bcc-criticalstat - Man Page

A tracer to find and report long atomic critical sections in kernel

Synopsis

criticalstat [-h] [-p] [-i] [-d DURATION]

Description

criticalstat traces and reports occurrences of atomic critical sections in the kernel with useful stacktraces showing the origin of them. Such critical sections frequently occur due to use of spinlocks, or if interrupts or preemption were explicitly disabled by a driver. IRQ routines in Linux are also executed with interrupts disabled. There are many reasons. Such critical sections are a source of long latency/responsive issues for real-time systems.

This works by probing the preempt/irq and cpuidle tracepoints in the kernel. Since this uses BPF, only the root user can use this tool. Further, the kernel has to be built with certain CONFIG options enabled. See below.

Requirements

Enable following kernel configurations based on which kernel version you use.
   - CONFIG_DEBUG_PREEMPT
   - CONFIG_PREEMPT_TRACER
   
   For kernel 4.19 and later:
   - CONFIG_PREEMPTIRQ_TRACEPOINTS
   - CONFIG_TRACE_IRQFLAGS
   - CONFIG_TRACE_PREEMPT_TOGGLE
   
   For kernel 4.15 to 4.18:
   - CONFIG_PREEMPTIRQ_EVENTS
   - CONFIG_PROVE_LOCKING
   - CONFIG_DEBUG_PREEMPT Additionally, the following options should be turned off on older kernels:
   - CONFIG_LOCKDEP

Options

-h

Print usage message.

-p

Find long sections where preemption was disabled on local CPU.

-i

Find long sections where interrupt was disabled on local CPU.

-d DURATION

Only identify sections that are longer than DURATION in microseconds.

Examples

Run with default options: irq disabled for more than 100 uS

# criticalstat

Find sections with preemption disabled for more than 100 uS.

# criticalstat -p

Find sections with IRQ disabled for more than 500 uS.

# criticalstat -d 500

Find sections with preemption disabled for more than 500 uS.

# criticalstat -p -d 500

Overhead

This tool can cause overhead if the application is spending a lot of time in kernel mode. The overhead is variable but can be 2-4% of performance degradation. If overhead is seen to be too much, please pass a higher DURATION to the -d option to filter more aggressively.

Source

This is from bcc.

https://github.com/iovisor/bcc

Also look in the bcc distribution for a companion _examples.txt file containing example usage, output, and commentary for this tool.

OS

Linux

Stability

Unstable - in development.

Author

Joel Fernandes

See Also

Linux kernel's preemptoff and irqoff tracers.

Info

2018-06-07 USER COMMANDS