[openib-general] tavor quirks etc (opensm compliance etc)

Or Gerlitz ogerlitz at voltaire.com
Wed Dec 27 06:03:38 PST 2006


Eitan Zahavi wrote:
> Hi Or,
> 
> Sorry it took me a while.
> 
> According to the IBTA spec:
> 1. In order for MTU and MTUSelector to have any effect their component 
> mask bits MUST be set to 1 in the query
> 2. Behavior of the SM is defined with small "freedom" to choose between 
> multiple matching MTU values if they exist.
> 3. The table below summarizes all options:
> 
> Assuming the value M represents the lowest MTU on the path
> We denote by M-1 the MTU value one level below M (e.g. 1K if M=2K)
> R represents the MTU value in the request. Similarly R-1 is one below R 
> and R+1 is one above R.
> 
> Query-MTU | Query-Sel | Resp by Spec     | OpenSM Should  | OpenSM Quirk 
> w. Tavor End Port
> ----------------------------------------------------------------------------------------- 
> 
> UNDEFINED | UNDEFINED | <= M             | M              | min(M,1K)
> R         | <         | <= min(R-1, M)   | min(R-1, M)    | min(R-1, M, 1K)
> R         | =         | R if M>=R /ERR   | R if M>=R /ERR | R if M>=R /ERR
> R         | >         | R < <= M         | R+1 if M>R /ERR| R+1 if M>R /ERR

Hi Eitan,

Not that it matters too much for the decision if to push this into the 
Open SM, but the SM group here is positive w.r.t to the approach and 
patch you have sent.

However, there are some clarifications i will be happy to get:

1st maybe its clear to everyone expect me, but what do you mean by /ERR 
in the table above, is it what opensm would return before the patch you 
suggested?

2nd can you post the open sm tavor quirk patch?

3rd Eitan/Michael: what is the bigger picture here? what is the 
dependency between these four patches

+1 osm:Fix PathRecord bug MTU/rate/PktLife explicitly ignoring selectors
+2 osm: tavor quirk
+3 IB/rdmacm: tavor quirk
+4 IB/ipoib: use appropriate mtu selector for path queries

for example is it correct that:

if [2] is applied on the SA side then [4] must be applied on ipoib else 
if will get 1K mtu on its path query?

if [2] is not applied on the SA side, then [3] is useless?

Or.







More information about the general mailing list