All Virtuozzo development lists (kernel + QEMU)
 help / color / mirror / Atom feed
From: Konstantin Khorenko <khorenko@virtuozzo.com>
To: Andrey Zhadchenko <andrey.zhadchenko@virtuozzo.com>
Cc: devel@openvz.org
Subject: Re: [Devel] [PATCH hci-8.1 2/2] dm-ploop: set max discard segments to one
Date: Tue, 10 Nov 2026 18:46:49 +0100	[thread overview]
Message-ID: <179433280956.3561434.18350690260771711057.b4-review@b4> (raw)
In-Reply-To: <20261109153619.277888-3-andrey.zhadchenko@virtuozzo.com>

Applying with these fixes on my side:
- the example: a whole 1M cluster [0, 2048) built from bios [0, 1024)
  and [2048, 3072), instead of [0, 512) and [1024, 1536)
- "range in the file" -> "range of the device", "always" dropped
- added why the limit is USHRT_MAX and what the user sees, split into
  paragraphs

On Mon, 09 Nov 2026 18:36:19 +0300, Andrey Zhadchenko wrote:
> Imagine we have a request with starting sector 0 and length 1024,
> so read or write means [0, 1024) range in the file. For discard this
> request can have 2 bios [0, 512) and [1024, 1536), but we always
> discarded [0, 1024).

ploop_handle_discard_pio() ignores a discard that is not a whole
cluster, so with the default 1M cluster this request discards nothing.
Data is lost only when a gapped request adds up to a whole cluster. The
message now reads:

    Discard is a special type of request that can have non-contiguous
    bios: dm-ploop keeps the dm stacking default max_discard_segments =
    USHRT_MAX, so the block layer merges discard bios with gaps.

    Imagine we have 1M clusters and a request with starting sector 0 and
    length 2048 sectors, so read or write means the [0, 2048) range of
    the device. For discard this request can have 2 bios [0, 1024) and
    [2048, 3072), but we discarded the whole cluster [0, 2048).

    Data in sectors 1024-2047 reads back as zeroes.

    Set max_discard_segments to 1 to avoid such merges.

-- 
Konstantin Khorenko,
Virtuozzo Linux Kernel Team

_______________________________________________
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel

  parent reply	other threads:[~2026-11-10 17:48 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-09 15:36 [Devel] [PATCH hci-8.1 0/2] dm-qcow2, dm-ploop: do not merge discards with gaps Andrey Zhadchenko
2026-11-09 15:36 ` [Devel] [PATCH hci-8.1 1/2] dm-qcow2: set max discard segments to one Andrey Zhadchenko
2026-11-09 15:44   ` no-reply
2026-11-10 17:46   ` Konstantin Khorenko
2026-11-09 15:36 ` [Devel] [PATCH hci-8.1 2/2] dm-ploop: " Andrey Zhadchenko
2026-11-09 15:44   ` no-reply
2026-11-10 17:46   ` Konstantin Khorenko [this message]
2026-11-10 10:03 ` [Devel] [PATCH hci-8.1 0/2] dm-qcow2, dm-ploop: do not merge discards with gaps Alexander Ivanov
2026-11-10 17:46 ` Konstantin Khorenko
2026-11-10 17:47 ` Konstantin Khorenko

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=179433280956.3561434.18350690260771711057.b4-review@b4 \
    --to=khorenko@virtuozzo.com \
    --cc=andrey.zhadchenko@virtuozzo.com \
    --cc=devel@openvz.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.