On Fri, 2006-11-17 at 15:36 -0500, Alan D. Brunelle wrote: > OK, how about this: > > % btt -i bp.bin -p pio.txt > ... > % less pio.txt > 8,32 0.000062589 Q 500384 22 > 0.000065108 I 500384 22 > 8,32 0.000066560 Q 500406 10 > 0.000066964 M 500406 10 > 0.000163419 D 500384 32 > 0.005295956 C 500384 32 > > 8,80 0.000089685 Q 500384 22 > 0.000091863 I 500384 22 > 8,80 0.000093251 Q 500406 10 > 0.000093653 M 500406 10 > 0.000149032 D 500384 32 > 0.005338638 C 500384 32 > > 8,96 0.000097627 Q 500384 22 > 0.000100355 I 500384 22 > 8,96 0.000104798 Q 500406 10 > 0.000105205 M 500406 10 > 0.000123277 D 500384 32 > 0.005413636 C 500384 32 > ... > > So, for each IO we see it's complete chain of commands. each line > contains: (optional) device, time stamp, action-letter, sector number > and numbe rof sectors. (Thus we see that the first Q had 22 sectors, the > second Q had 10 sectors, and they were merged into one 32 sector IO.) >
cool. one more consideration. shall we have a time range option so we can decode a period we want? for example, a 1 hour activity but only have 1 minute strange behavior. so we might want to see that 1 minute only. > (It is costly - lots of output, but it would be optional.) > yes, it is optional, so should be fine. > Alan - To unsubscribe from this list: send the line "unsubscribe linux-btrace" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
