From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wr1-f54.google.com (mail-wr1-f54.google.com [209.85.221.54]) by mail19.linbit.com (LINBIT Mail Daemon) with ESMTP id 881011627BB for ; Mon, 20 Apr 2026 21:57:16 +0200 (CEST) Received: by mail-wr1-f54.google.com with SMTP id ffacd0b85a97d-43d70c30767so2577726f8f.0 for ; Mon, 20 Apr 2026 12:57:16 -0700 (PDT) Received: from ryzen9 (192-164-131-220.hdsl.highway.telekom.at. [192.164.131.220]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-43fe4e59f97sm34988727f8f.37.2026.04.20.12.57.14 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 20 Apr 2026 12:57:14 -0700 (PDT) From: Philipp Reisner 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 Message-ID: <86h5p5o15y.fsf@linbit.com> MIME-Version: 1.0 Content-Type: text/plain Reply-To: drbd-user@lists.linbit.com List-Id: Announcements of new releases and critical bugs found List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , 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