ioprio_set(2)

Set a thread's I/O scheduling class and priority (ionice is the CLI wrapper).

Since: Linux 2.6.13check your kernel →
glibc: none (use syscall(2))
System: Linux
Man page: ioprio_set(2)

Synopsis

#include <linux/ioprio.h>    /* Definition of IOPRIO_* constants */
#include <sys/syscall.h>     /* Definition of SYS_* constants */
#include <unistd.h>

int syscall(SYS_ioprio_get, int which, int who);
int syscall(SYS_ioprio_set, int which, int who, int ioprio);

Rod's take

Somebody slapped nice -n 19 on the 2am backup and p99 still tripled, because nice is CPU and the backup was fighting for disk. ionice, which is ioprio_set under the hood, is the next guess, and it only does anything if the device's I/O scheduler honors priorities at all. The man page still talks about CFQ as if it's 2006; on a modern box, go read /sys/block/*/queue/scheduler before you trust it. It also admits priorities don't apply to async buffered writes. If you need real protection, cgroup v2 io.latency guards the workload that matters. ionice is a hint, not a fence.

Flags and arguments that matter

Name	What it does
IOPRIO_WHO_PROCESS	who is a process or thread ID; 0 means the calling thread.
IOPRIO_WHO_PGRP	who is a process group ID; 0 means the caller's process group.
IOPRIO_WHO_USER	who is a UID; applies to all processes with that real UID.
IOPRIO_CLASS_RT	Real-time class, levels 0-7; gets the disk first and can starve everyone. Needs CAP_SYS_ADMIN.
IOPRIO_CLASS_BE	Best-effort class, levels 0 (highest) to 7; the default.
IOPRIO_CLASS_IDLE	Only gets disk time when nobody else wants it. No CAP_SYS_ADMIN needed since Linux 2.6.25.
IOPRIO_PRIO_VALUE(class, data)	Macro that packs class and level into the ioprio argument.

Errors you will actually hit

errno	Meaning
EPERM	Not allowed: target owned by another UID without CAP_SYS_NICE, or RT class without CAP_SYS_ADMIN.
EINVAL	Invalid value for which or ioprio.
ESRCH	No process matched which and who.

Example

# does this device's scheduler even look at I/O priorities?
cat /sys/block/nvme0n1/queue/scheduler

# idle class: only gets the disk when nobody else wants it
ionice -c 3 /usr/local/bin/nightly-backup
ionice -p "$pid"               # read a running process's class/priority

# what actually protects the database: cgroup v2 io.latency
mkdir /sys/fs/cgroup/database
echo "259:0 target=10" > /sys/fs/cgroup/database/io.latency
echo "$pgpid" > /sys/fs/cgroup/database/cgroup.procs

Trimmed from the full walkthrough in Stop your backup job from taking production down with it.

BSD equivalent

FreeBSD and OpenBSD: no per-process I/O priority syscall.

The long version, from the console

Stop your backup job from taking production down with it

nice does nothing for I/O. ionice only works on one scheduler that most systems no longer use. cgroup v2 io.latency and io.max are the two knobs that actually work, and they work on the thing you already have.

2026-07-28

Sources

Version numbers are read off the cited man pages, not memory. Spot one that's wrong? Tell Rod.