[openib-general] Re: [PATCH] [DAPL] [RFC] - remove duplicate disconnect event.

James Lentini jlentini at netapp.com
Wed Apr 19 09:38:33 PDT 2006



On Wed, 5 Apr 2006, Steve Wise wrote:

> James,
> 
> Running a 4 thread, 8 ep/thread dapltest (the last test in regress.sh),
> I was intermittently seeing a seg fault in dapltest.  This is running
> over the chelsio rnic using the iwarp branch.  After debugging I found
> out that dapltest was freeing an already freed endpoint due to it
> receiving duplicate disconnect events during test shutdown.  The code
> assumes it will get exactly one disconnect event for every endpoint
> (rightly so I guess).  

There should only be 1 disconnect event generated. dapltest should 
print out an error instead of crashing on this though.

> I tracked this down to the code in dapl_ep_disconnect() that generates
> its own disconnect event in certain circumstances.  I removed this and
> ran regress.sh over both mthca and cxgb3 with no problems.  
>
> So my question to the dapl experts is: why is this code here?  For our
> iwarp devices, it ends up sometimes generating duplicate disconnect
> events.  I don't see why its needed.  If anyone can explain the logic,
> that would be great.

I've looked into this. Some older verbs APIs didn't generate a 
disconnect on an abrupt close. 

I moved the support for these older APIs into a new location in 
revision 6517 and committed your changes in revision 6518.

-james



More information about the general mailing list