Use when erlang distributed systems including node connectivity, distributed processes, global name registration, distributed supervision, network partitions, and building fault-tolerant multi-node applications on the BEAM VM.
Read-only skill
Additional assets for this skill
This skill cannot use any tools. It operates in read-only mode without the ability to modify files or execute commands.
Erlang's built-in distribution enables building clustered, fault-tolerant systems across multiple nodes. Processes on different nodes communicate transparently through the same message-passing primitives used locally. This location transparency makes distributed programming natural and straightforward.
The distribution layer handles network communication, serialization, and node connectivity automatically. Nodes discover each other through naming, with processes addressable globally via registered names or pid references. Understanding distribution patterns is essential for building scalable, resilient systems.
This skill covers node connectivity and clustering, distributed message passing, global name registration, distributed supervision, handling network partitions, RPC patterns, and building production distributed applications.
Nodes connect to form clusters for distributed computation and fault tolerance.
%% Starting named nodes
%% erl -name node1@hostname -setcookie secret
%% erl -sname node2 -setcookie secret
%% Connecting nodes
connect_nodes() ->
Node1 = 'node1@host',
Node2 = 'node2@host',
net_kernel:connect_node(Node2).
%% Check connected nodes
list_nodes() ->
Nodes = [node() | nodes()],
io:format("Connected nodes: ~p~n", [Nodes]).
%% Monitor node connections
monitor_nodes() ->
net_kernel:monitor_nodes(true),
receive
{nodeup, Node} ->
io:format("Node up: ~p~n", [Node]);
{nodedown, Node} ->
io:format("Node down: ~p~n", [Node])
end.
%% Node configuration
start_distributed() ->
{ok, _} = net_kernel:start([mynode, shortnames]),
erlang:set_cookie(node(), secret_cookie).
%% Hidden nodes (for monitoring)
connect_hidden(Node) ->
net_kernel:connect_node(Node),
erlang:disconnect_node(Node),
net_kernel:hidden_connect_node(Node).
%% Get node information
node_info() ->
#{
name => node(),
cookie => erlang:get_cookie(),
nodes => nodes(),
alive => is_alive()
}.
Node connectivity enables building distributed clusters with automatic discovery.
Send messages to processes on remote nodes using same syntax as local messaging.
%% Send to registered process on remote node
send_remote(Node, Name, Message) ->
{Name, Node} ! Message.
%% Spawn process on remote node
spawn_on_remote(Node, Fun) ->
spawn(Node, Fun).
spawn_on_remote(Node, Module, Function, Args) ->
spawn(Node, Module, Function, Args).
%% Distributed request-response
remote_call(Node, Module, Function, Args) ->
Pid = spawn(Node, fun() ->
Result = apply(Module, Function, Args),
receive
{From, Ref} -> From ! {Ref, Result}
end
end),
Ref = make_ref(),
Pid ! {self(), Ref},
receive
{Ref, Result} -> {ok, Result}
after 5000 ->
{error, timeout}
end.
%% Distributed work distribution
-module(work_dispatcher).
-export([start/0, dispatch/1]).
start() ->
register(?MODULE, spawn(fun() -> loop([]) end)).
dispatch(Work) ->
?MODULE ! {dispatch, Work}.
loop(Workers) ->
receive
{dispatch, Work} ->
Node = select_node(nodes()),
Pid = spawn(Node, fun() -> do_work(Work) end),
loop([{Pid, Node} | Workers])
end.
select_node(Nodes) ->
lists:nth(rand:uniform(length(Nodes)), Nodes).
do_work(Work) ->
Result = process_work(Work),
io:format("Work done on ~p: ~p~n", [node(), Result]).
process_work(Work) -> Work * 2.
%% Remote group leader for output
remote_process_with_io(Node) ->
spawn(Node, fun() ->
group_leader(self(), self()),
io:format("Output from ~p~n", [node()])
end).
Location-transparent messaging enables seamless distributed communication.
Register process names globally across distributed clusters.
%% Global registration
register_global(Name) ->
Pid = spawn(fun() -> global_loop() end),
global:register_name(Name, Pid),
Pid.
global_loop() ->
receive
{From, Message} ->
From ! {reply, Message},
global_loop();
stop -> ok
end.
%% Send to globally registered process
send_global(Name, Message) ->
case global:whereis_name(Name) of
undefined ->
{error, not_found};
Pid ->
Pid ! Message,
ok
end.
%% Global name with conflict resolution
register_with_resolve(Name) ->
Pid = spawn(fun() -> server_loop() end),
ResolveFun = fun(Name, Pid1, Pid2) ->
%% Keep process on node with lower name
case node(Pid1) < node(Pid2) of
true -> Pid1;
false -> Pid2
end
end,
global:register_name(Name, Pid, ResolveFun).
server_loop() ->
receive
Message ->
io:format("Received: ~p on ~p~n", [Message, node()]),
server_loop()
end.
%% Global synchronization
sync_global() ->
global:sync().
%% List globally registered names
list_global_names() ->
global:registered_names().
%% Re-register after node reconnection
ensure_global_registration(Name, Fun) ->
case global:whereis_name(Name) of
undefined ->
Pid = spawn(Fun),
global:register_name(Name, Pid),
Pid;
Pid ->
Pid
end.
Global registration enables location-independent process discovery.
Supervise processes across multiple nodes for cluster-wide fault tolerance.
-module(distributed_supervisor).
-behaviour(supervisor).
-export([start_link/0, start_worker/1]).
-export([init/1]).
start_link() ->
supervisor:start_link({local, ?MODULE}, ?MODULE, []).
start_worker(Node) ->
ChildSpec = #{
id => make_ref(),
start => {worker, start_link, [Node]},
restart => permanent,
type => worker
},
supervisor:start_child(?MODULE, ChildSpec).
init([]) ->
SupFlags = #{
strategy => one_for_one,
intensity => 5,
period => 60
},
{ok, {SupFlags, []}}.
%% Worker module spawning on specific node
-module(worker).
-export([start_link/1, loop/0]).
start_link(Node) ->
Pid = spawn_link(Node, ?MODULE, loop, []),
{ok, Pid}.
loop() ->
receive
stop -> ok;
Msg ->
io:format("Worker on ~p: ~p~n", [node(), Msg]),
loop()
end.
%% Distributed process groups
-module(pg_example).
-export([start/0, join/1, broadcast/1]).
start() ->
pg:start_link().
join(Group) ->
pg:join(Group, self()).
broadcast(Group, Message) ->
Members = pg:get_members(Group),
[Pid ! Message || Pid <- Members].
Distributed supervision maintains system health across node failures.
Execute function calls on remote nodes with various invocation patterns.
%% Basic RPC
simple_rpc(Node, Module, Function, Args) ->
rpc:call(Node, Module, Function, Args).
%% RPC with timeout
timed_rpc(Node, Module, Function, Args, Timeout) ->
rpc:call(Node, Module, Function, Args, Timeout).
%% Async RPC
async_rpc(Node, Module, Function, Args) ->
Key = rpc:async_call(Node, Module, Function, Args),
%% Later retrieve result
rpc:yield(Key).
%% Parallel RPC to multiple nodes
parallel_rpc(Nodes, Module, Function, Args) ->
rpc:multicall(Nodes, Module, Function, Args).
%% Parallel call with results
parallel_rpc_results(Nodes, Module, Function, Args) ->
rpc:multicall(Nodes, Module, Function, Args, 5000).
%% Cast (fire and forget)
cast_rpc(Node, Module, Function, Args) ->
rpc:cast(Node, Module, Function, Args).
%% Broadcast to all nodes
broadcast_rpc(Module, Function, Args) ->
Nodes = [node() | nodes()],
rpc:multicall(Nodes, Module, Function, Args).
%% Parallel map over nodes
pmap_nodes(Fun, List) ->
Nodes = nodes(),
DistFun = fun(X) ->
Node = lists:nth((X rem length(Nodes)) + 1, Nodes),
rpc:call(Node, erlang, apply, [Fun, [X]])
end,
lists:map(DistFun, List).
RPC enables convenient remote execution with location transparency.
Handle network partitions and understand CAP theorem trade-offs.
%% Detect network partition
detect_partition() ->
ExpectedNodes = [node1@host, node2@host, node3@host],
CurrentNodes = nodes(),
Missing = ExpectedNodes -- CurrentNodes,
case Missing of
[] -> ok;
Nodes -> {partition, Nodes}
end.
%% Partition healing strategy
-module(partition_handler).
-export([monitor_cluster/1]).
monitor_cluster(ExpectedNodes) ->
net_kernel:monitor_nodes(true),
monitor_loop(ExpectedNodes, nodes()).
monitor_loop(Expected, Current) ->
receive
{nodeup, Node} ->
NewCurrent = [Node | Current],
case length(NewCurrent) == length(Expected) of
true ->
io:format("Cluster fully connected~n"),
heal_partition();
false ->
ok
end,
monitor_loop(Expected, NewCurrent);
{nodedown, Node} ->
NewCurrent = lists:delete(Node, Current),
io:format("Partition detected: ~p~n", [Node]),
monitor_loop(Expected, NewCurrent)
end.
heal_partition() ->
%% Synchronize state after partition heals
global:sync(),
ok.
%% Consensus with majority
-module(consensus).
-export([propose/2, vote/3]).
propose(Nodes, Value) ->
Ref = make_ref(),
[Node ! {vote, self(), Ref, Value} || Node <- Nodes],
collect_votes(Ref, length(Nodes), 0).
collect_votes(_Ref, Total, Votes) when Votes > Total div 2 ->
{ok, majority};
collect_votes(_Ref, Total, Total) ->
{error, no_majority};
collect_votes(Ref, Total, Votes) ->
receive
{vote, Ref, accept} ->
collect_votes(Ref, Total, Votes + 1);
{vote, Ref, reject} ->
collect_votes(Ref, Total, Votes)
after 5000 ->
{error, timeout}
end.
vote(From, Ref, Value) ->
Decision = evaluate_proposal(Value),
From ! {vote, Ref, Decision}.
evaluate_proposal(_Value) -> accept.
Partition handling strategies maintain system availability during network failures.
Use short names for local clusters and long names for internet-wide distribution
Set same cookie on all nodes in trusted cluster for security
Monitor node connections to detect and handle network partitions
Use global registration sparingly as it adds coordination overhead
Implement partition detection and healing strategies for resilience
Design for eventual consistency in distributed systems accepting CAP limitations
Use RPC for simple calls but prefer message passing for complex protocols
Test with network failures using tools like toxiproxy or chaos engineering
Implement proper timeouts on distributed calls to handle slow networks
Use distributed supervision to maintain fault tolerance across nodes
Not setting cookies prevents nodes from connecting causing silent failures
Using global registry everywhere creates single point of failure and bottleneck
Not handling node disconnection causes processes to hang indefinitely
Assuming network reliability leads to incorrect behavior during partitions
Using long timeouts in RPC calls causes cascading delays during failures
Not testing network partitions misses critical failure modes
Forgetting to synchronize global registry after partition heals
Using same node name on multiple machines causes conflicts
Not monitoring node health prevents detecting degraded cluster state
Relying on strict consistency in distributed setting violates CAP theorem
Apply distribution when building systems requiring high availability and fault tolerance.
Use distributed supervision for critical services needing automatic failover.
Leverage multiple nodes for horizontal scalability beyond single machine limits.
Implement distributed systems when geographic distribution provides latency benefits.
Use clustering for load distribution across multiple servers.
Apply distribution patterns for building resilient microservices architectures.