[Pvfs2-developers] Re: BMI TCP socket close for sock buf size
Phil Carns
pcarns at wastedcycles.org
Mon Jul 17 11:59:45 EDT 2006
Hi Walt,
I'm not sure that we really want to literally run client state machines
on the server. Most of them probably are probably not going to map
correctly to that environment (they store results in different places,
have different assumptions about who to contact, look for config values
in different places, etc.).
I think if one were doing server to server communication it would be
better to just implement new states that send requests (using
msgpairarray) where needed according to the server's assumptions. In
that case, a server would just be acting as a client in the request
protocol sense, rather than in the state machine sense. It would need
different code to handle the resonses etc.
-Phil
Walt Ligon wrote:
> OK, thanks (and thanks Brad). that's kind of what I thought. For the
> moment it really isn't an issue of being "in" the server, as being used
> by client state machines versus server state machines. I presume when
> you used it in the server, the server was acting as a client and running
> a client state machine.
>
> This is where I get to the complicated part of this whole thing. The
> concurrency is *almost* done (he says with undeserved bravado) but the
> real trick is we want to be able to run client state machines on the
> server. I have ideas for this, but they're a little sketchy. Anyway,
> it's not a big deal at this point, I'm getting to the point I can move
> things around a bit if I need to.
>
> Phil, thanks for your response to Sam. that is exactly how I was going
> to put it (word for word, how did you DO that?) so I'm glad I don't have
> to type it up.
>
> Good stuff! onward!
>
> Walt
>
> Phil Carns wrote:
>
>> The server is definitely not using the msgpairarray code right now. I
>> think it would be handy to keep it in the common area, though, because
>> it could be used for server to server communication in the future.
>>
>> It actually started out just being a client side thing, but I moved it
>> to common while I was working on my dissertation.
>>
>> -Phil
>>
>> Walt Ligon wrote:
>>
>>>
>>> Hey guy, I'm trying to understand why the msgpairarray stuff is in the
>>> common directory and has this stuff to let it work with both the
>>> client and the server (and in fact gets compiled with both the client
>>> and the server) when it doesn't appear to get used by the server at
>>> all. Is it getting used in some tricky way I overlooked, or is this
>>> an historical artifact, or was it supposed it might get used, even
>>> though it never did?
>>>
>>> Unless there's a good reason otherwise I'm inclined to move it into
>>> the client code.
>>>
>>> Walt
>>> _______________________________________________
>>> Pvfs2-developers mailing list
>>> Pvfs2-developers at beowulf-underground.org
>>> http://www.beowulf-underground.org/mailman/listinfo/pvfs2-developers
More information about the Pvfs2-developers
mailing list