Skip to content

Unblock peer discovery on boot when attempting connectivity to unreachable cluster nodes #14743

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 18, 2025
Merged

Unblock peer discovery on boot when attempting connectivity to unreachable cluster nodes #14743

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7c346a1
Ensure peer discovery node connectivity attempts for configured clust…
Ayanda-D Oct 16, 2025
3e1ad6d
update comment in peer_discovery_classic_config_SUITE on nonexistent
Ayanda-D Oct 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions deps/rabbit/src/rabbit_peer_discovery.erl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,8 @@
-define(DEFAULT_DISCOVERY_RETRY_COUNT, 30).
-define(DEFAULT_DISCOVERY_RETRY_INTERVAL_MS, 1000).

-define(ERPC_CALL_TIMEOUT, 10_000).

-define(NODENAME_PART_SEPARATOR, "@").

-define(PT_PEER_DISC_BACKEND, {?MODULE, backend}).
Expand Down Expand Up @@ -636,7 +638,7 @@ query_node_props2([{Node, Members} | Rest], NodesAndProps, FromNode) ->
Node, logger, debug,
["Peer discovery: temporary hidden node '~ts' "
"queries properties from node '~ts'",
[node(), Node]], FromNode),
[node(), Node]], FromNode, ?ERPC_CALL_TIMEOUT),
StartTime = get_node_start_time(Node, FromNode),
IsReady = is_node_db_ready(Node, FromNode),
NodeAndProps = {Node, Members, StartTime, IsReady},
Expand Down Expand Up @@ -726,7 +728,7 @@ is_node_db_ready(Node, FromNode) ->
end.

erpc_call(Node, Mod, Fun, Args, FromNode) ->
erpc_call(Node, Mod, Fun, Args, FromNode, 10000).
erpc_call(Node, Mod, Fun, Args, FromNode, 0).

erpc_call(Node, Mod, Fun, Args, FromNode, Timeout) when Timeout >= 0 ->
try
Expand Down
13 changes: 6 additions & 7 deletions deps/rabbit/test/peer_discovery_classic_config_SUITE.erl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,18 +138,17 @@ init_per_testcase(successful_discovery_with_a_subset_of_nodes_coming_online = Te
{rmq_nodes_count, tl(NodeNames)},
{rmq_nodes_clustered, false}
]),
NodeNamesWithHostname = [rabbit_nodes:make({Name, "localhost"}) || Name <- NodeNames],
%% reduce retry time since we know one node on the list does
%% not exist and not just unreachable
%% We no longer test non-existing nodes, it just times out
%% constantly in CI
%% To compare, this suite takes ~23min in my machine with
%% unreachable nodes vs ~6min without them
NodeNamesWithHostname =
[rabbit_nodes:make({Name, "localhost"}) || Name <- [nonexistent1, nonexistent2 | NodeNames]],
%% reduce retry time since we know two nodes on the list do
%% not exist and are not just unreachable
Config3 = rabbit_ct_helpers:merge_app_env(Config2,
{rabbit, [
{forced_feature_flags_on_init, []},
{cluster_nodes, {NodeNamesWithHostname, disc}},
{cluster_formation, [
{discovery_retry_limit, 2},
{discovery_retry_interval, 100},
{internal_lock_retries, 10}
]}
]}),
Expand Down
Loading