Search code examples
erlangerlang-otphotswap

Achieving code swapping in Erlang's gen_server


I am looking to make use of Erlang's hot code swapping feature on a gen_server, so that I don't have to restart it. How should I do that? When I searched, all I could find was one article which mentioned that I need to make use of gen_server:code_change callback.

However, I could not really find any documentation/examples on how to use this. Any help or links to resources greatly appreciated!


Solution

  • As I already mentioned the normal way of upgrading is creating the proper .appup and .relup files, and let release_handler do what needs to be done. However you can manually execute the steps involved, as described here. Sorry for the long answer.

    The following dummy gen_server implements a counter. The old version ("0") simply stores an integer as state, while the new version ("1") stores {tschak, Int} as state. As I said, this is a dummy example.

    z.erl (old):

    -module(z).
    -version("0").
    
    -export([start_link/0, boing/0]).
    
    -behavior(gen_server).
    -export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
    
    start_link() -> gen_server:start_link({local, ?MODULE}, ?MODULE, [], [{debug, [trace]}]). 
    
    boing() -> gen_server:call(?MODULE, boom).
    
    
    init([]) -> {ok, 0}.
    
    handle_call(boom, _From, Num) -> {reply, Num, Num+1};
    handle_call(_Call, _From, State) -> {noreply, State}.
    
    handle_cast(_Cast, State) -> {noreply, State}.
    
    handle_info(_Info, State) -> {noreply, State}.
    
    terminate(_Reason, _State) -> ok.
    
    code_change(_OldVsn, State, _Extra) -> {ok, State}.
    

    z.erl (new):

    -module(z).
    -version("1").
    
    -export([start_link/0, boing/0]).
    
    -behavior(gen_server).
    -export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
    
    start_link() -> gen_server:start_link({local, ?MODULE}, ?MODULE, [], [{debug, [trace]}]).
    
    boing() -> gen_server:call(?MODULE, boom).
    
    
    init([]) -> {ok, {tschak, 0}}.
    
    handle_call(boom, _From, {tschak, Num}) -> {reply, Num, {tschak, Num+1}};
    handle_call(_Call, _From, State) -> {noreply, State}.
    
    handle_cast(_Cast, State) -> {noreply, State}.
    
    handle_info(_Info, State) -> {noreply, State}.
    
    terminate(_Reason, _State) -> ok.
    
    code_change("0", Num, _Extra) -> {ok, {tschak, Num}}.
    

    Start the shell, and compile the old code. Notice the gen_server is started with debug trace.

    1> c(z).
    {ok,z}
    2> z:start_link().
    {ok,<0.38.0>}
    3> z:boing().
    *DBG* z got call boom from <0.31.0>
    *DBG* z sent 0 to <0.31.0>, new state 1
    0
    4> z:boing().
    *DBG* z got call boom from <0.31.0>
    *DBG* z sent 1 to <0.31.0>, new state 2
    1
    

    Works as expected: returns the Int, and new state is Int+1.

    Now replace z.erl with the new one, and execute the following steps.

    5> compile:file(z).
    {ok,z}
    6> sys:suspend(z).
    ok
    7> code:purge(z).
    false
    8> code:load_file(z).
    {module,z}
    9> sys:change_code(z,z,"0",[]).
    ok
    10> sys:resume(z).
    ok
    

    What you just did: 5: compiled the new code. 6: suspended the server. 7: purged older code (just in case). 8: loaded the new code. 9: invoked code change in process 'z' for module 'z' from version "0" with [] passed as "Extra" to code_change. 10: resumed the server.

    Now if you run some more tests, you can see, that the server works with the new state format:

    11> z:boing().
    *DBG* z got call boom from <0.31.0>
    *DBG* z sent 2 to <0.31.0>, new state {tschak,3}
    2
    12> z:boing().
    *DBG* z got call boom from <0.31.0>
    *DBG* z sent 3 to <0.31.0>, new state {tschak,4}
    3