[netperf-talk] Throughput overflow when run UDP_STREAM test via loopback

Hangbin Liu haliu at redhat.com
Fri Mar 30 19:26:22 PDT 2012


Hi,

Sometimes the Throughput will overflow when run UDP_STREAM test via
loopback. Should be a bug ?

# netperf -H 127.0.0.1 -t UDP_STREAM
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to
127.0.0.1 (127.0.0.1) port 0 AF_INET
Socket  Message  Elapsed      Messages                
Size    Size     Time         Okay Errors   Throughput
bytes   bytes    secs            #      #   10^6bits/sec

188416   65507   10.00      358146      0
-710098123775531873324459307788354122837134422606260017760067080697223902638766456284866087222463400103365561059345413778309505442013381541021122340539880547578200138163161429163411474325182334780517410965202571032329761267721676259328.00
1087525910           -2.00     1076101154              0.00

# netperf -H 127.0.0.1 -t UDP_STREAM
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to
127.0.0.1 (127.0.0.1) port 0 AF_INET
Socket  Message  Elapsed      Messages                
Size    Size     Time         Okay Errors   Throughput
bytes   bytes    secs            #      #   10^6bits/sec

188416   65507   10.00      361529      0
9375911473112558296652506513476266338703852973592259660635890776618250547950188865152372446374280771315165316163207010126160562510187347944406875853204604739268003198492808454499991552.00
1087537262           0.00      1076101149              0.00

# netperf -H 127.0.0.1 -t UDP_STREAM
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to
127.0.0.1 (127.0.0.1) port 0 AF_INET
Socket  Message  Elapsed      Messages                
Size    Size     Time         Okay Errors   Throughput
bytes   bytes    secs            #      #   10^6bits/sec

188416   65507   10.00      361775      0      -0.00
1087538087
-26815615861007072584417859704564453759415650782313189212967346894783537592512461922242101866064541861168506143508534905079263270726944756152611525544116224.00   1076101148              0.00


Thanks
Hangbin Liu



More information about the netperf-talk mailing list