.cz>, Vlastimil Babka <vbabka@suse.cz>,
Andrew Morton <akpm@linux-foundation.org>,
Matthew Wilcox <willy@infradead.org>,
Michal Hocko <mhocko@suse.com>,
stable@vger.kernel.org, regressions@lists.linux.dev,
Alasdair Kergon <agk@redhat.com>,
Mike Snitzer <snitzer@kernel.org>,
dm-devel@lists.linux.dev, linux-mm@kvack.org
Subject: Re: Intermittent storage (dm-crypt?) freeze - regression 6.4->6.5
Date: Thu, 2 Nov 2023 10:28:57 +0100 (CET) [thread overview]
Message-ID: <ac5b5ac0-9e8-c1b0-a26-62f832f845f0@redhat.com> (raw)
In-Reply-To: <ZULvkPhcpgAVyI8w@mail-itl>
[-- Attachment #1: Type: text/plain, Size: 1945 bytes --]
On Thu, 2 Nov 2023, Marek Marczykowski-Górecki wrote:
> On Tue, Oct 31, 2023 at 06:24:19PM +0100, Mikulas Patocka wrote:
>
> > > Hi
> > >
> > > I would like to ask you to try this patch. Revert the changes to "order"
> > > and "PAGE_ALLOC_COSTLY_ORDER" back to normal and apply this patch on a
> > > clean upstream kernel.
> > >
> > > Does it deadlock?
> > >
> > > There is a bug in dm-crypt that it doesn't account large pages in
> > > cc->n_allocated_pages, this patch fixes the bug.
>
> This patch did not help.
>
> > If the previous patch didn't fix it, try this patch (on a clean upstream
> > kernel).
> >
> > This patch allocates large pages, but it breaks them up into single-page
> > entries when adding them to the bio.
>
> But this does help.
Thanks. So we can stop blaming the memory allocator and start blaming the
NVMe subsystem.
I added NVMe maintainers to this thread - the summary of the problem is:
In dm-crypt, we allocate a large compound page and add this compound page
to the bio as a single big vector entry. Marek reports that on his system
it causes deadlocks, the deadlocks look like a lost bio that was never
completed. When I chop the large compound page to individual pages in
dm-crypt and add bio vector for each of them, Marek reports that there are
no longer any deadlocks. So, we have a problem (either hardware or
software) that the NVMe subsystem doesn't like bio vectors with large
bv_len. This is the original bug report:
https://lore.kernel.org/stable/ZTNH0qtmint%2FzLJZ@mail-itl/
Marek, what NVMe devices do you use? Do you use the same device on all 3
machines where you hit this bug?
In the directory /sys/block/nvme0n1/queue: what is the value of
dma_alignment, max_hw_sectors_kb, max_sectors_kb, max_segment_size,
max_segments, virt_boundary_mask?
Try lowring /sys/block/nvme0n1/queue/max_sectors_kb to some small value
(for example 64) and test if it helps.
Mikulas
next prev parent reply other threads:[~2023-11-02 9:29 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-21 3:38 Intermittent storage (dm-crypt?) freeze - regression 6.4->6.5 Marek Marczykowski-Górecki
2023-10-21 7:48 ` Bagas Sanjaya
2023-10-29 6:23 ` Linux regression tracking #update (Thorsten Leemhuis)
2023-10-23 20:59 ` Mikulas Patocka
2023-10-25 3:10 ` Marek Marczykowski-Górecki
2023-10-25 3:22 ` Marek Marczykowski-Górecki
2023-10-25 10:13 ` Mikulas Patocka
2023-10-27 17:32 ` Mikulas Patocka
2023-10-28 9:23 ` Matthew Wilcox
2023-10-28 15:14 ` Mike Snitzer
2023-10-29 11:15 ` Marek Marczykowski-Górecki
2023-10-29 20:02 ` Vlastimil Babka
2023-10-30 7:37 ` Mikulas Patocka
2023-10-30 8:37 ` Vlastimil Babka
2023-10-30 11:22 ` Mikulas Patocka
2023-10-30 11:30 ` Vlastimil Babka
2023-10-30 11:37 ` Mikulas Patocka
2023-10-30 12:25 ` Jan Kara
2023-10-30 13:30 ` Marek Marczykowski-Górecki
2023-10-30 14:08 ` Mikulas Patocka
2023-10-30 15:56 ` Jan Kara
2023-10-30 16:51 ` Marek Marczykowski-Górecki
2023-10-30 17:50 ` Mikulas Patocka
2023-10-31 3:48 ` Marek Marczykowski-Górecki
2023-10-31 14:01 ` Jan Kara
2023-10-31 15:42 ` Marek Marczykowski-Górecki
2023-10-31 17:17 ` Mikulas Patocka
2023-10-31 17:24 ` Mikulas Patocka
2023-11-02 0:38 ` Marek Marczykowski-Górecki
2023-11-02 9:28 ` Mikulas Patocka [this message]
2023-11-02 11:45 ` Marek Marczykowski-Górecki
2023-11-02 17:06 ` Mikulas Patocka
2023-11-03 15:01 ` Marek Marczykowski-Górecki
2023-11-03 15:10 ` Keith Busch
2023-11-03 16:15 ` Marek Marczykowski-Górecki
2023-11-03 16:54 ` Keith Busch
2023-11-03 20:30 ` Marek Marczykowski-G'orecki
2023-11-03 22:42 ` Keith Busch
2023-11-04 9:27 ` Mikulas Patocka
2023-11-04 13:59 ` Keith Busch
2023-11-06 7:10 ` Christoph Hellwig
2023-11-06 14:59 ` [PATCH] swiotlb-xen: provide the "max_mapping_size" method Mikulas Patocka
2023-11-06 15:16 ` Keith Busch
2023-11-06 15:30 ` Mike Snitzer
2023-11-06 17:12 ` [PATCH v2] " Mikulas Patocka
2023-11-07 4:18 ` Stefano Stabellini
2023-11-08 7:31 ` Christoph Hellwig
2023-11-06 7:08 ` Intermittent storage (dm-crypt?) freeze - regression 6.4->6.5 Christoph Hellwig
2023-11-02 12:21 ` Jan Kara
2023-11-01 1:27 ` Ming Lei
2023-11-01 2:14 ` Marek Marczykowski-Górecki
2023-11-01 2:15 ` Marek Marczykowski-Górecki
2023-11-01 2:35 ` Marek Marczykowski-Górecki
2023-11-01 3:24 ` Ming Lei
2023-11-01 10:15 ` Hannes Reinecke
2023-11-01 10:26 ` Jan Kara
2023-11-01 11:23 ` Ming Lei
2023-11-02 14:02 ` Keith Busch
2023-11-01 12:16 ` Mikulas Patocka
2023-10-30 11:28 ` Jan Kara
2023-10-30 11:49 ` Mikulas Patocka
2023-10-30 12:11 ` Jan Kara
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=ac5b5ac0-9e8-c1b0-a26-62f832f845f0@redhat.com \
--to=mpatocka@redhat.com \
--cc=agk@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=axboe@fb.com \
--cc=dm-devel@lists.linux.dev \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=kbusch@kernel.org \
--cc=linux-mm@kvack.org \
--cc=marmarek@invisiblethingslab.com \
--cc=mhocko@suse.com \
--cc=regressions@lists.linux.dev \
--cc=sagi@grimberg.me \
--cc=snitzer@kernel.org \
--cc=stable@vger.kernel.org \
--cc=vbabka@suse.cz \
--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;
as well as URLs for NNTP newsgroup(s).