1. Why didn't they just use Twisted? 2. Why didn't they predict tornado and make it better? 3. Yeah, but (tornado|twisted|my half baked implementation) is still faster at serving 'hello world' than diesel.

---

I for one welcome this new breed of choice in this space. I'm interested in "real-timing" an application I'm currently working on, so having more choices as to which way to implement it is great.

One huge Twisted advantage is that you can have your async comet reactors running in the same process as other Twister reactors, which can be very useful for many applications you might want Comet for. What's the payoff for using this instead?

BTW: These are straight questions, not sarcastic questions. I am perfectly willing to extend benefit of the doubt and assume there are good answers. I just don't know what they are, and I'd like to know, as I am potentially looking to use some stuff like this myself in the near future.

Twisted is a very capable system, very well written, with all kinds of capabilities that diesel doesn't have and never will. So it's not a capabilities thing.

It's written by a team of guys who are crazy smart, and who know async better than most people on the planet, me included. So it's not a competence thing.

The performance difference between twisted and most other Python async libraries isn't going to be significant. We're all mostly benchmarking epoll or select or whathaveyou, plus a thin layer of frames to get from there to your application code. So it's really not a performance thing either, though hackers love to talk about this anyway.

It's a style thing. Twisted doesn't feel "Pythonic" to me. It doesn't have that succinctness that makes you say "shit, I'm done already?" It's got lots of big-A architecture that's very Correct, but in practice, leaves you wondering why you're being burdened with it when that rainy day when it pays dividends never comes. Purity is allowed to triumph over practicality at every turn.

That's one man's take. I don't claim it's the universal truth, and Twisted has many very happy users. But I suspect I'm not alone in this assessment.

That being said, I will relish the day when someone can do _something_ in the Python async space and not immediately be thrust into the ring as the latest combatant in the twisted-vs-the-new-guy debate. New guys never stop coming, and that's a wonderful thing for the evolution of computing and programming.

Every time you have to do asynchronous work, you have to mentally follow the chain of deferreds to ensure you understand exactly what code will be called at what time. Coupled with its unpythonic, deep hierarchical API, Twisted almost literally twists your code into a jumbled blob.

Unless you need the existing protocol-specific APIs twisted provides, stay far, far away. Find something more lightweight, like this, or Eventlet, or something else that lets your code remain concise and clear.

This comes from my experience writing a Twisted server for my startup, and subsequently rewriting it when the Twisted version became far too difficult and frustrating to maintain.

I hear this all the time, "argh, Deferreds are so hard to understand," as if there's some kind of magic going on in a Deferred. Deferreds are just a way to encapsulate two callbacks, one for errors and another for successful callbacks.

If you're writing any kind of significantly complicated asynchronous process, what is the difference between following a bunch of Deferreds and following a bunch of callbacks??

Asynchronous coding is hard. There's no framework that is going to make that go away. Diesel looks nice enough, but although it shows promise, there's not enough examples of hardcore usage to make a sufficient comparison. An asynchronous IO framework that has nothing but HTTP and echo examples doesn't even scratch the surface of the kinds of apps that require the advanced asynchrony available in Twisted.

The difference is that in co-routine based code (such as concurrence or eventlet) there are no callbacks. Co-routines are all about message passing which leads to much cleaner and much less code in most applications.

It's not uncommon to see 40%+ boilerplate callback-handling code in a twisted app. Those are not needed in a coro-environment.

Asynchronous coding is hard.

Actually the established patterns for implementing asynchronous code are hard. You get to choose between threading-hell (deadlocks, races) and callback-hell (code-bloat). I have no idea why these abstractions grew so popular, my guess would be because they are "closest to the metal".

But they are not without alternatives; co-routines, actor-based concurrency and erlang exist - all of which enable fairly straightforward "Do what I mean" development.

I've been including Eventlet in a lot of my comments lately, but not because I have any affiliation with it (I don't). But it has quite literally made asynchronous coding so much easier that going back to deferreds or callbacks is a huge inconvenience.

My comments previously reflect equally on deferreds and callback-based asynchronous programming. Of course those make async programming hard.

It doesn't have to be that hard.

    def echo(remote_addr):
        their_message = yield until_eol()
        yield "you said: %s\r\n" % their_message.strip()

They both have a fairly small audience but when you look at their mailing lists you'll see activity.

But you're right, it doesn't have much to do with comet at this point.

I can only assume you're probably referring to some of these things:

1. Response latency, esp at 99%-ish mark, under load 2. Memory usage per connection under many idle connections 3. Scalability wrt. data sharing, backing persistent data, replication/redundancy strategies, etc

I'm not sure if you were referring to us, the diesel authors, when you indicated that someone didn't understand something about Comet scaling, but I assure you that diesel does 1 and 2 quite nicely, as do most sensibly-written things based on epoll, kqueue, etc. The benchmark page is with 1k concurrent connections, and it does well with more than that, too.

If you're referring to item 3, I'm afraid diesel doesn't tackle that element of scalability yet. It's more of an I/O library, not really a framework with aspirations of providing high availability. We have some plans and quite a bit of mostly-working code that implements a paxos-based framework for achieving those goals as well, but release of that part of the framework is some months out.

Writing good unit tests for this stuff is a higher priority--unit testing async code is a PITA. We're probably going to need to steal ideas from twisted.trial or something.

Thanks for checking out diesel.

...

We have some plans and quite a bit of mostly-working code that implements a paxos-based framework

Don't. Seriously, don't go that route, it's a huge waste of time. Instead: Keep your server shared-nothing and make it interface with as many different breeds of Message Queues on the backend as possible (AMQP, Stomp etc.).

That's what any non-trivial comet app needs to do anyways and any kind of intelligence inside the comet-server beyond dispatching between the backend-queue and the browser only gets in the way.

The canonical setup is:

    Browser <-> Diesel <-> Message Queue

So, we're internalizing that queueing behavior into diesel.

(You can tell us not to do it, but it's pretty much done. :-)

Yes, and the message broker is pretty much the only place where it makes sense.

So, we're internalizing that queueing behavior into diesel.

An exercise in futility.

The main application dealing with the actual messages will still need to know which Diesel instance to talk to, in order to reach a particular subscriber.

How do you solve that?

Every diesel node is an instance of an application that is willing to be provide a service that acts as the master/router for a certain class of messages. Paxos ensures there is only one master elected for every message class, and this router is re-elected should the router go down. The routing table of who is master for what class of messages is kept in sync across all nodes.

It's almost exactly like registered processes in an erlang cluster--reserving the exclusive right to handle certain messages. Simpler master/slave relationships can take over from there.

You mean one that the user writes (starting with "import diesel")? If so then I'd think such a tight coupling is a bad idea. Why prevent non-python users from using Diesel as a comet-broker? Why even force python-users to tightly couple their app with Diesel when it'd be so much easier to abstract out the interface they need?

provide a service that acts as the master/router for a certain class of messages. Paxos ensures there is only one master elected for every message class, and this router is re-elected should the router go down. The routing table of who is master for what class of messages is kept in sync across all nodes.

If you're going to all these lengths then why on earth couple it to a comet server? All these features belong in a message broker, not in a protocol endpoint. You'd make many people happy by building a STOMP or AMQP broker with these features, even people that are not interested in comet at all.

Wrt your other reply: No, we don't agree. But at least I have a better idea of what you have in mind now, thanks for that. Also this all is ofcourse just my humble opinion. It's your project and you're free to overengineer at your peril ;-)

To clarify--we're going to build a comet framework _on_ diesel, but diesel itself is more of a general async I/O system with cluster messaging features. We intend it to be applicable for building arbitrary networked application using similar patterns to what you'd do in erlang--message passing.

We just _happen_ to be focusing on building a comet framework first and foremost on it. That will probably be called "dieselweb".

So, the "comet server" portion of our framework may not, in fact, utilize any of this message-broker stuff. But other components might. We're actually going to try to build something fairly unique here, but I don't have all the details ready to put out there yet.

I guess I just have "Here's a graph showing req/s for twisted/tornado/etc etc" overload lately.

It's definitely nice to see more open source options in the Comet arena :)

Oh and http://shoptalkapp.com/ looks very interesting also

IO errors are some of the most annoying errors to debug, and the whole point of using a preexisting IO package is to not have to worry about errors in it. I would say you need 100% test coverage of your core library before I could consider using Diesel for a major project.

Just my $0.02...