linux - Understanding strace output against userland process (CPU hog) -

linux - Understanding strace output against userland process (CPU hog) -

problem : userland process hogging cpu. scheme conf: linux 2.6.34

executed strace different command line options , below few queries:

strace -f -rtt -p 12661

0.000058 restart_syscall(<... resuming interrupted phone call ...>) = -487663192 <0.000017> 0.000056 restart_syscall(<... resuming interrupted phone call ...>) = -487663192 <0.000017> 0.000056 restart_syscall(<... resuming interrupted phone call ...>) = -487663192 <0.000017> 0.000057 restart_syscall(<... resuming interrupted phone call ...>) = -487663192 <0.000017> 0.000057 restart_syscall(<... resuming interrupted phone call ...>) = -487663192 <0.000018> 0.000057 restart_syscall(<... resuming interrupted phone call ...>) = -487663192 <0.000017>

strace -c -p 12661

% time seconds usecs/call calls errors syscall 100.00 0.001191 0 23216 restart_syscall 0.00 0.000000 0 188 sigreturn 0.00 0.000000 0 1 rt_sigprocmask 0.00 0.000000 0 21 stat64 100.00 0.001191 23426 total

i'm confused strace first column "time" saying 100 % straight refer cpu occupancy ?

and also, restart_syscall occupancy (100%) due strace ??

objective of userland process emulate not supported instructions/memory , have 1 clone process dequeue packets eth (using netfilter).

could help/clarify above points ?

thanks in advance

linux powerpc strace