[netperf-talk] ENOBUFS on linux?

[Rick Jones]

Andrew Gallatin wrote:
> Please see attached patch, which only sets the option for the send
> side of UDP_STREAM, and even there, only on linux.   You mentioned
> that HPUX does this as well.  It might be interesting to see if
> this "fixes" HPUX also (you'll need to adjust the #ifdefs).

HP-UX 11.11 at least has no IP_RECVERR define, and I don't think HP-UX 11.X has 
any other way to convince the stack to report the dropped traffic so there won't 
be an opportunity to "fix" it there.  Folks running on HP-UX 11.X have been 
living with it since 1997 (FCS for 11.0) so I figure it isn't a pressing problem 
for them :)

> 
> Rick Jones wrote:
> 
>> If you can show the effect on achieved performance is epsilon for the 
>> cases when the drops don't occur I'm OK with that (preferably with 
>> something other than a 100 Mbit/s link, or at least with high confidence 
> 
> 
> I'm not used to the conf. interval stuff.  Is this what you want to see?
> In the tests below "netperf.orig" is a build of the 2.2 svn before
> applying my patch, and "netperf" is after the patch.
> 

Numbers snipped - look good.
>> level service demands).  Bonus points for making sure it works with 
>> the omni tests (although IIRC those are already using the 
>> nettest_bsd.c create_data_socket() stuff anyway)
> 
> 
> The way I did it probably won't work with them.  I couldn't figure out
> how to run them, so I didn't attempt to fix them as well.

No worries - my initial take was you were altering create_data_socket, but from 
the stuff you included I see that it is a new call you added to send_udp_stream.

If you are curious about the omni tests, to run the omni stuff one needs to 
first ./configure --enable-omni ...  and then one can mimic the command lines 
found in things like:

ftp://ftp.netperf.org/netperf/misc/runemomni.sh

happy benchmarking,

rick jones