[Pvfs2-developers] BMI send implemtations

[Rob Ross]

Thanks! -- Rob

Scott Atchley wrote:
> Hi Rob,
> 
> I will ping them. We can easily expand the bits for the peer id to 20 
> (or even 24).
> 
> Scott
> 
> On Aug 23, 2006, at 11:13 AM, Rob Ross wrote:
> 
>> Hi Scott,
>>
>> You might want to ping your colleagues at ORNL and see how many 
>> distinct peers they expect on upcoming XT* systems. Could be more than 
>> 64K, if they don't do I/O forwarding (which we at ANL all hope for...).
>>
>> Rob
>>
>> Scott Atchley wrote:
>>
>>> MX provides 64 bits of match info for sends/recvs. I plan to 
>>> partition the bits as follows:
>>> bits    comment
>>> 0-3    msg_type (conn_req, conn_ack, expected, unexpected, ...?)
>>> 4-7    reserved for credits (if used)
>>> 8-15     reserved
>>> 15-31    peer id (16 bits => 65K peers)
>>> 32-63    BMI tag
>>> The conn_req and con_ack message types allow me to do a simple 
>>> handshake to establish MX state (hostname, NIC index, endpoint index) 
>>> and agree on a version number. I'm reserving bits for credits should 
>>> flow control be necessary and another 8 bits for future use if 
>>> needed. I am assuming that 65K peers will be enough for awhile. If 
>>> you think that PVFS will be deployed on systems with more than 65K 
>>> peers, I can pull from the reserved bits to increase this id. Lastly, 
>>> I will pass the BMI tag, which is 32 bits.
>