Distributed Replicated Block Device (DRBD) announcements
 help / color / mirror / Atom feed
From: Philipp Reisner <philipp.reisner@linbit.com>
To: drbd-announce@lists.linbit.com
Subject: drbd-9.3.2 and drbd-9.2.18
Date: Mon, 20 Apr 2026 21:57:13 +0200	[thread overview]
Message-ID: <86h5p5o15y.fsf@linbit.com> (raw)


Hi,

Another release coming. This time, it includes important fixes for
large, dynamic LINSTOR clusters. Linstor 1.33.2 already contains fixes
for most cases, but for disaggregated setups with diskless primary
nodes, this DRBD update is also necessary.

The bugs affect resources that got a replica added later, after creation
time. It only affects thinly-provisioned volumes, and only if they never
had a write request with a node absent and fully utilized peer
slots.
So, usually only a small percentage of all resources are
affected. Unfortunately, the affected resources show UpToDate/UpToDate,
but the younger replica misses some blocks.

Now we have tests for all those scenarios.

As these fixes are important for such larger LINSTOR installations, I
start this release cycle about two weeks earlier than usual.

During the release candidate phase, a regression in the RDMA transport
in the drbd-9.3 branch was discovered and fixed. And a problem with
attaching devices of ~100TiB or more was discovered and fixed.

9.3.2 (api:genl2/proto:86-101,118-124/transport:21)
--------
 * Use genl pre_doit/post_doit for netlink request setup and teardown
 * Handle recv returning 0 (EOF) in recv_bio
 * Revert flush_send_buffer send error causing state change
 * Fix a page leak in the RDMA transport's send-page path
 * All fixes from 9.2.18
  - Fix when a diskless primary creates a new current UUID,
    fixing possible silent data divergence later
  - Fix quorum calculation upon attach/detach operations
  - Handle split-brain recovery strategies during attach
    like they are handled during connect
  - Hanle attaching of large devices (~100TiB) without triggering
    the NMI watchdog
  - Fix a race condition in the RDMA code that could lead to
    leaking a cm object
  - Skip new-region resync for zero-guarantee backends at attach
  - drbdsetup attach waits for completion of disk state negotiation
    before returning
  - Fix missing disk line in drbdsetup show while in D_NEGOTIATING state
  - A few fixes found by the static analyzer smatch

https://pkg.linbit.com//downloads/drbd/9/drbd-9.3.2.tar.gz
https://github.com/LINBIT/drbd/commit/0605140bf521251f4f362b5bad2eeaf33dba1e9f

https://pkg.linbit.com//downloads/drbd/9/drbd-9.2.18.tar.gz
https://github.com/LINBIT/drbd/commit/a7afc67e5873f3fedce8d944c89edf87ffb7c116

cheers,
 Philipp

                 reply	other threads:[~2026-04-20 19:57 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=86h5p5o15y.fsf@linbit.com \
    --to=philipp.reisner@linbit.com \
    --cc=drbd-announce@lists.linbit.com \
    --cc=drbd-user@lists.linbit.com \
    /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