Skip to content

rabbit_mnesia: add retries #15502

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

Draft
mkuratczyk wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

rabbit_mnesia: add retries #15502

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
39 changes: 36 additions & 3 deletions deps/rabbit/src/rabbit_mnesia.erl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -965,13 +965,27 @@ stop_mnesia() ->
ensure_mnesia_not_running().

change_extra_db_nodes(ClusterNodes0, CheckOtherNodes) ->
change_extra_db_nodes(ClusterNodes0, CheckOtherNodes, 3).

change_extra_db_nodes(ClusterNodes0, CheckOtherNodes, RetriesLeft) ->
ClusterNodes = rabbit_nodes:nodes_excl_me(ClusterNodes0),
case {mnesia:change_config(extra_db_nodes, ClusterNodes), ClusterNodes} of
{{ok, []}, [_|_]} when CheckOtherNodes ->
throw({error, {failed_to_cluster_with, ClusterNodes,
"Mnesia could not connect to any nodes."}});
{{ok, Nodes}, _} ->
Nodes
Nodes;
{{error, _} = Error, _} when RetriesLeft > 0 ->
?LOG_WARNING(
"Failed to add extra Mnesia db nodes ~tp: ~tp. "
"Retrying (~b attempts left).",
[ClusterNodes, Error, RetriesLeft - 1]),
timer:sleep(1000),
change_extra_db_nodes(ClusterNodes0, CheckOtherNodes,
RetriesLeft - 1);
{{error, _} = Error, _} ->
throw({error, {failed_to_cluster_with, ClusterNodes,
rabbit_misc:format("~tp", [Error])}})
end.

check_nodes_consistency(Node, {RemoteAllNodes, _, _}) ->
Expand Down Expand Up @@ -1011,8 +1025,27 @@ check_mnesia_consistency(Node, ProtocolVersion) ->
end
end).

negotiate_protocol([Node]) ->
mnesia_monitor:negotiate_protocol([Node]).
negotiate_protocol(Nodes) ->
negotiate_protocol(Nodes, 3).

negotiate_protocol([Node], RetriesLeft) ->
try
mnesia_monitor:negotiate_protocol([Node])
catch
exit:Reason when RetriesLeft > 0 ->
?LOG_WARNING(
"Mnesia protocol negotiation with node ~tp "
"failed: ~tp. Retrying (~b attempts left).",
[Node, Reason, RetriesLeft - 1]),
timer:sleep(1000),
negotiate_protocol([Node], RetriesLeft - 1);
exit:Reason ->
?LOG_WARNING(
"Mnesia protocol negotiation with node ~tp "
"failed: ~tp. No retries left.",
[Node, Reason]),
[]
end.

with_running_or_clean_mnesia(Fun) ->
IsMnesiaRunning = case mnesia:system_info(is_running) of
Expand Down
Loading