SCHEDTOOL(8)

๐Ÿ“ฆ
version 1.3.0 ยท 2 versions
, in debian bookworm, debian trixie, ubuntu jammy, ubuntu noble, ubuntu questing, ubuntu resolute, ubuntu stonking

๐ŸŒธ SCHEDTOOL(8) ๐ŸŒธ

okay so bestie, welcome to SCHEDTOOL(8) from the System Manager's Manual โ€” it's literally your CPU scheduling bestie, and it's giving main character energy ๐Ÿ’–


โœจ NAME โœจ

schedtool โ€” query and set CPU scheduling parameters ๐Ÿ‘‘


โœจ SYNOPSIS โœจ

schedtool
       [-0|-N] [-1|-F] [-2|-R] [-3|-B] [-4|-I] [-5|-D]
       [-M policy]
       [-a affinity]
       [-p prio]
       [-n nice_level]
       [-e command [arg ...]]
       [-r]
       [-v]
       [-h]
       [LIST OF PIDs]

โœจ DESCRIPTION โœจ

okay so schedtool can set all the CPU scheduling parameters Linux is capable of, or it can display information for given processes. no cap ๐Ÿ’…

Long-running, non-interactive tasks may benefit from SCHED_BATCH because timeslices are longer, less system-time is wasted by computing the next runnable process, and the caches stay stable. obsessed with a stable cache, honestly. โœจ

Audio/video or other near-realtime applications may run with less skipping if set to SCHED_RR. Use the static priority-switch -p to designate inter-process-hierarchies. ๐ŸŽง

schedtool now supports setting the CPU-affinity introduced in linux 2.5.8. iconic behavior. ๐Ÿฆ‹


๐Ÿ’… OPTIONS ๐Ÿ’…

  • -N or -0 โ€” set all PIDs to SCHED_NORMAL/OTHER ๐Ÿ˜Œ
  • -F or -1 โ€” set to SCHED_FIFO; root-credentials required ๐Ÿ”ฅ
  • -R or -2 โ€” set to SCHED_RR; root-credentials required ๐ŸŒ€
  • -B or -3 โ€” set to SCHED_BATCH ๐Ÿง
  • -I or -4 โ€” set to SCHED_ISO ๐ŸŽฎ
  • -D or -5 โ€” set to SCHED_IDLEPRIO ๐Ÿ˜ด
  • -M policy โ€” for manual/raw mode; policy is the number of the scheduling policy (see above for 0-4). This option is mostly for kernel guys that want to test their new implementations. ๐Ÿงช
  • -p prio โ€” specify static priority required for SCHED_FIFO and SCHED_RR. Usually ranged from 1-99. โšก
  • -a affinity โ€” set the PID's affinity to this bitmask (hexadecimal); alternatively, a list mode is supported. ๐Ÿงญ
  • -n nice_level โ€” set the PID's nice level; see nice(2), nice(1). ๐Ÿ“
  • -e command [arg ...] โ€” execute command with given scheduling parameters (overwrites schedtool's process image). See EXAMPLES. ๐Ÿš€
  • -r โ€” display min and max priority for each policy. ๐Ÿ“Š
  • -v โ€” be verbose. ๐Ÿ—ฃ๏ธ
  • -h โ€” help. ๐Ÿ†˜

๐ŸŽ€ EXAMPLES ๐ŸŽ€

To query the $SHELL's policies:

#> schedtool $$

To query some PIDs, namely 1 2 and 3:

#> schedtool 1 2 3

To execute mplayer in SCHED_RR with priority 20. The priority arg is needed for both SCHED_RR and SCHED_FIFO.

#> schedtool -R -p 20 -e mplayer -quiet some_file.avi

To set current shell to SCHED_BATCH, which all programs the shell starts will inherit:

#> schedtool -3 $$

To set all processes with the name 'cpu_hog' to SCHED_BATCH:

#> schedtool -3 `pidof cpu_hog`

To set a process' affinity to only the first CPU (CPU0):

#> schedtool -a 0x1 <PID>

Using the list mode and affinty of CPU0 and CPU3:

#> schedtool -a 0,3 <PID>

A combination of an affinity and a policy-argument is - of course - always possible.

#> schedtool -B -a 0x1 <PID>

๐ŸŒˆ AFFINITY MASK ๐ŸŒˆ

The affinity-argument determines on which CPUs a process is allowed to run. It consists of a simple bitmask represented in hexadecimal. CPU0 is denoted by the least-significant bit, CPU1 by the second least-significant and so on, thus giving:

0x1 -> only run on CPU0
0x2 -> only run on CPU1
0x4 -> only run on CPU2
0x8 -> only run on CPU3 ... and so on.

Multi-target CPUs may be specified using bitwise OR of the values:

0x7 -> run on CPUs 0, 1, 2 but NOT on 4
0x3 -> run only on CPUs 0 and 1

The default is to run a process on all CPUs, giving a mask of:

0xf for all 4 CPUs
0xff for all 8 CPUs

๐Ÿฆ‹ AFFINITY MASK - LIST MODE ๐Ÿฆ‹

Alternatively a list mode is supported where you can specify the CPUs delimited by ,. The following runs <PID> on CPU0 and CPU1 (equivalent to 0x3):

#> schedtool -a 0,1 <PID>

๐Ÿ‘‘ POLICY OVERVIEW ๐Ÿ‘‘

  • SCHED_NORMAL / SCHED_OTHER โ€” This is the default policy and for the average program with some interaction. Does preemption of other processes. ๐Ÿ˜Œ
  • SCHED_FIFO โ€” First-In, First Out Scheduler, used only for real-time constraints. Processes in this class are usually not preempted by others, they need to free themselves from the CPU via sched_yield() and as such you need special designed applications. Use with extreme care. ROOT-credentials required. ๐Ÿ’€
  • SCHED_RR โ€” Round-Robin Scheduler, also used for real-time constraints. CPU-time is assigned in an round-robin fashion with a much smaller timeslice than with SCHED_NORMAL and processes in this group are favoured over SCHED_NORMAL. Usable for audio/video applications near peak rate of the system. ROOT-credentials required. ๐ŸŽง
  • SCHED_BATCH [ since 2.6.16 in mainline ] โ€” SCHED_BATCH was designed for non-interactive, CPU-bound applications. It uses longer timeslices (to better exploit the cache), but can be interrupted anytime by other processes in other classes to guaratee interaction of the system. Processes in this class are selected last but may result in a considerable speed-up (up to 300%). No interactive boosting is done. ๐Ÿง
  • SCHED_ISO [ patch needed ] โ€” SCHED_ISO was designed to give users a SCHED_RR-similar class. To quote Con Kolivas: "This is a non-expiring scheduler policy designed to guarantee a timeslice within a reasonable latency while preventing starvation. Good for gaming, video at the limits of hardware, video capture etc." ๐ŸŽฎ
  • SCHED_IDLEPRIO [ patch needed ] โ€” SCHED_IDLEPRIO is similar to SCHED_BATCH, but was explicitly designed to consume only the time the CPU is idle. No interactive boosting is done. If you used SCHED_BATCH in the -ck kernels this is what you want since 2.6.16 ๐Ÿ˜ด

๐Ÿงš HINTS ๐Ÿงš

  • PID 0 means "current process", in our case, schedtool. May occur when using the -e switch. ๐Ÿซถ
  • > Be careful with SCHED_FIFO! You may lock out other processes from the CPU, including your shell. ๐Ÿ˜ญ
  • For SCHED_BATCH you certainly need the a recent 2.6 kernel. ๐ŸŒฑ
  • A short overview is given in SCHED_DESIGN and the README contains thorough discussion. The INSTALL file also lists all prerequisites and where you can get patches. ๐Ÿ“š
  • > Affinity 0x0 should never be used. ๐Ÿšซ

๐Ÿ” SEE ALSO ๐Ÿ”

sched_setscheduler(2), sched_setaffinity(2), nice(2), nice(1), renice(3).


๐Ÿ’€ BUGS ๐Ÿ’€

You need some knowledge about the kernel and scheduling. The author is a grumpy little elitist. ๐Ÿ˜ญ


๐Ÿ’Œ AUTHOR ๐Ÿ’Œ

Freek

Please contact me via freshmeat.net's "contact author"-feature (http://freshmeat.net/projects/schedtool). ๐Ÿ“ฌ


and that's a wrap from the System Manager's Manual, dated 1 November 2006, filed under SCHEDTOOL(8) โ€” mwah ๐Ÿ’‹