6ee9ba5898
* Changelog from Linbit:
9.1.23 (api:genl2/proto:86-101,118-121/transport:18)
--------
* Fix a corner case that can happen when DRBD establishes multiple
connections in parallel, which could lead one connection to end up in
an inconsistent replication state of WFBitMapT/Established
* Fix a corner case in which a reconciliation resync ends up in
WFBitMapT/Established
* Restrict protocol compatibility to the most recent 8.4 and 9.0 releases
* Fix a corner case causing a module ref leak on drbd_transport_tcp;
if it hits, you can not rmmod it
* rate-limit resync progress while resync is paused
* resync-target inherits history UUIDs when resync finishes,
this can prevent unexpected "unrelared data" events later
* Updated compatibility code for Linux 6.11 and 6.12
* remove patches which already included in the new version:
0001-drbd-properly-rate-limit-resync-progress-reports.patch
0002-drbd-inherit-history-UUIDs-from-sync-source-when-res.patch
0003-build-compat-fix-line-offset-in-annotation-pragmas-p.patch
0004-drbd-fix-exposed_uuid-going-backward.patch
0005-drbd-Proper-locking-around-new_current_uuid-on-a-dis.patch
0006-build-CycloneDX-fix-bom-ref-add-purl.patch
0007-build-Another-update-to-the-spdx-files.patch
0008-build-generate-spdx.json-not-tag-value-format.patch
0009-compat-fix-gen_patch_names-for-bdev_file_open_by_pat.patch
0010-compat-fix-nla_nest_start_noflag-test.patch
0011-compat-fix-blk_alloc_disk-rule.patch
0012-drbd-remove-const-from-function-return-type.patch
0013-drbd-don-t-set-max_write_zeroes_sectors-in-decide_on.patch
0014-drbd-split-out-a-drbd_discard_supported-helper.patch
0015-drbd-atomically-update-queue-limits-in-drbd_reconsid.patch
0016-compat-test-and-patch-for-queue_limits_start_update.patch
0017-compat-specify-which-essential-change-was-not-made.patch
0018-gen_patch_names-reorder-blk_mode_t.patch
0019-compat-fix-blk_queue_update_readahead-patch.patch
0020-compat-test-and-patch-for-que_limits-max_hw_discard_.patch
0021-compat-fixup-write_zeroes__no_capable.patch
0022-compat-fixup-queue_flag_discard__yes_present.patch
0023-drbd-move-flags-to-queue_limits.patch
0024-compat-test-and-patch-for-queue_limits.features.patch
0025-drbd-Annotate-struct-fifo_buffer-with-__counted_by.patch
0026-compat-test-and-patch-for-__counted_by.patch
0027-drbd-fix-function-cast-warnings-in-state-machine.patch
0028-Add-missing-documentation-of-peer_device-parameter-t.patch
0030-drbd-kref_put-path-when-kernel_accept-fails.patch
0031-build-fix-typo-in-Makefile.spatch.patch
0032-drbd-open-do-not-delay-open-if-already-Primary.patch
* removed patch which is not needed anymore:
boo1231290_fix_drbd_build_error_against_kernel_v6.11.0.patch
boo1233222_fix_drbd_build_error_against_kernel_v6.11.6.patch
* update:
drbd_git_revision
drbd.spec
* add upstream patches to align commit d64ebe7eb7df:
0001-drbd-Fix-memory-leak.patch
OBS-URL: https://build.opensuse.org/package/show/network:ha-clustering:Factory/drbd?expand=0&rev=155
66 lines
2.5 KiB
Diff
66 lines
2.5 KiB
Diff
From f2cd05b8d60d27f43b07175b92ef4c2a69b8e3a2 Mon Sep 17 00:00:00 2001
|
|
From: Joel Colledge <joel.colledge@linbit.com>
|
|
Date: Wed, 6 Sep 2023 15:49:44 +0200
|
|
Subject: [PATCH 02/20] drbd: improve decision about marking a failed disk
|
|
Outdated
|
|
|
|
Sometimes it is possible to update the metadata even after our disk has
|
|
failed. We were too eager to remove the MDF_WAS_UP_TO_DATE flag in this
|
|
case.
|
|
|
|
Firstly, we used the "NOW" states, so would mark our metadata Outdated
|
|
if we were a Primary with UpToDate data and no peers, and our disk
|
|
failed. Use the "NEW" states instead.
|
|
|
|
Secondly, do not consider peers that are disconnecting, because they
|
|
will not see that our disk state is Failed, and so will outdate
|
|
themselves. We do not want to outdate both nodes in this situation.
|
|
---
|
|
drbd/drbd_state.c | 18 ++++++++++++++----
|
|
1 file changed, 14 insertions(+), 4 deletions(-)
|
|
|
|
diff --git a/drbd/drbd_state.c b/drbd/drbd_state.c
|
|
index 7e6e3477893d..8b60afeb097b 100644
|
|
--- a/drbd/drbd_state.c
|
|
+++ b/drbd/drbd_state.c
|
|
@@ -2489,15 +2489,24 @@ static void initialize_resync(struct drbd_peer_device *peer_device)
|
|
/* Is there a primary with access to up to date data known */
|
|
static bool primary_and_data_present(struct drbd_device *device)
|
|
{
|
|
- bool up_to_date_data = device->disk_state[NOW] == D_UP_TO_DATE;
|
|
- bool primary = device->resource->role[NOW] == R_PRIMARY;
|
|
+ bool up_to_date_data = device->disk_state[NEW] == D_UP_TO_DATE;
|
|
+ struct drbd_resource *resource = device->resource;
|
|
+ bool primary = resource->role[NEW] == R_PRIMARY;
|
|
struct drbd_peer_device *peer_device;
|
|
|
|
for_each_peer_device(peer_device, device) {
|
|
- if (peer_device->connection->peer_role[NOW] == R_PRIMARY)
|
|
+ struct drbd_connection *connection = peer_device->connection;
|
|
+
|
|
+ /* Do not consider the peer if we are disconnecting. */
|
|
+ if (resource->remote_state_change &&
|
|
+ drbd_twopc_between_peer_and_me(connection) &&
|
|
+ resource->twopc_reply.is_disconnect)
|
|
+ continue;
|
|
+
|
|
+ if (connection->peer_role[NEW] == R_PRIMARY)
|
|
primary = true;
|
|
|
|
- if (peer_device->disk_state[NOW] == D_UP_TO_DATE)
|
|
+ if (peer_device->disk_state[NEW] == D_UP_TO_DATE)
|
|
up_to_date_data = true;
|
|
}
|
|
|
|
@@ -4808,6 +4817,7 @@ change_cluster_wide_state(bool (*change)(struct change_context *, enum change_ph
|
|
} else if (context->mask.conn == conn_MASK && context->val.conn == C_DISCONNECTING) {
|
|
reply->target_reachable_nodes = NODE_MASK(context->target_node_id);
|
|
reply->reachable_nodes &= ~reply->target_reachable_nodes;
|
|
+ reply->is_disconnect = 1;
|
|
} else {
|
|
reply->target_reachable_nodes = reply->reachable_nodes;
|
|
}
|
|
--
|
|
2.35.3
|
|
|