From: Stefan Hajnoczi <[email protected]>
To: Ming Lei <[email protected]>
Cc: "Denis V. Lunev" <[email protected]>,
[email protected], [email protected],
[email protected],
Kirill Tkhai <[email protected]>,
Manuel Bentele <[email protected]>,
[email protected], Kevin Wolf <[email protected]>,
[email protected], Xie Yongji <[email protected]>,
Stefano Garzarella <[email protected]>,
Josef Bacik <[email protected]>,
Mike Christie <[email protected]>
Subject: Re: ublk-qcow2: ublk-qcow2 is available
Date: Thu, 6 Oct 2022 14:29:55 -0400 [thread overview]
Message-ID: <Yz8eo0IWMAJOwKWn@fedora> (raw)
In-Reply-To: <Yz7vvNKSNRyBVObo@T590>
[-- Attachment #1: Type: text/plain, Size: 4166 bytes --]
On Thu, Oct 06, 2022 at 11:09:48PM +0800, Ming Lei wrote:
> On Thu, Oct 06, 2022 at 09:59:40AM -0400, Stefan Hajnoczi wrote:
> > On Thu, Oct 06, 2022 at 06:26:15PM +0800, Ming Lei wrote:
> > > On Wed, Oct 05, 2022 at 11:11:32AM -0400, Stefan Hajnoczi wrote:
> > > > On Tue, Oct 04, 2022 at 01:57:50AM +0200, Denis V. Lunev wrote:
> > > > > On 10/3/22 21:53, Stefan Hajnoczi wrote:
> > > > > > On Fri, Sep 30, 2022 at 05:24:11PM +0800, Ming Lei wrote:
> > > > > > > ublk-qcow2 is available now.
> > > > > > Cool, thanks for sharing!
> > > > > yep
> > > > >
> > > > > > > So far it provides basic read/write function, and compression and snapshot
> > > > > > > aren't supported yet. The target/backend implementation is completely
> > > > > > > based on io_uring, and share the same io_uring with ublk IO command
> > > > > > > handler, just like what ublk-loop does.
> > > > > > >
> > > > > > > Follows the main motivations of ublk-qcow2:
> > > > > > >
> > > > > > > - building one complicated target from scratch helps libublksrv APIs/functions
> > > > > > > become mature/stable more quickly, since qcow2 is complicated and needs more
> > > > > > > requirement from libublksrv compared with other simple ones(loop, null)
> > > > > > >
> > > > > > > - there are several attempts of implementing qcow2 driver in kernel, such as
> > > > > > > ``qloop`` [2], ``dm-qcow2`` [3] and ``in kernel qcow2(ro)`` [4], so ublk-qcow2
> > > > > > > might useful be for covering requirement in this field
> > > > > There is one important thing to keep in mind about all partly-userspace
> > > > > implementations though:
> > > > > * any single allocation happened in the context of the
> > > > > userspace daemon through try_to_free_pages() in
> > > > > kernel has a possibility to trigger the operation,
> > > > > which will require userspace daemon action, which
> > > > > is inside the kernel now.
> > > > > * the probability of this is higher in the overcommitted
> > > > > environment
> > > > >
> > > > > This was the main motivation of us in favor for the in-kernel
> > > > > implementation.
> > > >
> > > > CCed Josef Bacik because the Linux NBD driver has dealt with memory
> > > > reclaim hangs in the past.
> > > >
> > > > Josef: Any thoughts on userspace block drivers (whether NBD or ublk) and
> > > > how to avoid hangs in memory reclaim?
> > >
> > > If I remember correctly, there isn't new report after the last NBD(TCMU) deadlock
> > > in memory reclaim was addressed by 8d19f1c8e193 ("prctl: PR_{G,S}ET_IO_FLUSHER
> > > to support controlling memory reclaim").
> >
> > Denis: I'm trying to understand the problem you described. Is this
> > correct:
> >
> > Due to memory pressure, the kernel reclaims pages and submits a write to
> > a ublk block device. The userspace process attempts to allocate memory
> > in order to service the write request, but it gets stuck because there
> > is no memory available. As a result reclaim gets stuck, the system is
> > unable to free more memory and therefore it hangs?
>
> The process should be killed in this situation if PR_SET_IO_FLUSHER
> is applied since the page allocation is done in VM fault handler.
Thanks for mentioning PR_SET_IO_FLUSHER. There is more info in commit
8d19f1c8e1937baf74e1962aae9f90fa3aeab463 ("prctl: PR_{G,S}ET_IO_FLUSHER
to support controlling memory reclaim").
It requires CAP_SYS_RESOURCE :/. This makes me wonder whether
unprivileged ublk will ever be possible.
I think this addresses Denis' concern about hangs, but it doesn't solve
them because I/O will fail. The real solution is probably what you
mentioned...
> Firstly in theory the userspace part should provide forward progress
> guarantee in code path for handling IO, such as reserving/mlock pages
> for such situation. However, this issue isn't unique for nbd or ublk,
> all userspace block device should have such potential risk, and vduse
> is no exception, IMO.
...here. Userspace needs to minimize memory allocations in the I/O code
path and reserve sufficient resources to make forward progress.
Stefan
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
next prev parent reply other threads:[~2022-10-06 18:30 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-30 9:24 ublk-qcow2: ublk-qcow2 is available Ming Lei
2022-10-03 19:53 ` Stefan Hajnoczi
2022-10-03 23:57 ` Denis V. Lunev
2022-10-05 15:11 ` Stefan Hajnoczi
2022-10-06 10:26 ` Ming Lei
2022-10-06 13:59 ` Stefan Hajnoczi
2022-10-06 15:09 ` Ming Lei
2022-10-06 18:29 ` Stefan Hajnoczi [this message]
2022-10-07 11:21 ` Ming Lei
2022-10-04 9:43 ` Ming Lei
2022-10-04 13:53 ` Stefan Hajnoczi
2022-10-05 4:18 ` Ming Lei
2022-10-05 12:21 ` Stefan Hajnoczi
2022-10-05 12:38 ` Denis V. Lunev
2022-10-06 11:24 ` Ming Lei
2022-10-07 10:04 ` Yongji Xie
2022-10-07 10:51 ` Ming Lei
2022-10-07 11:21 ` Yongji Xie
2022-10-07 11:23 ` Ming Lei
2022-10-08 8:43 ` Ziyang Zhang
2022-10-12 14:22 ` Stefan Hajnoczi
2022-10-13 6:48 ` Yongji Xie
2022-10-13 16:02 ` Stefan Hajnoczi
2022-10-14 12:56 ` Ming Lei
2022-10-17 11:11 ` Yongji Xie
2022-10-18 6:59 ` Ming Lei
2022-10-18 13:17 ` Yongji Xie
2022-10-18 14:54 ` Stefan Hajnoczi
2022-10-19 9:09 ` Ming Lei
2022-10-24 16:11 ` Stefan Hajnoczi
2022-10-21 5:33 ` Yongji Xie
2022-10-21 6:30 ` Jason Wang
2022-10-25 8:17 ` Yongji Xie
2022-10-25 12:02 ` Stefan Hajnoczi
2022-10-28 13:33 ` Yongji Xie
2022-11-01 2:36 ` Jason Wang
2022-11-02 19:13 ` Stefan Hajnoczi
2022-11-04 6:55 ` Jason Wang
2022-10-21 6:28 ` Jason Wang
2022-10-06 10:14 ` Richard W.M. Jones
2022-10-12 14:15 ` Stefan Hajnoczi
2022-10-13 1:50 ` Ming Lei
2022-10-13 16:01 ` Stefan Hajnoczi
2022-10-04 5:43 ` Manuel Bentele
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=Yz8eo0IWMAJOwKWn@fedora \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/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