[rds-devel] RDS-HA

[Or Gerlitz]

Carl Yang (caryang) wrote:
> Are you referring to ipoib_ha.pl when you referred to IPoIB high 
> availability patch?

I did not see any communication on this list re IPoIB nor RDS HA etc

With Oracle/RDS being an open source project, lets move to do all
rds devel related communication over this list.


> Can you please point me to the file that contains RDS HA?  I would like 
> to understand how the current RDS code handles IB RC connection failure 
> on one HCA and reestablish a new connection on the backup HCA while 
> maintaining socket connection.

Basically, what i understand is that once RDS gets a completion with 
error / disconnection of its IB RC connection, it attempts to reconnect.

Now with the linux bonding driver scheme, if there is now an available 
active slave in the bond that groups IPoIB devices (eg ib0 and ib1) the 
second connection establishment would be carried out "over" this slave 
and the same RDS socket can now be served by the new IB RC connection.
Zach - am i describing well what's going on?

Or.