davisp commented on a change in pull request #470: Scheduling Replicator URL: https://github.com/apache/couchdb/pull/470#discussion_r110424393
########## File path: src/couch_replicator/src/couch_replicator_connection.erl ########## @@ -0,0 +1,211 @@ +% Licensed under the Apache License, Version 2.0 (the "License"); you may not +% use this file except in compliance with the License. You may obtain a copy of +% the License at +% +% http://www.apache.org/licenses/LICENSE-2.0 +% +% Unless required by applicable law or agreed to in writing, software +% distributed under the License is distributed on an "AS IS" BASIS, WITHOUT +% WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the +% License for the specific language governing permissions and limitations under +% the License. + +-module(couch_replicator_connection). + +-behavior(gen_server). +-behavior(config_listener). + +-export([start_link/0]). +-export([init/1, handle_call/3, handle_cast/2, handle_info/2]). +-export([code_change/3, terminate/2]). + +-export([acquire/1, relinquish/1]). + +-export([handle_config_change/5, handle_config_terminate/3]). + +-define(DEFAULT_CLOSE_INTERVAL, 90000). +-define(RELISTEN_DELAY, 5000). + +-record(state, { + close_interval, + timer +}). + +-record(connection, { + worker, + host, + port, + mref +}). + +-include_lib("ibrowse/include/ibrowse.hrl"). + + +start_link() -> + gen_server:start_link({local, ?MODULE}, ?MODULE, [], []). + + +init([]) -> + process_flag(trap_exit, true), + ?MODULE = ets:new(?MODULE, [named_table, public, {keypos, #connection.worker}]), + ok = config:listen_for_changes(?MODULE, nil), + Interval = config:get_integer("replicator", "connection_close_interval", ?DEFAULT_CLOSE_INTERVAL), + {ok, Timer} = timer:send_after(Interval, close_idle_connections), + ibrowse:add_config([{inactivity_timeout, Interval}]), + {ok, #state{close_interval=Interval, timer=Timer}}. + + +acquire(URL) when is_binary(URL) -> + acquire(binary_to_list(URL)); + +acquire(URL) -> + case gen_server:call(?MODULE, {acquire, URL}) of + {ok, Worker} -> + link(Worker), + {ok, Worker}; + {error, all_allocated} -> + {ok, Pid} = ibrowse:spawn_link_worker_process(URL), + ok = gen_server:call(?MODULE, {create, URL, Pid}), + {ok, Pid}; + {error, Reason} -> + {error, Reason} + end. + + +relinquish(Worker) -> + unlink(Worker), + gen_server:cast(?MODULE, {relinquish, Worker}). + + +handle_call({acquire, URL}, From, State) -> + {Pid, _Ref} = From, + case ibrowse_lib:parse_url(URL) of + #url{host=Host, port=Port} -> Review comment: This is the most worrisome part of the whole PR for me. We're starting HTTP connections outside of this pool and then parsing the URLs after the fact. And specifically, we're not checking here that the URLs we're provided don't have a username/password set. If we did get one with that and assuming that ibrowse caches the credentials in the worker then its possible we're leaking authentication credentials across replications. We should very much insist that all workers do not have authentication cached and then make sure we provide it for each request individually. And we should also assert that ibrowse isn't caching credentials between requests as well. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
