Tag Info

New answers tagged


I have to do it with a script that does something like this: pidtree= pidtree() { local _pid=$1 for _child in $(ps -o pid --no-headers --ppid ${_pid}); do pidtree ${_child} done pidlist=$(ls -1 /proc/${_pid}/task)" $pidlist" } pidtree $1 cgcreate -g cpu:/job$1 cgclassify -g cpu:/job$1 $pidlist


You can run your command(s) via systemd-run --scope. This creates a transient (ie temporary) cgroup for your command. You can then modify the cgroup to your needs. Use systemd-cgls to find your process in the cgroup hierarchy under /sys/fs/cgroup. According to the systemd-run manpage systemd-run may be used to create and start a transient .service or a ...


Your system is swapping heavily (17G swap used) which will make any I/O from regular processes to the respective drive extremely slow - which translates into high %wa. Not 100% sure but even swapping itself may contribute directly to the %wa figure as well (typically via the kswapd process, also likely the top CPU hugger in your situation). First you want ...


Did you try the man pages? Both cgconfig.conf(5) and cgrules.conf(5) have nice examples, it shouldn't be difficult modifying those to match your needs. You will probably want to start from something like (be warned I have not tested it): In /etc/cgrules.conf: root:sshd * sshdcg/ * * default/ and ...

Top 50 recent answers are included