<html>
<body>
<font size=3>At 09:43 AM 2/10/2006, Grant Grundler wrote:<br>
<blockquote type=cite class=cite cite="">On Fri, Feb 10, 2006 at
11:05:34AM -0500, Hal Rosenstock wrote:<br>
> > Hi, Roland!<br>
> > One issue we have with IPoIB is that IPoIB may cache a remote
node path<br>
> > for a long time. Remote LID may get changed e.g. if the SM is
changed,<br>
> > and IPoIB might lose connectivity.<br><br>
I wonder if this is why when I reload the IB drivers on one node<br>
I sometimes have to reload them on other nodes too. Otherwise<br>
ping over IPoIB doesn't work.</font></blockquote><br>
If endnodes are not periodically refreshing their caches or are not
subscribing to event management to be informed a refresh is in order,
then endnodes will fall out of sync and would need to be restarted to
establish communication. This is a classic problem that was
illustrated in various early router protocols and is why today's
protocols rely implement a two-prong approach in many cases - limited
cache lifetime and proactive cache event updates.<br><br>
<br>
<blockquote type=cite class=cite cite=""><font size=3>> The remote LID
may get changed for other reasons too without an SM<br>
> change (SM merge of 2 separate subnets). How can this be handled
?<br><br>
Isn't this just another case of the SM changing for one of the
subnets?</blockquote><br>
A SM merge that involves updating LIDs is a non-trivial event. It
requires connections to be effectively restarted as one cannot ascertain
whether all packets are flushed from the fabric otherwise - that can
cause silent data corruption. For a subsystem such as IPoverIB, a
LID update should result in an unsolicited ARP / ND exchange which will
cause all remote endnodes to receive the new information.<br><br>
Mike</font></body>
</html>