On Tue Mar 6 10:37:06 EST 2012, 9p...@imu.li wrote: > > my working theory is that i'm getting all the interrupts, but not soon > > enough... the fascinating piece is that the olpc and the pc with intel > > ehc take just about the same amount of time. > > indeed, if i set the interrupt threshold control to 1 micro-frame (they > default to 8), i get 10-11 sec dd, say, half as slow. and ping time to my > switch is half. and i can get about twice the throughput from the file > server, which is still kinda slow. > > (hget yields about 6Mbit over a 100Mbit link)
it sounds like you have it all figured out. but just in case there is a spurious interrupt causing trouble, you can check with this rather embarassing acid script. sorry, i can't get acid to recoginze intrcountx as a vlong. acid -l acid -k 1 /386/9pccpu acid: i=0; while i<256*2 do {if(intrcountx[i]>0) then {print(i/2\D, "\t", intrcountx[i]);} i=i+2;} 7 143 14 44355 50 99090099 65 19938 73 37571 145 9814 153 1 161 42 169 7 - erik