I've noticed several commands taking > 1 second that used to happen "instantaneously" and I'm trying to find out what's causing the delay. I try to use "getdelays", but it shows no more delay for a delayed command than for a sleep -- but a command like 'man' seems to have >1 sec of unaccounted for time: Example: First I try "sleep 1": # time getdelays -i -d -c /usr/bin/sleep 1 printing IO accounting print delayacct stats ON PID 30145 CPU count real total virtual total delay total delay average 3 1000000 1373539 79022 0.026ms IO count delay total delay average 0 0 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms sleep: read=0, write=0, cancelled_write=0 1.00sec 0.00usr 0.00sys (0.19% cpu) --------- Total time = 1sec (w/get delays showing < 1ms delay). Looks fine. Then a man lookup ('man sleep>/tmp/man'): # time getdelays -i -d -c /usr/bin/man sleep >/tmp/man; tail -12 /tmp/man PID 31255 CPU count real total virtual total delay total delay average 113 1151000000 1149782817 1349827 0.012ms IO count delay total delay average 0 0 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms man: read=0, write=0, cancelled_write=0 -------------- 1.19sec 0.00usr 0.00sys (0.25% cpu) =========================== 'man' is taking >1 second, even though "getdelays" shows there is less "delay" than for sleep -- so where would the time be going? Ideas? Thanks! -linda -- To unsubscribe, e-mail: opensuse+unsubscribe@opensuse.org To contact the owner, e-mail: opensuse+owner@opensuse.org