--- AnyEvent-MP/MP.pm 2009/08/24 08:04:52 1.60 +++ AnyEvent-MP/MP.pm 2009/08/31 11:11:27 1.74 @@ -13,9 +13,7 @@ $SELF # receiving/own port id in rcv callbacks # initialise the node so it can send/receive messages - initialise_node; # -OR- - initialise_node "localhost:4040"; # -OR- - initialise_node "slave/", "localhost:4040" + configure; # ports are message endpoints @@ -25,12 +23,12 @@ snd @msg_with_first_element_being_a_port; # creating/using ports, the simple way - my $simple_port = port { my @msg = @_; 0 }; + my $simple_port = port { my @msg = @_ }; # creating/using ports, tagged message matching my $port = port; - rcv $port, ping => sub { snd $_[0], "pong"; 0 }; - rcv $port, pong => sub { warn "pong received\n"; 0 }; + rcv $port, ping => sub { snd $_[0], "pong" }; + rcv $port, pong => sub { warn "pong received\n" }; # create a port on another node my $port = spawn $node, $initfunc, @initdata; @@ -42,10 +40,11 @@ =head1 CURRENT STATUS - AnyEvent::MP - stable API, should work - AnyEvent::MP::Intro - outdated - AnyEvent::MP::Kernel - WIP - AnyEvent::MP::Transport - mostly stable + bin/aemp - stable. + AnyEvent::MP - stable API, should work. + AnyEvent::MP::Intro - uptodate, but incomplete. + AnyEvent::MP::Kernel - mostly stable. + AnyEvent::MP::Global - stable API, protocol not yet final. stay tuned. @@ -54,14 +53,12 @@ This module (-family) implements a simple message passing framework. Despite its simplicity, you can securely message other processes running -on the same or other hosts. +on the same or other hosts, and you can supervise entities remotely. For an introduction to this module family, see the L -manual page. +manual page and the examples under F. -At the moment, this module family is severly broken and underdocumented, -so do not use. This was uploaded mainly to reserve the CPAN namespace - -stay tuned! +At the moment, this module family is a bit underdocumented. =head1 CONCEPTS @@ -72,38 +69,52 @@ A port is something you can send messages to (with the C function). Ports allow you to register C handlers that can match all or just -some messages. Messages will not be queued. +some messages. Messages send to ports will not be queued, regardless of +anything was listening for them or not. -=item port id - C +=item port ID - C -A port ID is the concatenation of a noderef, a hash-mark (C<#>) as -separator, and a port name (a printable string of unspecified format). An -exception is the the node port, whose ID is identical to its node -reference. +A port ID is the concatenation of a node ID, a hash-mark (C<#>) as +separator, and a port name (a printable string of unspecified format). =item node A node is a single process containing at least one port - the node port, -which provides nodes to manage each other remotely, and to create new +which enables nodes to manage each other remotely, and to create new ports. -Nodes are either private (single-process only), slaves (connected to a -master node only) or public nodes (connectable from unrelated nodes). +Nodes are either public (have one or more listening ports) or private +(no listening ports). Private nodes cannot talk to other private nodes +currently. + +=item node ID - C<[a-za-Z0-9_\-.:]+> + +A node ID is a string that uniquely identifies the node within a +network. Depending on the configuration used, node IDs can look like a +hostname, a hostname and a port, or a random string. AnyEvent::MP itself +doesn't interpret node IDs in any way. + +=item binds - C + +Nodes can only talk to each other by creating some kind of connection to +each other. To do this, nodes should listen on one or more local transport +endpoints - binds. Currently, only standard C specifications can +be used, which specify TCP ports to listen on. + +=item seeds - C + +When a node starts, it knows nothing about the network. To teach the node +about the network it first has to contact some other node within the +network. This node is called a seed. + +Seeds are transport endpoint(s) of as many nodes as one wants. Those nodes +are expected to be long-running, and at least one of those should always +be available. When nodes run out of connections (e.g. due to a network +error), they try to re-establish connections to some seednodes again to +join the network. -=item noderef - C, C, C - -A node reference is a string that either simply identifies the node (for -private and slave nodes), or contains a recipe on how to reach a given -node (for public nodes). - -This recipe is simply a comma-separated list of C pairs (for -TCP/IP, other protocols might look different). - -Node references come in two flavours: resolved (containing only numerical -addresses) or unresolved (where hostnames are used instead of addresses). - -Before using an unresolved node reference in a message you first have to -resolve it. +Apart from being sued for seeding, seednodes are not special in any way - +every public node can be a seednode. =back @@ -129,8 +140,8 @@ our @EXPORT = qw( NODE $NODE *SELF node_of after - resolve_node initialise_node - snd rcv mon mob_guard kil reg psub spawn + configure + snd rcv mon mon_guard kil reg psub spawn port ); @@ -144,164 +155,131 @@ =item $thisnode = NODE / $NODE -The C function returns, and the C<$NODE> variable contains the -noderef of the local node. The value is initialised by a call to -C. +The C function returns, and the C<$NODE> variable contains, the node +ID of the node running in the current process. This value is initialised by +a call to C. -=item $noderef = node_of $port +=item $nodeid = node_of $port -Extracts and returns the noderef from a port ID or a noderef. +Extracts and returns the node ID from a port ID or a node ID. -=item initialise_node $noderef, $seednode, $seednode... +=item configure key => value... -=item initialise_node "slave/", $master, $master... +Before a node can talk to other nodes on the network (i.e. enter +"distributed mode") it has to configure itself - the minimum a node needs +to know is its own name, and optionally it should know the addresses of +some other nodes in the network to discover other nodes. -Before a node can talk to other nodes on the network it has to initialise -itself - the minimum a node needs to know is it's own name, and optionally -it should know the noderefs of some other nodes in the network. - -This function initialises a node - it must be called exactly once (or +This function configures a node - it must be called exactly once (or never) before calling other AnyEvent::MP functions. -All arguments (optionally except for the first) are noderefs, which can be -either resolved or unresolved. - -The first argument will be looked up in the configuration database first -(if it is C then the current nodename will be used instead) to find -the relevant configuration profile (see L). If none is found then -the default configuration is used. The configuration supplies additional -seed/master nodes and can override the actual noderef. - -There are two types of networked nodes, public nodes and slave nodes: - =over 4 -=item public nodes +=item step 1, gathering configuration from profiles -For public nodes, C<$noderef> (supplied either directly to -C or indirectly via a profile or the nodename) must be a -noderef (possibly unresolved, in which case it will be resolved). - -After resolving, the node will bind itself on all endpoints and try to -connect to all additional C<$seednodes> that are specified. Seednodes are -optional and can be used to quickly bootstrap the node into an existing -network. - -=item slave nodes - -When the C<$noderef> (either as given or overriden by the config file) -is the special string C, then the node will become a slave -node. Slave nodes cannot be contacted from outside and will route most of -their traffic to the master node that they attach to. - -At least one additional noderef is required (either by specifying it -directly or because it is part of the configuration profile): The node -will try to connect to all of them and will become a slave attached to the -first node it can successfully connect to. - -Note that slave nodes cannot change their name, and consequently, their -master, so if the master goes down, the slave node will not function well -anymore until it can re-establish conenciton to its master. This makes -slave nodes unsuitable for long-term nodes or fault-tolerant networks. +The function first looks up a profile in the aemp configuration (see the +L commandline utility). The profile name can be specified via the +named C parameter. If it is missing, then the nodename (F) will be used as profile name. + +The profile data is then gathered as follows: + +First, all remaining key => value pairs (all of which are conviniently +undocumented at the moment) will be interpreted as configuration +data. Then they will be overwritten by any values specified in the global +default configuration (see the F utility), then the chain of +profiles chosen by the profile name (and any C attributes). + +That means that the values specified in the profile have highest priority +and the values specified directly via C have lowest priority, +and can only be used to specify defaults. + +If the profile specifies a node ID, then this will become the node ID of +this process. If not, then the profile name will be used as node ID. The +special node ID of C will be replaced by a random node ID. + +=item step 2, bind listener sockets + +The next step is to look up the binds in the profile, followed by binding +aemp protocol listeners on all binds specified (it is possible and valid +to have no binds, meaning that the node cannot be contacted form the +outside. This means the node cannot talk to other nodes that also have no +binds, but it can still talk to all "normal" nodes). + +If the profile does not specify a binds list, then a default of C<*> is +used, meaning the node will bind on a dynamically-assigned port on every +local IP address it finds. + +=item step 3, connect to seed nodes + +As the last step, the seeds list from the profile is passed to the +L module, which will then use it to keep +connectivity with at least one node at any point in time. =back -This function will block until all nodes have been resolved and, for slave -nodes, until it has successfully established a connection to a master -server. - -All the seednodes will also be specially marked to automatically retry -connecting to them infinitely. - -Example: become a public node listening on the guessed noderef, or the one -specified via C for the current node. This should be the most common -form of invocation for "daemon"-type nodes. - - initialise_node; - -Example: become a slave node to any of the the seednodes specified via -C. This form is often used for commandline clients. - - initialise_node "slave/"; - -Example: become a slave node to any of the specified master servers. This -form is also often used for commandline clients. - - initialise_node "slave/", "master1", "192.168.13.17", "mp.example.net"; - -Example: become a public node, and try to contact some well-known master -servers to become part of the network. +Example: become a distributed node using the locla node name as profile. +This should be the most common form of invocation for "daemon"-type nodes. - initialise_node undef, "master1", "master2"; + configure -Example: become a public node listening on port C<4041>. +Example: become an anonymous node. This form is often used for commandline +clients. - initialise_node 4041; + configure nodeid => "anon/"; -Example: become a public node, only visible on localhost port 4044. +Example: configure a node using a profile called seed, which si suitable +for a seed node as it binds on all local addresses on a fixed port (4040, +customary for aemp). - initialise_node "localhost:4044"; + # use the aemp commandline utility + # aemp profile seed nodeid anon/ binds '*:4040' -=item $cv = resolve_node $noderef + # then use it + configure profile => "seed"; -Takes an unresolved node reference that may contain hostnames and -abbreviated IDs, resolves all of them and returns a resolved node -reference. + # or simply use aemp from the shell again: + # aemp run profile seed -In addition to C pairs allowed in resolved noderefs, the -following forms are supported: - -=over 4 - -=item the empty string - -An empty-string component gets resolved as if the default port (4040) was -specified. - -=item naked port numbers (e.g. C<1234>) - -These are resolved by prepending the local nodename and a colon, to be -further resolved. - -=item hostnames (e.g. C, C) - -These are resolved by using AnyEvent::DNS to resolve them, optionally -looking up SRV records for the C port, if no port was -specified. - -=back + # or provide a nicer-to-remember nodeid + # aemp run profile seed nodeid "$(hostname)" =item $SELF Contains the current port id while executing C callbacks or C blocks. -=item SELF, %SELF, @SELF... +=item *SELF, SELF, %SELF, @SELF... Due to some quirks in how perl exports variables, it is impossible to -just export C<$SELF>, all the symbols called C are exported by this +just export C<$SELF>, all the symbols named C are exported by this module, but only C<$SELF> is currently used. =item snd $port, type => @data =item snd $port, @msg -Send the given message to the given port ID, which can identify either -a local or a remote port, and must be a port ID. +Send the given message to the given port, which can identify either a +local or a remote port, and must be a port ID. -While the message can be about anything, it is highly recommended to use a -string as first element (a port ID, or some word that indicates a request -type etc.). - -The message data effectively becomes read-only after a call to this -function: modifying any argument is not allowed and can cause many -problems. +While the message can be almost anything, it is highly recommended to +use a string as first element (a port ID, or some word that indicates a +request type etc.) and to consist if only simple perl values (scalars, +arrays, hashes) - if you think you need to pass an object, think again. + +The message data logically becomes read-only after a call to this +function: modifying any argument (or values referenced by them) is +forbidden, as there can be considerable time between the call to C +and the time the message is actually being serialised - in fact, it might +never be copied as within the same process it is simply handed to the +receiving port. The type of data you can transfer depends on the transport protocol: when JSON is used, then only strings, numbers and arrays and hashes consisting of those are allowed (no objects). When Storable is used, then anything that Storable can serialise and deserialise is allowed, and for the local -node, anything can be passed. +node, anything can be passed. Best rely only on the common denominator of +these. =item $local_port = port @@ -487,28 +465,28 @@ } } -=item $guard = mon $port, $cb->(@reason) +=item $guard = mon $port, $cb->(@reason) # call $cb when $port dies -=item $guard = mon $port, $rcvport +=item $guard = mon $port, $rcvport # kill $rcvport when $port dies -=item $guard = mon $port +=item $guard = mon $port # kill $SELF when $port dies -=item $guard = mon $port, $rcvport, @msg +=item $guard = mon $port, $rcvport, @msg # send a message when $port dies Monitor the given port and do something when the port is killed or messages to it were lost, and optionally return a guard that can be used to stop monitoring again. C effectively guarantees that, in the absence of hardware failures, -that after starting the monitor, either all messages sent to the port -will arrive, or the monitoring action will be invoked after possible -message loss has been detected. No messages will be lost "in between" -(after the first lost message no further messages will be received by the +after starting the monitor, either all messages sent to the port will +arrive, or the monitoring action will be invoked after possible message +loss has been detected. No messages will be lost "in between" (after +the first lost message no further messages will be received by the port). After the monitoring action was invoked, further messages might get delivered again. -Note that monitoring-actions are one-shot: once released, they are removed -and will not trigger again. +Note that monitoring-actions are one-shot: once messages are lost (and a +monitoring alert was raised), they are removed and will not trigger again. In the first form (callback), the callback is simply called with any number of C<@reason> elements (no @reason means that the port was deleted @@ -580,10 +558,10 @@ Optionally returns a guard that will stop the monitoring. This function is useful when you create e.g. timers or other watchers and -want to free them when the port gets killed: +want to free them when the port gets killed (note the use of C): $port->rcv (start => sub { - my $timer; $timer = mon_guard $port, AE::timer 1, 1, sub { + my $timer; $timer = mon_guard $port, AE::timer 1, 1, psub { undef $timer if 0.9 < rand; }); }); @@ -602,11 +580,12 @@ Kill the specified port with the given C<@reason>. -If no C<@reason> is specified, then the port is killed "normally" (linked -ports will not be kileld, or even notified). +If no C<@reason> is specified, then the port is killed "normally" (ports +monitoring other ports will not necessarily die because a port dies +"normally"). Otherwise, linked ports get killed with the same reason (second form of -C, see below). +C, see above). Runtime errors while evaluating C callbacks or inside C blocks will be reported as reason C<< die => $@ >>. @@ -621,13 +600,13 @@ Creates a port on the node C<$node> (which can also be a port ID, in which case it's the node where that port resides). -The port ID of the newly created port is return immediately, and it is -permissible to immediately start sending messages or monitor the port. +The port ID of the newly created port is returned immediately, and it is +possible to immediately start sending messages or to monitor the port. -After the port has been created, the init function is -called. This function must be a fully-qualified function name -(e.g. C). To specify a function in the main -program, use C<::name>. +After the port has been created, the init function is called on the remote +node, in the same context as a C callback. This function must be a +fully-qualified function name (e.g. C). To +specify a function in the main program, use C<::name>. If the function doesn't exist, then the node tries to C the package, then the package above the package and so on (e.g. @@ -637,9 +616,10 @@ The init function is then called with the newly-created port as context object (C<$SELF>) and the C<@initdata> values as arguments. -A common idiom is to pass your own port, monitor the spawned port, and -in the init function, monitor the original port. This two-way monitoring -ensures that both ports get cleaned up when there is a problem. +A common idiom is to pass a local port, immediately monitor the spawned +port, and in the remote init function, immediately monitor the passed +local port. This two-way monitoring ensures that both ports get cleaned up +when there is a problem. Example: spawn a chat server port on C<$othernode>. @@ -691,7 +671,9 @@ Either sends the given message, or call the given callback, after the specified number of seconds. -This is simply a utility function that come sin handy at times. +This is simply a utility function that comes in handy at times - the +AnyEvent::MP author is not convinced of the wisdom of having it, though, +so it may go away in the future. =cut @@ -724,14 +706,11 @@ =over 4 -=item * Node references contain the recipe on how to contact them. +=item * Node IDs are arbitrary strings in AEMP. -Erlang relies on special naming and DNS to work everywhere in the -same way. AEMP relies on each node knowing it's own address(es), with -convenience functionality. - -This means that AEMP requires a less tightly controlled environment at the -cost of longer node references and a slightly higher management overhead. +Erlang relies on special naming and DNS to work everywhere in the same +way. AEMP relies on each node somehow knowing its own address(es) (e.g. by +configuraiton or DNS), but will otherwise discover other odes itself. =item * Erlang has a "remote ports are like local ports" philosophy, AEMP uses "local ports are like remote ports". @@ -770,19 +749,10 @@ without any of the processes realising it (i.e. you send messages a, b, and c, and the other side only receives messages a and c). -AEMP guarantees correct ordering, and the guarantee that there are no -holes in the message sequence. - -=item * In Erlang, processes can be declared dead and later be found to be -alive. - -In Erlang it can happen that a monitored process is declared dead and -linked processes get killed, but later it turns out that the process is -still alive - and can receive messages. - -In AEMP, when port monitoring detects a port as dead, then that port will -eventually be killed - it cannot happen that a node detects a port as dead -and then later sends messages to it, finding it is still alive. +AEMP guarantees correct ordering, and the guarantee that after one message +is lost, all following ones sent to the same port are lost as well, until +monitoring raises an error, so there are no silent "holes" in the message +sequence. =item * Erlang can send messages to the wrong port, AEMP does not. @@ -796,18 +766,19 @@ =item * Erlang uses unprotected connections, AEMP uses secure authentication and can use TLS. -AEMP can use a proven protocol - SSL/TLS - to protect connections and +AEMP can use a proven protocol - TLS - to protect connections and securely authenticate nodes. =item * The AEMP protocol is optimised for both text-based and binary communications. -The AEMP protocol, unlike the Erlang protocol, supports both -language-independent text-only protocols (good for debugging) and binary, -language-specific serialisers (e.g. Storable). +The AEMP protocol, unlike the Erlang protocol, supports both programming +language independent text-only protocols (good for debugging) and binary, +language-specific serialisers (e.g. Storable). By default, unless TLS is +used, the protocol is actually completely text-based. It has also been carefully designed to be implementable in other languages -with a minimum of work while gracefully degrading fucntionality to make the +with a minimum of work while gracefully degrading functionality to make the protocol simple. =item * AEMP has more flexible monitoring options than Erlang. @@ -820,14 +791,14 @@ =item * Erlang tries to hide remote/local connections, AEMP does not. -Monitoring in Erlang is not an indicator of process death/crashes, -as linking is (except linking is unreliable in Erlang). +Monitoring in Erlang is not an indicator of process death/crashes, in the +same way as linking is (except linking is unreliable in Erlang). In AEMP, you don't "look up" registered port names or send to named ports that might or might not be persistent. Instead, you normally spawn a port -on the remote node. The init function monitors the you, and you monitor -the remote port. Since both monitors are local to the node, they are much -more reliable. +on the remote node. The init function monitors you, and you monitor the +remote port. Since both monitors are local to the node, they are much more +reliable (no need for C). This also saves round-trips and avoids sending messages to the wrong port (hard to do in Erlang). @@ -838,29 +809,29 @@ =over 4 -=item Why strings for ports and noderefs, why not objects? +=item Why strings for port and node IDs, why not objects? We considered "objects", but found that the actual number of methods -thatc an be called are very low. Since port IDs and noderefs travel over +that can be called are quite low. Since port and node IDs travel over the network frequently, the serialising/deserialising would add lots of -overhead, as well as having to keep a proxy object. +overhead, as well as having to keep a proxy object everywhere. Strings can easily be printed, easily serialised etc. and need no special procedures to be "valid". -And a a miniport consists of a single closure stored in a global hash - it -can't become much cheaper. +And as a result, a miniport consists of a single closure stored in a +global hash - it can't become much cheaper. -=item Why favour JSON, why not real serialising format such as Storable? +=item Why favour JSON, why not a real serialising format such as Storable? In fact, any AnyEvent::MP node will happily accept Storable as framing format, but currently there is no way to make a node use Storable by -default. +default (although all nodes will accept it). The default framing protocol is JSON because a) JSON::XS is many times faster for small messages and b) most importantly, after years of experience we found that object serialisation is causing more problems -than it gains: Just like function calls, objects simply do not travel +than it solves: Just like function calls, objects simply do not travel easily over the network, mostly because they will always be a copy, so you always have to re-think your design. @@ -871,6 +842,13 @@ =head1 SEE ALSO +L - a gentle introduction. + +L - more, lower-level, stuff. + +L - network maintainance and port groups, to find +your applications. + L. =head1 AUTHOR