<html>
<body>
<font size=3>At 10:42 AM 5/1/2006, Ranjit Pandit wrote:<br>
<blockquote type=cite class=cite cite="">On 5/1/06, Or Gerlitz
<ogerlitz@voltaire.com> wrote:<br>
<blockquote type=cite class=cite cite="">Can you elaborate on each of the
features, specifically the following<br>
points are of interest to us:<br><br>
+1 so you running Oracle Loopback traffic over RDS sockets? if yes,
what<br>
the issue here?<br>
the openib CMA supports listen/connect on loopback addresses (eg<br>
127.0.0.1 or IPoIB local address)</blockquote><br>
Yes.<br>
There is no issue. It's just next in line for me to implement.<br><br>
<blockquote type=cite class=cite cite=""><br>
+2 by failover, are you referring to APM? that is failover between
IB<br>
pathes to/from the same HCA<br>
over which the original connection/QP was established or you are
talking<br>
on failover between HCAs</blockquote><br>
Failover within and across HCAs. APM does not work for failover across
HCAs.</font></blockquote><br>
That is because it is two different types of fail over being
discussed. APM is completely transparent to the IB RC connections
thus there is no disruption or loss of data. Fail over across HCA
is in effect replaying ULP transactions across a new RC connection.
Without an application / ULP level acknowledgement, there is still a hole
in the RDS proposal that has been raised and acknowledged in the past as
existing as recently as the Sonoma get together.<br><br>
I still have not seen a response to my inquiry about the this ULP and API
changes being at least comprehended beyond the Oracle usage model and
perhaps being reviewed within the IETF given it represents changes in API
and communication semantics. If the goal is to have RDS be a
generic service then it should be reviewed and validated by other
potential consumers as well as those subsystems that may be
impacted.<br><br>
Mike<br><br>
<br><br>
<blockquote type=cite class=cite cite="">
<blockquote type=cite class=cite cite=""><font size=3>+3 is the no
support for /proc like for RDS an issue to run crload or<br>
demo Oracle (that is specific tuning<br>
and usage of non defaults is needed for any/optimal
operation)</blockquote><br>
No, this does not affect core functionality. You should be able to
run<br>
Oracle or crload without this feature.<br><br>
That was a list of things that still need to be implemented for GA
and<br>
not just demo<br><br>
<blockquote type=cite class=cite cite=""><br>
Or.<br><br>
[openfabrics-ewg] Before we can start testing - we needto ensure
that<br>
RDS is fully ported.<br><br>
Pandit, Ranjit rpandit at silverstorm.com<br><br>
Following features are yet to be implemented in OpenFabric Rds:<br><br>
1. Failover<br>
2. Loopback connections<br>
3. support for /proc fs like Rds config,
stats and info.<br><br>
<br><br>
Ranjit<br><br>
<br><br>
_______________________________________________<br>
openib-general mailing list<br>
openib-general@openib.org<br>
<a href="http://openib.org/mailman/listinfo/openib-general" eudora="autourl">
http://openib.org/mailman/listinfo/openib-general</a><br><br>
To unsubscribe, please visit
<a href="http://openib.org/mailman/listinfo/openib-general" eudora="autourl">
http://openib.org/mailman/listinfo/openib-general</a><br>
</blockquote>_______________________________________________<br>
openib-general mailing list<br>
openib-general@openib.org<br>
<a href="http://openib.org/mailman/listinfo/openib-general" eudora="autourl">
http://openib.org/mailman/listinfo/openib-general</a><br><br>
To unsubscribe, please visit
<a href="http://openib.org/mailman/listinfo/openib-general" eudora="autourl">
http://openib.org/mailman/listinfo/openib-general</a></font></blockquote>
</body>
</html>