[netperf-talk] Considering declaring a 2.6.0 release

[Cook, Jonathan]

Here is a patch to correct the test length when using a burst of send calls and the elapsed time/throughput calculations when using UDP receive tests on Windows.  I hope that this can make it into release 2.6.0.

Regards,
Jon Cook

-----Original Message-----
From: netperf-talk-bounces at netperf.org [mailto:netperf-talk-bounces at netperf.org] On Behalf Of Cook, Jonathan
Sent: Wednesday, May 02, 2012 9:35 AM
To: Rick Jones; netperf-talk at netperf.org; netperf-dev at netperf.org
Subject: Re: [netperf-talk] Considering declaring a 2.6.0 release

I have done some more experimenting with the -b global option and have found one thing that is a problem to me.  I am using the omni test to send UDP data from netserver (on Linux) to netperf (on Windows) and I find that if I use the -b global option that netserver always sends packets for 10 seconds and then stops regardless of the test length that was specified in the command.  I have verified this by watching the network traffic in task manager.

C:\Users\jonc\Documents\netperf-latest\netperf2\src\NetPerfDir\objfre_wxp_x86\i3
86>netperf.exe -H10.8.7.240 -L10.8.7.117 -tOMNI -l 30 -fk 
86>-F,"/home/demo/ftp_fil
es/1GB_1" -D 1 -b,200 -- -Tudp -R1 -dreceive -m,1400 -s128k -S128k -O PROTOCOL,T HROUGHPUT,THROUGHPUT_UNITS,DIRECTION,ELAPSED_TIME,REMOTE_BYTES_RECVD,LOCAL_BYTES
_RECVD,
OMNI Receive TEST from 10.8.7.117 () port 0 AF_INET to 10.8.7.240 () port 0 AF_I NET : histogram : demo Interim result: 201036.58 10^3bits/s over 1.000 seconds ending at 1335970363.280

Interim result: 188224.45 10^3bits/s over 1.068 seconds ending at 1335970364.348

Interim result: 201898.75 10^3bits/s over 1.002 seconds ending at 1335970365.350

Interim result: 196227.50 10^3bits/s over 1.029 seconds ending at 1335970366.380

Interim result: 194548.36 10^3bits/s over 1.009 seconds ending at 1335970367.389

Interim result: 208957.90 10^3bits/s over 1.001 seconds ending at 1335970368.390

Interim result: 204707.65 10^3bits/s over 1.021 seconds ending at 1335970369.411

Interim result: 202743.49 10^3bits/s over 1.010 seconds ending at 1335970370.420

Interim result: 194844.38 10^3bits/s over 1.041 seconds ending at 1335970371.461

Protocol Throughput Throughput  Direction Elapsed Remote   Local
                    Units                 Time    Bytes    Bytes
                                          (sec)   Received Received

UDP      55473.33   10^3bits/s  Receive   32.00   0        249648000

In case you are wondering why I care so much about pacing the data it is because I am testing an over-the-air link which has a maximum throughput of 70Mb/s while the netserver computer can transmit at 1Gb/s out of its port(soon to be upgraded to 10Gb/s).  I don't want to flood our wired network with traffic that isn't going anywhere.

FYI, if I use a low number with the -b option (e.g. -b,1) then interim results do not get displayed.  I find that odd, but not a problem.  With bursts of 5 or more the interim results get displayed.

Thanks,
Jon

-----Original Message-----
From: netperf-talk-bounces at netperf.org [mailto:netperf-talk-bounces at netperf.org] On Behalf Of Rick Jones
Sent: Friday, April 27, 2012 3:20 PM
To: netperf-talk at netperf.org; netperf-dev at netperf.org
Subject: [netperf-talk] Considering declaring a 2.6.0 release

Folks -

There have been enough changes to netperf2 since the 2.5.0 release that I'm considering declaring a 2.6.0 release.  So, if you could grab top-of-trunk bits and try them out and let me know what problems you find I would appreciate it.

sincerely,

rick jones

(2.6.0 rather than 2.5.1 because some of the changes altered the control message size - again :) and while netperf never has supported mixed versions, if I know I've made a change like that, upping the middle digit seems warranted) _______________________________________________
netperf-talk mailing list
netperf-talk at netperf.org
http://www.netperf.org/cgi-bin/mailman/listinfo/netperf-talk
_______________________________________________
netperf-talk mailing list
netperf-talk at netperf.org
http://www.netperf.org/cgi-bin/mailman/listinfo/netperf-talk
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 2_6_0_tot.patch
Type: application/octet-stream
Size: 1959 bytes
Desc: 2_6_0_tot.patch
URL: <http://www.netperf.org/pipermail/netperf-talk/attachments/20120502/cf46123a/attachment.obj>