Re: [Discuss-gnuradio] FreeBSD - more

[LRK]

On Thu, Oct 13, 2005 at 10:06:28AM -0700, Eric Blossom wrote:
> 
> Don't use the -M option with small values.  You won't get a good
> answer unless you let it run for 10 - 20 seconds or so.  We want to
> know what it will sustain over an extended period of time.  You'll
> probabably want to run each test a couple of times too.  [There may be
> a problem where the fifo's aren't flushed between runs which is
> another reason to use longer test periods.  I think that may be why
> usb_benchmark doesn't work as expected.]


Here run as user gr:

./test_usrp_standard_rx -D 128
xfered 1.34e+08 bytes in 67.3 seconds.  1.996e+06 bytes/sec.  cpu time = 1.312
noverruns = 16

./test_usrp_standard_rx -D 64
xfered 1.34e+08 bytes in 33.6 seconds.  3.994e+06 bytes/sec.  cpu time = 1.31
noverruns = 5

./test_usrp_standard_rx -D 32
xfered 1.34e+08 bytes in 32.8 seconds.  4.086e+06 bytes/sec.  cpu time = 1.279
noverruns = 167

./test_usrp_standard_rx -D 16
xfered 1.34e+08 bytes in 32.8 seconds.  4.088e+06 bytes/sec.  cpu time = 1.21
noverruns = 83

./test_usrp_standard_rx -D 8
xfered 1.34e+08 bytes in 32.8 seconds.  4.086e+06 bytes/sec.  cpu time = 1.321
noverruns = 41


> > > Likewise, try test_usrp_standard_tx with different values of the 
> > > -I <interp> option.  Start with -I 256, then try -I 128, 64, 32, 16.
> >  
> > Can't, no Tx board.
> 
> The measurement should work fine with no Tx board.

./test_usrp_standard_tx -I 256
xfered 5.37e+08 bytes in 269 seconds.  1.998e+06 bytes/sec.  cpu time = 7.15
70 underruns

./test_usrp_standard_tx -I 128
xfered 5.37e+08 bytes in 140 seconds.  3.848e+06 bytes/sec.  cpu time = 7.33
32768 underruns

./test_usrp_standard_tx -I 64
xfered 5.37e+08 bytes in 140 seconds.  3.848e+06 bytes/sec.  cpu time = 7.19
32768 underruns

./test_usrp_standard_tx -I 32
xfered 5.37e+08 bytes in 140 seconds.  3.847e+06 bytes/sec.  cpu time = 7.63
32768 underruns

./test_usrp_standard_tx -I 16
xfered 5.37e+08 bytes in 140 seconds.  3.847e+06 bytes/sec.  cpu time = 6.89
32768 underruns


Both of these are about the same running as root and nice -20.



> If you've got a logic analyzer available and want to play, I can give
> you some suggestions of things to watch.  I suspect that what you'll
> see are *highly* variable inter-packet arrival times.

No such luck. Lotsa stuff in my toy box but not much modern test equipment.


-- 
LRK
address@hidden