[rds-devel] FW: RDS -- how to detect peer is gone ?

[Andy Grover]

Tang, Changqing wrote:
> Andy: I don't see file rds-ping.c from OFED 1.5 package, do you have
> a newer version ?

Hi CQ,

It is in the rds-tools src rpm.

> As "how the sender would be notified the message was dropped", I
> don't want to report all Dropped messages, it just reports if the
> special heartbeat message get dropped.
> 
> What I want to do here is that, a receiver is waiting for a message
> from another Process, if it does not receive it after some interval,
> it sends a heartbeat message to that Process, when the heartbeat
> message reaches the target node, it calls rds_find_bound() and Send
> the checking result back, the heartbeat message itself get dropped.

I don't quite follow. If you're not getting the response, you could
always issue an rds ping, and that will return (or not) depending on if
rds is alive on the other end. You know that the machine is up but the
process is unresponsive. Is that the goal?

Regards -- Andy